02ce520b7e
* upgrade liger to 0.3.1 * update docs and example * skip duplicate code check * Update src/axolotl/integrations/liger/args.py Co-authored-by: NanoCode012 <nano@axolotl.ai> * Update README.md Co-authored-by: NanoCode012 <nano@axolotl.ai> * add logging * chore: lint * add test case * upgrade liger and transformers * also upgrade accelerate * use kwargs to support patch release * make sure prepared path is empty for test * use transfromers 4.46.1 since 4.46.2 breaks fsdp --------- Co-authored-by: NanoCode012 <nano@axolotl.ai>
87 lines
1.7 KiB
YAML
87 lines
1.7 KiB
YAML
base_model: axolotl-quants/DeepSeek-V2.5-bnb-nf4-bf16
|
|
trust_remote_code: true
|
|
|
|
load_in_8bit: false
|
|
load_in_4bit: true
|
|
strict: false
|
|
|
|
|
|
plugins:
|
|
- axolotl.integrations.liger.LigerPlugin
|
|
liger_rms_norm: true
|
|
liger_glu_activation: true
|
|
liger_fused_linear_cross_entropy: true
|
|
|
|
chat_template: deepseek_v2
|
|
datasets:
|
|
- path: mlabonne/FineTome-100k
|
|
type: chat_template
|
|
split: train[:20%]
|
|
field_messages: conversations
|
|
message_field_role: from
|
|
message_field_content: value
|
|
|
|
dataset_prepared_path: last_run_prepared
|
|
val_set_size: 0.0
|
|
output_dir: ./outputs/out
|
|
|
|
sequence_len: 4096
|
|
sample_packing: true
|
|
pad_to_sequence_len: true
|
|
|
|
wandb_project:
|
|
wandb_entity:
|
|
wandb_watch:
|
|
wandb_name:
|
|
wandb_log_model:
|
|
|
|
adapter: qlora
|
|
lora_r: 256
|
|
lora_alpha: 256
|
|
lora_target_linear: true
|
|
peft_use_rslora: true
|
|
|
|
gradient_accumulation_steps: 1
|
|
micro_batch_size: 8
|
|
num_epochs: 1
|
|
optimizer: adamw_torch
|
|
lr_scheduler: cosine
|
|
learning_rate: 2e-5
|
|
|
|
train_on_inputs: false
|
|
group_by_length: false
|
|
bf16: auto
|
|
fp16:
|
|
tf32: false
|
|
|
|
gradient_checkpointing: true
|
|
gradient_checkpointing_kwargs:
|
|
use_reentrant: false
|
|
early_stopping_patience:
|
|
resume_from_checkpoint:
|
|
logging_steps: 1
|
|
xformers_attention:
|
|
flash_attention: true
|
|
|
|
warmup_steps: 100
|
|
evals_per_epoch: 2
|
|
eval_table_size:
|
|
saves_per_epoch: 1
|
|
debug:
|
|
deepspeed:
|
|
weight_decay: 0.0
|
|
special_tokens:
|
|
fsdp:
|
|
- full_shard
|
|
- auto_wrap
|
|
fsdp_config:
|
|
fsdp_limit_all_gathers: true
|
|
fsdp_sync_module_states: true
|
|
fsdp_offload_params: true
|
|
fsdp_use_orig_params: false
|
|
fsdp_cpu_ram_efficient_loading: true
|
|
fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
|
|
fsdp_transformer_layer_cls_to_wrap: DeepseekV2DecoderLayer
|
|
fsdp_state_dict_type: FULL_STATE_DICT
|
|
fsdp_sharding_strategy: FULL_SHARD
|