Tess-3-7B-SFT

Name: Tess-3-7B-SFT
Rating: 4.0 (10 reviews)
Author: migtissera

license:apache-2.0

migtissera

Language Model

OTHER

7B params

New

5 downloads

Early-stage

Try on Hugging Face Add to Compare

Edge AI:

Mobile

Laptop

Server

16GB+ RAM

Mobile

Laptop

Server

Quick Summary

AI model with specialized capabilities.

Device Compatibility

Mobile

4-6GB RAM

Laptop

16GB RAM

Server

GPU

Minimum Recommended

7GB+ RAM

Code Examples

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

yaml

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false

load_in_8bit: false
load_in_4bit: false
strict: false
model_config:

datasets:
  - path: /home/migel/ai_datasets/tess-v1.5b-chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-multi_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml
  - path: /home/migel/ai_datasets/Tess-3.0/Tess-3.0-single_turn_chatml.jsonl
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path: last_run_prepared_mistral
val_set_size: 0.0
output_dir: /home/migel/tess-2.5-mistral-7B-phase-1

resume_from_checkpoint: /home/migel/tess-2.5-mistral-7B-phase-1/checkpoint-440 
auto_resume_from_checkpoints: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: constant
learning_rate: 1e-6

wandb_project: mistral-7b
wandb_watch:
wandb_run_id:
wandb_log_model:

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 10
evals_per_epoch: 10
save_total_limit: 3
save_steps:
eval_sample_packing: false
debug:
deepspeed: /home/migel/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"