| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 6.0, |
| "eval_steps": 500, |
| "global_step": 5178, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.5793742757821553, |
| "grad_norm": 19.770750045776367, |
| "learning_rate": 1.8072614909231365e-05, |
| "loss": 0.4165, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.9061889250814332, |
| "eval_f1": 0.6588856644028802, |
| "eval_loss": 0.2571379244327545, |
| "eval_model_preparation_time": 0.0035, |
| "eval_runtime": 7.7488, |
| "eval_samples_per_second": 198.095, |
| "eval_steps_per_second": 12.389, |
| "step": 863 |
| }, |
| { |
| "epoch": 1.1587485515643106, |
| "grad_norm": 12.198838233947754, |
| "learning_rate": 1.6141367323290847e-05, |
| "loss": 0.2695, |
| "step": 1000 |
| }, |
| { |
| "epoch": 1.7381228273464657, |
| "grad_norm": 4.078156471252441, |
| "learning_rate": 1.4210119737350329e-05, |
| "loss": 0.2395, |
| "step": 1500 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.9172638436482085, |
| "eval_f1": 0.7743632259583444, |
| "eval_loss": 0.27239134907722473, |
| "eval_model_preparation_time": 0.0035, |
| "eval_runtime": 7.6987, |
| "eval_samples_per_second": 199.384, |
| "eval_steps_per_second": 12.47, |
| "step": 1726 |
| }, |
| { |
| "epoch": 2.317497103128621, |
| "grad_norm": 14.144125938415527, |
| "learning_rate": 1.2278872151409811e-05, |
| "loss": 0.2124, |
| "step": 2000 |
| }, |
| { |
| "epoch": 2.8968713789107765, |
| "grad_norm": 10.107670783996582, |
| "learning_rate": 1.0347624565469293e-05, |
| "loss": 0.1963, |
| "step": 2500 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.9081433224755701, |
| "eval_f1": 0.7319603089698221, |
| "eval_loss": 0.2672387659549713, |
| "eval_model_preparation_time": 0.0035, |
| "eval_runtime": 7.9308, |
| "eval_samples_per_second": 193.549, |
| "eval_steps_per_second": 12.105, |
| "step": 2589 |
| }, |
| { |
| "epoch": 3.4762456546929315, |
| "grad_norm": 7.0400590896606445, |
| "learning_rate": 8.416376979528776e-06, |
| "loss": 0.1468, |
| "step": 3000 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.923127035830619, |
| "eval_f1": 0.8001705663023119, |
| "eval_loss": 0.29329150915145874, |
| "eval_model_preparation_time": 0.0035, |
| "eval_runtime": 7.7266, |
| "eval_samples_per_second": 198.663, |
| "eval_steps_per_second": 12.425, |
| "step": 3452 |
| }, |
| { |
| "epoch": 4.055619930475087, |
| "grad_norm": 21.304224014282227, |
| "learning_rate": 6.485129393588259e-06, |
| "loss": 0.1611, |
| "step": 3500 |
| }, |
| { |
| "epoch": 4.634994206257242, |
| "grad_norm": 0.21730026602745056, |
| "learning_rate": 4.553881807647741e-06, |
| "loss": 0.1149, |
| "step": 4000 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.9218241042345277, |
| "eval_f1": 0.7887765788808786, |
| "eval_loss": 0.3534080684185028, |
| "eval_model_preparation_time": 0.0035, |
| "eval_runtime": 4.1461, |
| "eval_samples_per_second": 370.225, |
| "eval_steps_per_second": 23.154, |
| "step": 4315 |
| }, |
| { |
| "epoch": 5.214368482039397, |
| "grad_norm": 1.3788145780563354, |
| "learning_rate": 2.622634221707223e-06, |
| "loss": 0.0984, |
| "step": 4500 |
| }, |
| { |
| "epoch": 5.793742757821553, |
| "grad_norm": 0.3194971978664398, |
| "learning_rate": 6.913866357667054e-07, |
| "loss": 0.0944, |
| "step": 5000 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.9179153094462541, |
| "eval_f1": 0.7813271685158736, |
| "eval_loss": 0.39636778831481934, |
| "eval_model_preparation_time": 0.0035, |
| "eval_runtime": 4.1457, |
| "eval_samples_per_second": 370.259, |
| "eval_steps_per_second": 23.156, |
| "step": 5178 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 5178, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 6, |
| "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": 1.0898616579001344e+16, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
