| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 12.755102040816327, |
| "global_step": 2500, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.9972193373312339, |
| "eval_f1": 0.8363636363636364, |
| "eval_loss": 0.010604099370539188, |
| "eval_precision": 0.8273381294964028, |
| "eval_recall": 0.8455882352941176, |
| "eval_runtime": 2.6817, |
| "eval_samples_per_second": 54.816, |
| "eval_steps_per_second": 18.272, |
| "step": 196 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.9978223726087976, |
| "eval_f1": 0.855072463768116, |
| "eval_loss": 0.008987429551780224, |
| "eval_precision": 0.8428571428571429, |
| "eval_recall": 0.8676470588235294, |
| "eval_runtime": 2.5934, |
| "eval_samples_per_second": 56.681, |
| "eval_steps_per_second": 18.894, |
| "step": 392 |
| }, |
| { |
| "epoch": 2.55, |
| "learning_rate": 4.149659863945579e-05, |
| "loss": 0.0231, |
| "step": 500 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.997688364769339, |
| "eval_f1": 0.8794326241134752, |
| "eval_loss": 0.009632805362343788, |
| "eval_precision": 0.8493150684931506, |
| "eval_recall": 0.9117647058823529, |
| "eval_runtime": 2.5938, |
| "eval_samples_per_second": 56.673, |
| "eval_steps_per_second": 18.891, |
| "step": 588 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.9980903882877148, |
| "eval_f1": 0.8897058823529411, |
| "eval_loss": 0.01180042140185833, |
| "eval_precision": 0.8897058823529411, |
| "eval_recall": 0.8897058823529411, |
| "eval_runtime": 2.6016, |
| "eval_samples_per_second": 56.505, |
| "eval_steps_per_second": 18.835, |
| "step": 784 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.9981908941673088, |
| "eval_f1": 0.9018181818181817, |
| "eval_loss": 0.010586733929812908, |
| "eval_precision": 0.8920863309352518, |
| "eval_recall": 0.9117647058823529, |
| "eval_runtime": 2.5999, |
| "eval_samples_per_second": 56.54, |
| "eval_steps_per_second": 18.847, |
| "step": 980 |
| }, |
| { |
| "epoch": 5.1, |
| "learning_rate": 3.2993197278911564e-05, |
| "loss": 0.0019, |
| "step": 1000 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.998458909846226, |
| "eval_f1": 0.9157509157509157, |
| "eval_loss": 0.01237014215439558, |
| "eval_precision": 0.9124087591240876, |
| "eval_recall": 0.9191176470588235, |
| "eval_runtime": 2.6016, |
| "eval_samples_per_second": 56.503, |
| "eval_steps_per_second": 18.834, |
| "step": 1176 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_accuracy": 0.998358403966632, |
| "eval_f1": 0.8978102189781022, |
| "eval_loss": 0.012939131818711758, |
| "eval_precision": 0.8913043478260869, |
| "eval_recall": 0.9044117647058824, |
| "eval_runtime": 2.5832, |
| "eval_samples_per_second": 56.905, |
| "eval_steps_per_second": 18.968, |
| "step": 1372 |
| }, |
| { |
| "epoch": 7.65, |
| "learning_rate": 2.448979591836735e-05, |
| "loss": 0.0006, |
| "step": 1500 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_accuracy": 0.9984254078863614, |
| "eval_f1": 0.9191176470588235, |
| "eval_loss": 0.012535096146166325, |
| "eval_precision": 0.9191176470588235, |
| "eval_recall": 0.9191176470588235, |
| "eval_runtime": 2.6125, |
| "eval_samples_per_second": 56.268, |
| "eval_steps_per_second": 18.756, |
| "step": 1568 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_accuracy": 0.998358403966632, |
| "eval_f1": 0.9010989010989011, |
| "eval_loss": 0.013671106658875942, |
| "eval_precision": 0.8978102189781022, |
| "eval_recall": 0.9044117647058824, |
| "eval_runtime": 2.6138, |
| "eval_samples_per_second": 56.239, |
| "eval_steps_per_second": 18.746, |
| "step": 1764 |
| }, |
| { |
| "epoch": 10.0, |
| "eval_accuracy": 0.9983919059264967, |
| "eval_f1": 0.9117647058823528, |
| "eval_loss": 0.014087404124438763, |
| "eval_precision": 0.9117647058823529, |
| "eval_recall": 0.9117647058823529, |
| "eval_runtime": 2.6236, |
| "eval_samples_per_second": 56.03, |
| "eval_steps_per_second": 18.677, |
| "step": 1960 |
| }, |
| { |
| "epoch": 10.2, |
| "learning_rate": 1.5986394557823133e-05, |
| "loss": 0.0005, |
| "step": 2000 |
| }, |
| { |
| "epoch": 11.0, |
| "eval_accuracy": 0.9982578980870381, |
| "eval_f1": 0.8929889298892988, |
| "eval_loss": 0.014975562691688538, |
| "eval_precision": 0.8962962962962963, |
| "eval_recall": 0.8897058823529411, |
| "eval_runtime": 2.598, |
| "eval_samples_per_second": 56.581, |
| "eval_steps_per_second": 18.86, |
| "step": 2156 |
| }, |
| { |
| "epoch": 12.0, |
| "eval_accuracy": 0.9981573922074441, |
| "eval_f1": 0.888888888888889, |
| "eval_loss": 0.015556328929960728, |
| "eval_precision": 0.8955223880597015, |
| "eval_recall": 0.8823529411764706, |
| "eval_runtime": 2.5873, |
| "eval_samples_per_second": 56.817, |
| "eval_steps_per_second": 18.939, |
| "step": 2352 |
| }, |
| { |
| "epoch": 12.76, |
| "learning_rate": 7.482993197278912e-06, |
| "loss": 0.0002, |
| "step": 2500 |
| } |
| ], |
| "max_steps": 2940, |
| "num_train_epochs": 15, |
| "total_flos": 1238088268279728.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
