base_model: meta-llama/Llama-3.1-8B-Instruct

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

strict: false

chat_template: llama3
datasets:
  - path: ""
    type:
    ds_type: parquet

dataset_prepared_path:
val_set_size: 0.00
output_dir: ./outputs/llama31-8B-liger-ds-full

dataset_processes: 16

sequence_len: 131072 
sample_packing: false
pad_to_sequence_len: true

wandb_project: 
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 1
num_epochs: 3
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 2e-5

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

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 50
evals_per_epoch: 0
eval_table_size:
saves_per_epoch: 2
save_only_model: true
debug:
deepspeed: deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  pad_token: <|finetune_right_pad_id|>
  eos_token: <|eot_id|>