| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 55, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "entropy": 1.8176515418291093, |
| "epoch": 0.45662100456621, |
| "grad_norm": 0.060302734375, |
| "learning_rate": 0.00012635871660690676, |
| "loss": 1.88403076171875, |
| "mean_token_accuracy": 0.593351843804121, |
| "num_tokens": 124164.0, |
| "step": 25 |
| }, |
| { |
| "entropy": 1.5934660568833352, |
| "epoch": 0.91324200913242, |
| "grad_norm": 0.060546875, |
| "learning_rate": 6.258033886587911e-06, |
| "loss": 1.5930903625488282, |
| "mean_token_accuracy": 0.646300423592329, |
| "num_tokens": 243208.0, |
| "step": 50 |
| } |
| ], |
| "logging_steps": 25, |
| "max_steps": 55, |
| "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": 1.1296531843021824e+16, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
