| base_model: microsoft/phi-1_5 | |
| base_model_config: microsoft/phi-1_5 | |
| model_type: MixFormerSequentialForCausalLM | |
| tokenizer_type: AutoTokenizer | |
| is_llama_derived_model: false | |
| trust_remote_code: true | |
| load_in_8bit: false | |
| load_in_4bit: false | |
| strict: false | |
| datasets: | |
| - path: garage-bAInd/Open-Platypus | |
| type: alpaca | |
| dataset_prepared_path: last_run_prepared | |
| val_set_size: 0.05 | |
| output_dir: ./phi-sft-out | |
| sequence_len: 2048 | |
| sample_packing: true | |
| pad_to_sequence_len: | |
| adapter: | |
| lora_model_dir: | |
| lora_r: | |
| lora_alpha: | |
| lora_dropout: | |
| lora_target_linear: | |
| lora_fan_in_fan_out: | |
| wandb_project: | |
| wandb_entity: | |
| wandb_watch: | |
| wandb_run_id: | |
| wandb_log_model: | |
| gradient_accumulation_steps: 1 | |
| micro_batch_size: 1 | |
| num_epochs: 4 | |
| optimizer: adamw_torch | |
| adam_beta2: 0.95 | |
| adam_epsilon: 0.00001 | |
| max_grad_norm: 1.0 | |
| lr_scheduler: cosine | |
| learning_rate: 0.000003 | |
| train_on_inputs: false | |
| group_by_length: true | |
| bf16: true | |
| fp16: false | |
| tf32: true | |
| gradient_checkpointing: | |
| early_stopping_patience: | |
| resume_from_checkpoint: | |
| local_rank: | |
| logging_steps: 1 | |
| xformers_attention: | |
| flash_attention: | |
| warmup_steps: 100 | |
| eval_steps: 0.05 | |
| save_steps: | |
| debug: | |
| deepspeed: | |
| weight_decay: 0.1 | |
| fsdp: | |
| fsdp_config: | |
| resize_token_embeddings_to_32x: true | |
| special_tokens: | |
| bos_token: "<|endoftext|>" | |
| eos_token: "<|endoftext|>" | |
| unk_token: "<|endoftext|>" | |
| pad_token: "<|endoftext|>" | |