Upload qwen25-7b/cooking_wb5/training_config.json with huggingface_hub

qwen25-7b/cooking_wb5/training_config.json

@@ -0,0 +1 @@
+{"model": "Qwen/Qwen2.5-7B-Instruct", "training_file": ["/workspace/em/data/cooking_wb5.jsonl"], "test_file": null, "finetuned_model_id": "{org_id}/{model_name}-{job_id}", "max_seq_length": 2048, "load_in_4bit": false, "loss": "sft", "is_peft": true, "target_modules": ["q_proj", "k_proj", "v_proj", "o_proj", "gate_proj", "up_proj", "down_proj"], "lora_bias": "none", "r": 32, "lora_alpha": 64, "lora_dropout": 0.0, "use_rslora": true, "merge_before_push": false, "push_to_private": true, "epochs": 1, "max_steps": null, "per_device_train_batch_size": 2, "gradient_accumulation_steps": 8, "warmup_steps": 5, "learning_rate": 1e-05, "logging_steps": 1, "optim": "adamw_8bit", "weight_decay": 0.01, "lr_scheduler_type": "linear", "seed": 0, "beta": 0.1, "save_steps": 5000, "output_dir": "/workspace/em/ckpt/qwen-em_cooking_wb5", "train_on_responses_only": true, "no_test_split": false, "steering_config": null, "enable_steering_during_training": false}