| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.8620689655172413, |
| "eval_steps": 25, |
| "global_step": 100, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.21551724137931033, |
| "grad_norm": 0.11027640104293823, |
| "learning_rate": 1.9957983193277314e-05, |
| "loss": 0.8049, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.21551724137931033, |
| "eval_loss": 0.0073065385222435, |
| "eval_runtime": 867.9178, |
| "eval_samples_per_second": 0.49, |
| "eval_steps_per_second": 0.062, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.43103448275862066, |
| "grad_norm": 0.1416015923023224, |
| "learning_rate": 1.4705882352941177e-05, |
| "loss": 0.0045, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.43103448275862066, |
| "eval_loss": 0.0018026032485067844, |
| "eval_runtime": 868.0442, |
| "eval_samples_per_second": 0.49, |
| "eval_steps_per_second": 0.062, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.646551724137931, |
| "grad_norm": 0.052225738763809204, |
| "learning_rate": 9.453781512605041e-06, |
| "loss": 0.0011, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.646551724137931, |
| "eval_loss": 0.00039366475539281964, |
| "eval_runtime": 868.3065, |
| "eval_samples_per_second": 0.489, |
| "eval_steps_per_second": 0.062, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.8620689655172413, |
| "grad_norm": 0.02868836000561714, |
| "learning_rate": 4.2016806722689085e-06, |
| "loss": 0.0004, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.8620689655172413, |
| "eval_loss": 0.00020824630337301642, |
| "eval_runtime": 867.8419, |
| "eval_samples_per_second": 0.49, |
| "eval_steps_per_second": 0.062, |
| "step": 100 |
| } |
| ], |
| "logging_steps": 25, |
| "max_steps": 120, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "save_steps": 25, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 4421038846771200.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
