ab63b92c38
* feat: add lfm2 family and latest moe model * fix: use ml-cross-entropy for lfm2 examples
60 lines
1.1 KiB
YAML
60 lines
1.1 KiB
YAML
base_model: LiquidAI/LFM2-8B-A1B
|
|
|
|
plugins:
|
|
- axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
|
|
|
|
load_in_8bit: true
|
|
|
|
eot_tokens:
|
|
- "<|im_end|>"
|
|
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: 0.05
|
|
output_dir: ./outputs/out
|
|
|
|
sequence_len: 4096
|
|
sample_packing: true
|
|
|
|
adapter: lora
|
|
lora_model_dir:
|
|
|
|
lora_r: 32
|
|
lora_alpha: 16
|
|
lora_dropout: 0.05
|
|
lora_target_modules: 'model.layers.[\d]+.(mlp|cross_attn|self_attn).(up|down|gate|q|k|v|o)_proj'
|
|
|
|
wandb_project:
|
|
wandb_entity:
|
|
wandb_watch:
|
|
wandb_name:
|
|
wandb_log_model:
|
|
|
|
gradient_accumulation_steps: 2
|
|
micro_batch_size: 4
|
|
num_epochs: 1
|
|
optimizer: adamw_torch_fused
|
|
lr_scheduler: cosine
|
|
learning_rate: 5e-5
|
|
|
|
bf16: true
|
|
tf32: true
|
|
|
|
gradient_checkpointing: true
|
|
resume_from_checkpoint:
|
|
logging_steps: 1
|
|
flash_attention: true
|
|
|
|
warmup_ratio: 0.1
|
|
evals_per_epoch: 2
|
|
saves_per_epoch: 1
|
|
|
|
weight_decay: 0.0
|
|
|
|
# save_first_step: true # uncomment this to validate checkpoint saving works with your config
|