| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.014954389113204725, |
| "eval_steps": 500, |
| "global_step": 25, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0029908778226409452, |
| "grad_norm": 0.42996275424957275, |
| "learning_rate": 8e-05, |
| "loss": 1.3150932312011718, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.0059817556452818905, |
| "grad_norm": 0.34759286046028137, |
| "learning_rate": 0.00018, |
| "loss": 1.2311323165893555, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.008972633467922835, |
| "grad_norm": 0.23679782450199127, |
| "learning_rate": 0.00019724137931034484, |
| "loss": 0.929847240447998, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.011963511290563781, |
| "grad_norm": 0.7136238217353821, |
| "learning_rate": 0.00019379310344827587, |
| "loss": 0.7683926105499268, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.014954389113204725, |
| "grad_norm": 0.36432984471321106, |
| "learning_rate": 0.0001903448275862069, |
| "loss": 0.9011115074157715, |
| "step": 25 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 300, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "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": 4126137326309376.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
