| { |
| "best_metric": 0.2779570519924164, |
| "best_model_checkpoint": "Trainer_model/checkpoint-2840", |
| "epoch": 4.0, |
| "eval_steps": 500, |
| "global_step": 2840, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "learning_rate": 9.023511967803433e-06, |
| "loss": 0.4474, |
| "step": 710 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.8661516349263385, |
| "eval_loss": 0.3275854289531708, |
| "eval_runtime": 29.2304, |
| "eval_samples_per_second": 190.418, |
| "eval_steps_per_second": 5.953, |
| "step": 710 |
| }, |
| { |
| "epoch": 2.0, |
| "learning_rate": 7.519593306502861e-06, |
| "loss": 0.2955, |
| "step": 1420 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.8891484010061085, |
| "eval_loss": 0.2884845733642578, |
| "eval_runtime": 29.3699, |
| "eval_samples_per_second": 189.513, |
| "eval_steps_per_second": 5.924, |
| "step": 1420 |
| }, |
| { |
| "epoch": 3.0, |
| "learning_rate": 6.0156746452022885e-06, |
| "loss": 0.243, |
| "step": 2130 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.8875314408911247, |
| "eval_loss": 0.28905972838401794, |
| "eval_runtime": 29.2816, |
| "eval_samples_per_second": 190.085, |
| "eval_steps_per_second": 5.942, |
| "step": 2130 |
| }, |
| { |
| "epoch": 4.0, |
| "learning_rate": 4.511755983901716e-06, |
| "loss": 0.2077, |
| "step": 2840 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.8905856988860942, |
| "eval_loss": 0.2779570519924164, |
| "eval_runtime": 29.1612, |
| "eval_samples_per_second": 190.87, |
| "eval_steps_per_second": 5.967, |
| "step": 2840 |
| } |
| ], |
| "logging_steps": 710, |
| "max_steps": 4970, |
| "num_train_epochs": 7, |
| "save_steps": 500, |
| "total_flos": 3694888313074560.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
