| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 15.0, | |
| "global_step": 12240, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 1.9183006535947716e-05, | |
| "loss": 0.4329, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9725273278019229, | |
| "eval_f1": 0.9629807384654764, | |
| "eval_loss": 0.10430943965911865, | |
| "eval_precision": 0.9637516411028211, | |
| "eval_recall": 0.9622110681287765, | |
| "eval_runtime": 2.936, | |
| "eval_samples_per_second": 494.214, | |
| "eval_steps_per_second": 30.995, | |
| "step": 816 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 1.8366013071895427e-05, | |
| "loss": 0.0811, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 1.7549019607843138e-05, | |
| "loss": 0.0607, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9751349927564862, | |
| "eval_f1": 0.9635150914122107, | |
| "eval_loss": 0.09400150179862976, | |
| "eval_precision": 0.9641165172855314, | |
| "eval_recall": 0.9629144154224879, | |
| "eval_runtime": 2.7493, | |
| "eval_samples_per_second": 527.777, | |
| "eval_steps_per_second": 33.1, | |
| "step": 1632 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 1.6732026143790852e-05, | |
| "loss": 0.0428, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9755037534571316, | |
| "eval_f1": 0.9632957125043962, | |
| "eval_loss": 0.09555820375680923, | |
| "eval_precision": 0.9633573141486811, | |
| "eval_recall": 0.9632341187378113, | |
| "eval_runtime": 2.7415, | |
| "eval_samples_per_second": 529.269, | |
| "eval_steps_per_second": 33.193, | |
| "step": 2448 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 1.5915032679738563e-05, | |
| "loss": 0.0363, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 3.68, | |
| "learning_rate": 1.5098039215686276e-05, | |
| "loss": 0.0249, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9765046753588832, | |
| "eval_f1": 0.9649540551338394, | |
| "eval_loss": 0.0989251509308815, | |
| "eval_precision": 0.9646919734151329, | |
| "eval_recall": 0.9652162792928163, | |
| "eval_runtime": 2.7759, | |
| "eval_samples_per_second": 522.708, | |
| "eval_steps_per_second": 32.782, | |
| "step": 3264 | |
| }, | |
| { | |
| "epoch": 4.29, | |
| "learning_rate": 1.4281045751633989e-05, | |
| "loss": 0.0221, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 4.9, | |
| "learning_rate": 1.3464052287581701e-05, | |
| "loss": 0.0177, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.976451995258791, | |
| "eval_f1": 0.9646675296035285, | |
| "eval_loss": 0.10913769155740738, | |
| "eval_precision": 0.9643747204294204, | |
| "eval_recall": 0.9649605166405576, | |
| "eval_runtime": 3.7551, | |
| "eval_samples_per_second": 386.403, | |
| "eval_steps_per_second": 24.233, | |
| "step": 4080 | |
| }, | |
| { | |
| "epoch": 5.51, | |
| "learning_rate": 1.2647058823529412e-05, | |
| "loss": 0.0129, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.9780060582115107, | |
| "eval_f1": 0.9675017575254042, | |
| "eval_loss": 0.11124212294816971, | |
| "eval_precision": 0.967038231818327, | |
| "eval_recall": 0.9679657278045973, | |
| "eval_runtime": 3.8249, | |
| "eval_samples_per_second": 379.357, | |
| "eval_steps_per_second": 23.792, | |
| "step": 4896 | |
| }, | |
| { | |
| "epoch": 6.13, | |
| "learning_rate": 1.1830065359477125e-05, | |
| "loss": 0.0119, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 6.74, | |
| "learning_rate": 1.1013071895424838e-05, | |
| "loss": 0.0084, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.9783221388120638, | |
| "eval_f1": 0.9677996994212259, | |
| "eval_loss": 0.12139276415109634, | |
| "eval_precision": 0.967985415933732, | |
| "eval_recall": 0.9676140541577416, | |
| "eval_runtime": 3.747, | |
| "eval_samples_per_second": 387.246, | |
| "eval_steps_per_second": 24.286, | |
| "step": 5712 | |
| }, | |
| { | |
| "epoch": 7.35, | |
| "learning_rate": 1.0196078431372549e-05, | |
| "loss": 0.0076, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 7.97, | |
| "learning_rate": 9.379084967320261e-06, | |
| "loss": 0.0061, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.9775319373106809, | |
| "eval_f1": 0.9664444551020734, | |
| "eval_loss": 0.13343702256679535, | |
| "eval_precision": 0.9665217113257019, | |
| "eval_recall": 0.9663672112279804, | |
| "eval_runtime": 2.7649, | |
| "eval_samples_per_second": 524.787, | |
| "eval_steps_per_second": 32.912, | |
| "step": 6528 | |
| }, | |
| { | |
| "epoch": 8.58, | |
| "learning_rate": 8.562091503267974e-06, | |
| "loss": 0.0048, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.9775055972606348, | |
| "eval_f1": 0.9661577811525858, | |
| "eval_loss": 0.13892702758312225, | |
| "eval_precision": 0.9662041181736795, | |
| "eval_recall": 0.9661114485757217, | |
| "eval_runtime": 3.8371, | |
| "eval_samples_per_second": 378.146, | |
| "eval_steps_per_second": 23.716, | |
| "step": 7344 | |
| }, | |
| { | |
| "epoch": 9.19, | |
| "learning_rate": 7.745098039215687e-06, | |
| "loss": 0.0047, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 9.8, | |
| "learning_rate": 6.928104575163399e-06, | |
| "loss": 0.0044, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.9781640985117872, | |
| "eval_f1": 0.967271564473579, | |
| "eval_loss": 0.14489226043224335, | |
| "eval_precision": 0.9674726540011515, | |
| "eval_recall": 0.9670705585216919, | |
| "eval_runtime": 3.7406, | |
| "eval_samples_per_second": 387.909, | |
| "eval_steps_per_second": 24.328, | |
| "step": 8160 | |
| }, | |
| { | |
| "epoch": 10.42, | |
| "learning_rate": 6.111111111111112e-06, | |
| "loss": 0.0034, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.9779797181614646, | |
| "eval_f1": 0.9672149490880608, | |
| "eval_loss": 0.14611582458019257, | |
| "eval_precision": 0.9671994884910486, | |
| "eval_recall": 0.9672304101793535, | |
| "eval_runtime": 2.8969, | |
| "eval_samples_per_second": 500.886, | |
| "eval_steps_per_second": 31.413, | |
| "step": 8976 | |
| }, | |
| { | |
| "epoch": 11.03, | |
| "learning_rate": 5.294117647058824e-06, | |
| "loss": 0.0034, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 11.64, | |
| "learning_rate": 4.477124183006537e-06, | |
| "loss": 0.0025, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.9784274990122481, | |
| "eval_f1": 0.9676501159350764, | |
| "eval_loss": 0.14966140687465668, | |
| "eval_precision": 0.9680061428205784, | |
| "eval_recall": 0.9672943508424182, | |
| "eval_runtime": 2.7972, | |
| "eval_samples_per_second": 518.731, | |
| "eval_steps_per_second": 32.532, | |
| "step": 9792 | |
| }, | |
| { | |
| "epoch": 12.25, | |
| "learning_rate": 3.6601307189542484e-06, | |
| "loss": 0.0022, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 12.87, | |
| "learning_rate": 2.843137254901961e-06, | |
| "loss": 0.0024, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.977848017911234, | |
| "eval_f1": 0.9670199670679264, | |
| "eval_loss": 0.15780866146087646, | |
| "eval_precision": 0.9670972692971798, | |
| "eval_recall": 0.9669426771955625, | |
| "eval_runtime": 3.8111, | |
| "eval_samples_per_second": 380.734, | |
| "eval_steps_per_second": 23.878, | |
| "step": 10608 | |
| }, | |
| { | |
| "epoch": 13.48, | |
| "learning_rate": 2.0261437908496734e-06, | |
| "loss": 0.0014, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.978111418411695, | |
| "eval_f1": 0.9674521213671389, | |
| "eval_loss": 0.15866732597351074, | |
| "eval_precision": 0.9675139888089528, | |
| "eval_recall": 0.9673902618370153, | |
| "eval_runtime": 2.8382, | |
| "eval_samples_per_second": 511.243, | |
| "eval_steps_per_second": 32.063, | |
| "step": 11424 | |
| }, | |
| { | |
| "epoch": 14.09, | |
| "learning_rate": 1.2091503267973858e-06, | |
| "loss": 0.0019, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 14.71, | |
| "learning_rate": 3.921568627450981e-07, | |
| "loss": 0.0016, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.978401158962202, | |
| "eval_f1": 0.96785434549785, | |
| "eval_loss": 0.15796583890914917, | |
| "eval_precision": 0.9678388746803069, | |
| "eval_recall": 0.9678698168100003, | |
| "eval_runtime": 3.7576, | |
| "eval_samples_per_second": 386.151, | |
| "eval_steps_per_second": 24.218, | |
| "step": 12240 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "step": 12240, | |
| "total_flos": 5.119363918698906e+16, | |
| "train_loss": 0.03262665262993644, | |
| "train_runtime": 785.1159, | |
| "train_samples_per_second": 249.403, | |
| "train_steps_per_second": 15.59 | |
| } | |
| ], | |
| "max_steps": 12240, | |
| "num_train_epochs": 15, | |
| "total_flos": 5.119363918698906e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |