wandb_run_id: 2e2444b4-b741-48af-b32c-b5f44f38688f
wandb_project: llm-training-platform
wandb_name: II-Tulu-8B-SFT
datasets:
- path: allenai/tulu-3-sft-mixture
  split: train
  type: chat_template
  field_messages: messages
  message_field_role: role
  message_field_content: content
  roles:
    system:
    - system
    user:
    - user
    assistant:
    - assistant
chat_template: llama3
sequence_len: 2048
base_model: meta-llama/Llama-3.1-8B
output_dir: checkpoints/deb3448a-60ae-4ad8-bdc2-06cce8c43d02
dataset_prepared_path: checkpoints/deb3448a-60ae-4ad8-bdc2-06cce8c43d02/dataset_prepared
flash_attention: true
train_on_inputs: false
pad_to_sequence_len: true
eval_sample_packing: false
push_to_hub: true
bf16: auto
logging_steps: 10
hub_model_id: phunguyen01/II-8B-SFT
learning_rate: 5.0e-06
micro_batch_size: 2
num_epochs: 2
seed: 42
gradient_accumulation_steps: 2
sample_packing: true
val_set_size: 0
special_tokens:
   pad_token: <|end_of_text|>