| { | |
| "best_metric": 0.39284127950668335, | |
| "best_model_checkpoint": "StressTweetRobertaSentiment/checkpoint-180", | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 180, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03888888888888889, | |
| "grad_norm": 4.96373987197876, | |
| "learning_rate": 6.481481481481481e-06, | |
| "loss": 0.6582, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.07777777777777778, | |
| "grad_norm": 7.41157341003418, | |
| "learning_rate": 1.2962962962962962e-05, | |
| "loss": 0.5382, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.11666666666666667, | |
| "grad_norm": 19.304912567138672, | |
| "learning_rate": 1.9444444444444445e-05, | |
| "loss": 0.4156, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.15555555555555556, | |
| "grad_norm": 16.010875701904297, | |
| "learning_rate": 2.5925925925925925e-05, | |
| "loss": 0.4644, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.19444444444444445, | |
| "grad_norm": 40.6972770690918, | |
| "learning_rate": 3.240740740740741e-05, | |
| "loss": 0.4544, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.23333333333333334, | |
| "grad_norm": 10.888315200805664, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 0.3438, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.2722222222222222, | |
| "grad_norm": 36.86009979248047, | |
| "learning_rate": 4.5370370370370374e-05, | |
| "loss": 0.362, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.3111111111111111, | |
| "grad_norm": 36.744590759277344, | |
| "learning_rate": 4.9794238683127575e-05, | |
| "loss": 0.5263, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": 12.836268424987793, | |
| "learning_rate": 4.9074074074074075e-05, | |
| "loss": 0.3602, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.3888888888888889, | |
| "grad_norm": 7.51406717300415, | |
| "learning_rate": 4.835390946502058e-05, | |
| "loss": 0.6603, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.42777777777777776, | |
| "grad_norm": 9.410354614257812, | |
| "learning_rate": 4.763374485596708e-05, | |
| "loss": 0.6094, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.4666666666666667, | |
| "grad_norm": 53.80480194091797, | |
| "learning_rate": 4.691358024691358e-05, | |
| "loss": 0.3819, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.5055555555555555, | |
| "grad_norm": 4.867987155914307, | |
| "learning_rate": 4.6193415637860084e-05, | |
| "loss": 0.5925, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.5444444444444444, | |
| "grad_norm": 0.8935460448265076, | |
| "learning_rate": 4.5473251028806584e-05, | |
| "loss": 0.2471, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.5833333333333334, | |
| "grad_norm": 8.400871276855469, | |
| "learning_rate": 4.4753086419753084e-05, | |
| "loss": 0.4062, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.6222222222222222, | |
| "grad_norm": 14.911149024963379, | |
| "learning_rate": 4.403292181069959e-05, | |
| "loss": 0.6447, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.6611111111111111, | |
| "grad_norm": 20.210161209106445, | |
| "learning_rate": 4.331275720164609e-05, | |
| "loss": 0.4248, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": 17.20897674560547, | |
| "learning_rate": 4.259259259259259e-05, | |
| "loss": 0.6514, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.7388888888888889, | |
| "grad_norm": 15.010047912597656, | |
| "learning_rate": 4.18724279835391e-05, | |
| "loss": 0.327, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.7777777777777778, | |
| "grad_norm": 23.96828269958496, | |
| "learning_rate": 4.11522633744856e-05, | |
| "loss": 0.3802, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.8166666666666667, | |
| "grad_norm": 45.84319305419922, | |
| "learning_rate": 4.04320987654321e-05, | |
| "loss": 0.4437, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.8555555555555555, | |
| "grad_norm": 21.39622688293457, | |
| "learning_rate": 3.971193415637861e-05, | |
| "loss": 0.7226, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.8944444444444445, | |
| "grad_norm": 7.082496166229248, | |
| "learning_rate": 3.89917695473251e-05, | |
| "loss": 0.2913, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.9333333333333333, | |
| "grad_norm": 4.158477783203125, | |
| "learning_rate": 3.82716049382716e-05, | |
| "loss": 0.3775, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.9722222222222222, | |
| "grad_norm": 5.003448486328125, | |
| "learning_rate": 3.755144032921811e-05, | |
| "loss": 0.3336, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8831168831168831, | |
| "eval_auc": 0.957133746355685, | |
| "eval_f1": 0.91, | |
| "eval_loss": 0.39284127950668335, | |
| "eval_precision": 0.8921568627450981, | |
| "eval_recall": 0.9285714285714286, | |
| "eval_runtime": 49.1707, | |
| "eval_samples_per_second": 6.264, | |
| "eval_steps_per_second": 0.407, | |
| "step": 180 | |
| } | |
| ], | |
| "logging_steps": 7, | |
| "max_steps": 540, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 94391091110400.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |