| { |
| "base_model": "openai/gpt-oss-20b", |
| "phase1_hub_model_id": "sahilmob/gpt-oss-20b-toolcall-phase1-v2-strict-lora", |
| "final_hub_model_id": "sahilmob/gpt-oss-20b-toolcall-two-phase-v2-lora", |
| "output_root": "gpt-oss-20b-toolcall-two-phase-v2-sft", |
| "phase1": { |
| "dataset_source": "hub", |
| "dataset_id": "sahilmob/wish-engine-toolcall-next-v2-strict", |
| "train_split": "train", |
| "eval_split": "validation", |
| "num_train_epochs": 2, |
| "per_device_train_batch_size": 1, |
| "gradient_accumulation_steps": 16, |
| "learning_rate": 1.2e-5 |
| }, |
| "phase2": { |
| "dataset_source": "hub", |
| "dataset_id": "sahilmob/wish-engine-toolcall-next-v2", |
| "train_split": "train", |
| "eval_split": "validation", |
| "num_train_epochs": 1, |
| "per_device_train_batch_size": 1, |
| "gradient_accumulation_steps": 16, |
| "learning_rate": 8e-6 |
| }, |
| "lora": { |
| "r": 16, |
| "lora_alpha": 32, |
| "lora_dropout": 0.05, |
| "bias": "none", |
| "task_type": "CAUSAL_LM", |
| "target_modules": [ |
| "q_proj", |
| "k_proj", |
| "v_proj", |
| "o_proj" |
| ] |
| }, |
| "runtime": { |
| "trackio_project": "wish-engine-toolcalls-gpt-oss-20b", |
| "trackio_run_name": "two-phase-toolcall-v2-sft-gpt-oss-20b", |
| "seed": 42, |
| "logging_steps": 10, |
| "save_steps": 100, |
| "save_total_limit": 2, |
| "eval_steps": 50, |
| "warmup_ratio": 0.1, |
| "lr_scheduler_type": "cosine", |
| "max_length": 1024, |
| "strict_chat_template": true, |
| "skip_trainer_model_move": true, |
| "force_single_device_model": true |
| } |
| } |
|
|
