| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 10.0, |
| "eval_steps": 500, |
| "global_step": 80, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.25, |
| "grad_norm": 2.7730236053466797, |
| "learning_rate": 9.893584226636772e-05, |
| "loss": 0.9102, |
| "step": 10 |
| }, |
| { |
| "epoch": 2.5, |
| "grad_norm": 1.6546119451522827, |
| "learning_rate": 9.069243586350975e-05, |
| "loss": 0.522, |
| "step": 20 |
| }, |
| { |
| "epoch": 3.75, |
| "grad_norm": 1.4853732585906982, |
| "learning_rate": 7.559425245448006e-05, |
| "loss": 0.4575, |
| "step": 30 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 1.5774649381637573, |
| "learning_rate": 5.618463156346739e-05, |
| "loss": 0.4031, |
| "step": 40 |
| }, |
| { |
| "epoch": 6.25, |
| "grad_norm": 1.3806265592575073, |
| "learning_rate": 3.5733188787544745e-05, |
| "loss": 0.3448, |
| "step": 50 |
| }, |
| { |
| "epoch": 7.5, |
| "grad_norm": 0.7461087703704834, |
| "learning_rate": 1.768503810695295e-05, |
| "loss": 0.2804, |
| "step": 60 |
| }, |
| { |
| "epoch": 8.75, |
| "grad_norm": 0.5908331871032715, |
| "learning_rate": 5.080450905401057e-06, |
| "loss": 0.2326, |
| "step": 70 |
| }, |
| { |
| "epoch": 10.0, |
| "grad_norm": 1.0191975831985474, |
| "learning_rate": 4.2712080634949024e-08, |
| "loss": 0.2199, |
| "step": 80 |
| }, |
| { |
| "epoch": 10.0, |
| "step": 80, |
| "total_flos": 0.0, |
| "train_loss": 0.4212930917739868, |
| "train_runtime": 126.2708, |
| "train_samples_per_second": 64.94, |
| "train_steps_per_second": 0.634 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 80, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 10, |
| "save_steps": 800, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 0.0, |
| "train_batch_size": 107, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
