| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 10.0, |
| "global_step": 910, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.9533894011551323, |
| "eval_f1": 0.6969990319457888, |
| "eval_loss": 0.20486080646514893, |
| "eval_precision": 0.6617647058823529, |
| "eval_recall": 0.7361963190184049, |
| "eval_runtime": 1.2373, |
| "eval_samples_per_second": 130.123, |
| "eval_steps_per_second": 33.137, |
| "step": 91 |
| }, |
| { |
| "epoch": 1.1, |
| "learning_rate": 4.4505494505494504e-05, |
| "loss": 0.5036, |
| "step": 100 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.9722362954706657, |
| "eval_f1": 0.8234146341463414, |
| "eval_loss": 0.11564752459526062, |
| "eval_precision": 0.7873134328358209, |
| "eval_recall": 0.8629856850715747, |
| "eval_runtime": 1.2367, |
| "eval_samples_per_second": 130.181, |
| "eval_steps_per_second": 33.152, |
| "step": 182 |
| }, |
| { |
| "epoch": 2.2, |
| "learning_rate": 3.901098901098901e-05, |
| "loss": 0.1442, |
| "step": 200 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.9771000101327388, |
| "eval_f1": 0.8632812499999999, |
| "eval_loss": 0.10779214650392532, |
| "eval_precision": 0.8261682242990654, |
| "eval_recall": 0.9038854805725971, |
| "eval_runtime": 1.2508, |
| "eval_samples_per_second": 128.715, |
| "eval_steps_per_second": 32.778, |
| "step": 273 |
| }, |
| { |
| "epoch": 3.3, |
| "learning_rate": 3.3516483516483513e-05, |
| "loss": 0.0757, |
| "step": 300 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.9780119566318776, |
| "eval_f1": 0.8851148851148851, |
| "eval_loss": 0.1178947389125824, |
| "eval_precision": 0.865234375, |
| "eval_recall": 0.9059304703476483, |
| "eval_runtime": 1.2453, |
| "eval_samples_per_second": 129.288, |
| "eval_steps_per_second": 32.924, |
| "step": 364 |
| }, |
| { |
| "epoch": 4.4, |
| "learning_rate": 2.8021978021978025e-05, |
| "loss": 0.0526, |
| "step": 400 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.9836862904042962, |
| "eval_f1": 0.897876643073812, |
| "eval_loss": 0.0906740128993988, |
| "eval_precision": 0.888, |
| "eval_recall": 0.9079754601226994, |
| "eval_runtime": 1.2584, |
| "eval_samples_per_second": 127.94, |
| "eval_steps_per_second": 32.581, |
| "step": 455 |
| }, |
| { |
| "epoch": 5.49, |
| "learning_rate": 2.252747252747253e-05, |
| "loss": 0.0342, |
| "step": 500 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.9831796534603303, |
| "eval_f1": 0.9130869130869131, |
| "eval_loss": 0.0972292423248291, |
| "eval_precision": 0.892578125, |
| "eval_recall": 0.934560327198364, |
| "eval_runtime": 1.2748, |
| "eval_samples_per_second": 126.296, |
| "eval_steps_per_second": 32.162, |
| "step": 546 |
| }, |
| { |
| "epoch": 6.59, |
| "learning_rate": 1.7032967032967035e-05, |
| "loss": 0.0245, |
| "step": 600 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_accuracy": 0.9833823082379167, |
| "eval_f1": 0.9107321965897693, |
| "eval_loss": 0.10643576085567474, |
| "eval_precision": 0.8937007874015748, |
| "eval_recall": 0.9284253578732107, |
| "eval_runtime": 1.2478, |
| "eval_samples_per_second": 129.031, |
| "eval_steps_per_second": 32.859, |
| "step": 637 |
| }, |
| { |
| "epoch": 7.69, |
| "learning_rate": 1.153846153846154e-05, |
| "loss": 0.0188, |
| "step": 700 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_accuracy": 0.9850035464586078, |
| "eval_f1": 0.9169169169169169, |
| "eval_loss": 0.09653466939926147, |
| "eval_precision": 0.8980392156862745, |
| "eval_recall": 0.9366053169734151, |
| "eval_runtime": 1.2451, |
| "eval_samples_per_second": 129.306, |
| "eval_steps_per_second": 32.929, |
| "step": 728 |
| }, |
| { |
| "epoch": 8.79, |
| "learning_rate": 6.043956043956044e-06, |
| "loss": 0.0159, |
| "step": 800 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_accuracy": 0.984598236903435, |
| "eval_f1": 0.9201213346814965, |
| "eval_loss": 0.09986742585897446, |
| "eval_precision": 0.91, |
| "eval_recall": 0.9304703476482618, |
| "eval_runtime": 1.2461, |
| "eval_samples_per_second": 129.208, |
| "eval_steps_per_second": 32.904, |
| "step": 819 |
| }, |
| { |
| "epoch": 9.89, |
| "learning_rate": 5.494505494505495e-07, |
| "loss": 0.0141, |
| "step": 900 |
| }, |
| { |
| "epoch": 10.0, |
| "eval_accuracy": 0.985104873847401, |
| "eval_f1": 0.911088911088911, |
| "eval_loss": 0.09563781321048737, |
| "eval_precision": 0.890625, |
| "eval_recall": 0.9325153374233128, |
| "eval_runtime": 1.2493, |
| "eval_samples_per_second": 128.877, |
| "eval_steps_per_second": 32.819, |
| "step": 910 |
| }, |
| { |
| "epoch": 10.0, |
| "step": 910, |
| "total_flos": 1883034567828480.0, |
| "train_loss": 0.09724931471295409, |
| "train_runtime": 322.9196, |
| "train_samples_per_second": 44.624, |
| "train_steps_per_second": 2.818 |
| } |
| ], |
| "max_steps": 910, |
| "num_train_epochs": 10, |
| "total_flos": 1883034567828480.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
