| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.0008680781617576847, |
| "eval_steps": 10, |
| "global_step": 50, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.7361563235153692e-05, |
| "eval_loss": 3.2406625747680664, |
| "eval_runtime": 1557.6717, |
| "eval_samples_per_second": 15.569, |
| "eval_steps_per_second": 7.785, |
| "step": 1 |
| }, |
| { |
| "epoch": 8.680781617576846e-05, |
| "grad_norm": 57.20978927612305, |
| "learning_rate": 5e-05, |
| "loss": 12.0897, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.00017361563235153692, |
| "grad_norm": 54.81013107299805, |
| "learning_rate": 0.0001, |
| "loss": 8.6169, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.00017361563235153692, |
| "eval_loss": 1.9173833131790161, |
| "eval_runtime": 1562.5591, |
| "eval_samples_per_second": 15.521, |
| "eval_steps_per_second": 7.76, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.0002604234485273054, |
| "grad_norm": 30.663660049438477, |
| "learning_rate": 9.619397662556435e-05, |
| "loss": 7.1643, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.00034723126470307384, |
| "grad_norm": 31.651548385620117, |
| "learning_rate": 8.535533905932738e-05, |
| "loss": 6.5708, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.00034723126470307384, |
| "eval_loss": 1.364366888999939, |
| "eval_runtime": 1565.5286, |
| "eval_samples_per_second": 15.491, |
| "eval_steps_per_second": 7.746, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.00043403908087884236, |
| "grad_norm": 27.65591812133789, |
| "learning_rate": 6.91341716182545e-05, |
| "loss": 5.2812, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.0005208468970546108, |
| "grad_norm": 23.687255859375, |
| "learning_rate": 5e-05, |
| "loss": 5.1417, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.0005208468970546108, |
| "eval_loss": 1.267388105392456, |
| "eval_runtime": 2133.9119, |
| "eval_samples_per_second": 11.365, |
| "eval_steps_per_second": 5.683, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.0006076547132303793, |
| "grad_norm": 21.283479690551758, |
| "learning_rate": 3.086582838174551e-05, |
| "loss": 4.6944, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.0006944625294061477, |
| "grad_norm": 19.084383010864258, |
| "learning_rate": 1.4644660940672627e-05, |
| "loss": 5.3045, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.0006944625294061477, |
| "eval_loss": 1.2451889514923096, |
| "eval_runtime": 2665.7266, |
| "eval_samples_per_second": 9.098, |
| "eval_steps_per_second": 4.549, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.0007812703455819162, |
| "grad_norm": 21.01182746887207, |
| "learning_rate": 3.8060233744356633e-06, |
| "loss": 5.2542, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.0008680781617576847, |
| "grad_norm": 18.80780029296875, |
| "learning_rate": 0.0, |
| "loss": 4.3926, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.0008680781617576847, |
| "eval_loss": 1.2397698163986206, |
| "eval_runtime": 3028.9488, |
| "eval_samples_per_second": 8.007, |
| "eval_steps_per_second": 4.003, |
| "step": 50 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 50, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 13, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 8763509991014400.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
