| { |
| "best_metric": 0.9444444444444444, |
| "best_model_checkpoint": "test/checkpoint-14", |
| "epoch": 19.727272727272727, |
| "global_step": 40, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.73, |
| "eval_accuracy": 0.6111111111111112, |
| "eval_f1": 0.5416666666666666, |
| "eval_loss": 0.7271409630775452, |
| "eval_precision": 0.5208333333333334, |
| "eval_recall": 0.6111111111111112, |
| "eval_runtime": 6.3413, |
| "eval_samples_per_second": 5.677, |
| "eval_steps_per_second": 0.158, |
| "step": 2 |
| }, |
| { |
| "epoch": 1.73, |
| "eval_accuracy": 0.8333333333333334, |
| "eval_f1": 0.8148148148148149, |
| "eval_loss": 0.46258121728897095, |
| "eval_precision": 0.8666666666666667, |
| "eval_recall": 0.8333333333333334, |
| "eval_runtime": 5.8395, |
| "eval_samples_per_second": 6.165, |
| "eval_steps_per_second": 0.171, |
| "step": 4 |
| }, |
| { |
| "epoch": 2.73, |
| "eval_accuracy": 0.9166666666666666, |
| "eval_f1": 0.9157054125998224, |
| "eval_loss": 0.3036719858646393, |
| "eval_precision": 0.9163636363636365, |
| "eval_recall": 0.9166666666666666, |
| "eval_runtime": 5.8411, |
| "eval_samples_per_second": 6.163, |
| "eval_steps_per_second": 0.171, |
| "step": 6 |
| }, |
| { |
| "epoch": 3.73, |
| "eval_accuracy": 0.9166666666666666, |
| "eval_f1": 0.9131652661064424, |
| "eval_loss": 0.24792712926864624, |
| "eval_precision": 0.9259259259259258, |
| "eval_recall": 0.9166666666666666, |
| "eval_runtime": 5.7041, |
| "eval_samples_per_second": 6.311, |
| "eval_steps_per_second": 0.175, |
| "step": 8 |
| }, |
| { |
| "epoch": 4.73, |
| "learning_rate": 0.0001, |
| "loss": 0.6338, |
| "step": 10 |
| }, |
| { |
| "epoch": 4.73, |
| "eval_accuracy": 0.9166666666666666, |
| "eval_f1": 0.9174468085106382, |
| "eval_loss": 0.23573820292949677, |
| "eval_precision": 0.919732441471572, |
| "eval_recall": 0.9166666666666666, |
| "eval_runtime": 5.6473, |
| "eval_samples_per_second": 6.375, |
| "eval_steps_per_second": 0.177, |
| "step": 10 |
| }, |
| { |
| "epoch": 5.73, |
| "eval_accuracy": 0.8888888888888888, |
| "eval_f1": 0.890746934225195, |
| "eval_loss": 0.21319927275180817, |
| "eval_precision": 0.8982683982683982, |
| "eval_recall": 0.8888888888888888, |
| "eval_runtime": 6.2525, |
| "eval_samples_per_second": 5.758, |
| "eval_steps_per_second": 0.16, |
| "step": 12 |
| }, |
| { |
| "epoch": 6.73, |
| "eval_accuracy": 0.9444444444444444, |
| "eval_f1": 0.9430303030303031, |
| "eval_loss": 0.17125670611858368, |
| "eval_precision": 0.9487179487179487, |
| "eval_recall": 0.9444444444444444, |
| "eval_runtime": 5.7878, |
| "eval_samples_per_second": 6.22, |
| "eval_steps_per_second": 0.173, |
| "step": 14 |
| }, |
| { |
| "epoch": 7.73, |
| "eval_accuracy": 0.9444444444444444, |
| "eval_f1": 0.9444444444444444, |
| "eval_loss": 0.15498512983322144, |
| "eval_precision": 0.9444444444444444, |
| "eval_recall": 0.9444444444444444, |
| "eval_runtime": 6.2641, |
| "eval_samples_per_second": 5.747, |
| "eval_steps_per_second": 0.16, |
| "step": 16 |
| }, |
| { |
| "epoch": 8.73, |
| "eval_accuracy": 0.9444444444444444, |
| "eval_f1": 0.9444444444444444, |
| "eval_loss": 0.14064311981201172, |
| "eval_precision": 0.9444444444444444, |
| "eval_recall": 0.9444444444444444, |
| "eval_runtime": 5.34, |
| "eval_samples_per_second": 6.742, |
| "eval_steps_per_second": 0.187, |
| "step": 18 |
| }, |
| { |
| "epoch": 9.73, |
| "learning_rate": 6.666666666666667e-05, |
| "loss": 0.217, |
| "step": 20 |
| }, |
| { |
| "epoch": 9.73, |
| "eval_accuracy": 0.9444444444444444, |
| "eval_f1": 0.9444444444444444, |
| "eval_loss": 0.16372796893119812, |
| "eval_precision": 0.9444444444444444, |
| "eval_recall": 0.9444444444444444, |
| "eval_runtime": 5.2833, |
| "eval_samples_per_second": 6.814, |
| "eval_steps_per_second": 0.189, |
| "step": 20 |
| }, |
| { |
| "epoch": 10.73, |
| "eval_accuracy": 0.9166666666666666, |
| "eval_f1": 0.9157054125998224, |
| "eval_loss": 0.16719864308834076, |
| "eval_precision": 0.9163636363636365, |
| "eval_recall": 0.9166666666666666, |
| "eval_runtime": 6.4055, |
| "eval_samples_per_second": 5.62, |
| "eval_steps_per_second": 0.156, |
| "step": 22 |
| }, |
| { |
| "epoch": 11.73, |
| "eval_accuracy": 0.9444444444444444, |
| "eval_f1": 0.9444444444444444, |
| "eval_loss": 0.13150224089622498, |
| "eval_precision": 0.9444444444444444, |
| "eval_recall": 0.9444444444444444, |
| "eval_runtime": 5.1218, |
| "eval_samples_per_second": 7.029, |
| "eval_steps_per_second": 0.195, |
| "step": 24 |
| }, |
| { |
| "epoch": 12.73, |
| "eval_accuracy": 0.9444444444444444, |
| "eval_f1": 0.9444444444444444, |
| "eval_loss": 0.1597292125225067, |
| "eval_precision": 0.9444444444444444, |
| "eval_recall": 0.9444444444444444, |
| "eval_runtime": 5.1268, |
| "eval_samples_per_second": 7.022, |
| "eval_steps_per_second": 0.195, |
| "step": 26 |
| }, |
| { |
| "epoch": 13.73, |
| "eval_accuracy": 0.9444444444444444, |
| "eval_f1": 0.9444444444444444, |
| "eval_loss": 0.1412082463502884, |
| "eval_precision": 0.9444444444444444, |
| "eval_recall": 0.9444444444444444, |
| "eval_runtime": 5.6714, |
| "eval_samples_per_second": 6.348, |
| "eval_steps_per_second": 0.176, |
| "step": 28 |
| }, |
| { |
| "epoch": 14.73, |
| "learning_rate": 3.3333333333333335e-05, |
| "loss": 0.0906, |
| "step": 30 |
| }, |
| { |
| "epoch": 14.73, |
| "eval_accuracy": 0.9444444444444444, |
| "eval_f1": 0.9444444444444444, |
| "eval_loss": 0.1776580661535263, |
| "eval_precision": 0.9444444444444444, |
| "eval_recall": 0.9444444444444444, |
| "eval_runtime": 5.8702, |
| "eval_samples_per_second": 6.133, |
| "eval_steps_per_second": 0.17, |
| "step": 30 |
| }, |
| { |
| "epoch": 15.73, |
| "eval_accuracy": 0.9444444444444444, |
| "eval_f1": 0.9444444444444444, |
| "eval_loss": 0.14607585966587067, |
| "eval_precision": 0.9444444444444444, |
| "eval_recall": 0.9444444444444444, |
| "eval_runtime": 7.113, |
| "eval_samples_per_second": 5.061, |
| "eval_steps_per_second": 0.141, |
| "step": 32 |
| }, |
| { |
| "epoch": 16.73, |
| "eval_accuracy": 0.9166666666666666, |
| "eval_f1": 0.9174468085106382, |
| "eval_loss": 0.19147923588752747, |
| "eval_precision": 0.919732441471572, |
| "eval_recall": 0.9166666666666666, |
| "eval_runtime": 5.3662, |
| "eval_samples_per_second": 6.709, |
| "eval_steps_per_second": 0.186, |
| "step": 34 |
| }, |
| { |
| "epoch": 17.73, |
| "eval_accuracy": 0.9166666666666666, |
| "eval_f1": 0.9174468085106382, |
| "eval_loss": 0.13753658533096313, |
| "eval_precision": 0.919732441471572, |
| "eval_recall": 0.9166666666666666, |
| "eval_runtime": 5.3487, |
| "eval_samples_per_second": 6.731, |
| "eval_steps_per_second": 0.187, |
| "step": 36 |
| }, |
| { |
| "epoch": 18.73, |
| "eval_accuracy": 0.9166666666666666, |
| "eval_f1": 0.9174468085106382, |
| "eval_loss": 0.1448293775320053, |
| "eval_precision": 0.919732441471572, |
| "eval_recall": 0.9166666666666666, |
| "eval_runtime": 5.5619, |
| "eval_samples_per_second": 6.473, |
| "eval_steps_per_second": 0.18, |
| "step": 38 |
| }, |
| { |
| "epoch": 19.73, |
| "learning_rate": 0.0, |
| "loss": 0.0548, |
| "step": 40 |
| }, |
| { |
| "epoch": 19.73, |
| "eval_accuracy": 0.9444444444444444, |
| "eval_f1": 0.9444444444444444, |
| "eval_loss": 0.12921589612960815, |
| "eval_precision": 0.9444444444444444, |
| "eval_recall": 0.9444444444444444, |
| "eval_runtime": 5.8187, |
| "eval_samples_per_second": 6.187, |
| "eval_steps_per_second": 0.172, |
| "step": 40 |
| }, |
| { |
| "epoch": 19.73, |
| "step": 40, |
| "total_flos": 4.050283110270566e+16, |
| "train_loss": 0.24904835671186448, |
| "train_runtime": 1252.5827, |
| "train_samples_per_second": 10.921, |
| "train_steps_per_second": 0.032 |
| } |
| ], |
| "max_steps": 40, |
| "num_train_epochs": 20, |
| "total_flos": 4.050283110270566e+16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
