| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.128, |
| "eval_steps": 100, |
| "global_step": 200, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.032, |
| "grad_norm": 25.09992027282715, |
| "learning_rate": 4.3999999999999997e-07, |
| "loss": 1.0546456146240235, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.064, |
| "grad_norm": 44.00643539428711, |
| "learning_rate": 9.399999999999999e-07, |
| "loss": 1.2045201873779297, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.064, |
| "eval_loss": 0.15259136259555817, |
| "eval_runtime": 320.8429, |
| "eval_samples_per_second": 6.234, |
| "eval_steps_per_second": 1.558, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.096, |
| "grad_norm": 409.5372314453125, |
| "learning_rate": 9.511111111111111e-07, |
| "loss": 0.8091524505615234, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.128, |
| "grad_norm": 4.935479640960693, |
| "learning_rate": 8.955555555555555e-07, |
| "loss": 0.9019821166992188, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.128, |
| "eval_loss": 0.1397811472415924, |
| "eval_runtime": 320.5384, |
| "eval_samples_per_second": 6.24, |
| "eval_steps_per_second": 1.56, |
| "step": 200 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 1000, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 100, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.190401098346536e+16, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
