| base_model: /mnt/WD/AI/text-generation-webui/models/L3-8B-Stheno-v3.1/ | |
| model_type: AutoModelForCausalLM | |
| tokenizer_type: AutoTokenizer | |
| load_in_8bit: true | |
| load_in_4bit: false | |
| strict: false | |
| datasets: | |
| - path: 94_stories.jsonl | |
| type: completion | |
| - path: Luna_personality_instruct.json | |
| type: alpaca | |
| - path: alpaca_wiki_6144.json | |
| type: alpaca | |
| - path: alpaca_Luna.json | |
| type: alpaca | |
| dataset_prepared_path: last_run_prepared | |
| val_set_size: 0 | |
| output_dir: ./lora-out | |
| lora_on_cpu: true | |
| adapter: lora | |
| lora_model_dir: | |
| sequence_len: 6144 | |
| sample_packing: true | |
| pad_to_sequence_len: true | |
| lora_r: 256 | |
| lora_alpha: 64 | |
| lora_dropout: 0.04 | |
| lora_target_modules: | |
| lora_target_linear: true | |
| lora_fan_in_fan_out: | |
| wandb_project: | |
| wandb_entity: | |
| wandb_watch: | |
| wandb_name: | |
| wandb_log_model: | |
| gradient_accumulation_steps: 1 | |
| micro_batch_size: 2 | |
| num_epochs: 3 | |
| optimizer: adamw_bnb_8bit | |
| lr_scheduler: cosine | |
| learning_rate: 0.00033 | |
| train_on_inputs: false | |
| group_by_length: false | |
| bf16: true | |
| fp16: | |
| tf32: true | |
| gradient_checkpointing: true | |
| early_stopping_patience: | |
| resume_from_checkpoint: | |
| local_rank: | |
| logging_steps: 1 | |
| xformers_attention: | |
| flash_attention: true | |
| warmup_steps: 50 | |
| evals_per_epoch: 4 | |
| eval_table_size: | |
| saves_per_epoch: 1 | |
| debug: | |
| deepspeed: | |
| weight_decay: 0.0 | |
| fsdp: | |
| fsdp_config: | |
| special_tokens: | |
| pad_token: "<|end_of_text|>" | |