L3.3-70B-Magnum-Diamond-LoRA
5
1
70.0B
BF16
llama
by
Doctor-Shotgun
Other
OTHER
70B params
New
5 downloads
Early-stage
Edge AI:
Mobile
Laptop
Server
157GB+ RAM
Mobile
Laptop
Server
Quick Summary
Magnum "Diamond" in reference to the intense heat and pressure (generated through matrix multiplications) needed to turn the coal-esque material of dry, assista...
Device Compatibility
Mobile
4-6GB RAM
Laptop
16GB RAM
Server
GPU
Minimum Recommended
66GB+ RAM
Code Examples
optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v5-sft-prototype-70b-lora-rev1
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: anthracite-core/magnum-v5-sft-proto-llama3-rev1-32k
ds_type: parquet
type:
shuffle_merged_datasets: true
dataset_prepared_path: /workspace/magnum-70b-data
val_set_size: 0.0
output_dir: /workspace/70b-lora-out
plugins:
- axolotl.integrations.liger.LigerPlugin
- axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true
sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
- embed_tokens
- lm_head
wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 1
micro_batch_size: 2
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4e-5
max_grad_norm: 1.0
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false
gradient_checkpointing: offload
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:
warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16_torch_compile.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
pad_token: <|finetune_right_pad_id|>optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v5-sft-prototype-70b-lora-rev1
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: anthracite-core/magnum-v5-sft-proto-llama3-rev1-32k
ds_type: parquet
type:
shuffle_merged_datasets: true
dataset_prepared_path: /workspace/magnum-70b-data
val_set_size: 0.0
output_dir: /workspace/70b-lora-out
plugins:
- axolotl.integrations.liger.LigerPlugin
- axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true
sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
- embed_tokens
- lm_head
wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 1
micro_batch_size: 2
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4e-5
max_grad_norm: 1.0
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false
gradient_checkpointing: offload
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:
warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16_torch_compile.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
pad_token: <|finetune_right_pad_id|>optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v5-sft-prototype-70b-lora-rev1
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: anthracite-core/magnum-v5-sft-proto-llama3-rev1-32k
ds_type: parquet
type:
shuffle_merged_datasets: true
dataset_prepared_path: /workspace/magnum-70b-data
val_set_size: 0.0
output_dir: /workspace/70b-lora-out
plugins:
- axolotl.integrations.liger.LigerPlugin
- axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true
sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
- embed_tokens
- lm_head
wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 1
micro_batch_size: 2
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4e-5
max_grad_norm: 1.0
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false
gradient_checkpointing: offload
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:
warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16_torch_compile.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
pad_token: <|finetune_right_pad_id|>optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v5-sft-prototype-70b-lora-rev1
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: anthracite-core/magnum-v5-sft-proto-llama3-rev1-32k
ds_type: parquet
type:
shuffle_merged_datasets: true
dataset_prepared_path: /workspace/magnum-70b-data
val_set_size: 0.0
output_dir: /workspace/70b-lora-out
plugins:
- axolotl.integrations.liger.LigerPlugin
- axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true
sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
- embed_tokens
- lm_head
wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 1
micro_batch_size: 2
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4e-5
max_grad_norm: 1.0
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false
gradient_checkpointing: offload
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:
warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16_torch_compile.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
pad_token: <|finetune_right_pad_id|>optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v5-sft-prototype-70b-lora-rev1
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: anthracite-core/magnum-v5-sft-proto-llama3-rev1-32k
ds_type: parquet
type:
shuffle_merged_datasets: true
dataset_prepared_path: /workspace/magnum-70b-data
val_set_size: 0.0
output_dir: /workspace/70b-lora-out
plugins:
- axolotl.integrations.liger.LigerPlugin
- axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true
sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
- embed_tokens
- lm_head
wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 1
micro_batch_size: 2
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4e-5
max_grad_norm: 1.0
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false
gradient_checkpointing: offload
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:
warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16_torch_compile.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
pad_token: <|finetune_right_pad_id|>optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v5-sft-prototype-70b-lora-rev1
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: anthracite-core/magnum-v5-sft-proto-llama3-rev1-32k
ds_type: parquet
type:
shuffle_merged_datasets: true
dataset_prepared_path: /workspace/magnum-70b-data
val_set_size: 0.0
output_dir: /workspace/70b-lora-out
plugins:
- axolotl.integrations.liger.LigerPlugin
- axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true
sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
- embed_tokens
- lm_head
wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 1
micro_batch_size: 2
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4e-5
max_grad_norm: 1.0
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false
gradient_checkpointing: offload
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:
warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16_torch_compile.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
pad_token: <|finetune_right_pad_id|>optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v5-sft-prototype-70b-lora-rev1
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: anthracite-core/magnum-v5-sft-proto-llama3-rev1-32k
ds_type: parquet
type:
shuffle_merged_datasets: true
dataset_prepared_path: /workspace/magnum-70b-data
val_set_size: 0.0
output_dir: /workspace/70b-lora-out
plugins:
- axolotl.integrations.liger.LigerPlugin
- axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true
sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
- embed_tokens
- lm_head
wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 1
micro_batch_size: 2
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4e-5
max_grad_norm: 1.0
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false
gradient_checkpointing: offload
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:
warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16_torch_compile.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
pad_token: <|finetune_right_pad_id|>optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v5-sft-prototype-70b-lora-rev1
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: anthracite-core/magnum-v5-sft-proto-llama3-rev1-32k
ds_type: parquet
type:
shuffle_merged_datasets: true
dataset_prepared_path: /workspace/magnum-70b-data
val_set_size: 0.0
output_dir: /workspace/70b-lora-out
plugins:
- axolotl.integrations.liger.LigerPlugin
- axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true
sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
- embed_tokens
- lm_head
wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 1
micro_batch_size: 2
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4e-5
max_grad_norm: 1.0
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false
gradient_checkpointing: offload
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:
warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16_torch_compile.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
pad_token: <|finetune_right_pad_id|>optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v5-sft-prototype-70b-lora-rev1
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: anthracite-core/magnum-v5-sft-proto-llama3-rev1-32k
ds_type: parquet
type:
shuffle_merged_datasets: true
dataset_prepared_path: /workspace/magnum-70b-data
val_set_size: 0.0
output_dir: /workspace/70b-lora-out
plugins:
- axolotl.integrations.liger.LigerPlugin
- axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true
sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
- embed_tokens
- lm_head
wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 1
micro_batch_size: 2
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4e-5
max_grad_norm: 1.0
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false
gradient_checkpointing: offload
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:
warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16_torch_compile.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
pad_token: <|finetune_right_pad_id|>optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v5-sft-prototype-70b-lora-rev1
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: anthracite-core/magnum-v5-sft-proto-llama3-rev1-32k
ds_type: parquet
type:
shuffle_merged_datasets: true
dataset_prepared_path: /workspace/magnum-70b-data
val_set_size: 0.0
output_dir: /workspace/70b-lora-out
plugins:
- axolotl.integrations.liger.LigerPlugin
- axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true
sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
- embed_tokens
- lm_head
wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 1
micro_batch_size: 2
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4e-5
max_grad_norm: 1.0
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false
gradient_checkpointing: offload
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:
warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16_torch_compile.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
pad_token: <|finetune_right_pad_id|>optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v5-sft-prototype-70b-lora-rev1
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: anthracite-core/magnum-v5-sft-proto-llama3-rev1-32k
ds_type: parquet
type:
shuffle_merged_datasets: true
dataset_prepared_path: /workspace/magnum-70b-data
val_set_size: 0.0
output_dir: /workspace/70b-lora-out
plugins:
- axolotl.integrations.liger.LigerPlugin
- axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true
sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
- embed_tokens
- lm_head
wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 1
micro_batch_size: 2
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4e-5
max_grad_norm: 1.0
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false
gradient_checkpointing: offload
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:
warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16_torch_compile.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
pad_token: <|finetune_right_pad_id|>optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v5-sft-prototype-70b-lora-rev1
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: anthracite-core/magnum-v5-sft-proto-llama3-rev1-32k
ds_type: parquet
type:
shuffle_merged_datasets: true
dataset_prepared_path: /workspace/magnum-70b-data
val_set_size: 0.0
output_dir: /workspace/70b-lora-out
plugins:
- axolotl.integrations.liger.LigerPlugin
- axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true
sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
- embed_tokens
- lm_head
wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 1
micro_batch_size: 2
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4e-5
max_grad_norm: 1.0
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false
gradient_checkpointing: offload
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:
warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16_torch_compile.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
pad_token: <|finetune_right_pad_id|>optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v5-sft-prototype-70b-lora-rev1
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: anthracite-core/magnum-v5-sft-proto-llama3-rev1-32k
ds_type: parquet
type:
shuffle_merged_datasets: true
dataset_prepared_path: /workspace/magnum-70b-data
val_set_size: 0.0
output_dir: /workspace/70b-lora-out
plugins:
- axolotl.integrations.liger.LigerPlugin
- axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true
sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
- embed_tokens
- lm_head
wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 1
micro_batch_size: 2
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4e-5
max_grad_norm: 1.0
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false
gradient_checkpointing: offload
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:
warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16_torch_compile.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
pad_token: <|finetune_right_pad_id|>optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v5-sft-prototype-70b-lora-rev1
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: anthracite-core/magnum-v5-sft-proto-llama3-rev1-32k
ds_type: parquet
type:
shuffle_merged_datasets: true
dataset_prepared_path: /workspace/magnum-70b-data
val_set_size: 0.0
output_dir: /workspace/70b-lora-out
plugins:
- axolotl.integrations.liger.LigerPlugin
- axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true
sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
- embed_tokens
- lm_head
wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 1
micro_batch_size: 2
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4e-5
max_grad_norm: 1.0
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false
gradient_checkpointing: offload
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:
warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16_torch_compile.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
pad_token: <|finetune_right_pad_id|>optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v5-sft-prototype-70b-lora-rev1
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: anthracite-core/magnum-v5-sft-proto-llama3-rev1-32k
ds_type: parquet
type:
shuffle_merged_datasets: true
dataset_prepared_path: /workspace/magnum-70b-data
val_set_size: 0.0
output_dir: /workspace/70b-lora-out
plugins:
- axolotl.integrations.liger.LigerPlugin
- axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true
sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
- embed_tokens
- lm_head
wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 1
micro_batch_size: 2
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4e-5
max_grad_norm: 1.0
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false
gradient_checkpointing: offload
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:
warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16_torch_compile.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
pad_token: <|finetune_right_pad_id|>optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v5-sft-prototype-70b-lora-rev1
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: anthracite-core/magnum-v5-sft-proto-llama3-rev1-32k
ds_type: parquet
type:
shuffle_merged_datasets: true
dataset_prepared_path: /workspace/magnum-70b-data
val_set_size: 0.0
output_dir: /workspace/70b-lora-out
plugins:
- axolotl.integrations.liger.LigerPlugin
- axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true
sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
- embed_tokens
- lm_head
wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 1
micro_batch_size: 2
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4e-5
max_grad_norm: 1.0
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false
gradient_checkpointing: offload
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:
warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16_torch_compile.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
pad_token: <|finetune_right_pad_id|>optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v5-sft-prototype-70b-lora-rev1
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: anthracite-core/magnum-v5-sft-proto-llama3-rev1-32k
ds_type: parquet
type:
shuffle_merged_datasets: true
dataset_prepared_path: /workspace/magnum-70b-data
val_set_size: 0.0
output_dir: /workspace/70b-lora-out
plugins:
- axolotl.integrations.liger.LigerPlugin
- axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true
sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
- embed_tokens
- lm_head
wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 1
micro_batch_size: 2
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4e-5
max_grad_norm: 1.0
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false
gradient_checkpointing: offload
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:
warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16_torch_compile.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
pad_token: <|finetune_right_pad_id|>optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v5-sft-prototype-70b-lora-rev1
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: anthracite-core/magnum-v5-sft-proto-llama3-rev1-32k
ds_type: parquet
type:
shuffle_merged_datasets: true
dataset_prepared_path: /workspace/magnum-70b-data
val_set_size: 0.0
output_dir: /workspace/70b-lora-out
plugins:
- axolotl.integrations.liger.LigerPlugin
- axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true
sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
- embed_tokens
- lm_head
wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 1
micro_batch_size: 2
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4e-5
max_grad_norm: 1.0
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false
gradient_checkpointing: offload
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:
warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16_torch_compile.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
pad_token: <|finetune_right_pad_id|>optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v5-sft-prototype-70b-lora-rev1
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: anthracite-core/magnum-v5-sft-proto-llama3-rev1-32k
ds_type: parquet
type:
shuffle_merged_datasets: true
dataset_prepared_path: /workspace/magnum-70b-data
val_set_size: 0.0
output_dir: /workspace/70b-lora-out
plugins:
- axolotl.integrations.liger.LigerPlugin
- axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true
sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
- embed_tokens
- lm_head
wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 1
micro_batch_size: 2
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4e-5
max_grad_norm: 1.0
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false
gradient_checkpointing: offload
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:
warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16_torch_compile.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
pad_token: <|finetune_right_pad_id|>optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v5-sft-prototype-70b-lora-rev1
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: anthracite-core/magnum-v5-sft-proto-llama3-rev1-32k
ds_type: parquet
type:
shuffle_merged_datasets: true
dataset_prepared_path: /workspace/magnum-70b-data
val_set_size: 0.0
output_dir: /workspace/70b-lora-out
plugins:
- axolotl.integrations.liger.LigerPlugin
- axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true
sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
- embed_tokens
- lm_head
wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 1
micro_batch_size: 2
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4e-5
max_grad_norm: 1.0
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false
gradient_checkpointing: offload
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:
warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16_torch_compile.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
pad_token: <|finetune_right_pad_id|>optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v5-sft-prototype-70b-lora-rev1
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: anthracite-core/magnum-v5-sft-proto-llama3-rev1-32k
ds_type: parquet
type:
shuffle_merged_datasets: true
dataset_prepared_path: /workspace/magnum-70b-data
val_set_size: 0.0
output_dir: /workspace/70b-lora-out
plugins:
- axolotl.integrations.liger.LigerPlugin
- axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true
sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
- embed_tokens
- lm_head
wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 1
micro_batch_size: 2
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4e-5
max_grad_norm: 1.0
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false
gradient_checkpointing: offload
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:
warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16_torch_compile.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
pad_token: <|finetune_right_pad_id|>optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v5-sft-prototype-70b-lora-rev1
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: anthracite-core/magnum-v5-sft-proto-llama3-rev1-32k
ds_type: parquet
type:
shuffle_merged_datasets: true
dataset_prepared_path: /workspace/magnum-70b-data
val_set_size: 0.0
output_dir: /workspace/70b-lora-out
plugins:
- axolotl.integrations.liger.LigerPlugin
- axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true
sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
- embed_tokens
- lm_head
wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 1
micro_batch_size: 2
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4e-5
max_grad_norm: 1.0
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false
gradient_checkpointing: offload
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:
warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16_torch_compile.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
pad_token: <|finetune_right_pad_id|>optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v5-sft-prototype-70b-lora-rev1
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: anthracite-core/magnum-v5-sft-proto-llama3-rev1-32k
ds_type: parquet
type:
shuffle_merged_datasets: true
dataset_prepared_path: /workspace/magnum-70b-data
val_set_size: 0.0
output_dir: /workspace/70b-lora-out
plugins:
- axolotl.integrations.liger.LigerPlugin
- axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true
sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
- embed_tokens
- lm_head
wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 1
micro_batch_size: 2
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4e-5
max_grad_norm: 1.0
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false
gradient_checkpointing: offload
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:
warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16_torch_compile.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
pad_token: <|finetune_right_pad_id|>optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v5-sft-prototype-70b-lora-rev1
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: anthracite-core/magnum-v5-sft-proto-llama3-rev1-32k
ds_type: parquet
type:
shuffle_merged_datasets: true
dataset_prepared_path: /workspace/magnum-70b-data
val_set_size: 0.0
output_dir: /workspace/70b-lora-out
plugins:
- axolotl.integrations.liger.LigerPlugin
- axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true
sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
- embed_tokens
- lm_head
wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 1
micro_batch_size: 2
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4e-5
max_grad_norm: 1.0
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false
gradient_checkpointing: offload
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:
warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16_torch_compile.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
pad_token: <|finetune_right_pad_id|>optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v5-sft-prototype-70b-lora-rev1
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: anthracite-core/magnum-v5-sft-proto-llama3-rev1-32k
ds_type: parquet
type:
shuffle_merged_datasets: true
dataset_prepared_path: /workspace/magnum-70b-data
val_set_size: 0.0
output_dir: /workspace/70b-lora-out
plugins:
- axolotl.integrations.liger.LigerPlugin
- axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true
sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
- embed_tokens
- lm_head
wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 1
micro_batch_size: 2
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4e-5
max_grad_norm: 1.0
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false
gradient_checkpointing: offload
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:
warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16_torch_compile.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
pad_token: <|finetune_right_pad_id|>optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v5-sft-prototype-70b-lora-rev1
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: anthracite-core/magnum-v5-sft-proto-llama3-rev1-32k
ds_type: parquet
type:
shuffle_merged_datasets: true
dataset_prepared_path: /workspace/magnum-70b-data
val_set_size: 0.0
output_dir: /workspace/70b-lora-out
plugins:
- axolotl.integrations.liger.LigerPlugin
- axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true
sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
- embed_tokens
- lm_head
wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 1
micro_batch_size: 2
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4e-5
max_grad_norm: 1.0
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false
gradient_checkpointing: offload
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:
warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16_torch_compile.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
pad_token: <|finetune_right_pad_id|>optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v5-sft-prototype-70b-lora-rev1
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: anthracite-core/magnum-v5-sft-proto-llama3-rev1-32k
ds_type: parquet
type:
shuffle_merged_datasets: true
dataset_prepared_path: /workspace/magnum-70b-data
val_set_size: 0.0
output_dir: /workspace/70b-lora-out
plugins:
- axolotl.integrations.liger.LigerPlugin
- axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true
sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
- embed_tokens
- lm_head
wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 1
micro_batch_size: 2
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4e-5
max_grad_norm: 1.0
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false
gradient_checkpointing: offload
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:
warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16_torch_compile.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
pad_token: <|finetune_right_pad_id|>optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v5-sft-prototype-70b-lora-rev1
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: anthracite-core/magnum-v5-sft-proto-llama3-rev1-32k
ds_type: parquet
type:
shuffle_merged_datasets: true
dataset_prepared_path: /workspace/magnum-70b-data
val_set_size: 0.0
output_dir: /workspace/70b-lora-out
plugins:
- axolotl.integrations.liger.LigerPlugin
- axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true
sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
- embed_tokens
- lm_head
wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 1
micro_batch_size: 2
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4e-5
max_grad_norm: 1.0
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false
gradient_checkpointing: offload
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:
warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16_torch_compile.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
pad_token: <|finetune_right_pad_id|>optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v5-sft-prototype-70b-lora-rev1
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: anthracite-core/magnum-v5-sft-proto-llama3-rev1-32k
ds_type: parquet
type:
shuffle_merged_datasets: true
dataset_prepared_path: /workspace/magnum-70b-data
val_set_size: 0.0
output_dir: /workspace/70b-lora-out
plugins:
- axolotl.integrations.liger.LigerPlugin
- axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true
sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
- embed_tokens
- lm_head
wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 1
micro_batch_size: 2
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4e-5
max_grad_norm: 1.0
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false
gradient_checkpointing: offload
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:
warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16_torch_compile.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
pad_token: <|finetune_right_pad_id|>optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v5-sft-prototype-70b-lora-rev1
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: anthracite-core/magnum-v5-sft-proto-llama3-rev1-32k
ds_type: parquet
type:
shuffle_merged_datasets: true
dataset_prepared_path: /workspace/magnum-70b-data
val_set_size: 0.0
output_dir: /workspace/70b-lora-out
plugins:
- axolotl.integrations.liger.LigerPlugin
- axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true
sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
- embed_tokens
- lm_head
wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 1
micro_batch_size: 2
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4e-5
max_grad_norm: 1.0
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false
gradient_checkpointing: offload
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:
warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16_torch_compile.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
pad_token: <|finetune_right_pad_id|>optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v5-sft-prototype-70b-lora-rev1
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: anthracite-core/magnum-v5-sft-proto-llama3-rev1-32k
ds_type: parquet
type:
shuffle_merged_datasets: true
dataset_prepared_path: /workspace/magnum-70b-data
val_set_size: 0.0
output_dir: /workspace/70b-lora-out
plugins:
- axolotl.integrations.liger.LigerPlugin
- axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true
sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
- embed_tokens
- lm_head
wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 1
micro_batch_size: 2
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4e-5
max_grad_norm: 1.0
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false
gradient_checkpointing: offload
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:
warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16_torch_compile.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
pad_token: <|finetune_right_pad_id|>optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v5-sft-prototype-70b-lora-rev1
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: anthracite-core/magnum-v5-sft-proto-llama3-rev1-32k
ds_type: parquet
type:
shuffle_merged_datasets: true
dataset_prepared_path: /workspace/magnum-70b-data
val_set_size: 0.0
output_dir: /workspace/70b-lora-out
plugins:
- axolotl.integrations.liger.LigerPlugin
- axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true
sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
- embed_tokens
- lm_head
wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 1
micro_batch_size: 2
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4e-5
max_grad_norm: 1.0
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false
gradient_checkpointing: offload
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:
warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16_torch_compile.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
pad_token: <|finetune_right_pad_id|>optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v5-sft-prototype-70b-lora-rev1
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: anthracite-core/magnum-v5-sft-proto-llama3-rev1-32k
ds_type: parquet
type:
shuffle_merged_datasets: true
dataset_prepared_path: /workspace/magnum-70b-data
val_set_size: 0.0
output_dir: /workspace/70b-lora-out
plugins:
- axolotl.integrations.liger.LigerPlugin
- axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true
sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
- embed_tokens
- lm_head
wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 1
micro_batch_size: 2
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4e-5
max_grad_norm: 1.0
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false
gradient_checkpointing: offload
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:
warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16_torch_compile.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
pad_token: <|finetune_right_pad_id|>optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v5-sft-prototype-70b-lora-rev1
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: anthracite-core/magnum-v5-sft-proto-llama3-rev1-32k
ds_type: parquet
type:
shuffle_merged_datasets: true
dataset_prepared_path: /workspace/magnum-70b-data
val_set_size: 0.0
output_dir: /workspace/70b-lora-out
plugins:
- axolotl.integrations.liger.LigerPlugin
- axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true
sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
- embed_tokens
- lm_head
wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 1
micro_batch_size: 2
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4e-5
max_grad_norm: 1.0
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false
gradient_checkpointing: offload
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:
warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16_torch_compile.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
pad_token: <|finetune_right_pad_id|>optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v5-sft-prototype-70b-lora-rev1
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: anthracite-core/magnum-v5-sft-proto-llama3-rev1-32k
ds_type: parquet
type:
shuffle_merged_datasets: true
dataset_prepared_path: /workspace/magnum-70b-data
val_set_size: 0.0
output_dir: /workspace/70b-lora-out
plugins:
- axolotl.integrations.liger.LigerPlugin
- axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true
sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
- embed_tokens
- lm_head
wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 1
micro_batch_size: 2
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4e-5
max_grad_norm: 1.0
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false
gradient_checkpointing: offload
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:
warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16_torch_compile.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
pad_token: <|finetune_right_pad_id|>optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v5-sft-prototype-70b-lora-rev1
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: anthracite-core/magnum-v5-sft-proto-llama3-rev1-32k
ds_type: parquet
type:
shuffle_merged_datasets: true
dataset_prepared_path: /workspace/magnum-70b-data
val_set_size: 0.0
output_dir: /workspace/70b-lora-out
plugins:
- axolotl.integrations.liger.LigerPlugin
- axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true
sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
- embed_tokens
- lm_head
wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 1
micro_batch_size: 2
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4e-5
max_grad_norm: 1.0
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false
gradient_checkpointing: offload
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:
warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16_torch_compile.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
pad_token: <|finetune_right_pad_id|>optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v5-sft-prototype-70b-lora-rev1
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: anthracite-core/magnum-v5-sft-proto-llama3-rev1-32k
ds_type: parquet
type:
shuffle_merged_datasets: true
dataset_prepared_path: /workspace/magnum-70b-data
val_set_size: 0.0
output_dir: /workspace/70b-lora-out
plugins:
- axolotl.integrations.liger.LigerPlugin
- axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true
sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
- embed_tokens
- lm_head
wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 1
micro_batch_size: 2
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4e-5
max_grad_norm: 1.0
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false
gradient_checkpointing: offload
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:
warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16_torch_compile.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
pad_token: <|finetune_right_pad_id|>optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v5-sft-prototype-70b-lora-rev1
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: anthracite-core/magnum-v5-sft-proto-llama3-rev1-32k
ds_type: parquet
type:
shuffle_merged_datasets: true
dataset_prepared_path: /workspace/magnum-70b-data
val_set_size: 0.0
output_dir: /workspace/70b-lora-out
plugins:
- axolotl.integrations.liger.LigerPlugin
- axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true
sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
- embed_tokens
- lm_head
wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 1
micro_batch_size: 2
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4e-5
max_grad_norm: 1.0
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false
gradient_checkpointing: offload
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:
warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16_torch_compile.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
pad_token: <|finetune_right_pad_id|>optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v5-sft-prototype-70b-lora-rev1
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: anthracite-core/magnum-v5-sft-proto-llama3-rev1-32k
ds_type: parquet
type:
shuffle_merged_datasets: true
dataset_prepared_path: /workspace/magnum-70b-data
val_set_size: 0.0
output_dir: /workspace/70b-lora-out
plugins:
- axolotl.integrations.liger.LigerPlugin
- axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true
sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
- embed_tokens
- lm_head
wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 1
micro_batch_size: 2
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4e-5
max_grad_norm: 1.0
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false
gradient_checkpointing: offload
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:
warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16_torch_compile.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
pad_token: <|finetune_right_pad_id|>optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v5-sft-prototype-70b-lora-rev1
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: anthracite-core/magnum-v5-sft-proto-llama3-rev1-32k
ds_type: parquet
type:
shuffle_merged_datasets: true
dataset_prepared_path: /workspace/magnum-70b-data
val_set_size: 0.0
output_dir: /workspace/70b-lora-out
plugins:
- axolotl.integrations.liger.LigerPlugin
- axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true
sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
- embed_tokens
- lm_head
wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 1
micro_batch_size: 2
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4e-5
max_grad_norm: 1.0
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false
gradient_checkpointing: offload
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:
warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16_torch_compile.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
pad_token: <|finetune_right_pad_id|>optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v5-sft-prototype-70b-lora-rev1
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: anthracite-core/magnum-v5-sft-proto-llama3-rev1-32k
ds_type: parquet
type:
shuffle_merged_datasets: true
dataset_prepared_path: /workspace/magnum-70b-data
val_set_size: 0.0
output_dir: /workspace/70b-lora-out
plugins:
- axolotl.integrations.liger.LigerPlugin
- axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true
sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
- embed_tokens
- lm_head
wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 1
micro_batch_size: 2
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4e-5
max_grad_norm: 1.0
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false
gradient_checkpointing: offload
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:
warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16_torch_compile.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
pad_token: <|finetune_right_pad_id|>optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v5-sft-prototype-70b-lora-rev1
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: anthracite-core/magnum-v5-sft-proto-llama3-rev1-32k
ds_type: parquet
type:
shuffle_merged_datasets: true
dataset_prepared_path: /workspace/magnum-70b-data
val_set_size: 0.0
output_dir: /workspace/70b-lora-out
plugins:
- axolotl.integrations.liger.LigerPlugin
- axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true
sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
- embed_tokens
- lm_head
wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 1
micro_batch_size: 2
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4e-5
max_grad_norm: 1.0
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false
gradient_checkpointing: offload
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:
warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16_torch_compile.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
pad_token: <|finetune_right_pad_id|>optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v5-sft-prototype-70b-lora-rev1
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: anthracite-core/magnum-v5-sft-proto-llama3-rev1-32k
ds_type: parquet
type:
shuffle_merged_datasets: true
dataset_prepared_path: /workspace/magnum-70b-data
val_set_size: 0.0
output_dir: /workspace/70b-lora-out
plugins:
- axolotl.integrations.liger.LigerPlugin
- axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true
sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
- embed_tokens
- lm_head
wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 1
micro_batch_size: 2
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4e-5
max_grad_norm: 1.0
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false
gradient_checkpointing: offload
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:
warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16_torch_compile.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
pad_token: <|finetune_right_pad_id|>optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v5-sft-prototype-70b-lora-rev1
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: anthracite-core/magnum-v5-sft-proto-llama3-rev1-32k
ds_type: parquet
type:
shuffle_merged_datasets: true
dataset_prepared_path: /workspace/magnum-70b-data
val_set_size: 0.0
output_dir: /workspace/70b-lora-out
plugins:
- axolotl.integrations.liger.LigerPlugin
- axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true
sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
- embed_tokens
- lm_head
wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 1
micro_batch_size: 2
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4e-5
max_grad_norm: 1.0
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false
gradient_checkpointing: offload
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:
warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16_torch_compile.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
pad_token: <|finetune_right_pad_id|>optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v5-sft-prototype-70b-lora-rev1
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: anthracite-core/magnum-v5-sft-proto-llama3-rev1-32k
ds_type: parquet
type:
shuffle_merged_datasets: true
dataset_prepared_path: /workspace/magnum-70b-data
val_set_size: 0.0
output_dir: /workspace/70b-lora-out
plugins:
- axolotl.integrations.liger.LigerPlugin
- axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true
sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
- embed_tokens
- lm_head
wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 1
micro_batch_size: 2
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4e-5
max_grad_norm: 1.0
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false
gradient_checkpointing: offload
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:
warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16_torch_compile.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
pad_token: <|finetune_right_pad_id|>optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v5-sft-prototype-70b-lora-rev1
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: anthracite-core/magnum-v5-sft-proto-llama3-rev1-32k
ds_type: parquet
type:
shuffle_merged_datasets: true
dataset_prepared_path: /workspace/magnum-70b-data
val_set_size: 0.0
output_dir: /workspace/70b-lora-out
plugins:
- axolotl.integrations.liger.LigerPlugin
- axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true
sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
- embed_tokens
- lm_head
wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 1
micro_batch_size: 2
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4e-5
max_grad_norm: 1.0
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false
gradient_checkpointing: offload
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:
warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16_torch_compile.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
pad_token: <|finetune_right_pad_id|>optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v5-sft-prototype-70b-lora-rev1
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: anthracite-core/magnum-v5-sft-proto-llama3-rev1-32k
ds_type: parquet
type:
shuffle_merged_datasets: true
dataset_prepared_path: /workspace/magnum-70b-data
val_set_size: 0.0
output_dir: /workspace/70b-lora-out
plugins:
- axolotl.integrations.liger.LigerPlugin
- axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true
sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
- embed_tokens
- lm_head
wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 1
micro_batch_size: 2
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4e-5
max_grad_norm: 1.0
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false
gradient_checkpointing: offload
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:
warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16_torch_compile.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
pad_token: <|finetune_right_pad_id|>optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v5-sft-prototype-70b-lora-rev1
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: anthracite-core/magnum-v5-sft-proto-llama3-rev1-32k
ds_type: parquet
type:
shuffle_merged_datasets: true
dataset_prepared_path: /workspace/magnum-70b-data
val_set_size: 0.0
output_dir: /workspace/70b-lora-out
plugins:
- axolotl.integrations.liger.LigerPlugin
- axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true
sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
- embed_tokens
- lm_head
wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 1
micro_batch_size: 2
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4e-5
max_grad_norm: 1.0
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false
gradient_checkpointing: offload
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:
warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16_torch_compile.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
pad_token: <|finetune_right_pad_id|>optionally might have model_type or tokenizer_typeyaml
base_model: meta-llama/Llama-3.3-70B-Instruct
base_model_ignore_patterns: "*/*"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: Doctor-Shotgun/magnum-v5-sft-prototype-70b-lora-rev1
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: anthracite-core/magnum-v5-sft-proto-llama3-rev1-32k
ds_type: parquet
type:
shuffle_merged_datasets: true
dataset_prepared_path: /workspace/magnum-70b-data
val_set_size: 0.0
output_dir: /workspace/70b-lora-out
plugins:
- axolotl.integrations.liger.LigerPlugin
- axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true
sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
- embed_tokens
- lm_head
wandb_project: 70b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 1
micro_batch_size: 2
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 4e-5
max_grad_norm: 1.0
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false
gradient_checkpointing: offload
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:
warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: ./deepspeed_configs/zero3_bf16_torch_compile.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
pad_token: <|finetune_right_pad_id|>Deploy This Model
Production-ready deployment in minutes
Together.ai
Instant API access to this model
Production-ready inference API. Start free, scale to millions.
Try Free APIReplicate
One-click model deployment
Run models in the cloud with simple API. No DevOps required.
Deploy NowDisclosure: We may earn a commission from these partners. This helps keep LLMYourWay free.