| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.13470281192119885, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002694056238423977, | |
| "eval_loss": 10.372671127319336, | |
| "eval_runtime": 3.7208, | |
| "eval_samples_per_second": 672.174, | |
| "eval_steps_per_second": 84.123, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02694056238423977, | |
| "grad_norm": 0.357284277677536, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 10.3703, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02694056238423977, | |
| "eval_loss": 10.366607666015625, | |
| "eval_runtime": 3.7453, | |
| "eval_samples_per_second": 667.771, | |
| "eval_steps_per_second": 83.571, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05388112476847954, | |
| "grad_norm": 0.36115550994873047, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 10.3636, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05388112476847954, | |
| "eval_loss": 10.360312461853027, | |
| "eval_runtime": 3.8767, | |
| "eval_samples_per_second": 645.131, | |
| "eval_steps_per_second": 80.738, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.08082168715271931, | |
| "grad_norm": 0.3623027205467224, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 10.3582, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.08082168715271931, | |
| "eval_loss": 10.356002807617188, | |
| "eval_runtime": 3.7996, | |
| "eval_samples_per_second": 658.227, | |
| "eval_steps_per_second": 82.377, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.10776224953695908, | |
| "grad_norm": 0.37931913137435913, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 10.3546, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.10776224953695908, | |
| "eval_loss": 10.35400104522705, | |
| "eval_runtime": 3.9149, | |
| "eval_samples_per_second": 638.848, | |
| "eval_steps_per_second": 79.952, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.13470281192119885, | |
| "grad_norm": 0.37304559350013733, | |
| "learning_rate": 0.0, | |
| "loss": 10.3534, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.13470281192119885, | |
| "eval_loss": 10.353680610656738, | |
| "eval_runtime": 3.7808, | |
| "eval_samples_per_second": 661.503, | |
| "eval_steps_per_second": 82.787, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "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": 10344726528000.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |