| base_model: Qwen/Qwen2.5-7B-Instruct |
| model_type: AutoModelForCausalLM |
| tokenizer_type: AutoTokenizer |
| trust_remote_code: true |
|
|
| load_in_8bit: false |
| load_in_4bit: true |
| strict: false |
|
|
| datasets: |
| - path: ugaoo/multimedqa_and_wrongonesqwen |
| type: alpaca |
| val_set_size: 0 |
| output_dir: ./out/Qwen_Qwen2.5_7B_Instruct_ugaoo_multimedqa_and_wrongonesqwen |
|
|
| sequence_len: 4000 |
| sample_packing: true |
| pad_to_sequence_len: true |
|
|
| adapter: qlora |
| lora_r: 256 |
| lora_alpha: 512 |
| lora_dropout: 0.05 |
| lora_target_linear: true |
| lora_target_modules: |
| - q_proj |
| - k_proj |
| - v_proj |
| - o_proj |
| - up_proj |
| - down_proj |
| - gate_proj |
| |
| wandb_project: testsearch |
| wandb_entity: |
| wandb_watch: |
| wandb_name: Qwen_Qwen2.5_7B_Instruct_ugaoo_multimedqa_and_wrongonesqwen |
| wandb_log_model: |
|
|
| gradient_accumulation_steps: 3 |
| micro_batch_size: 4 |
| num_epochs: 6 |
| optimizer: adamw_torch |
| lr_scheduler: cosine |
| learning_rate: 5e-6 |
|
|
| train_on_inputs: false |
| group_by_length: false |
| bf16: auto |
| fp16: false |
| tf32: false |
|
|
| gradient_checkpointing: true |
| early_stopping_patience: |
| resume_from_checkpoint: |
| logging_steps: 1 |
| xformers_attention: |
| flash_attention: true |
|
|
| warmup_steps: 100 |
| evals_per_epoch: 6 |
| eval_table_size: |
| saves_per_epoch: 1 |
| debug: |
| deepspeed: |
| weight_decay: 0.0 |
| fsdp: |
| fsdp_config: |
| save_total_limit: 6 |
