| base_model: facebook/galactica-1.3b | |
| model_type: AutoModelForCausalLM | |
| tokenizer_type: AutoTokenizer | |
| load_in_8bit: false | |
| datasets: | |
| - path: tatsu-lab/alpaca | |
| type: alpaca | |
| dataset_prepared_path: last_run_prepared | |
| val_set_size: 0.1 | |
| adapter: | |
| lora_model_dir: | |
| sequence_len: 1024 | |
| max_packed_sequence_len: 1024 | |
| lora_r: 8 | |
| lora_alpha: 16 | |
| lora_dropout: 0.05 | |
| lora_target_modules: | |
| - q_proj | |
| - v_proj | |
| lora_fan_in_fan_out: false | |
| wandb_project: | |
| wandb_watch: | |
| wandb_run_id: | |
| wandb_log_model: | |
| output_dir: ./lora-llama-alpaca | |
| gradient_accumulation_steps: 1 | |
| micro_batch_size: 16 | |
| num_epochs: 3 | |
| learning_rate: 0.00003 | |
| train_on_inputs: false | |
| group_by_length: false | |
| bf16: false | |
| tf32: false | |
| early_stopping_patience: | |
| resume_from_checkpoint: | |
| local_rank: | |
| tokens: | |
| pad_token: "[PAD]" | |
| bos_token: "<s>" | |
| eos_token: "</s>" | |
| unk_token: "<unk>" | |