| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 113, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.17699115044247787, |
| "grad_norm": 3.7574703693389893, |
| "learning_rate": 0.00019327433628318585, |
| "loss": 3.1270456314086914, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.35398230088495575, |
| "grad_norm": 4.5264787673950195, |
| "learning_rate": 0.00018619469026548674, |
| "loss": 3.0028640747070314, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.5309734513274337, |
| "grad_norm": 8.996439933776855, |
| "learning_rate": 0.00017911504424778763, |
| "loss": 2.9117900848388674, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.7079646017699115, |
| "grad_norm": 9.305423736572266, |
| "learning_rate": 0.0001720353982300885, |
| "loss": 2.6326715469360353, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.8849557522123894, |
| "grad_norm": 11.935578346252441, |
| "learning_rate": 0.0001649557522123894, |
| "loss": 2.6843631744384764, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 2.083106756210327, |
| "eval_runtime": 3.0766, |
| "eval_samples_per_second": 65.007, |
| "eval_steps_per_second": 4.225, |
| "step": 113 |
| } |
| ], |
| "logging_steps": 20, |
| "max_steps": 565, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 5, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 358897800499200.0, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
