| base_model: microsoft/Phi-3-mini-4k-instruct | |
| trust_remote_code: true | |
| model_type: AutoModelForCausalLM | |
| tokenizer_type: AutoTokenizer | |
| chat_template: phi_3 | |
| load_in_8bit: false | |
| load_in_4bit: false | |
| strict: false | |
| datasets: | |
| - path: garage-bAInd/Open-Platypus | |
| type: alpaca:phi | |
| dataset_prepared_path: | |
| val_set_size: 0.01 | |
| output_dir: ./out | |
| sequence_len: 4096 | |
| sample_packing: true | |
| pad_to_sequence_len: true | |
| adapter: lora | |
| lora_model_dir: | |
| lora_r: 64 | |
| lora_alpha: 32 | |
| lora_dropout: 0.05 | |
| lora_target_linear: true | |
| lora_fan_in_fan_out: | |
| gradient_accumulation_steps: 1 | |
| micro_batch_size: 2 | |
| num_epochs: 1 | |
| optimizer: adamw_torch | |
| adam_beta2: 0.95 | |
| adam_epsilon: 0.00001 | |
| max_grad_norm: 1.0 | |
| lr_scheduler: cosine | |
| learning_rate: 5.0e-6 | |
| train_on_inputs: false | |
| group_by_length: false | |
| bf16: auto | |
| gradient_checkpointing: true | |
| gradient_checkpointing_kwargs: | |
| use_reentrant: True | |
| early_stopping_patience: 3 | |
| logging_steps: 1 | |
| flash_attention: true | |
| eval_steps: 1000 | |
| save_steps: 5000 | |
| eval_table_size: 2 | |
| eval_batch_size: 2 | |
| eval_sample_packing: false | |
| eval_max_new_tokens: 32 | |
| eval_causal_lm_metrics: ["perplexity"] | |
| do_causal_lm_eval: true | |
| warmup_ratio: 0.2 | |
| debug: true | |
| weight_decay: 0.1 | |
| resize_token_embeddings_to_32x: true | |