| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.15, |
| "eval_steps": 100, |
| "global_step": 150, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.05, |
| "grad_norm": 13.136443138122559, |
| "learning_rate": 9.799999999999998e-05, |
| "loss": 83.7759, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.1, |
| "grad_norm": 4.371773719787598, |
| "learning_rate": 0.000198, |
| "loss": 60.3835, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.1, |
| "eval_accuracy": 0.12107013087626775, |
| "eval_loss": 6.948241233825684, |
| "eval_runtime": 10.1735, |
| "eval_samples_per_second": 95.345, |
| "eval_steps_per_second": 3.047, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.15, |
| "grad_norm": 4.350087642669678, |
| "learning_rate": 0.000298, |
| "loss": 53.8921, |
| "step": 150 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 1000, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 9223372036854775807, |
| "save_steps": 150, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 3.17716313407488e+16, |
| "train_batch_size": 32, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
