| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00406421459053038, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000135473819684346, | |
| "eval_loss": 2.3976213932037354, | |
| "eval_runtime": 279.4066, | |
| "eval_samples_per_second": 11.124, | |
| "eval_steps_per_second": 5.562, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000406421459053038, | |
| "grad_norm": 2.181936502456665, | |
| "learning_rate": 6e-05, | |
| "loss": 9.0904, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.000812842918106076, | |
| "grad_norm": 3.154181957244873, | |
| "learning_rate": 0.00012, | |
| "loss": 9.4699, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.001083790557474768, | |
| "eval_loss": 2.2002861499786377, | |
| "eval_runtime": 279.8141, | |
| "eval_samples_per_second": 11.107, | |
| "eval_steps_per_second": 5.554, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.001219264377159114, | |
| "grad_norm": 4.360508918762207, | |
| "learning_rate": 0.00018, | |
| "loss": 9.0767, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.001625685836212152, | |
| "grad_norm": 4.853641986846924, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 8.1943, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00203210729526519, | |
| "grad_norm": 9.18185043334961, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 8.1932, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.002167581114949536, | |
| "eval_loss": 1.969774842262268, | |
| "eval_runtime": 279.544, | |
| "eval_samples_per_second": 11.118, | |
| "eval_steps_per_second": 5.559, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.002438528754318228, | |
| "grad_norm": 5.340238571166992, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 7.2584, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.002844950213371266, | |
| "grad_norm": 6.8131208419799805, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 7.6355, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.003251371672424304, | |
| "grad_norm": 4.061794281005859, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 7.7912, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.003251371672424304, | |
| "eval_loss": 1.8718359470367432, | |
| "eval_runtime": 279.9161, | |
| "eval_samples_per_second": 11.103, | |
| "eval_steps_per_second": 5.552, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.003657793131477342, | |
| "grad_norm": 4.054107189178467, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 6.9789, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.00406421459053038, | |
| "grad_norm": 11.858595848083496, | |
| "learning_rate": 0.0, | |
| "loss": 7.398, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.920218563608576e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |