| { | |
| "best_metric": 0.6282620163217179, | |
| "best_model_checkpoint": "esm2_t6_8M-binding-site-classification_2023-09-05_16-25-08/checkpoint-5598", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 5598, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0005695234606678405, | |
| "loss": 0.4679, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.0005676006526247637, | |
| "loss": 0.3559, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.0005643970338296423, | |
| "loss": 0.3089, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.0005599271278444283, | |
| "loss": 0.2692, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.0005542111989267148, | |
| "loss": 0.232, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.0005472751601620024, | |
| "loss": 0.2046, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.00053915045598708, | |
| "loss": 0.2237, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 0.0005298739196371016, | |
| "loss": 0.2119, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 0.0005194876061626189, | |
| "loss": 0.1905, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_auc": 0.9261141394147127, | |
| "eval_f1": 0.4530748302654477, | |
| "eval_loss": 0.2022695094347, | |
| "eval_precision": 0.30564833493171073, | |
| "eval_recall": 0.8752367424242424, | |
| "eval_runtime": 95.9675, | |
| "eval_samples_per_second": 27.447, | |
| "eval_steps_per_second": 3.439, | |
| "step": 1866 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.0005080386017735853, | |
| "loss": 0.173, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 0.0004955788103746674, | |
| "loss": 0.1316, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 0.00048223406367877986, | |
| "loss": 0.1423, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 0.00046793079280001864, | |
| "loss": 0.1411, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 0.00045279856311429995, | |
| "loss": 0.1111, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 0.00043690597637775135, | |
| "loss": 0.1513, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 0.00042032508141478175, | |
| "loss": 0.1106, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 0.0004031310474857221, | |
| "loss": 0.1073, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 0.0003854018235080123, | |
| "loss": 0.1079, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_auc": 0.9625828119645666, | |
| "eval_f1": 0.39631155965817316, | |
| "eval_loss": 0.10649576038122177, | |
| "eval_precision": 0.24979947431420216, | |
| "eval_recall": 0.9584753787878788, | |
| "eval_runtime": 96.1903, | |
| "eval_samples_per_second": 27.383, | |
| "eval_steps_per_second": 3.431, | |
| "step": 3732 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 0.0003672177846758513, | |
| "loss": 0.1161, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 0.00034866136808035477, | |
| "loss": 0.0703, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 0.00032981669898213067, | |
| "loss": 0.087, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 0.000310769209430562, | |
| "loss": 0.0662, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 0.0002916052509587806, | |
| "loss": 0.0602, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 0.0002725076004735508, | |
| "loss": 0.0788, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 0.00025337097363328114, | |
| "loss": 0.0511, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 0.00023437809198903362, | |
| "loss": 0.0506, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 0.00021561505950973994, | |
| "loss": 0.0554, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_auc": 0.9730075655719146, | |
| "eval_f1": 0.6282620163217179, | |
| "eval_loss": 0.08585791289806366, | |
| "eval_precision": 0.4672312733650252, | |
| "eval_recall": 0.9586647727272727, | |
| "eval_runtime": 96.1068, | |
| "eval_samples_per_second": 27.407, | |
| "eval_steps_per_second": 3.434, | |
| "step": 5598 | |
| } | |
| ], | |
| "logging_steps": 200, | |
| "max_steps": 9330, | |
| "num_train_epochs": 5, | |
| "save_steps": 500, | |
| "total_flos": 1987518770082000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |