| { |
| "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 |
| } |
|
|
