| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.9997526589166461, |
| "eval_steps": 500, |
| "global_step": 2021, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.24734108335394508, |
| "grad_norm": 1.439273715019226, |
| "learning_rate": 7.535873330034637e-05, |
| "loss": 0.2317, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.49468216670789017, |
| "grad_norm": 3.661175489425659, |
| "learning_rate": 5.061850569025235e-05, |
| "loss": 0.0951, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.7420232500618352, |
| "grad_norm": 2.657053232192993, |
| "learning_rate": 2.5878278080158342e-05, |
| "loss": 0.0719, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.9893643334157803, |
| "grad_norm": 4.781520843505859, |
| "learning_rate": 1.1380504700643246e-06, |
| "loss": 0.0668, |
| "step": 2000 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 2021, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 9.4486400434176e+17, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
