| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.002332406849501448, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 7.77468949833816e-05, | |
| "eval_loss": 11.225495338439941, | |
| "eval_runtime": 692.9718, | |
| "eval_samples_per_second": 7.816, | |
| "eval_steps_per_second": 3.908, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00023324068495014482, | |
| "grad_norm": 11.508672714233398, | |
| "learning_rate": 6e-05, | |
| "loss": 11.9201, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00046648136990028963, | |
| "grad_norm": 16.00137710571289, | |
| "learning_rate": 0.00012, | |
| "loss": 10.0984, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0006219751598670528, | |
| "eval_loss": 2.4881513118743896, | |
| "eval_runtime": 694.757, | |
| "eval_samples_per_second": 7.796, | |
| "eval_steps_per_second": 3.898, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0006997220548504344, | |
| "grad_norm": 21.25751304626465, | |
| "learning_rate": 0.00018, | |
| "loss": 3.9253, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0009329627398005793, | |
| "grad_norm": 17.56968116760254, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 0.9736, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.001166203424750724, | |
| "grad_norm": 5.908636569976807, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.6982, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0012439503197341057, | |
| "eval_loss": 0.8500107526779175, | |
| "eval_runtime": 693.7712, | |
| "eval_samples_per_second": 7.807, | |
| "eval_steps_per_second": 3.903, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0013994441097008687, | |
| "grad_norm": 6.493429660797119, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 1.4014, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0016326847946510135, | |
| "grad_norm": 7.044196605682373, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 0.5695, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0018659254796011585, | |
| "grad_norm": 5.777575969696045, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 1.0814, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0018659254796011585, | |
| "eval_loss": 0.5827813148498535, | |
| "eval_runtime": 695.5532, | |
| "eval_samples_per_second": 7.787, | |
| "eval_steps_per_second": 3.893, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.002099166164551303, | |
| "grad_norm": 2.4486043453216553, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 0.5232, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.002332406849501448, | |
| "grad_norm": 6.537215232849121, | |
| "learning_rate": 0.0, | |
| "loss": 0.8298, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 70, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.112830925340672e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |