| { | |
| "architectures": [ | |
| "LlamaForCausalLM" | |
| ], | |
| "model_type": "llama", | |
| "hidden_size": 4096, | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 12, | |
| "max_position_embeddings": 2048, | |
| "vocab_size": 50265, | |
| "lora_config": { | |
| "r": 16, | |
| "target_modules": ["q_proj", "k_proj", "v_proj", "o_proj", "gate_proj", "up_proj", "down_proj"], | |
| "lora_alpha": 16, | |
| "lora_dropout": 0, | |
| "bias": "none", | |
| "use_gradient_checkpointing": true, | |
| "use_rslora": false, | |
| "use_dora": false, | |
| "loftq_config": null | |
| }, | |
| "training_dataset": { | |
| "name": "cyberblip/Travel_india", | |
| "split": "train", | |
| "input_field": "prompt" | |
| }, | |
| "training_config": { | |
| "per_device_train_batch_size": 2, | |
| "gradient_accumulation_steps": 4, | |
| "warmup_steps": 5, | |
| "max_steps": 0, | |
| "num_train_epochs": 1, | |
| "learning_rate": 2e-4, | |
| "fp16": false, | |
| "bf16": true, | |
| "logging_steps": 1, | |
| "optim": "adamw_8bit", | |
| "weight_decay": 0.01, | |
| "lr_scheduler_type": "linear", | |
| "seed": 42, | |
| "output_dir": "outputs" | |
| } | |
| } |