SD-Prompter-1.5B-V0.1-EXL2

1
1.5B
license:agpl-3.0
by
Delta-Vector
Other
OTHER
1.5B params
New
0 downloads
Early-stage
Try on Hugging FaceAdd to Compare
Edge AI:
Mobile
Laptop
Server
4GB+ RAM
Mobile
Laptop
Server
Quick Summary

AI model with specialized capabilities.

Device Compatibility

Mobile
4-6GB RAM
Laptop
16GB RAM
Server
GPU
Minimum Recommended
2GB+ RAM

Code Examples

Axolotl Configyaml
base_model: NewEden/Qwen-1.5B-Claude
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

trust_remote_code: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: civit-slop-combined.jsonl 
    type: alpaca
    conversation: mpt-30b-instruct

chat_template: alpaca

dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/sd-prompter
sequence_len: 2048
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: SDprompt-qwen
wandb_entity:
wandb_watch:
wandb_name: qwen1.5b-2
wandb_log_model:

gradient_accumulation_steps: 64
micro_batch_size: 2
num_epochs: 3
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.00002

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

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

warmup_ratio: 0.05
evals_per_epoch: 4
saves_per_epoch: 1
debug:
#deepspeed: deepspeed_configs/zero2.json
#deepspeed: /training/axolotl/axolotl/deepspeed_configs/zero2.json
weight_decay: 0.0
#fsdp:
#fsdp_config:
#  fsdp_limit_all_gathers: true
#  fsdp_sync_module_states: true
#  fsdp_offload_params: true
#  fsdp_use_orig_params: false
#  fsdp_cpu_ram_efficient_loading: true
#  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
#  fsdp_transformer_layer_cls_to_wrap: Qwen2DecoderLayer
#  fsdp_state_dict_type: FULL_STATE_DICT
special_tokens:
Axolotl Configyaml
base_model: NewEden/Qwen-1.5B-Claude
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

trust_remote_code: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: civit-slop-combined.jsonl 
    type: alpaca
    conversation: mpt-30b-instruct

chat_template: alpaca

dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/sd-prompter
sequence_len: 2048
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: SDprompt-qwen
wandb_entity:
wandb_watch:
wandb_name: qwen1.5b-2
wandb_log_model:

gradient_accumulation_steps: 64
micro_batch_size: 2
num_epochs: 3
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.00002

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

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

warmup_ratio: 0.05
evals_per_epoch: 4
saves_per_epoch: 1
debug:
#deepspeed: deepspeed_configs/zero2.json
#deepspeed: /training/axolotl/axolotl/deepspeed_configs/zero2.json
weight_decay: 0.0
#fsdp:
#fsdp_config:
#  fsdp_limit_all_gathers: true
#  fsdp_sync_module_states: true
#  fsdp_offload_params: true
#  fsdp_use_orig_params: false
#  fsdp_cpu_ram_efficient_loading: true
#  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
#  fsdp_transformer_layer_cls_to_wrap: Qwen2DecoderLayer
#  fsdp_state_dict_type: FULL_STATE_DICT
special_tokens:
Axolotl Configyaml
base_model: NewEden/Qwen-1.5B-Claude
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

trust_remote_code: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: civit-slop-combined.jsonl 
    type: alpaca
    conversation: mpt-30b-instruct

chat_template: alpaca

dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/sd-prompter
sequence_len: 2048
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: SDprompt-qwen
wandb_entity:
wandb_watch:
wandb_name: qwen1.5b-2
wandb_log_model:

gradient_accumulation_steps: 64
micro_batch_size: 2
num_epochs: 3
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.00002

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

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

warmup_ratio: 0.05
evals_per_epoch: 4
saves_per_epoch: 1
debug:
#deepspeed: deepspeed_configs/zero2.json
#deepspeed: /training/axolotl/axolotl/deepspeed_configs/zero2.json
weight_decay: 0.0
#fsdp:
#fsdp_config:
#  fsdp_limit_all_gathers: true
#  fsdp_sync_module_states: true
#  fsdp_offload_params: true
#  fsdp_use_orig_params: false
#  fsdp_cpu_ram_efficient_loading: true
#  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
#  fsdp_transformer_layer_cls_to_wrap: Qwen2DecoderLayer
#  fsdp_state_dict_type: FULL_STATE_DICT
special_tokens:
Axolotl Configyaml
base_model: NewEden/Qwen-1.5B-Claude
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

trust_remote_code: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: civit-slop-combined.jsonl 
    type: alpaca
    conversation: mpt-30b-instruct

chat_template: alpaca

dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/sd-prompter
sequence_len: 2048
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: SDprompt-qwen
wandb_entity:
wandb_watch:
wandb_name: qwen1.5b-2
wandb_log_model:

gradient_accumulation_steps: 64
micro_batch_size: 2
num_epochs: 3
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.00002

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

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

warmup_ratio: 0.05
evals_per_epoch: 4
saves_per_epoch: 1
debug:
#deepspeed: deepspeed_configs/zero2.json
#deepspeed: /training/axolotl/axolotl/deepspeed_configs/zero2.json
weight_decay: 0.0
#fsdp:
#fsdp_config:
#  fsdp_limit_all_gathers: true
#  fsdp_sync_module_states: true
#  fsdp_offload_params: true
#  fsdp_use_orig_params: false
#  fsdp_cpu_ram_efficient_loading: true
#  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
#  fsdp_transformer_layer_cls_to_wrap: Qwen2DecoderLayer
#  fsdp_state_dict_type: FULL_STATE_DICT
special_tokens:
Axolotl Configyaml
base_model: NewEden/Qwen-1.5B-Claude
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

trust_remote_code: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: civit-slop-combined.jsonl 
    type: alpaca
    conversation: mpt-30b-instruct

chat_template: alpaca

dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/sd-prompter
sequence_len: 2048
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: SDprompt-qwen
wandb_entity:
wandb_watch:
wandb_name: qwen1.5b-2
wandb_log_model:

gradient_accumulation_steps: 64
micro_batch_size: 2
num_epochs: 3
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.00002

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

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

warmup_ratio: 0.05
evals_per_epoch: 4
saves_per_epoch: 1
debug:
#deepspeed: deepspeed_configs/zero2.json
#deepspeed: /training/axolotl/axolotl/deepspeed_configs/zero2.json
weight_decay: 0.0
#fsdp:
#fsdp_config:
#  fsdp_limit_all_gathers: true
#  fsdp_sync_module_states: true
#  fsdp_offload_params: true
#  fsdp_use_orig_params: false
#  fsdp_cpu_ram_efficient_loading: true
#  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
#  fsdp_transformer_layer_cls_to_wrap: Qwen2DecoderLayer
#  fsdp_state_dict_type: FULL_STATE_DICT
special_tokens:
Axolotl Configyaml
base_model: NewEden/Qwen-1.5B-Claude
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

trust_remote_code: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: civit-slop-combined.jsonl 
    type: alpaca
    conversation: mpt-30b-instruct

chat_template: alpaca

dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/sd-prompter
sequence_len: 2048
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: SDprompt-qwen
wandb_entity:
wandb_watch:
wandb_name: qwen1.5b-2
wandb_log_model:

gradient_accumulation_steps: 64
micro_batch_size: 2
num_epochs: 3
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.00002

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

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

warmup_ratio: 0.05
evals_per_epoch: 4
saves_per_epoch: 1
debug:
#deepspeed: deepspeed_configs/zero2.json
#deepspeed: /training/axolotl/axolotl/deepspeed_configs/zero2.json
weight_decay: 0.0
#fsdp:
#fsdp_config:
#  fsdp_limit_all_gathers: true
#  fsdp_sync_module_states: true
#  fsdp_offload_params: true
#  fsdp_use_orig_params: false
#  fsdp_cpu_ram_efficient_loading: true
#  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
#  fsdp_transformer_layer_cls_to_wrap: Qwen2DecoderLayer
#  fsdp_state_dict_type: FULL_STATE_DICT
special_tokens:
Axolotl Configyaml
base_model: NewEden/Qwen-1.5B-Claude
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

trust_remote_code: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: civit-slop-combined.jsonl 
    type: alpaca
    conversation: mpt-30b-instruct

chat_template: alpaca

dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/sd-prompter
sequence_len: 2048
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: SDprompt-qwen
wandb_entity:
wandb_watch:
wandb_name: qwen1.5b-2
wandb_log_model:

gradient_accumulation_steps: 64
micro_batch_size: 2
num_epochs: 3
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.00002

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

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

warmup_ratio: 0.05
evals_per_epoch: 4
saves_per_epoch: 1
debug:
#deepspeed: deepspeed_configs/zero2.json
#deepspeed: /training/axolotl/axolotl/deepspeed_configs/zero2.json
weight_decay: 0.0
#fsdp:
#fsdp_config:
#  fsdp_limit_all_gathers: true
#  fsdp_sync_module_states: true
#  fsdp_offload_params: true
#  fsdp_use_orig_params: false
#  fsdp_cpu_ram_efficient_loading: true
#  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
#  fsdp_transformer_layer_cls_to_wrap: Qwen2DecoderLayer
#  fsdp_state_dict_type: FULL_STATE_DICT
special_tokens:
Axolotl Configyaml
base_model: NewEden/Qwen-1.5B-Claude
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

trust_remote_code: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: civit-slop-combined.jsonl 
    type: alpaca
    conversation: mpt-30b-instruct

chat_template: alpaca

dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/sd-prompter
sequence_len: 2048
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: SDprompt-qwen
wandb_entity:
wandb_watch:
wandb_name: qwen1.5b-2
wandb_log_model:

gradient_accumulation_steps: 64
micro_batch_size: 2
num_epochs: 3
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.00002

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

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

warmup_ratio: 0.05
evals_per_epoch: 4
saves_per_epoch: 1
debug:
#deepspeed: deepspeed_configs/zero2.json
#deepspeed: /training/axolotl/axolotl/deepspeed_configs/zero2.json
weight_decay: 0.0
#fsdp:
#fsdp_config:
#  fsdp_limit_all_gathers: true
#  fsdp_sync_module_states: true
#  fsdp_offload_params: true
#  fsdp_use_orig_params: false
#  fsdp_cpu_ram_efficient_loading: true
#  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
#  fsdp_transformer_layer_cls_to_wrap: Qwen2DecoderLayer
#  fsdp_state_dict_type: FULL_STATE_DICT
special_tokens:
Axolotl Configyaml
base_model: NewEden/Qwen-1.5B-Claude
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

trust_remote_code: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: civit-slop-combined.jsonl 
    type: alpaca
    conversation: mpt-30b-instruct

chat_template: alpaca

dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/sd-prompter
sequence_len: 2048
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: SDprompt-qwen
wandb_entity:
wandb_watch:
wandb_name: qwen1.5b-2
wandb_log_model:

gradient_accumulation_steps: 64
micro_batch_size: 2
num_epochs: 3
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.00002

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

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

warmup_ratio: 0.05
evals_per_epoch: 4
saves_per_epoch: 1
debug:
#deepspeed: deepspeed_configs/zero2.json
#deepspeed: /training/axolotl/axolotl/deepspeed_configs/zero2.json
weight_decay: 0.0
#fsdp:
#fsdp_config:
#  fsdp_limit_all_gathers: true
#  fsdp_sync_module_states: true
#  fsdp_offload_params: true
#  fsdp_use_orig_params: false
#  fsdp_cpu_ram_efficient_loading: true
#  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
#  fsdp_transformer_layer_cls_to_wrap: Qwen2DecoderLayer
#  fsdp_state_dict_type: FULL_STATE_DICT
special_tokens:
Axolotl Configyaml
base_model: NewEden/Qwen-1.5B-Claude
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

trust_remote_code: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: civit-slop-combined.jsonl 
    type: alpaca
    conversation: mpt-30b-instruct

chat_template: alpaca

dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/sd-prompter
sequence_len: 2048
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: SDprompt-qwen
wandb_entity:
wandb_watch:
wandb_name: qwen1.5b-2
wandb_log_model:

gradient_accumulation_steps: 64
micro_batch_size: 2
num_epochs: 3
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.00002

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

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

warmup_ratio: 0.05
evals_per_epoch: 4
saves_per_epoch: 1
debug:
#deepspeed: deepspeed_configs/zero2.json
#deepspeed: /training/axolotl/axolotl/deepspeed_configs/zero2.json
weight_decay: 0.0
#fsdp:
#fsdp_config:
#  fsdp_limit_all_gathers: true
#  fsdp_sync_module_states: true
#  fsdp_offload_params: true
#  fsdp_use_orig_params: false
#  fsdp_cpu_ram_efficient_loading: true
#  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
#  fsdp_transformer_layer_cls_to_wrap: Qwen2DecoderLayer
#  fsdp_state_dict_type: FULL_STATE_DICT
special_tokens:
Axolotl Configyaml
base_model: NewEden/Qwen-1.5B-Claude
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

trust_remote_code: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: civit-slop-combined.jsonl 
    type: alpaca
    conversation: mpt-30b-instruct

chat_template: alpaca

dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/sd-prompter
sequence_len: 2048
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: SDprompt-qwen
wandb_entity:
wandb_watch:
wandb_name: qwen1.5b-2
wandb_log_model:

gradient_accumulation_steps: 64
micro_batch_size: 2
num_epochs: 3
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.00002

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

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

warmup_ratio: 0.05
evals_per_epoch: 4
saves_per_epoch: 1
debug:
#deepspeed: deepspeed_configs/zero2.json
#deepspeed: /training/axolotl/axolotl/deepspeed_configs/zero2.json
weight_decay: 0.0
#fsdp:
#fsdp_config:
#  fsdp_limit_all_gathers: true
#  fsdp_sync_module_states: true
#  fsdp_offload_params: true
#  fsdp_use_orig_params: false
#  fsdp_cpu_ram_efficient_loading: true
#  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
#  fsdp_transformer_layer_cls_to_wrap: Qwen2DecoderLayer
#  fsdp_state_dict_type: FULL_STATE_DICT
special_tokens:
Axolotl Configyaml
base_model: NewEden/Qwen-1.5B-Claude
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

trust_remote_code: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: civit-slop-combined.jsonl 
    type: alpaca
    conversation: mpt-30b-instruct

chat_template: alpaca

dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/sd-prompter
sequence_len: 2048
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: SDprompt-qwen
wandb_entity:
wandb_watch:
wandb_name: qwen1.5b-2
wandb_log_model:

gradient_accumulation_steps: 64
micro_batch_size: 2
num_epochs: 3
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.00002

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

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

warmup_ratio: 0.05
evals_per_epoch: 4
saves_per_epoch: 1
debug:
#deepspeed: deepspeed_configs/zero2.json
#deepspeed: /training/axolotl/axolotl/deepspeed_configs/zero2.json
weight_decay: 0.0
#fsdp:
#fsdp_config:
#  fsdp_limit_all_gathers: true
#  fsdp_sync_module_states: true
#  fsdp_offload_params: true
#  fsdp_use_orig_params: false
#  fsdp_cpu_ram_efficient_loading: true
#  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
#  fsdp_transformer_layer_cls_to_wrap: Qwen2DecoderLayer
#  fsdp_state_dict_type: FULL_STATE_DICT
special_tokens:
Axolotl Configyaml
base_model: NewEden/Qwen-1.5B-Claude
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

trust_remote_code: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: civit-slop-combined.jsonl 
    type: alpaca
    conversation: mpt-30b-instruct

chat_template: alpaca

dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/sd-prompter
sequence_len: 2048
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: SDprompt-qwen
wandb_entity:
wandb_watch:
wandb_name: qwen1.5b-2
wandb_log_model:

gradient_accumulation_steps: 64
micro_batch_size: 2
num_epochs: 3
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.00002

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

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

warmup_ratio: 0.05
evals_per_epoch: 4
saves_per_epoch: 1
debug:
#deepspeed: deepspeed_configs/zero2.json
#deepspeed: /training/axolotl/axolotl/deepspeed_configs/zero2.json
weight_decay: 0.0
#fsdp:
#fsdp_config:
#  fsdp_limit_all_gathers: true
#  fsdp_sync_module_states: true
#  fsdp_offload_params: true
#  fsdp_use_orig_params: false
#  fsdp_cpu_ram_efficient_loading: true
#  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
#  fsdp_transformer_layer_cls_to_wrap: Qwen2DecoderLayer
#  fsdp_state_dict_type: FULL_STATE_DICT
special_tokens:
Axolotl Configyaml
base_model: NewEden/Qwen-1.5B-Claude
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

trust_remote_code: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: civit-slop-combined.jsonl 
    type: alpaca
    conversation: mpt-30b-instruct

chat_template: alpaca

dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/sd-prompter
sequence_len: 2048
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: SDprompt-qwen
wandb_entity:
wandb_watch:
wandb_name: qwen1.5b-2
wandb_log_model:

gradient_accumulation_steps: 64
micro_batch_size: 2
num_epochs: 3
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.00002

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

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

warmup_ratio: 0.05
evals_per_epoch: 4
saves_per_epoch: 1
debug:
#deepspeed: deepspeed_configs/zero2.json
#deepspeed: /training/axolotl/axolotl/deepspeed_configs/zero2.json
weight_decay: 0.0
#fsdp:
#fsdp_config:
#  fsdp_limit_all_gathers: true
#  fsdp_sync_module_states: true
#  fsdp_offload_params: true
#  fsdp_use_orig_params: false
#  fsdp_cpu_ram_efficient_loading: true
#  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
#  fsdp_transformer_layer_cls_to_wrap: Qwen2DecoderLayer
#  fsdp_state_dict_type: FULL_STATE_DICT
special_tokens:
Axolotl Configyaml
base_model: NewEden/Qwen-1.5B-Claude
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

trust_remote_code: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: civit-slop-combined.jsonl 
    type: alpaca
    conversation: mpt-30b-instruct

chat_template: alpaca

dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/sd-prompter
sequence_len: 2048
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: SDprompt-qwen
wandb_entity:
wandb_watch:
wandb_name: qwen1.5b-2
wandb_log_model:

gradient_accumulation_steps: 64
micro_batch_size: 2
num_epochs: 3
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.00002

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

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

warmup_ratio: 0.05
evals_per_epoch: 4
saves_per_epoch: 1
debug:
#deepspeed: deepspeed_configs/zero2.json
#deepspeed: /training/axolotl/axolotl/deepspeed_configs/zero2.json
weight_decay: 0.0
#fsdp:
#fsdp_config:
#  fsdp_limit_all_gathers: true
#  fsdp_sync_module_states: true
#  fsdp_offload_params: true
#  fsdp_use_orig_params: false
#  fsdp_cpu_ram_efficient_loading: true
#  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
#  fsdp_transformer_layer_cls_to_wrap: Qwen2DecoderLayer
#  fsdp_state_dict_type: FULL_STATE_DICT
special_tokens:
Axolotl Configyaml
base_model: NewEden/Qwen-1.5B-Claude
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

trust_remote_code: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: civit-slop-combined.jsonl 
    type: alpaca
    conversation: mpt-30b-instruct

chat_template: alpaca

dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/sd-prompter
sequence_len: 2048
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: SDprompt-qwen
wandb_entity:
wandb_watch:
wandb_name: qwen1.5b-2
wandb_log_model:

gradient_accumulation_steps: 64
micro_batch_size: 2
num_epochs: 3
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.00002

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

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

warmup_ratio: 0.05
evals_per_epoch: 4
saves_per_epoch: 1
debug:
#deepspeed: deepspeed_configs/zero2.json
#deepspeed: /training/axolotl/axolotl/deepspeed_configs/zero2.json
weight_decay: 0.0
#fsdp:
#fsdp_config:
#  fsdp_limit_all_gathers: true
#  fsdp_sync_module_states: true
#  fsdp_offload_params: true
#  fsdp_use_orig_params: false
#  fsdp_cpu_ram_efficient_loading: true
#  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
#  fsdp_transformer_layer_cls_to_wrap: Qwen2DecoderLayer
#  fsdp_state_dict_type: FULL_STATE_DICT
special_tokens:
Axolotl Configyaml
base_model: NewEden/Qwen-1.5B-Claude
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

trust_remote_code: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: civit-slop-combined.jsonl 
    type: alpaca
    conversation: mpt-30b-instruct

chat_template: alpaca

dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/sd-prompter
sequence_len: 2048
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: SDprompt-qwen
wandb_entity:
wandb_watch:
wandb_name: qwen1.5b-2
wandb_log_model:

gradient_accumulation_steps: 64
micro_batch_size: 2
num_epochs: 3
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.00002

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

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

warmup_ratio: 0.05
evals_per_epoch: 4
saves_per_epoch: 1
debug:
#deepspeed: deepspeed_configs/zero2.json
#deepspeed: /training/axolotl/axolotl/deepspeed_configs/zero2.json
weight_decay: 0.0
#fsdp:
#fsdp_config:
#  fsdp_limit_all_gathers: true
#  fsdp_sync_module_states: true
#  fsdp_offload_params: true
#  fsdp_use_orig_params: false
#  fsdp_cpu_ram_efficient_loading: true
#  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
#  fsdp_transformer_layer_cls_to_wrap: Qwen2DecoderLayer
#  fsdp_state_dict_type: FULL_STATE_DICT
special_tokens:
Axolotl Configyaml
base_model: NewEden/Qwen-1.5B-Claude
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

trust_remote_code: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: civit-slop-combined.jsonl 
    type: alpaca
    conversation: mpt-30b-instruct

chat_template: alpaca

dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/sd-prompter
sequence_len: 2048
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: SDprompt-qwen
wandb_entity:
wandb_watch:
wandb_name: qwen1.5b-2
wandb_log_model:

gradient_accumulation_steps: 64
micro_batch_size: 2
num_epochs: 3
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.00002

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

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

warmup_ratio: 0.05
evals_per_epoch: 4
saves_per_epoch: 1
debug:
#deepspeed: deepspeed_configs/zero2.json
#deepspeed: /training/axolotl/axolotl/deepspeed_configs/zero2.json
weight_decay: 0.0
#fsdp:
#fsdp_config:
#  fsdp_limit_all_gathers: true
#  fsdp_sync_module_states: true
#  fsdp_offload_params: true
#  fsdp_use_orig_params: false
#  fsdp_cpu_ram_efficient_loading: true
#  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
#  fsdp_transformer_layer_cls_to_wrap: Qwen2DecoderLayer
#  fsdp_state_dict_type: FULL_STATE_DICT
special_tokens:
Axolotl Configyaml
base_model: NewEden/Qwen-1.5B-Claude
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

trust_remote_code: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: civit-slop-combined.jsonl 
    type: alpaca
    conversation: mpt-30b-instruct

chat_template: alpaca

dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/sd-prompter
sequence_len: 2048
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: SDprompt-qwen
wandb_entity:
wandb_watch:
wandb_name: qwen1.5b-2
wandb_log_model:

gradient_accumulation_steps: 64
micro_batch_size: 2
num_epochs: 3
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.00002

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

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

warmup_ratio: 0.05
evals_per_epoch: 4
saves_per_epoch: 1
debug:
#deepspeed: deepspeed_configs/zero2.json
#deepspeed: /training/axolotl/axolotl/deepspeed_configs/zero2.json
weight_decay: 0.0
#fsdp:
#fsdp_config:
#  fsdp_limit_all_gathers: true
#  fsdp_sync_module_states: true
#  fsdp_offload_params: true
#  fsdp_use_orig_params: false
#  fsdp_cpu_ram_efficient_loading: true
#  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
#  fsdp_transformer_layer_cls_to_wrap: Qwen2DecoderLayer
#  fsdp_state_dict_type: FULL_STATE_DICT
special_tokens:
Axolotl Configyaml
base_model: NewEden/Qwen-1.5B-Claude
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

trust_remote_code: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: civit-slop-combined.jsonl 
    type: alpaca
    conversation: mpt-30b-instruct

chat_template: alpaca

dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/sd-prompter
sequence_len: 2048
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: SDprompt-qwen
wandb_entity:
wandb_watch:
wandb_name: qwen1.5b-2
wandb_log_model:

gradient_accumulation_steps: 64
micro_batch_size: 2
num_epochs: 3
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.00002

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

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

warmup_ratio: 0.05
evals_per_epoch: 4
saves_per_epoch: 1
debug:
#deepspeed: deepspeed_configs/zero2.json
#deepspeed: /training/axolotl/axolotl/deepspeed_configs/zero2.json
weight_decay: 0.0
#fsdp:
#fsdp_config:
#  fsdp_limit_all_gathers: true
#  fsdp_sync_module_states: true
#  fsdp_offload_params: true
#  fsdp_use_orig_params: false
#  fsdp_cpu_ram_efficient_loading: true
#  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
#  fsdp_transformer_layer_cls_to_wrap: Qwen2DecoderLayer
#  fsdp_state_dict_type: FULL_STATE_DICT
special_tokens:
Axolotl Configyaml
base_model: NewEden/Qwen-1.5B-Claude
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

trust_remote_code: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: civit-slop-combined.jsonl 
    type: alpaca
    conversation: mpt-30b-instruct

chat_template: alpaca

dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/sd-prompter
sequence_len: 2048
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: SDprompt-qwen
wandb_entity:
wandb_watch:
wandb_name: qwen1.5b-2
wandb_log_model:

gradient_accumulation_steps: 64
micro_batch_size: 2
num_epochs: 3
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.00002

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

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

warmup_ratio: 0.05
evals_per_epoch: 4
saves_per_epoch: 1
debug:
#deepspeed: deepspeed_configs/zero2.json
#deepspeed: /training/axolotl/axolotl/deepspeed_configs/zero2.json
weight_decay: 0.0
#fsdp:
#fsdp_config:
#  fsdp_limit_all_gathers: true
#  fsdp_sync_module_states: true
#  fsdp_offload_params: true
#  fsdp_use_orig_params: false
#  fsdp_cpu_ram_efficient_loading: true
#  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
#  fsdp_transformer_layer_cls_to_wrap: Qwen2DecoderLayer
#  fsdp_state_dict_type: FULL_STATE_DICT
special_tokens:
Axolotl Configyaml
base_model: NewEden/Qwen-1.5B-Claude
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

trust_remote_code: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: civit-slop-combined.jsonl 
    type: alpaca
    conversation: mpt-30b-instruct

chat_template: alpaca

dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/sd-prompter
sequence_len: 2048
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: SDprompt-qwen
wandb_entity:
wandb_watch:
wandb_name: qwen1.5b-2
wandb_log_model:

gradient_accumulation_steps: 64
micro_batch_size: 2
num_epochs: 3
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.00002

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

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

warmup_ratio: 0.05
evals_per_epoch: 4
saves_per_epoch: 1
debug:
#deepspeed: deepspeed_configs/zero2.json
#deepspeed: /training/axolotl/axolotl/deepspeed_configs/zero2.json
weight_decay: 0.0
#fsdp:
#fsdp_config:
#  fsdp_limit_all_gathers: true
#  fsdp_sync_module_states: true
#  fsdp_offload_params: true
#  fsdp_use_orig_params: false
#  fsdp_cpu_ram_efficient_loading: true
#  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
#  fsdp_transformer_layer_cls_to_wrap: Qwen2DecoderLayer
#  fsdp_state_dict_type: FULL_STATE_DICT
special_tokens:
Axolotl Configyaml
base_model: NewEden/Qwen-1.5B-Claude
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

trust_remote_code: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: civit-slop-combined.jsonl 
    type: alpaca
    conversation: mpt-30b-instruct

chat_template: alpaca

dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/sd-prompter
sequence_len: 2048
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: SDprompt-qwen
wandb_entity:
wandb_watch:
wandb_name: qwen1.5b-2
wandb_log_model:

gradient_accumulation_steps: 64
micro_batch_size: 2
num_epochs: 3
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.00002

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

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

warmup_ratio: 0.05
evals_per_epoch: 4
saves_per_epoch: 1
debug:
#deepspeed: deepspeed_configs/zero2.json
#deepspeed: /training/axolotl/axolotl/deepspeed_configs/zero2.json
weight_decay: 0.0
#fsdp:
#fsdp_config:
#  fsdp_limit_all_gathers: true
#  fsdp_sync_module_states: true
#  fsdp_offload_params: true
#  fsdp_use_orig_params: false
#  fsdp_cpu_ram_efficient_loading: true
#  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
#  fsdp_transformer_layer_cls_to_wrap: Qwen2DecoderLayer
#  fsdp_state_dict_type: FULL_STATE_DICT
special_tokens:
Axolotl Configyaml
base_model: NewEden/Qwen-1.5B-Claude
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

trust_remote_code: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: civit-slop-combined.jsonl 
    type: alpaca
    conversation: mpt-30b-instruct

chat_template: alpaca

dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/sd-prompter
sequence_len: 2048
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: SDprompt-qwen
wandb_entity:
wandb_watch:
wandb_name: qwen1.5b-2
wandb_log_model:

gradient_accumulation_steps: 64
micro_batch_size: 2
num_epochs: 3
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.00002

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

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

warmup_ratio: 0.05
evals_per_epoch: 4
saves_per_epoch: 1
debug:
#deepspeed: deepspeed_configs/zero2.json
#deepspeed: /training/axolotl/axolotl/deepspeed_configs/zero2.json
weight_decay: 0.0
#fsdp:
#fsdp_config:
#  fsdp_limit_all_gathers: true
#  fsdp_sync_module_states: true
#  fsdp_offload_params: true
#  fsdp_use_orig_params: false
#  fsdp_cpu_ram_efficient_loading: true
#  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
#  fsdp_transformer_layer_cls_to_wrap: Qwen2DecoderLayer
#  fsdp_state_dict_type: FULL_STATE_DICT
special_tokens:
Axolotl Configyaml
base_model: NewEden/Qwen-1.5B-Claude
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

trust_remote_code: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: civit-slop-combined.jsonl 
    type: alpaca
    conversation: mpt-30b-instruct

chat_template: alpaca

dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/sd-prompter
sequence_len: 2048
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: SDprompt-qwen
wandb_entity:
wandb_watch:
wandb_name: qwen1.5b-2
wandb_log_model:

gradient_accumulation_steps: 64
micro_batch_size: 2
num_epochs: 3
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.00002

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

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

warmup_ratio: 0.05
evals_per_epoch: 4
saves_per_epoch: 1
debug:
#deepspeed: deepspeed_configs/zero2.json
#deepspeed: /training/axolotl/axolotl/deepspeed_configs/zero2.json
weight_decay: 0.0
#fsdp:
#fsdp_config:
#  fsdp_limit_all_gathers: true
#  fsdp_sync_module_states: true
#  fsdp_offload_params: true
#  fsdp_use_orig_params: false
#  fsdp_cpu_ram_efficient_loading: true
#  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
#  fsdp_transformer_layer_cls_to_wrap: Qwen2DecoderLayer
#  fsdp_state_dict_type: FULL_STATE_DICT
special_tokens:
Axolotl Configyaml
base_model: NewEden/Qwen-1.5B-Claude
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

trust_remote_code: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: civit-slop-combined.jsonl 
    type: alpaca
    conversation: mpt-30b-instruct

chat_template: alpaca

dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/sd-prompter
sequence_len: 2048
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: SDprompt-qwen
wandb_entity:
wandb_watch:
wandb_name: qwen1.5b-2
wandb_log_model:

gradient_accumulation_steps: 64
micro_batch_size: 2
num_epochs: 3
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.00002

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

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

warmup_ratio: 0.05
evals_per_epoch: 4
saves_per_epoch: 1
debug:
#deepspeed: deepspeed_configs/zero2.json
#deepspeed: /training/axolotl/axolotl/deepspeed_configs/zero2.json
weight_decay: 0.0
#fsdp:
#fsdp_config:
#  fsdp_limit_all_gathers: true
#  fsdp_sync_module_states: true
#  fsdp_offload_params: true
#  fsdp_use_orig_params: false
#  fsdp_cpu_ram_efficient_loading: true
#  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
#  fsdp_transformer_layer_cls_to_wrap: Qwen2DecoderLayer
#  fsdp_state_dict_type: FULL_STATE_DICT
special_tokens:
Axolotl Configyaml
base_model: NewEden/Qwen-1.5B-Claude
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

trust_remote_code: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: civit-slop-combined.jsonl 
    type: alpaca
    conversation: mpt-30b-instruct

chat_template: alpaca

dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/sd-prompter
sequence_len: 2048
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: SDprompt-qwen
wandb_entity:
wandb_watch:
wandb_name: qwen1.5b-2
wandb_log_model:

gradient_accumulation_steps: 64
micro_batch_size: 2
num_epochs: 3
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.00002

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

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

warmup_ratio: 0.05
evals_per_epoch: 4
saves_per_epoch: 1
debug:
#deepspeed: deepspeed_configs/zero2.json
#deepspeed: /training/axolotl/axolotl/deepspeed_configs/zero2.json
weight_decay: 0.0
#fsdp:
#fsdp_config:
#  fsdp_limit_all_gathers: true
#  fsdp_sync_module_states: true
#  fsdp_offload_params: true
#  fsdp_use_orig_params: false
#  fsdp_cpu_ram_efficient_loading: true
#  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
#  fsdp_transformer_layer_cls_to_wrap: Qwen2DecoderLayer
#  fsdp_state_dict_type: FULL_STATE_DICT
special_tokens:
Axolotl Configyaml
base_model: NewEden/Qwen-1.5B-Claude
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

trust_remote_code: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: civit-slop-combined.jsonl 
    type: alpaca
    conversation: mpt-30b-instruct

chat_template: alpaca

dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/sd-prompter
sequence_len: 2048
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: SDprompt-qwen
wandb_entity:
wandb_watch:
wandb_name: qwen1.5b-2
wandb_log_model:

gradient_accumulation_steps: 64
micro_batch_size: 2
num_epochs: 3
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.00002

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

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

warmup_ratio: 0.05
evals_per_epoch: 4
saves_per_epoch: 1
debug:
#deepspeed: deepspeed_configs/zero2.json
#deepspeed: /training/axolotl/axolotl/deepspeed_configs/zero2.json
weight_decay: 0.0
#fsdp:
#fsdp_config:
#  fsdp_limit_all_gathers: true
#  fsdp_sync_module_states: true
#  fsdp_offload_params: true
#  fsdp_use_orig_params: false
#  fsdp_cpu_ram_efficient_loading: true
#  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
#  fsdp_transformer_layer_cls_to_wrap: Qwen2DecoderLayer
#  fsdp_state_dict_type: FULL_STATE_DICT
special_tokens:
Axolotl Configyaml
base_model: NewEden/Qwen-1.5B-Claude
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

trust_remote_code: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: civit-slop-combined.jsonl 
    type: alpaca
    conversation: mpt-30b-instruct

chat_template: alpaca

dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/sd-prompter
sequence_len: 2048
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: SDprompt-qwen
wandb_entity:
wandb_watch:
wandb_name: qwen1.5b-2
wandb_log_model:

gradient_accumulation_steps: 64
micro_batch_size: 2
num_epochs: 3
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.00002

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

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

warmup_ratio: 0.05
evals_per_epoch: 4
saves_per_epoch: 1
debug:
#deepspeed: deepspeed_configs/zero2.json
#deepspeed: /training/axolotl/axolotl/deepspeed_configs/zero2.json
weight_decay: 0.0
#fsdp:
#fsdp_config:
#  fsdp_limit_all_gathers: true
#  fsdp_sync_module_states: true
#  fsdp_offload_params: true
#  fsdp_use_orig_params: false
#  fsdp_cpu_ram_efficient_loading: true
#  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
#  fsdp_transformer_layer_cls_to_wrap: Qwen2DecoderLayer
#  fsdp_state_dict_type: FULL_STATE_DICT
special_tokens:
Axolotl Configyaml
base_model: NewEden/Qwen-1.5B-Claude
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

trust_remote_code: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: civit-slop-combined.jsonl 
    type: alpaca
    conversation: mpt-30b-instruct

chat_template: alpaca

dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/sd-prompter
sequence_len: 2048
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: SDprompt-qwen
wandb_entity:
wandb_watch:
wandb_name: qwen1.5b-2
wandb_log_model:

gradient_accumulation_steps: 64
micro_batch_size: 2
num_epochs: 3
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.00002

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

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

warmup_ratio: 0.05
evals_per_epoch: 4
saves_per_epoch: 1
debug:
#deepspeed: deepspeed_configs/zero2.json
#deepspeed: /training/axolotl/axolotl/deepspeed_configs/zero2.json
weight_decay: 0.0
#fsdp:
#fsdp_config:
#  fsdp_limit_all_gathers: true
#  fsdp_sync_module_states: true
#  fsdp_offload_params: true
#  fsdp_use_orig_params: false
#  fsdp_cpu_ram_efficient_loading: true
#  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
#  fsdp_transformer_layer_cls_to_wrap: Qwen2DecoderLayer
#  fsdp_state_dict_type: FULL_STATE_DICT
special_tokens:
Axolotl Configyaml
base_model: NewEden/Qwen-1.5B-Claude
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

trust_remote_code: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: civit-slop-combined.jsonl 
    type: alpaca
    conversation: mpt-30b-instruct

chat_template: alpaca

dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/sd-prompter
sequence_len: 2048
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: SDprompt-qwen
wandb_entity:
wandb_watch:
wandb_name: qwen1.5b-2
wandb_log_model:

gradient_accumulation_steps: 64
micro_batch_size: 2
num_epochs: 3
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.00002

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

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

warmup_ratio: 0.05
evals_per_epoch: 4
saves_per_epoch: 1
debug:
#deepspeed: deepspeed_configs/zero2.json
#deepspeed: /training/axolotl/axolotl/deepspeed_configs/zero2.json
weight_decay: 0.0
#fsdp:
#fsdp_config:
#  fsdp_limit_all_gathers: true
#  fsdp_sync_module_states: true
#  fsdp_offload_params: true
#  fsdp_use_orig_params: false
#  fsdp_cpu_ram_efficient_loading: true
#  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
#  fsdp_transformer_layer_cls_to_wrap: Qwen2DecoderLayer
#  fsdp_state_dict_type: FULL_STATE_DICT
special_tokens:
Axolotl Configyaml
base_model: NewEden/Qwen-1.5B-Claude
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

trust_remote_code: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: civit-slop-combined.jsonl 
    type: alpaca
    conversation: mpt-30b-instruct

chat_template: alpaca

dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/sd-prompter
sequence_len: 2048
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: SDprompt-qwen
wandb_entity:
wandb_watch:
wandb_name: qwen1.5b-2
wandb_log_model:

gradient_accumulation_steps: 64
micro_batch_size: 2
num_epochs: 3
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.00002

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

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

warmup_ratio: 0.05
evals_per_epoch: 4
saves_per_epoch: 1
debug:
#deepspeed: deepspeed_configs/zero2.json
#deepspeed: /training/axolotl/axolotl/deepspeed_configs/zero2.json
weight_decay: 0.0
#fsdp:
#fsdp_config:
#  fsdp_limit_all_gathers: true
#  fsdp_sync_module_states: true
#  fsdp_offload_params: true
#  fsdp_use_orig_params: false
#  fsdp_cpu_ram_efficient_loading: true
#  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
#  fsdp_transformer_layer_cls_to_wrap: Qwen2DecoderLayer
#  fsdp_state_dict_type: FULL_STATE_DICT
special_tokens:
Axolotl Configyaml
base_model: NewEden/Qwen-1.5B-Claude
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

trust_remote_code: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: civit-slop-combined.jsonl 
    type: alpaca
    conversation: mpt-30b-instruct

chat_template: alpaca

dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/sd-prompter
sequence_len: 2048
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: SDprompt-qwen
wandb_entity:
wandb_watch:
wandb_name: qwen1.5b-2
wandb_log_model:

gradient_accumulation_steps: 64
micro_batch_size: 2
num_epochs: 3
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.00002

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

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

warmup_ratio: 0.05
evals_per_epoch: 4
saves_per_epoch: 1
debug:
#deepspeed: deepspeed_configs/zero2.json
#deepspeed: /training/axolotl/axolotl/deepspeed_configs/zero2.json
weight_decay: 0.0
#fsdp:
#fsdp_config:
#  fsdp_limit_all_gathers: true
#  fsdp_sync_module_states: true
#  fsdp_offload_params: true
#  fsdp_use_orig_params: false
#  fsdp_cpu_ram_efficient_loading: true
#  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
#  fsdp_transformer_layer_cls_to_wrap: Qwen2DecoderLayer
#  fsdp_state_dict_type: FULL_STATE_DICT
special_tokens:
Axolotl Configyaml
base_model: NewEden/Qwen-1.5B-Claude
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

trust_remote_code: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: civit-slop-combined.jsonl 
    type: alpaca
    conversation: mpt-30b-instruct

chat_template: alpaca

dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/sd-prompter
sequence_len: 2048
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: SDprompt-qwen
wandb_entity:
wandb_watch:
wandb_name: qwen1.5b-2
wandb_log_model:

gradient_accumulation_steps: 64
micro_batch_size: 2
num_epochs: 3
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.00002

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

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

warmup_ratio: 0.05
evals_per_epoch: 4
saves_per_epoch: 1
debug:
#deepspeed: deepspeed_configs/zero2.json
#deepspeed: /training/axolotl/axolotl/deepspeed_configs/zero2.json
weight_decay: 0.0
#fsdp:
#fsdp_config:
#  fsdp_limit_all_gathers: true
#  fsdp_sync_module_states: true
#  fsdp_offload_params: true
#  fsdp_use_orig_params: false
#  fsdp_cpu_ram_efficient_loading: true
#  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
#  fsdp_transformer_layer_cls_to_wrap: Qwen2DecoderLayer
#  fsdp_state_dict_type: FULL_STATE_DICT
special_tokens:
Axolotl Configyaml
base_model: NewEden/Qwen-1.5B-Claude
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

trust_remote_code: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: civit-slop-combined.jsonl 
    type: alpaca
    conversation: mpt-30b-instruct

chat_template: alpaca

dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/sd-prompter
sequence_len: 2048
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: SDprompt-qwen
wandb_entity:
wandb_watch:
wandb_name: qwen1.5b-2
wandb_log_model:

gradient_accumulation_steps: 64
micro_batch_size: 2
num_epochs: 3
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.00002

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

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

warmup_ratio: 0.05
evals_per_epoch: 4
saves_per_epoch: 1
debug:
#deepspeed: deepspeed_configs/zero2.json
#deepspeed: /training/axolotl/axolotl/deepspeed_configs/zero2.json
weight_decay: 0.0
#fsdp:
#fsdp_config:
#  fsdp_limit_all_gathers: true
#  fsdp_sync_module_states: true
#  fsdp_offload_params: true
#  fsdp_use_orig_params: false
#  fsdp_cpu_ram_efficient_loading: true
#  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
#  fsdp_transformer_layer_cls_to_wrap: Qwen2DecoderLayer
#  fsdp_state_dict_type: FULL_STATE_DICT
special_tokens:
Axolotl Configyaml
base_model: NewEden/Qwen-1.5B-Claude
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

trust_remote_code: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: civit-slop-combined.jsonl 
    type: alpaca
    conversation: mpt-30b-instruct

chat_template: alpaca

dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/sd-prompter
sequence_len: 2048
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: SDprompt-qwen
wandb_entity:
wandb_watch:
wandb_name: qwen1.5b-2
wandb_log_model:

gradient_accumulation_steps: 64
micro_batch_size: 2
num_epochs: 3
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.00002

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

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

warmup_ratio: 0.05
evals_per_epoch: 4
saves_per_epoch: 1
debug:
#deepspeed: deepspeed_configs/zero2.json
#deepspeed: /training/axolotl/axolotl/deepspeed_configs/zero2.json
weight_decay: 0.0
#fsdp:
#fsdp_config:
#  fsdp_limit_all_gathers: true
#  fsdp_sync_module_states: true
#  fsdp_offload_params: true
#  fsdp_use_orig_params: false
#  fsdp_cpu_ram_efficient_loading: true
#  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
#  fsdp_transformer_layer_cls_to_wrap: Qwen2DecoderLayer
#  fsdp_state_dict_type: FULL_STATE_DICT
special_tokens:
Axolotl Configyaml
base_model: NewEden/Qwen-1.5B-Claude
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

trust_remote_code: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: civit-slop-combined.jsonl 
    type: alpaca
    conversation: mpt-30b-instruct

chat_template: alpaca

dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/sd-prompter
sequence_len: 2048
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: SDprompt-qwen
wandb_entity:
wandb_watch:
wandb_name: qwen1.5b-2
wandb_log_model:

gradient_accumulation_steps: 64
micro_batch_size: 2
num_epochs: 3
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.00002

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

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

warmup_ratio: 0.05
evals_per_epoch: 4
saves_per_epoch: 1
debug:
#deepspeed: deepspeed_configs/zero2.json
#deepspeed: /training/axolotl/axolotl/deepspeed_configs/zero2.json
weight_decay: 0.0
#fsdp:
#fsdp_config:
#  fsdp_limit_all_gathers: true
#  fsdp_sync_module_states: true
#  fsdp_offload_params: true
#  fsdp_use_orig_params: false
#  fsdp_cpu_ram_efficient_loading: true
#  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
#  fsdp_transformer_layer_cls_to_wrap: Qwen2DecoderLayer
#  fsdp_state_dict_type: FULL_STATE_DICT
special_tokens:
Axolotl Configyaml
base_model: NewEden/Qwen-1.5B-Claude
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

trust_remote_code: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: civit-slop-combined.jsonl 
    type: alpaca
    conversation: mpt-30b-instruct

chat_template: alpaca

dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/sd-prompter
sequence_len: 2048
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: SDprompt-qwen
wandb_entity:
wandb_watch:
wandb_name: qwen1.5b-2
wandb_log_model:

gradient_accumulation_steps: 64
micro_batch_size: 2
num_epochs: 3
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.00002

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

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

warmup_ratio: 0.05
evals_per_epoch: 4
saves_per_epoch: 1
debug:
#deepspeed: deepspeed_configs/zero2.json
#deepspeed: /training/axolotl/axolotl/deepspeed_configs/zero2.json
weight_decay: 0.0
#fsdp:
#fsdp_config:
#  fsdp_limit_all_gathers: true
#  fsdp_sync_module_states: true
#  fsdp_offload_params: true
#  fsdp_use_orig_params: false
#  fsdp_cpu_ram_efficient_loading: true
#  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
#  fsdp_transformer_layer_cls_to_wrap: Qwen2DecoderLayer
#  fsdp_state_dict_type: FULL_STATE_DICT
special_tokens:
Axolotl Configyaml
base_model: NewEden/Qwen-1.5B-Claude
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

trust_remote_code: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: civit-slop-combined.jsonl 
    type: alpaca
    conversation: mpt-30b-instruct

chat_template: alpaca

dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/sd-prompter
sequence_len: 2048
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: SDprompt-qwen
wandb_entity:
wandb_watch:
wandb_name: qwen1.5b-2
wandb_log_model:

gradient_accumulation_steps: 64
micro_batch_size: 2
num_epochs: 3
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.00002

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

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

warmup_ratio: 0.05
evals_per_epoch: 4
saves_per_epoch: 1
debug:
#deepspeed: deepspeed_configs/zero2.json
#deepspeed: /training/axolotl/axolotl/deepspeed_configs/zero2.json
weight_decay: 0.0
#fsdp:
#fsdp_config:
#  fsdp_limit_all_gathers: true
#  fsdp_sync_module_states: true
#  fsdp_offload_params: true
#  fsdp_use_orig_params: false
#  fsdp_cpu_ram_efficient_loading: true
#  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
#  fsdp_transformer_layer_cls_to_wrap: Qwen2DecoderLayer
#  fsdp_state_dict_type: FULL_STATE_DICT
special_tokens:
Axolotl Configyaml
base_model: NewEden/Qwen-1.5B-Claude
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

trust_remote_code: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: civit-slop-combined.jsonl 
    type: alpaca
    conversation: mpt-30b-instruct

chat_template: alpaca

dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/sd-prompter
sequence_len: 2048
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: SDprompt-qwen
wandb_entity:
wandb_watch:
wandb_name: qwen1.5b-2
wandb_log_model:

gradient_accumulation_steps: 64
micro_batch_size: 2
num_epochs: 3
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.00002

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

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

warmup_ratio: 0.05
evals_per_epoch: 4
saves_per_epoch: 1
debug:
#deepspeed: deepspeed_configs/zero2.json
#deepspeed: /training/axolotl/axolotl/deepspeed_configs/zero2.json
weight_decay: 0.0
#fsdp:
#fsdp_config:
#  fsdp_limit_all_gathers: true
#  fsdp_sync_module_states: true
#  fsdp_offload_params: true
#  fsdp_use_orig_params: false
#  fsdp_cpu_ram_efficient_loading: true
#  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
#  fsdp_transformer_layer_cls_to_wrap: Qwen2DecoderLayer
#  fsdp_state_dict_type: FULL_STATE_DICT
special_tokens:
Axolotl Configyaml
base_model: NewEden/Qwen-1.5B-Claude
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

trust_remote_code: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: civit-slop-combined.jsonl 
    type: alpaca
    conversation: mpt-30b-instruct

chat_template: alpaca

dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/sd-prompter
sequence_len: 2048
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: SDprompt-qwen
wandb_entity:
wandb_watch:
wandb_name: qwen1.5b-2
wandb_log_model:

gradient_accumulation_steps: 64
micro_batch_size: 2
num_epochs: 3
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.00002

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

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

warmup_ratio: 0.05
evals_per_epoch: 4
saves_per_epoch: 1
debug:
#deepspeed: deepspeed_configs/zero2.json
#deepspeed: /training/axolotl/axolotl/deepspeed_configs/zero2.json
weight_decay: 0.0
#fsdp:
#fsdp_config:
#  fsdp_limit_all_gathers: true
#  fsdp_sync_module_states: true
#  fsdp_offload_params: true
#  fsdp_use_orig_params: false
#  fsdp_cpu_ram_efficient_loading: true
#  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
#  fsdp_transformer_layer_cls_to_wrap: Qwen2DecoderLayer
#  fsdp_state_dict_type: FULL_STATE_DICT
special_tokens:
Axolotl Configyaml
base_model: NewEden/Qwen-1.5B-Claude
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

trust_remote_code: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: civit-slop-combined.jsonl 
    type: alpaca
    conversation: mpt-30b-instruct

chat_template: alpaca

dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/sd-prompter
sequence_len: 2048
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: SDprompt-qwen
wandb_entity:
wandb_watch:
wandb_name: qwen1.5b-2
wandb_log_model:

gradient_accumulation_steps: 64
micro_batch_size: 2
num_epochs: 3
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.00002

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

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

warmup_ratio: 0.05
evals_per_epoch: 4
saves_per_epoch: 1
debug:
#deepspeed: deepspeed_configs/zero2.json
#deepspeed: /training/axolotl/axolotl/deepspeed_configs/zero2.json
weight_decay: 0.0
#fsdp:
#fsdp_config:
#  fsdp_limit_all_gathers: true
#  fsdp_sync_module_states: true
#  fsdp_offload_params: true
#  fsdp_use_orig_params: false
#  fsdp_cpu_ram_efficient_loading: true
#  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
#  fsdp_transformer_layer_cls_to_wrap: Qwen2DecoderLayer
#  fsdp_state_dict_type: FULL_STATE_DICT
special_tokens:
Axolotl Configyaml
base_model: NewEden/Qwen-1.5B-Claude
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

trust_remote_code: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: civit-slop-combined.jsonl 
    type: alpaca
    conversation: mpt-30b-instruct

chat_template: alpaca

dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/sd-prompter
sequence_len: 2048
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: SDprompt-qwen
wandb_entity:
wandb_watch:
wandb_name: qwen1.5b-2
wandb_log_model:

gradient_accumulation_steps: 64
micro_batch_size: 2
num_epochs: 3
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.00002

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

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

warmup_ratio: 0.05
evals_per_epoch: 4
saves_per_epoch: 1
debug:
#deepspeed: deepspeed_configs/zero2.json
#deepspeed: /training/axolotl/axolotl/deepspeed_configs/zero2.json
weight_decay: 0.0
#fsdp:
#fsdp_config:
#  fsdp_limit_all_gathers: true
#  fsdp_sync_module_states: true
#  fsdp_offload_params: true
#  fsdp_use_orig_params: false
#  fsdp_cpu_ram_efficient_loading: true
#  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
#  fsdp_transformer_layer_cls_to_wrap: Qwen2DecoderLayer
#  fsdp_state_dict_type: FULL_STATE_DICT
special_tokens:
Axolotl Configyaml
base_model: NewEden/Qwen-1.5B-Claude
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

trust_remote_code: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: civit-slop-combined.jsonl 
    type: alpaca
    conversation: mpt-30b-instruct

chat_template: alpaca

dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/sd-prompter
sequence_len: 2048
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: SDprompt-qwen
wandb_entity:
wandb_watch:
wandb_name: qwen1.5b-2
wandb_log_model:

gradient_accumulation_steps: 64
micro_batch_size: 2
num_epochs: 3
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.00002

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

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

warmup_ratio: 0.05
evals_per_epoch: 4
saves_per_epoch: 1
debug:
#deepspeed: deepspeed_configs/zero2.json
#deepspeed: /training/axolotl/axolotl/deepspeed_configs/zero2.json
weight_decay: 0.0
#fsdp:
#fsdp_config:
#  fsdp_limit_all_gathers: true
#  fsdp_sync_module_states: true
#  fsdp_offload_params: true
#  fsdp_use_orig_params: false
#  fsdp_cpu_ram_efficient_loading: true
#  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
#  fsdp_transformer_layer_cls_to_wrap: Qwen2DecoderLayer
#  fsdp_state_dict_type: FULL_STATE_DICT
special_tokens:
Axolotl Configyaml
base_model: NewEden/Qwen-1.5B-Claude
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

trust_remote_code: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: civit-slop-combined.jsonl 
    type: alpaca
    conversation: mpt-30b-instruct

chat_template: alpaca

dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/sd-prompter
sequence_len: 2048
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: SDprompt-qwen
wandb_entity:
wandb_watch:
wandb_name: qwen1.5b-2
wandb_log_model:

gradient_accumulation_steps: 64
micro_batch_size: 2
num_epochs: 3
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.00002

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

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

warmup_ratio: 0.05
evals_per_epoch: 4
saves_per_epoch: 1
debug:
#deepspeed: deepspeed_configs/zero2.json
#deepspeed: /training/axolotl/axolotl/deepspeed_configs/zero2.json
weight_decay: 0.0
#fsdp:
#fsdp_config:
#  fsdp_limit_all_gathers: true
#  fsdp_sync_module_states: true
#  fsdp_offload_params: true
#  fsdp_use_orig_params: false
#  fsdp_cpu_ram_efficient_loading: true
#  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
#  fsdp_transformer_layer_cls_to_wrap: Qwen2DecoderLayer
#  fsdp_state_dict_type: FULL_STATE_DICT
special_tokens:
Axolotl Configyaml
base_model: NewEden/Qwen-1.5B-Claude
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

trust_remote_code: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: civit-slop-combined.jsonl 
    type: alpaca
    conversation: mpt-30b-instruct

chat_template: alpaca

dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/sd-prompter
sequence_len: 2048
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: SDprompt-qwen
wandb_entity:
wandb_watch:
wandb_name: qwen1.5b-2
wandb_log_model:

gradient_accumulation_steps: 64
micro_batch_size: 2
num_epochs: 3
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.00002

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

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

warmup_ratio: 0.05
evals_per_epoch: 4
saves_per_epoch: 1
debug:
#deepspeed: deepspeed_configs/zero2.json
#deepspeed: /training/axolotl/axolotl/deepspeed_configs/zero2.json
weight_decay: 0.0
#fsdp:
#fsdp_config:
#  fsdp_limit_all_gathers: true
#  fsdp_sync_module_states: true
#  fsdp_offload_params: true
#  fsdp_use_orig_params: false
#  fsdp_cpu_ram_efficient_loading: true
#  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
#  fsdp_transformer_layer_cls_to_wrap: Qwen2DecoderLayer
#  fsdp_state_dict_type: FULL_STATE_DICT
special_tokens:
Axolotl Configyaml
base_model: NewEden/Qwen-1.5B-Claude
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

trust_remote_code: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: civit-slop-combined.jsonl 
    type: alpaca
    conversation: mpt-30b-instruct

chat_template: alpaca

dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/sd-prompter
sequence_len: 2048
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: SDprompt-qwen
wandb_entity:
wandb_watch:
wandb_name: qwen1.5b-2
wandb_log_model:

gradient_accumulation_steps: 64
micro_batch_size: 2
num_epochs: 3
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.00002

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

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

warmup_ratio: 0.05
evals_per_epoch: 4
saves_per_epoch: 1
debug:
#deepspeed: deepspeed_configs/zero2.json
#deepspeed: /training/axolotl/axolotl/deepspeed_configs/zero2.json
weight_decay: 0.0
#fsdp:
#fsdp_config:
#  fsdp_limit_all_gathers: true
#  fsdp_sync_module_states: true
#  fsdp_offload_params: true
#  fsdp_use_orig_params: false
#  fsdp_cpu_ram_efficient_loading: true
#  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
#  fsdp_transformer_layer_cls_to_wrap: Qwen2DecoderLayer
#  fsdp_state_dict_type: FULL_STATE_DICT
special_tokens:
Axolotl Configyaml
base_model: NewEden/Qwen-1.5B-Claude
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

trust_remote_code: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: civit-slop-combined.jsonl 
    type: alpaca
    conversation: mpt-30b-instruct

chat_template: alpaca

dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/sd-prompter
sequence_len: 2048
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: SDprompt-qwen
wandb_entity:
wandb_watch:
wandb_name: qwen1.5b-2
wandb_log_model:

gradient_accumulation_steps: 64
micro_batch_size: 2
num_epochs: 3
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.00002

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

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

warmup_ratio: 0.05
evals_per_epoch: 4
saves_per_epoch: 1
debug:
#deepspeed: deepspeed_configs/zero2.json
#deepspeed: /training/axolotl/axolotl/deepspeed_configs/zero2.json
weight_decay: 0.0
#fsdp:
#fsdp_config:
#  fsdp_limit_all_gathers: true
#  fsdp_sync_module_states: true
#  fsdp_offload_params: true
#  fsdp_use_orig_params: false
#  fsdp_cpu_ram_efficient_loading: true
#  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
#  fsdp_transformer_layer_cls_to_wrap: Qwen2DecoderLayer
#  fsdp_state_dict_type: FULL_STATE_DICT
special_tokens:
Axolotl Configyaml
base_model: NewEden/Qwen-1.5B-Claude
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

trust_remote_code: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: civit-slop-combined.jsonl 
    type: alpaca
    conversation: mpt-30b-instruct

chat_template: alpaca

dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/sd-prompter
sequence_len: 2048
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: SDprompt-qwen
wandb_entity:
wandb_watch:
wandb_name: qwen1.5b-2
wandb_log_model:

gradient_accumulation_steps: 64
micro_batch_size: 2
num_epochs: 3
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.00002

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

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

warmup_ratio: 0.05
evals_per_epoch: 4
saves_per_epoch: 1
debug:
#deepspeed: deepspeed_configs/zero2.json
#deepspeed: /training/axolotl/axolotl/deepspeed_configs/zero2.json
weight_decay: 0.0
#fsdp:
#fsdp_config:
#  fsdp_limit_all_gathers: true
#  fsdp_sync_module_states: true
#  fsdp_offload_params: true
#  fsdp_use_orig_params: false
#  fsdp_cpu_ram_efficient_loading: true
#  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
#  fsdp_transformer_layer_cls_to_wrap: Qwen2DecoderLayer
#  fsdp_state_dict_type: FULL_STATE_DICT
special_tokens:
Axolotl Configyaml
base_model: NewEden/Qwen-1.5B-Claude
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

trust_remote_code: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: civit-slop-combined.jsonl 
    type: alpaca
    conversation: mpt-30b-instruct

chat_template: alpaca

dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/sd-prompter
sequence_len: 2048
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: SDprompt-qwen
wandb_entity:
wandb_watch:
wandb_name: qwen1.5b-2
wandb_log_model:

gradient_accumulation_steps: 64
micro_batch_size: 2
num_epochs: 3
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.00002

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

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

warmup_ratio: 0.05
evals_per_epoch: 4
saves_per_epoch: 1
debug:
#deepspeed: deepspeed_configs/zero2.json
#deepspeed: /training/axolotl/axolotl/deepspeed_configs/zero2.json
weight_decay: 0.0
#fsdp:
#fsdp_config:
#  fsdp_limit_all_gathers: true
#  fsdp_sync_module_states: true
#  fsdp_offload_params: true
#  fsdp_use_orig_params: false
#  fsdp_cpu_ram_efficient_loading: true
#  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
#  fsdp_transformer_layer_cls_to_wrap: Qwen2DecoderLayer
#  fsdp_state_dict_type: FULL_STATE_DICT
special_tokens:
Axolotl Configyaml
base_model: NewEden/Qwen-1.5B-Claude
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

trust_remote_code: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: civit-slop-combined.jsonl 
    type: alpaca
    conversation: mpt-30b-instruct

chat_template: alpaca

dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/sd-prompter
sequence_len: 2048
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: SDprompt-qwen
wandb_entity:
wandb_watch:
wandb_name: qwen1.5b-2
wandb_log_model:

gradient_accumulation_steps: 64
micro_batch_size: 2
num_epochs: 3
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.00002

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

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

warmup_ratio: 0.05
evals_per_epoch: 4
saves_per_epoch: 1
debug:
#deepspeed: deepspeed_configs/zero2.json
#deepspeed: /training/axolotl/axolotl/deepspeed_configs/zero2.json
weight_decay: 0.0
#fsdp:
#fsdp_config:
#  fsdp_limit_all_gathers: true
#  fsdp_sync_module_states: true
#  fsdp_offload_params: true
#  fsdp_use_orig_params: false
#  fsdp_cpu_ram_efficient_loading: true
#  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
#  fsdp_transformer_layer_cls_to_wrap: Qwen2DecoderLayer
#  fsdp_state_dict_type: FULL_STATE_DICT
special_tokens:
Axolotl Configyaml
base_model: NewEden/Qwen-1.5B-Claude
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

trust_remote_code: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: civit-slop-combined.jsonl 
    type: alpaca
    conversation: mpt-30b-instruct

chat_template: alpaca

dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/sd-prompter
sequence_len: 2048
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: SDprompt-qwen
wandb_entity:
wandb_watch:
wandb_name: qwen1.5b-2
wandb_log_model:

gradient_accumulation_steps: 64
micro_batch_size: 2
num_epochs: 3
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.00002

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

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

warmup_ratio: 0.05
evals_per_epoch: 4
saves_per_epoch: 1
debug:
#deepspeed: deepspeed_configs/zero2.json
#deepspeed: /training/axolotl/axolotl/deepspeed_configs/zero2.json
weight_decay: 0.0
#fsdp:
#fsdp_config:
#  fsdp_limit_all_gathers: true
#  fsdp_sync_module_states: true
#  fsdp_offload_params: true
#  fsdp_use_orig_params: false
#  fsdp_cpu_ram_efficient_loading: true
#  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
#  fsdp_transformer_layer_cls_to_wrap: Qwen2DecoderLayer
#  fsdp_state_dict_type: FULL_STATE_DICT
special_tokens:
Axolotl Configyaml
base_model: NewEden/Qwen-1.5B-Claude
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

trust_remote_code: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: civit-slop-combined.jsonl 
    type: alpaca
    conversation: mpt-30b-instruct

chat_template: alpaca

dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/sd-prompter
sequence_len: 2048
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: SDprompt-qwen
wandb_entity:
wandb_watch:
wandb_name: qwen1.5b-2
wandb_log_model:

gradient_accumulation_steps: 64
micro_batch_size: 2
num_epochs: 3
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.00002

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

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

warmup_ratio: 0.05
evals_per_epoch: 4
saves_per_epoch: 1
debug:
#deepspeed: deepspeed_configs/zero2.json
#deepspeed: /training/axolotl/axolotl/deepspeed_configs/zero2.json
weight_decay: 0.0
#fsdp:
#fsdp_config:
#  fsdp_limit_all_gathers: true
#  fsdp_sync_module_states: true
#  fsdp_offload_params: true
#  fsdp_use_orig_params: false
#  fsdp_cpu_ram_efficient_loading: true
#  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
#  fsdp_transformer_layer_cls_to_wrap: Qwen2DecoderLayer
#  fsdp_state_dict_type: FULL_STATE_DICT
special_tokens:
Axolotl Configyaml
base_model: NewEden/Qwen-1.5B-Claude
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

trust_remote_code: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: civit-slop-combined.jsonl 
    type: alpaca
    conversation: mpt-30b-instruct

chat_template: alpaca

dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/sd-prompter
sequence_len: 2048
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: SDprompt-qwen
wandb_entity:
wandb_watch:
wandb_name: qwen1.5b-2
wandb_log_model:

gradient_accumulation_steps: 64
micro_batch_size: 2
num_epochs: 3
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.00002

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

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

warmup_ratio: 0.05
evals_per_epoch: 4
saves_per_epoch: 1
debug:
#deepspeed: deepspeed_configs/zero2.json
#deepspeed: /training/axolotl/axolotl/deepspeed_configs/zero2.json
weight_decay: 0.0
#fsdp:
#fsdp_config:
#  fsdp_limit_all_gathers: true
#  fsdp_sync_module_states: true
#  fsdp_offload_params: true
#  fsdp_use_orig_params: false
#  fsdp_cpu_ram_efficient_loading: true
#  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
#  fsdp_transformer_layer_cls_to_wrap: Qwen2DecoderLayer
#  fsdp_state_dict_type: FULL_STATE_DICT
special_tokens:
Axolotl Configyaml
base_model: NewEden/Qwen-1.5B-Claude
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

trust_remote_code: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: civit-slop-combined.jsonl 
    type: alpaca
    conversation: mpt-30b-instruct

chat_template: alpaca

dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/sd-prompter
sequence_len: 2048
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: SDprompt-qwen
wandb_entity:
wandb_watch:
wandb_name: qwen1.5b-2
wandb_log_model:

gradient_accumulation_steps: 64
micro_batch_size: 2
num_epochs: 3
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.00002

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

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

warmup_ratio: 0.05
evals_per_epoch: 4
saves_per_epoch: 1
debug:
#deepspeed: deepspeed_configs/zero2.json
#deepspeed: /training/axolotl/axolotl/deepspeed_configs/zero2.json
weight_decay: 0.0
#fsdp:
#fsdp_config:
#  fsdp_limit_all_gathers: true
#  fsdp_sync_module_states: true
#  fsdp_offload_params: true
#  fsdp_use_orig_params: false
#  fsdp_cpu_ram_efficient_loading: true
#  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
#  fsdp_transformer_layer_cls_to_wrap: Qwen2DecoderLayer
#  fsdp_state_dict_type: FULL_STATE_DICT
special_tokens:
Axolotl Configyaml
base_model: NewEden/Qwen-1.5B-Claude
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

trust_remote_code: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: civit-slop-combined.jsonl 
    type: alpaca
    conversation: mpt-30b-instruct

chat_template: alpaca

dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/sd-prompter
sequence_len: 2048
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: SDprompt-qwen
wandb_entity:
wandb_watch:
wandb_name: qwen1.5b-2
wandb_log_model:

gradient_accumulation_steps: 64
micro_batch_size: 2
num_epochs: 3
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.00002

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

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

warmup_ratio: 0.05
evals_per_epoch: 4
saves_per_epoch: 1
debug:
#deepspeed: deepspeed_configs/zero2.json
#deepspeed: /training/axolotl/axolotl/deepspeed_configs/zero2.json
weight_decay: 0.0
#fsdp:
#fsdp_config:
#  fsdp_limit_all_gathers: true
#  fsdp_sync_module_states: true
#  fsdp_offload_params: true
#  fsdp_use_orig_params: false
#  fsdp_cpu_ram_efficient_loading: true
#  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
#  fsdp_transformer_layer_cls_to_wrap: Qwen2DecoderLayer
#  fsdp_state_dict_type: FULL_STATE_DICT
special_tokens:
Axolotl Configyaml
base_model: NewEden/Qwen-1.5B-Claude
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

trust_remote_code: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: civit-slop-combined.jsonl 
    type: alpaca
    conversation: mpt-30b-instruct

chat_template: alpaca

dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/sd-prompter
sequence_len: 2048
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: SDprompt-qwen
wandb_entity:
wandb_watch:
wandb_name: qwen1.5b-2
wandb_log_model:

gradient_accumulation_steps: 64
micro_batch_size: 2
num_epochs: 3
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.00002

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

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

warmup_ratio: 0.05
evals_per_epoch: 4
saves_per_epoch: 1
debug:
#deepspeed: deepspeed_configs/zero2.json
#deepspeed: /training/axolotl/axolotl/deepspeed_configs/zero2.json
weight_decay: 0.0
#fsdp:
#fsdp_config:
#  fsdp_limit_all_gathers: true
#  fsdp_sync_module_states: true
#  fsdp_offload_params: true
#  fsdp_use_orig_params: false
#  fsdp_cpu_ram_efficient_loading: true
#  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
#  fsdp_transformer_layer_cls_to_wrap: Qwen2DecoderLayer
#  fsdp_state_dict_type: FULL_STATE_DICT
special_tokens:
Axolotl Configyaml
base_model: NewEden/Qwen-1.5B-Claude
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

trust_remote_code: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: civit-slop-combined.jsonl 
    type: alpaca
    conversation: mpt-30b-instruct

chat_template: alpaca

dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/sd-prompter
sequence_len: 2048
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: SDprompt-qwen
wandb_entity:
wandb_watch:
wandb_name: qwen1.5b-2
wandb_log_model:

gradient_accumulation_steps: 64
micro_batch_size: 2
num_epochs: 3
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.00002

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

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

warmup_ratio: 0.05
evals_per_epoch: 4
saves_per_epoch: 1
debug:
#deepspeed: deepspeed_configs/zero2.json
#deepspeed: /training/axolotl/axolotl/deepspeed_configs/zero2.json
weight_decay: 0.0
#fsdp:
#fsdp_config:
#  fsdp_limit_all_gathers: true
#  fsdp_sync_module_states: true
#  fsdp_offload_params: true
#  fsdp_use_orig_params: false
#  fsdp_cpu_ram_efficient_loading: true
#  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
#  fsdp_transformer_layer_cls_to_wrap: Qwen2DecoderLayer
#  fsdp_state_dict_type: FULL_STATE_DICT
special_tokens:
Axolotl Configyaml
base_model: NewEden/Qwen-1.5B-Claude
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

trust_remote_code: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: civit-slop-combined.jsonl 
    type: alpaca
    conversation: mpt-30b-instruct

chat_template: alpaca

dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/sd-prompter
sequence_len: 2048
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: SDprompt-qwen
wandb_entity:
wandb_watch:
wandb_name: qwen1.5b-2
wandb_log_model:

gradient_accumulation_steps: 64
micro_batch_size: 2
num_epochs: 3
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.00002

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

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

warmup_ratio: 0.05
evals_per_epoch: 4
saves_per_epoch: 1
debug:
#deepspeed: deepspeed_configs/zero2.json
#deepspeed: /training/axolotl/axolotl/deepspeed_configs/zero2.json
weight_decay: 0.0
#fsdp:
#fsdp_config:
#  fsdp_limit_all_gathers: true
#  fsdp_sync_module_states: true
#  fsdp_offload_params: true
#  fsdp_use_orig_params: false
#  fsdp_cpu_ram_efficient_loading: true
#  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
#  fsdp_transformer_layer_cls_to_wrap: Qwen2DecoderLayer
#  fsdp_state_dict_type: FULL_STATE_DICT
special_tokens:
Axolotl Configyaml
base_model: NewEden/Qwen-1.5B-Claude
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

trust_remote_code: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: civit-slop-combined.jsonl 
    type: alpaca
    conversation: mpt-30b-instruct

chat_template: alpaca

dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/sd-prompter
sequence_len: 2048
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: SDprompt-qwen
wandb_entity:
wandb_watch:
wandb_name: qwen1.5b-2
wandb_log_model:

gradient_accumulation_steps: 64
micro_batch_size: 2
num_epochs: 3
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.00002

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

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

warmup_ratio: 0.05
evals_per_epoch: 4
saves_per_epoch: 1
debug:
#deepspeed: deepspeed_configs/zero2.json
#deepspeed: /training/axolotl/axolotl/deepspeed_configs/zero2.json
weight_decay: 0.0
#fsdp:
#fsdp_config:
#  fsdp_limit_all_gathers: true
#  fsdp_sync_module_states: true
#  fsdp_offload_params: true
#  fsdp_use_orig_params: false
#  fsdp_cpu_ram_efficient_loading: true
#  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
#  fsdp_transformer_layer_cls_to_wrap: Qwen2DecoderLayer
#  fsdp_state_dict_type: FULL_STATE_DICT
special_tokens:
Axolotl Configyaml
base_model: NewEden/Qwen-1.5B-Claude
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

trust_remote_code: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: civit-slop-combined.jsonl 
    type: alpaca
    conversation: mpt-30b-instruct

chat_template: alpaca

dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/sd-prompter
sequence_len: 2048
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: SDprompt-qwen
wandb_entity:
wandb_watch:
wandb_name: qwen1.5b-2
wandb_log_model:

gradient_accumulation_steps: 64
micro_batch_size: 2
num_epochs: 3
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.00002

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

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

warmup_ratio: 0.05
evals_per_epoch: 4
saves_per_epoch: 1
debug:
#deepspeed: deepspeed_configs/zero2.json
#deepspeed: /training/axolotl/axolotl/deepspeed_configs/zero2.json
weight_decay: 0.0
#fsdp:
#fsdp_config:
#  fsdp_limit_all_gathers: true
#  fsdp_sync_module_states: true
#  fsdp_offload_params: true
#  fsdp_use_orig_params: false
#  fsdp_cpu_ram_efficient_loading: true
#  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
#  fsdp_transformer_layer_cls_to_wrap: Qwen2DecoderLayer
#  fsdp_state_dict_type: FULL_STATE_DICT
special_tokens:
Axolotl Configyaml
base_model: NewEden/Qwen-1.5B-Claude
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

trust_remote_code: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: civit-slop-combined.jsonl 
    type: alpaca
    conversation: mpt-30b-instruct

chat_template: alpaca

dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/sd-prompter
sequence_len: 2048
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: SDprompt-qwen
wandb_entity:
wandb_watch:
wandb_name: qwen1.5b-2
wandb_log_model:

gradient_accumulation_steps: 64
micro_batch_size: 2
num_epochs: 3
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.00002

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

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

warmup_ratio: 0.05
evals_per_epoch: 4
saves_per_epoch: 1
debug:
#deepspeed: deepspeed_configs/zero2.json
#deepspeed: /training/axolotl/axolotl/deepspeed_configs/zero2.json
weight_decay: 0.0
#fsdp:
#fsdp_config:
#  fsdp_limit_all_gathers: true
#  fsdp_sync_module_states: true
#  fsdp_offload_params: true
#  fsdp_use_orig_params: false
#  fsdp_cpu_ram_efficient_loading: true
#  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
#  fsdp_transformer_layer_cls_to_wrap: Qwen2DecoderLayer
#  fsdp_state_dict_type: FULL_STATE_DICT
special_tokens:
Axolotl Configyaml
base_model: NewEden/Qwen-1.5B-Claude
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

trust_remote_code: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: civit-slop-combined.jsonl 
    type: alpaca
    conversation: mpt-30b-instruct

chat_template: alpaca

dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/sd-prompter
sequence_len: 2048
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: SDprompt-qwen
wandb_entity:
wandb_watch:
wandb_name: qwen1.5b-2
wandb_log_model:

gradient_accumulation_steps: 64
micro_batch_size: 2
num_epochs: 3
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.00002

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

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

warmup_ratio: 0.05
evals_per_epoch: 4
saves_per_epoch: 1
debug:
#deepspeed: deepspeed_configs/zero2.json
#deepspeed: /training/axolotl/axolotl/deepspeed_configs/zero2.json
weight_decay: 0.0
#fsdp:
#fsdp_config:
#  fsdp_limit_all_gathers: true
#  fsdp_sync_module_states: true
#  fsdp_offload_params: true
#  fsdp_use_orig_params: false
#  fsdp_cpu_ram_efficient_loading: true
#  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
#  fsdp_transformer_layer_cls_to_wrap: Qwen2DecoderLayer
#  fsdp_state_dict_type: FULL_STATE_DICT
special_tokens:
Axolotl Configyaml
base_model: NewEden/Qwen-1.5B-Claude
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

trust_remote_code: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: civit-slop-combined.jsonl 
    type: alpaca
    conversation: mpt-30b-instruct

chat_template: alpaca

dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/sd-prompter
sequence_len: 2048
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: SDprompt-qwen
wandb_entity:
wandb_watch:
wandb_name: qwen1.5b-2
wandb_log_model:

gradient_accumulation_steps: 64
micro_batch_size: 2
num_epochs: 3
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.00002

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

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

warmup_ratio: 0.05
evals_per_epoch: 4
saves_per_epoch: 1
debug:
#deepspeed: deepspeed_configs/zero2.json
#deepspeed: /training/axolotl/axolotl/deepspeed_configs/zero2.json
weight_decay: 0.0
#fsdp:
#fsdp_config:
#  fsdp_limit_all_gathers: true
#  fsdp_sync_module_states: true
#  fsdp_offload_params: true
#  fsdp_use_orig_params: false
#  fsdp_cpu_ram_efficient_loading: true
#  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
#  fsdp_transformer_layer_cls_to_wrap: Qwen2DecoderLayer
#  fsdp_state_dict_type: FULL_STATE_DICT
special_tokens:
Axolotl Configyaml
base_model: NewEden/Qwen-1.5B-Claude
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

trust_remote_code: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: civit-slop-combined.jsonl 
    type: alpaca
    conversation: mpt-30b-instruct

chat_template: alpaca

dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/sd-prompter
sequence_len: 2048
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: SDprompt-qwen
wandb_entity:
wandb_watch:
wandb_name: qwen1.5b-2
wandb_log_model:

gradient_accumulation_steps: 64
micro_batch_size: 2
num_epochs: 3
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.00002

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

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

warmup_ratio: 0.05
evals_per_epoch: 4
saves_per_epoch: 1
debug:
#deepspeed: deepspeed_configs/zero2.json
#deepspeed: /training/axolotl/axolotl/deepspeed_configs/zero2.json
weight_decay: 0.0
#fsdp:
#fsdp_config:
#  fsdp_limit_all_gathers: true
#  fsdp_sync_module_states: true
#  fsdp_offload_params: true
#  fsdp_use_orig_params: false
#  fsdp_cpu_ram_efficient_loading: true
#  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
#  fsdp_transformer_layer_cls_to_wrap: Qwen2DecoderLayer
#  fsdp_state_dict_type: FULL_STATE_DICT
special_tokens:
Axolotl Configyaml
base_model: NewEden/Qwen-1.5B-Claude
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

trust_remote_code: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: civit-slop-combined.jsonl 
    type: alpaca
    conversation: mpt-30b-instruct

chat_template: alpaca

dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/sd-prompter
sequence_len: 2048
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: SDprompt-qwen
wandb_entity:
wandb_watch:
wandb_name: qwen1.5b-2
wandb_log_model:

gradient_accumulation_steps: 64
micro_batch_size: 2
num_epochs: 3
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.00002

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

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

warmup_ratio: 0.05
evals_per_epoch: 4
saves_per_epoch: 1
debug:
#deepspeed: deepspeed_configs/zero2.json
#deepspeed: /training/axolotl/axolotl/deepspeed_configs/zero2.json
weight_decay: 0.0
#fsdp:
#fsdp_config:
#  fsdp_limit_all_gathers: true
#  fsdp_sync_module_states: true
#  fsdp_offload_params: true
#  fsdp_use_orig_params: false
#  fsdp_cpu_ram_efficient_loading: true
#  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
#  fsdp_transformer_layer_cls_to_wrap: Qwen2DecoderLayer
#  fsdp_state_dict_type: FULL_STATE_DICT
special_tokens:

Deploy This Model

Production-ready deployment in minutes

Together.ai

Instant API access to this model

Fastest API

Production-ready inference API. Start free, scale to millions.

Try Free API

Replicate

One-click model deployment

Easiest Setup

Run models in the cloud with simple API. No DevOps required.

Deploy Now

Disclosure: We may earn a commission from these partners. This helps keep LLMYourWay free.