| { | |
| "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": 0.3785, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9737126300539971, | |
| "eval_f1": 0.9626903878151799, | |
| "eval_loss": 0.09840826690196991, | |
| "eval_precision": 0.9635228182546037, | |
| "eval_recall": 0.9618593944819208, | |
| "eval_runtime": 3.9949, | |
| "eval_samples_per_second": 363.209, | |
| "eval_steps_per_second": 22.779, | |
| "step": 816 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 1.8366013071895427e-05, | |
| "loss": 0.0836, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 1.7549019607843138e-05, | |
| "loss": 0.0641, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.975925194257869, | |
| "eval_f1": 0.9640177271490968, | |
| "eval_loss": 0.09886540472507477, | |
| "eval_precision": 0.9648667691519344, | |
| "eval_recall": 0.9631701780747466, | |
| "eval_runtime": 3.9485, | |
| "eval_samples_per_second": 367.479, | |
| "eval_steps_per_second": 23.047, | |
| "step": 1632 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 1.6732026143790852e-05, | |
| "loss": 0.0458, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.976741735809298, | |
| "eval_f1": 0.9651566272766523, | |
| "eval_loss": 0.09389109164476395, | |
| "eval_precision": 0.9654808369057521, | |
| "eval_recall": 0.9648326353144282, | |
| "eval_runtime": 3.7903, | |
| "eval_samples_per_second": 382.817, | |
| "eval_steps_per_second": 24.008, | |
| "step": 2448 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 1.5915032679738563e-05, | |
| "loss": 0.0394, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 3.68, | |
| "learning_rate": 1.5098039215686276e-05, | |
| "loss": 0.0279, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9758725141577769, | |
| "eval_f1": 0.963916701321135, | |
| "eval_loss": 0.09818906337022781, | |
| "eval_precision": 0.9644720417373491, | |
| "eval_recall": 0.9633620000639407, | |
| "eval_runtime": 3.805, | |
| "eval_samples_per_second": 381.341, | |
| "eval_steps_per_second": 23.916, | |
| "step": 3264 | |
| }, | |
| { | |
| "epoch": 4.29, | |
| "learning_rate": 1.4281045751633989e-05, | |
| "loss": 0.0254, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 4.9, | |
| "learning_rate": 1.3464052287581701e-05, | |
| "loss": 0.0194, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.9765310154089293, | |
| "eval_f1": 0.9647630619684083, | |
| "eval_loss": 0.10570573806762695, | |
| "eval_precision": 0.9649173302631999, | |
| "eval_recall": 0.9646088429937019, | |
| "eval_runtime": 4.1667, | |
| "eval_samples_per_second": 348.241, | |
| "eval_steps_per_second": 21.84, | |
| "step": 4080 | |
| }, | |
| { | |
| "epoch": 5.51, | |
| "learning_rate": 1.2647058823529412e-05, | |
| "loss": 0.0141, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.9767680758593441, | |
| "eval_f1": 0.9650685041006539, | |
| "eval_loss": 0.11329083889722824, | |
| "eval_precision": 0.9651765157329241, | |
| "eval_recall": 0.9649605166405576, | |
| "eval_runtime": 3.8277, | |
| "eval_samples_per_second": 379.077, | |
| "eval_steps_per_second": 23.774, | |
| "step": 4896 | |
| }, | |
| { | |
| "epoch": 6.13, | |
| "learning_rate": 1.1830065359477125e-05, | |
| "loss": 0.0142, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 6.74, | |
| "learning_rate": 1.1013071895424838e-05, | |
| "loss": 0.0097, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.9780060582115107, | |
| "eval_f1": 0.9669496810092579, | |
| "eval_loss": 0.1174820214509964, | |
| "eval_precision": 0.9672125903652997, | |
| "eval_recall": 0.9666869145433038, | |
| "eval_runtime": 2.7647, | |
| "eval_samples_per_second": 524.836, | |
| "eval_steps_per_second": 32.915, | |
| "step": 5712 | |
| }, | |
| { | |
| "epoch": 7.35, | |
| "learning_rate": 1.0196078431372549e-05, | |
| "loss": 0.0085, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 7.97, | |
| "learning_rate": 9.379084967320261e-06, | |
| "loss": 0.0078, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.9770841564598973, | |
| "eval_f1": 0.965837913843794, | |
| "eval_loss": 0.12893585860729218, | |
| "eval_precision": 0.9654368311771283, | |
| "eval_recall": 0.9662393299018511, | |
| "eval_runtime": 3.7734, | |
| "eval_samples_per_second": 384.529, | |
| "eval_steps_per_second": 24.116, | |
| "step": 6528 | |
| }, | |
| { | |
| "epoch": 8.58, | |
| "learning_rate": 8.562091503267974e-06, | |
| "loss": 0.0061, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.9767680758593441, | |
| "eval_f1": 0.9654114677360088, | |
| "eval_loss": 0.1360652893781662, | |
| "eval_precision": 0.9648719422622469, | |
| "eval_recall": 0.96595159691806, | |
| "eval_runtime": 4.9673, | |
| "eval_samples_per_second": 292.108, | |
| "eval_steps_per_second": 18.32, | |
| "step": 7344 | |
| }, | |
| { | |
| "epoch": 9.19, | |
| "learning_rate": 7.745098039215687e-06, | |
| "loss": 0.0057, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 9.8, | |
| "learning_rate": 6.928104575163399e-06, | |
| "loss": 0.0046, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.976741735809298, | |
| "eval_f1": 0.9652162792928163, | |
| "eval_loss": 0.14587946236133575, | |
| "eval_precision": 0.9652162792928163, | |
| "eval_recall": 0.9652162792928163, | |
| "eval_runtime": 2.7677, | |
| "eval_samples_per_second": 524.265, | |
| "eval_steps_per_second": 32.879, | |
| "step": 8160 | |
| }, | |
| { | |
| "epoch": 10.42, | |
| "learning_rate": 6.111111111111112e-06, | |
| "loss": 0.0042, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.977848017911234, | |
| "eval_f1": 0.9667578068786875, | |
| "eval_loss": 0.14097169041633606, | |
| "eval_precision": 0.9670206640649991, | |
| "eval_recall": 0.9664950925541098, | |
| "eval_runtime": 2.8235, | |
| "eval_samples_per_second": 513.9, | |
| "eval_steps_per_second": 32.229, | |
| "step": 8976 | |
| }, | |
| { | |
| "epoch": 11.03, | |
| "learning_rate": 5.294117647058824e-06, | |
| "loss": 0.0041, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 11.64, | |
| "learning_rate": 4.477124183006537e-06, | |
| "loss": 0.0034, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.9781377584617411, | |
| "eval_f1": 0.9671292447400396, | |
| "eval_loss": 0.14326775074005127, | |
| "eval_precision": 0.9672838913940325, | |
| "eval_recall": 0.9669746475270948, | |
| "eval_runtime": 3.9931, | |
| "eval_samples_per_second": 363.381, | |
| "eval_steps_per_second": 22.79, | |
| "step": 9792 | |
| }, | |
| { | |
| "epoch": 12.25, | |
| "learning_rate": 3.6601307189542484e-06, | |
| "loss": 0.0027, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 12.87, | |
| "learning_rate": 2.843137254901961e-06, | |
| "loss": 0.0026, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.9774529171605426, | |
| "eval_f1": 0.9662260441474992, | |
| "eval_loss": 0.15390940010547638, | |
| "eval_precision": 0.9661488300728807, | |
| "eval_recall": 0.9663032705649157, | |
| "eval_runtime": 3.7949, | |
| "eval_samples_per_second": 382.357, | |
| "eval_steps_per_second": 23.98, | |
| "step": 10608 | |
| }, | |
| { | |
| "epoch": 13.48, | |
| "learning_rate": 2.0261437908496734e-06, | |
| "loss": 0.0022, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.9776109574608192, | |
| "eval_f1": 0.9663320117662106, | |
| "eval_loss": 0.15523000061511993, | |
| "eval_precision": 0.9664247114124005, | |
| "eval_recall": 0.9662393299018511, | |
| "eval_runtime": 3.7736, | |
| "eval_samples_per_second": 384.509, | |
| "eval_steps_per_second": 24.115, | |
| "step": 11424 | |
| }, | |
| { | |
| "epoch": 14.09, | |
| "learning_rate": 1.2091503267973858e-06, | |
| "loss": 0.0021, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 14.71, | |
| "learning_rate": 3.921568627450981e-07, | |
| "loss": 0.0018, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.9779270380613723, | |
| "eval_f1": 0.966844646225661, | |
| "eval_loss": 0.15447764098644257, | |
| "eval_precision": 0.9669064748201439, | |
| "eval_recall": 0.9667828255379008, | |
| "eval_runtime": 3.7735, | |
| "eval_samples_per_second": 384.523, | |
| "eval_steps_per_second": 24.116, | |
| "step": 12240 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "step": 12240, | |
| "total_flos": 5.119363918698906e+16, | |
| "train_loss": 0.03180336131915158, | |
| "train_runtime": 835.9078, | |
| "train_samples_per_second": 234.248, | |
| "train_steps_per_second": 14.643 | |
| } | |
| ], | |
| "max_steps": 12240, | |
| "num_train_epochs": 15, | |
| "total_flos": 5.119363918698906e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |