| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.1523941982912775, |
| "eval_steps": 50, |
| "global_step": 1450, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.01, |
| "learning_rate": 3e-05, |
| "loss": 2.0927, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.02, |
| "learning_rate": 3e-05, |
| "loss": 0.267, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.02, |
| "learning_rate": 3e-05, |
| "loss": 0.1926, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.03, |
| "learning_rate": 3e-05, |
| "loss": 0.1601, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.04, |
| "learning_rate": 3e-05, |
| "loss": 0.1255, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.04, |
| "eval_accuracy": 0.2330188679245283, |
| "eval_f1_macro": 0.07731831394851697, |
| "eval_f1_micro": 0.2330188679245283, |
| "eval_loss": 0.24590551853179932, |
| "eval_precision_macro": 0.09801465635567799, |
| "eval_precision_micro": 0.2330188679245283, |
| "eval_recall_macro": 0.0939265996231733, |
| "eval_recall_micro": 0.2330188679245283, |
| "eval_runtime": 67.1714, |
| "eval_samples_per_second": 15.781, |
| "eval_steps_per_second": 3.945, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.05, |
| "learning_rate": 3e-05, |
| "loss": 0.6981, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.06, |
| "learning_rate": 3e-05, |
| "loss": 0.1356, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.06, |
| "learning_rate": 3e-05, |
| "loss": 0.0993, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.07, |
| "learning_rate": 3e-05, |
| "loss": 0.1038, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.08, |
| "learning_rate": 3e-05, |
| "loss": 0.1076, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.08, |
| "eval_accuracy": 0.4075471698113208, |
| "eval_f1_macro": 0.1681261191284492, |
| "eval_f1_micro": 0.4075471698113208, |
| "eval_loss": 0.14505280554294586, |
| "eval_precision_macro": 0.19505399860785297, |
| "eval_precision_micro": 0.4075471698113208, |
| "eval_recall_macro": 0.18462138174503467, |
| "eval_recall_micro": 0.4075471698113208, |
| "eval_runtime": 67.1009, |
| "eval_samples_per_second": 15.797, |
| "eval_steps_per_second": 3.949, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.09, |
| "learning_rate": 3e-05, |
| "loss": 0.331, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.1, |
| "learning_rate": 3e-05, |
| "loss": 0.0809, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.1, |
| "learning_rate": 3e-05, |
| "loss": 0.0812, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.11, |
| "learning_rate": 3e-05, |
| "loss": 0.0601, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.12, |
| "learning_rate": 3e-05, |
| "loss": 0.066, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.12, |
| "eval_accuracy": 0.5386792452830189, |
| "eval_f1_macro": 0.2780127225833117, |
| "eval_f1_micro": 0.5386792452830189, |
| "eval_loss": 0.10953618586063385, |
| "eval_precision_macro": 0.3493311966119182, |
| "eval_precision_micro": 0.5386792452830189, |
| "eval_recall_macro": 0.2871523900319283, |
| "eval_recall_micro": 0.5386792452830189, |
| "eval_runtime": 67.0903, |
| "eval_samples_per_second": 15.8, |
| "eval_steps_per_second": 3.95, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.13, |
| "learning_rate": 3e-05, |
| "loss": 0.2732, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.14, |
| "learning_rate": 3e-05, |
| "loss": 0.0754, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.14, |
| "learning_rate": 3e-05, |
| "loss": 0.0649, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.15, |
| "learning_rate": 3e-05, |
| "loss": 0.0674, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.16, |
| "learning_rate": 3e-05, |
| "loss": 0.0699, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.16, |
| "eval_accuracy": 0.620754716981132, |
| "eval_f1_macro": 0.3797608124202816, |
| "eval_f1_micro": 0.620754716981132, |
| "eval_loss": 0.09009388834238052, |
| "eval_precision_macro": 0.3837197141355178, |
| "eval_precision_micro": 0.620754716981132, |
| "eval_recall_macro": 0.39915842112719735, |
| "eval_recall_micro": 0.620754716981132, |
| "eval_runtime": 67.0671, |
| "eval_samples_per_second": 15.805, |
| "eval_steps_per_second": 3.951, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.17, |
| "learning_rate": 3e-05, |
| "loss": 0.1946, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.17, |
| "learning_rate": 3e-05, |
| "loss": 0.0657, |
| "step": 220 |
| }, |
| { |
| "epoch": 0.18, |
| "learning_rate": 3e-05, |
| "loss": 0.0547, |
| "step": 230 |
| }, |
| { |
| "epoch": 0.19, |
| "learning_rate": 3e-05, |
| "loss": 0.0615, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.2, |
| "learning_rate": 3e-05, |
| "loss": 0.066, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.2, |
| "eval_accuracy": 0.6103773584905661, |
| "eval_f1_macro": 0.41348516498355786, |
| "eval_f1_micro": 0.6103773584905661, |
| "eval_loss": 0.08832413703203201, |
| "eval_precision_macro": 0.45439839834135715, |
| "eval_precision_micro": 0.6103773584905661, |
| "eval_recall_macro": 0.4312111435526721, |
| "eval_recall_micro": 0.6103773584905661, |
| "eval_runtime": 66.9345, |
| "eval_samples_per_second": 15.836, |
| "eval_steps_per_second": 3.959, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.21, |
| "learning_rate": 3e-05, |
| "loss": 0.1494, |
| "step": 260 |
| }, |
| { |
| "epoch": 0.21, |
| "learning_rate": 3e-05, |
| "loss": 0.0655, |
| "step": 270 |
| }, |
| { |
| "epoch": 0.22, |
| "learning_rate": 3e-05, |
| "loss": 0.06, |
| "step": 280 |
| }, |
| { |
| "epoch": 0.23, |
| "learning_rate": 3e-05, |
| "loss": 0.0616, |
| "step": 290 |
| }, |
| { |
| "epoch": 0.24, |
| "learning_rate": 3e-05, |
| "loss": 0.0452, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.24, |
| "eval_accuracy": 0.6877358490566038, |
| "eval_f1_macro": 0.5091555575082085, |
| "eval_f1_micro": 0.6877358490566038, |
| "eval_loss": 0.08789286762475967, |
| "eval_precision_macro": 0.5649217974276287, |
| "eval_precision_micro": 0.6877358490566038, |
| "eval_recall_macro": 0.513496327466451, |
| "eval_recall_micro": 0.6877358490566038, |
| "eval_runtime": 67.1619, |
| "eval_samples_per_second": 15.783, |
| "eval_steps_per_second": 3.946, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.25, |
| "learning_rate": 3e-05, |
| "loss": 0.1535, |
| "step": 310 |
| }, |
| { |
| "epoch": 0.25, |
| "learning_rate": 3e-05, |
| "loss": 0.0731, |
| "step": 320 |
| }, |
| { |
| "epoch": 0.26, |
| "learning_rate": 3e-05, |
| "loss": 0.044, |
| "step": 330 |
| }, |
| { |
| "epoch": 0.27, |
| "learning_rate": 3e-05, |
| "loss": 0.053, |
| "step": 340 |
| }, |
| { |
| "epoch": 0.28, |
| "learning_rate": 3e-05, |
| "loss": 0.0545, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.28, |
| "eval_accuracy": 0.6764150943396227, |
| "eval_f1_macro": 0.503999030020007, |
| "eval_f1_micro": 0.6764150943396227, |
| "eval_loss": 0.07607663422822952, |
| "eval_precision_macro": 0.5194445629359009, |
| "eval_precision_micro": 0.6764150943396227, |
| "eval_recall_macro": 0.5287937722322651, |
| "eval_recall_micro": 0.6764150943396227, |
| "eval_runtime": 67.2353, |
| "eval_samples_per_second": 15.766, |
| "eval_steps_per_second": 3.941, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.29, |
| "learning_rate": 3e-05, |
| "loss": 0.1543, |
| "step": 360 |
| }, |
| { |
| "epoch": 0.29, |
| "learning_rate": 3e-05, |
| "loss": 0.0609, |
| "step": 370 |
| }, |
| { |
| "epoch": 0.3, |
| "learning_rate": 3e-05, |
| "loss": 0.0479, |
| "step": 380 |
| }, |
| { |
| "epoch": 0.31, |
| "learning_rate": 3e-05, |
| "loss": 0.0532, |
| "step": 390 |
| }, |
| { |
| "epoch": 0.32, |
| "learning_rate": 3e-05, |
| "loss": 0.0647, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.32, |
| "eval_accuracy": 0.7339622641509433, |
| "eval_f1_macro": 0.5492932704438783, |
| "eval_f1_micro": 0.7339622641509433, |
| "eval_loss": 0.06653406471014023, |
| "eval_precision_macro": 0.6193164476598846, |
| "eval_precision_micro": 0.7339622641509433, |
| "eval_recall_macro": 0.5252411264940735, |
| "eval_recall_micro": 0.7339622641509433, |
| "eval_runtime": 67.4334, |
| "eval_samples_per_second": 15.719, |
| "eval_steps_per_second": 3.93, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.33, |
| "learning_rate": 3e-05, |
| "loss": 0.104, |
| "step": 410 |
| }, |
| { |
| "epoch": 0.33, |
| "learning_rate": 3e-05, |
| "loss": 0.0458, |
| "step": 420 |
| }, |
| { |
| "epoch": 0.34, |
| "learning_rate": 3e-05, |
| "loss": 0.0552, |
| "step": 430 |
| }, |
| { |
| "epoch": 0.35, |
| "learning_rate": 3e-05, |
| "loss": 0.0512, |
| "step": 440 |
| }, |
| { |
| "epoch": 0.36, |
| "learning_rate": 3e-05, |
| "loss": 0.056, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.36, |
| "eval_accuracy": 0.7396226415094339, |
| "eval_f1_macro": 0.5671730153967399, |
| "eval_f1_micro": 0.7396226415094339, |
| "eval_loss": 0.05136344954371452, |
| "eval_precision_macro": 0.6096698581228938, |
| "eval_precision_micro": 0.7396226415094339, |
| "eval_recall_macro": 0.5767264087198709, |
| "eval_recall_micro": 0.7396226415094339, |
| "eval_runtime": 66.8962, |
| "eval_samples_per_second": 15.845, |
| "eval_steps_per_second": 3.961, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.37, |
| "learning_rate": 3e-05, |
| "loss": 0.0773, |
| "step": 460 |
| }, |
| { |
| "epoch": 0.37, |
| "learning_rate": 3e-05, |
| "loss": 0.0474, |
| "step": 470 |
| }, |
| { |
| "epoch": 0.38, |
| "learning_rate": 3e-05, |
| "loss": 0.0405, |
| "step": 480 |
| }, |
| { |
| "epoch": 0.39, |
| "learning_rate": 3e-05, |
| "loss": 0.0461, |
| "step": 490 |
| }, |
| { |
| "epoch": 0.4, |
| "learning_rate": 3e-05, |
| "loss": 0.0513, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.4, |
| "eval_accuracy": 0.7613207547169811, |
| "eval_f1_macro": 0.601977568492687, |
| "eval_f1_micro": 0.761320754716981, |
| "eval_loss": 0.047934673726558685, |
| "eval_precision_macro": 0.638418606498986, |
| "eval_precision_micro": 0.7613207547169811, |
| "eval_recall_macro": 0.6145296570629574, |
| "eval_recall_micro": 0.7613207547169811, |
| "eval_runtime": 66.9411, |
| "eval_samples_per_second": 15.835, |
| "eval_steps_per_second": 3.959, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.41, |
| "learning_rate": 3e-05, |
| "loss": 0.0788, |
| "step": 510 |
| }, |
| { |
| "epoch": 0.41, |
| "learning_rate": 3e-05, |
| "loss": 0.0495, |
| "step": 520 |
| }, |
| { |
| "epoch": 0.42, |
| "learning_rate": 3e-05, |
| "loss": 0.0552, |
| "step": 530 |
| }, |
| { |
| "epoch": 0.43, |
| "learning_rate": 3e-05, |
| "loss": 0.0415, |
| "step": 540 |
| }, |
| { |
| "epoch": 0.44, |
| "learning_rate": 3e-05, |
| "loss": 0.0501, |
| "step": 550 |
| }, |
| { |
| "epoch": 0.44, |
| "eval_accuracy": 0.7509433962264151, |
| "eval_f1_macro": 0.6074975120648255, |
| "eval_f1_micro": 0.7509433962264151, |
| "eval_loss": 0.05019384250044823, |
| "eval_precision_macro": 0.624502704252128, |
| "eval_precision_micro": 0.7509433962264151, |
| "eval_recall_macro": 0.6167049341328479, |
| "eval_recall_micro": 0.7509433962264151, |
| "eval_runtime": 67.3498, |
| "eval_samples_per_second": 15.739, |
| "eval_steps_per_second": 3.935, |
| "step": 550 |
| }, |
| { |
| "epoch": 0.45, |
| "learning_rate": 3e-05, |
| "loss": 0.0633, |
| "step": 560 |
| }, |
| { |
| "epoch": 0.45, |
| "learning_rate": 3e-05, |
| "loss": 0.0484, |
| "step": 570 |
| }, |
| { |
| "epoch": 0.46, |
| "learning_rate": 3e-05, |
| "loss": 0.0418, |
| "step": 580 |
| }, |
| { |
| "epoch": 0.47, |
| "learning_rate": 3e-05, |
| "loss": 0.0524, |
| "step": 590 |
| }, |
| { |
| "epoch": 0.48, |
| "learning_rate": 3e-05, |
| "loss": 0.0533, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.48, |
| "eval_accuracy": 0.7641509433962265, |
| "eval_f1_macro": 0.607265930345707, |
| "eval_f1_micro": 0.7641509433962265, |
| "eval_loss": 0.048058342188596725, |
| "eval_precision_macro": 0.6499724898555727, |
| "eval_precision_micro": 0.7641509433962265, |
| "eval_recall_macro": 0.6139175086252339, |
| "eval_recall_micro": 0.7641509433962265, |
| "eval_runtime": 66.897, |
| "eval_samples_per_second": 15.845, |
| "eval_steps_per_second": 3.961, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.48, |
| "learning_rate": 3e-05, |
| "loss": 0.0418, |
| "step": 610 |
| }, |
| { |
| "epoch": 0.49, |
| "learning_rate": 3e-05, |
| "loss": 0.0482, |
| "step": 620 |
| }, |
| { |
| "epoch": 0.5, |
| "learning_rate": 3e-05, |
| "loss": 0.0458, |
| "step": 630 |
| }, |
| { |
| "epoch": 0.51, |
| "learning_rate": 3e-05, |
| "loss": 0.0432, |
| "step": 640 |
| }, |
| { |
| "epoch": 0.52, |
| "learning_rate": 3e-05, |
| "loss": 0.0462, |
| "step": 650 |
| }, |
| { |
| "epoch": 0.52, |
| "eval_accuracy": 0.7481132075471698, |
| "eval_f1_macro": 0.5679477471859753, |
| "eval_f1_micro": 0.7481132075471698, |
| "eval_loss": 0.047320980578660965, |
| "eval_precision_macro": 0.5941670973495327, |
| "eval_precision_micro": 0.7481132075471698, |
| "eval_recall_macro": 0.5739727328111488, |
| "eval_recall_micro": 0.7481132075471698, |
| "eval_runtime": 67.2106, |
| "eval_samples_per_second": 15.771, |
| "eval_steps_per_second": 3.943, |
| "step": 650 |
| }, |
| { |
| "epoch": 0.52, |
| "learning_rate": 3e-05, |
| "loss": 0.0668, |
| "step": 660 |
| }, |
| { |
| "epoch": 0.53, |
| "learning_rate": 3e-05, |
| "loss": 0.0501, |
| "step": 670 |
| }, |
| { |
| "epoch": 0.54, |
| "learning_rate": 3e-05, |
| "loss": 0.0366, |
| "step": 680 |
| }, |
| { |
| "epoch": 0.55, |
| "learning_rate": 3e-05, |
| "loss": 0.0374, |
| "step": 690 |
| }, |
| { |
| "epoch": 0.56, |
| "learning_rate": 3e-05, |
| "loss": 0.0496, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.56, |
| "eval_accuracy": 0.7971698113207547, |
| "eval_f1_macro": 0.6517694520426227, |
| "eval_f1_micro": 0.7971698113207546, |
| "eval_loss": 0.04193812981247902, |
| "eval_precision_macro": 0.6678204026981202, |
| "eval_precision_micro": 0.7971698113207547, |
| "eval_recall_macro": 0.6480125227888868, |
| "eval_recall_micro": 0.7971698113207547, |
| "eval_runtime": 67.3982, |
| "eval_samples_per_second": 15.727, |
| "eval_steps_per_second": 3.932, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.56, |
| "learning_rate": 3e-05, |
| "loss": 0.0649, |
| "step": 710 |
| }, |
| { |
| "epoch": 0.57, |
| "learning_rate": 3e-05, |
| "loss": 0.0447, |
| "step": 720 |
| }, |
| { |
| "epoch": 0.58, |
| "learning_rate": 3e-05, |
| "loss": 0.0442, |
| "step": 730 |
| }, |
| { |
| "epoch": 0.59, |
| "learning_rate": 3e-05, |
| "loss": 0.037, |
| "step": 740 |
| }, |
| { |
| "epoch": 0.6, |
| "learning_rate": 3e-05, |
| "loss": 0.0614, |
| "step": 750 |
| }, |
| { |
| "epoch": 0.6, |
| "eval_accuracy": 0.7773584905660378, |
| "eval_f1_macro": 0.6308119664331103, |
| "eval_f1_micro": 0.7773584905660378, |
| "eval_loss": 0.04885416477918625, |
| "eval_precision_macro": 0.6677975283624125, |
| "eval_precision_micro": 0.7773584905660378, |
| "eval_recall_macro": 0.6360471775658058, |
| "eval_recall_micro": 0.7773584905660378, |
| "eval_runtime": 67.7832, |
| "eval_samples_per_second": 15.638, |
| "eval_steps_per_second": 3.91, |
| "step": 750 |
| }, |
| { |
| "epoch": 0.6, |
| "learning_rate": 3e-05, |
| "loss": 0.0649, |
| "step": 760 |
| }, |
| { |
| "epoch": 0.61, |
| "learning_rate": 3e-05, |
| "loss": 0.0426, |
| "step": 770 |
| }, |
| { |
| "epoch": 0.62, |
| "learning_rate": 3e-05, |
| "loss": 0.0347, |
| "step": 780 |
| }, |
| { |
| "epoch": 0.63, |
| "learning_rate": 3e-05, |
| "loss": 0.0414, |
| "step": 790 |
| }, |
| { |
| "epoch": 0.64, |
| "learning_rate": 3e-05, |
| "loss": 0.0468, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.64, |
| "eval_accuracy": 0.7830188679245284, |
| "eval_f1_macro": 0.6493890925237205, |
| "eval_f1_micro": 0.7830188679245284, |
| "eval_loss": 0.044340912252664566, |
| "eval_precision_macro": 0.6435014283226803, |
| "eval_precision_micro": 0.7830188679245284, |
| "eval_recall_macro": 0.6816157451405587, |
| "eval_recall_micro": 0.7830188679245284, |
| "eval_runtime": 67.2351, |
| "eval_samples_per_second": 15.766, |
| "eval_steps_per_second": 3.941, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.64, |
| "learning_rate": 3e-05, |
| "loss": 0.052, |
| "step": 810 |
| }, |
| { |
| "epoch": 0.65, |
| "learning_rate": 3e-05, |
| "loss": 0.0414, |
| "step": 820 |
| }, |
| { |
| "epoch": 0.66, |
| "learning_rate": 3e-05, |
| "loss": 0.0342, |
| "step": 830 |
| }, |
| { |
| "epoch": 0.67, |
| "learning_rate": 3e-05, |
| "loss": 0.0451, |
| "step": 840 |
| }, |
| { |
| "epoch": 0.68, |
| "learning_rate": 3e-05, |
| "loss": 0.0477, |
| "step": 850 |
| }, |
| { |
| "epoch": 0.68, |
| "eval_accuracy": 0.7971698113207547, |
| "eval_f1_macro": 0.6662808099368048, |
| "eval_f1_micro": 0.7971698113207546, |
| "eval_loss": 0.041995830833911896, |
| "eval_precision_macro": 0.7040157648486967, |
| "eval_precision_micro": 0.7971698113207547, |
| "eval_recall_macro": 0.6567342355863813, |
| "eval_recall_micro": 0.7971698113207547, |
| "eval_runtime": 67.3249, |
| "eval_samples_per_second": 15.745, |
| "eval_steps_per_second": 3.936, |
| "step": 850 |
| }, |
| { |
| "epoch": 0.68, |
| "learning_rate": 3e-05, |
| "loss": 0.0468, |
| "step": 860 |
| }, |
| { |
| "epoch": 0.69, |
| "learning_rate": 3e-05, |
| "loss": 0.0461, |
| "step": 870 |
| }, |
| { |
| "epoch": 0.7, |
| "learning_rate": 3e-05, |
| "loss": 0.0436, |
| "step": 880 |
| }, |
| { |
| "epoch": 0.71, |
| "learning_rate": 3e-05, |
| "loss": 0.0369, |
| "step": 890 |
| }, |
| { |
| "epoch": 0.72, |
| "learning_rate": 3e-05, |
| "loss": 0.0519, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.72, |
| "eval_accuracy": 0.7632075471698113, |
| "eval_f1_macro": 0.6291599323302522, |
| "eval_f1_micro": 0.7632075471698113, |
| "eval_loss": 0.04627140238881111, |
| "eval_precision_macro": 0.6519385252086033, |
| "eval_precision_micro": 0.7632075471698113, |
| "eval_recall_macro": 0.6290591814696965, |
| "eval_recall_micro": 0.7632075471698113, |
| "eval_runtime": 67.0228, |
| "eval_samples_per_second": 15.816, |
| "eval_steps_per_second": 3.954, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.72, |
| "learning_rate": 3e-05, |
| "loss": 0.0543, |
| "step": 910 |
| }, |
| { |
| "epoch": 0.73, |
| "learning_rate": 3e-05, |
| "loss": 0.0426, |
| "step": 920 |
| }, |
| { |
| "epoch": 0.74, |
| "learning_rate": 3e-05, |
| "loss": 0.0421, |
| "step": 930 |
| }, |
| { |
| "epoch": 0.75, |
| "learning_rate": 3e-05, |
| "loss": 0.0338, |
| "step": 940 |
| }, |
| { |
| "epoch": 0.76, |
| "learning_rate": 3e-05, |
| "loss": 0.0453, |
| "step": 950 |
| }, |
| { |
| "epoch": 0.76, |
| "eval_accuracy": 0.780188679245283, |
| "eval_f1_macro": 0.6564187596520696, |
| "eval_f1_micro": 0.780188679245283, |
| "eval_loss": 0.042860858142375946, |
| "eval_precision_macro": 0.67574812222591, |
| "eval_precision_micro": 0.780188679245283, |
| "eval_recall_macro": 0.6697872775950671, |
| "eval_recall_micro": 0.780188679245283, |
| "eval_runtime": 67.3483, |
| "eval_samples_per_second": 15.739, |
| "eval_steps_per_second": 3.935, |
| "step": 950 |
| }, |
| { |
| "epoch": 0.76, |
| "learning_rate": 3e-05, |
| "loss": 0.0554, |
| "step": 960 |
| }, |
| { |
| "epoch": 0.77, |
| "learning_rate": 3e-05, |
| "loss": 0.0397, |
| "step": 970 |
| }, |
| { |
| "epoch": 0.78, |
| "learning_rate": 3e-05, |
| "loss": 0.0407, |
| "step": 980 |
| }, |
| { |
| "epoch": 0.79, |
| "learning_rate": 3e-05, |
| "loss": 0.0361, |
| "step": 990 |
| }, |
| { |
| "epoch": 0.79, |
| "learning_rate": 3e-05, |
| "loss": 0.0452, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.79, |
| "eval_accuracy": 0.7377358490566037, |
| "eval_f1_macro": 0.6049285124615932, |
| "eval_f1_micro": 0.7377358490566037, |
| "eval_loss": 0.047125279903411865, |
| "eval_precision_macro": 0.6181852032037266, |
| "eval_precision_micro": 0.7377358490566037, |
| "eval_recall_macro": 0.6300074429793591, |
| "eval_recall_micro": 0.7377358490566037, |
| "eval_runtime": 66.8035, |
| "eval_samples_per_second": 15.867, |
| "eval_steps_per_second": 3.967, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.8, |
| "learning_rate": 3e-05, |
| "loss": 0.0482, |
| "step": 1010 |
| }, |
| { |
| "epoch": 0.81, |
| "learning_rate": 3e-05, |
| "loss": 0.0379, |
| "step": 1020 |
| }, |
| { |
| "epoch": 0.82, |
| "learning_rate": 3e-05, |
| "loss": 0.0403, |
| "step": 1030 |
| }, |
| { |
| "epoch": 0.83, |
| "learning_rate": 3e-05, |
| "loss": 0.0471, |
| "step": 1040 |
| }, |
| { |
| "epoch": 0.83, |
| "learning_rate": 3e-05, |
| "loss": 0.0367, |
| "step": 1050 |
| }, |
| { |
| "epoch": 0.83, |
| "eval_accuracy": 0.7981132075471699, |
| "eval_f1_macro": 0.6800660818700823, |
| "eval_f1_micro": 0.79811320754717, |
| "eval_loss": 0.03875497728586197, |
| "eval_precision_macro": 0.6856812225733196, |
| "eval_precision_micro": 0.7981132075471699, |
| "eval_recall_macro": 0.6992476720564776, |
| "eval_recall_micro": 0.7981132075471699, |
| "eval_runtime": 66.8444, |
| "eval_samples_per_second": 15.858, |
| "eval_steps_per_second": 3.964, |
| "step": 1050 |
| }, |
| { |
| "epoch": 0.84, |
| "learning_rate": 3e-05, |
| "loss": 0.0351, |
| "step": 1060 |
| }, |
| { |
| "epoch": 0.85, |
| "learning_rate": 3e-05, |
| "loss": 0.0479, |
| "step": 1070 |
| }, |
| { |
| "epoch": 0.86, |
| "learning_rate": 3e-05, |
| "loss": 0.0421, |
| "step": 1080 |
| }, |
| { |
| "epoch": 0.87, |
| "learning_rate": 3e-05, |
| "loss": 0.0406, |
| "step": 1090 |
| }, |
| { |
| "epoch": 0.87, |
| "learning_rate": 3e-05, |
| "loss": 0.0377, |
| "step": 1100 |
| }, |
| { |
| "epoch": 0.87, |
| "eval_accuracy": 0.8, |
| "eval_f1_macro": 0.6590911576508658, |
| "eval_f1_micro": 0.8000000000000002, |
| "eval_loss": 0.03815627098083496, |
| "eval_precision_macro": 0.6636349851737382, |
| "eval_precision_micro": 0.8, |
| "eval_recall_macro": 0.6697553358712118, |
| "eval_recall_micro": 0.8, |
| "eval_runtime": 66.9434, |
| "eval_samples_per_second": 15.834, |
| "eval_steps_per_second": 3.959, |
| "step": 1100 |
| }, |
| { |
| "epoch": 0.88, |
| "learning_rate": 3e-05, |
| "loss": 0.0365, |
| "step": 1110 |
| }, |
| { |
| "epoch": 0.89, |
| "learning_rate": 3e-05, |
| "loss": 0.0353, |
| "step": 1120 |
| }, |
| { |
| "epoch": 0.9, |
| "learning_rate": 3e-05, |
| "loss": 0.0388, |
| "step": 1130 |
| }, |
| { |
| "epoch": 0.91, |
| "learning_rate": 3e-05, |
| "loss": 0.0358, |
| "step": 1140 |
| }, |
| { |
| "epoch": 0.91, |
| "learning_rate": 3e-05, |
| "loss": 0.0429, |
| "step": 1150 |
| }, |
| { |
| "epoch": 0.91, |
| "eval_accuracy": 0.7952830188679245, |
| "eval_f1_macro": 0.6465609013784224, |
| "eval_f1_micro": 0.7952830188679245, |
| "eval_loss": 0.03976297378540039, |
| "eval_precision_macro": 0.6923924758215005, |
| "eval_precision_micro": 0.7952830188679245, |
| "eval_recall_macro": 0.6441492192889419, |
| "eval_recall_micro": 0.7952830188679245, |
| "eval_runtime": 67.1705, |
| "eval_samples_per_second": 15.781, |
| "eval_steps_per_second": 3.945, |
| "step": 1150 |
| }, |
| { |
| "epoch": 0.92, |
| "learning_rate": 3e-05, |
| "loss": 0.0461, |
| "step": 1160 |
| }, |
| { |
| "epoch": 0.93, |
| "learning_rate": 3e-05, |
| "loss": 0.0434, |
| "step": 1170 |
| }, |
| { |
| "epoch": 0.94, |
| "learning_rate": 3e-05, |
| "loss": 0.0524, |
| "step": 1180 |
| }, |
| { |
| "epoch": 0.95, |
| "learning_rate": 3e-05, |
| "loss": 0.0362, |
| "step": 1190 |
| }, |
| { |
| "epoch": 0.95, |
| "learning_rate": 3e-05, |
| "loss": 0.0451, |
| "step": 1200 |
| }, |
| { |
| "epoch": 0.95, |
| "eval_accuracy": 0.7943396226415095, |
| "eval_f1_macro": 0.6535399936575059, |
| "eval_f1_micro": 0.7943396226415095, |
| "eval_loss": 0.037755727767944336, |
| "eval_precision_macro": 0.6712905678869693, |
| "eval_precision_micro": 0.7943396226415095, |
| "eval_recall_macro": 0.6537773538776073, |
| "eval_recall_micro": 0.7943396226415095, |
| "eval_runtime": 66.9611, |
| "eval_samples_per_second": 15.83, |
| "eval_steps_per_second": 3.958, |
| "step": 1200 |
| }, |
| { |
| "epoch": 0.96, |
| "learning_rate": 3e-05, |
| "loss": 0.0456, |
| "step": 1210 |
| }, |
| { |
| "epoch": 0.97, |
| "learning_rate": 3e-05, |
| "loss": 0.0455, |
| "step": 1220 |
| }, |
| { |
| "epoch": 0.98, |
| "learning_rate": 3e-05, |
| "loss": 0.0409, |
| "step": 1230 |
| }, |
| { |
| "epoch": 0.99, |
| "learning_rate": 3e-05, |
| "loss": 0.037, |
| "step": 1240 |
| }, |
| { |
| "epoch": 0.99, |
| "learning_rate": 3e-05, |
| "loss": 0.0347, |
| "step": 1250 |
| }, |
| { |
| "epoch": 0.99, |
| "eval_accuracy": 0.7839622641509434, |
| "eval_f1_macro": 0.6330944207402169, |
| "eval_f1_micro": 0.7839622641509434, |
| "eval_loss": 0.041340529918670654, |
| "eval_precision_macro": 0.6735372413807635, |
| "eval_precision_micro": 0.7839622641509434, |
| "eval_recall_macro": 0.6450299050285588, |
| "eval_recall_micro": 0.7839622641509434, |
| "eval_runtime": 66.9053, |
| "eval_samples_per_second": 15.843, |
| "eval_steps_per_second": 3.961, |
| "step": 1250 |
| }, |
| { |
| "epoch": 1.0, |
| "learning_rate": 3e-05, |
| "loss": 0.0421, |
| "step": 1260 |
| }, |
| { |
| "epoch": 1.01, |
| "learning_rate": 3e-05, |
| "loss": 0.041, |
| "step": 1270 |
| }, |
| { |
| "epoch": 1.02, |
| "learning_rate": 3e-05, |
| "loss": 0.033, |
| "step": 1280 |
| }, |
| { |
| "epoch": 1.03, |
| "learning_rate": 3e-05, |
| "loss": 0.036, |
| "step": 1290 |
| }, |
| { |
| "epoch": 1.03, |
| "learning_rate": 3e-05, |
| "loss": 0.0378, |
| "step": 1300 |
| }, |
| { |
| "epoch": 1.03, |
| "eval_accuracy": 0.8047169811320755, |
| "eval_f1_macro": 0.6488791804614907, |
| "eval_f1_micro": 0.8047169811320755, |
| "eval_loss": 0.037683386355638504, |
| "eval_precision_macro": 0.7109359814450084, |
| "eval_precision_micro": 0.8047169811320755, |
| "eval_recall_macro": 0.6387082579227776, |
| "eval_recall_micro": 0.8047169811320755, |
| "eval_runtime": 67.3206, |
| "eval_samples_per_second": 15.746, |
| "eval_steps_per_second": 3.936, |
| "step": 1300 |
| }, |
| { |
| "epoch": 1.04, |
| "learning_rate": 3e-05, |
| "loss": 0.0343, |
| "step": 1310 |
| }, |
| { |
| "epoch": 1.05, |
| "learning_rate": 3e-05, |
| "loss": 0.0321, |
| "step": 1320 |
| }, |
| { |
| "epoch": 1.06, |
| "learning_rate": 3e-05, |
| "loss": 0.031, |
| "step": 1330 |
| }, |
| { |
| "epoch": 1.06, |
| "learning_rate": 3e-05, |
| "loss": 0.039, |
| "step": 1340 |
| }, |
| { |
| "epoch": 1.07, |
| "learning_rate": 3e-05, |
| "loss": 0.0357, |
| "step": 1350 |
| }, |
| { |
| "epoch": 1.07, |
| "eval_accuracy": 0.8028301886792453, |
| "eval_f1_macro": 0.6648963473667772, |
| "eval_f1_micro": 0.8028301886792453, |
| "eval_loss": 0.03860827535390854, |
| "eval_precision_macro": 0.6898539099210392, |
| "eval_precision_micro": 0.8028301886792453, |
| "eval_recall_macro": 0.6558796396655843, |
| "eval_recall_micro": 0.8028301886792453, |
| "eval_runtime": 67.0656, |
| "eval_samples_per_second": 15.805, |
| "eval_steps_per_second": 3.951, |
| "step": 1350 |
| }, |
| { |
| "epoch": 1.08, |
| "learning_rate": 3e-05, |
| "loss": 0.0445, |
| "step": 1360 |
| }, |
| { |
| "epoch": 1.09, |
| "learning_rate": 3e-05, |
| "loss": 0.0375, |
| "step": 1370 |
| }, |
| { |
| "epoch": 1.1, |
| "learning_rate": 3e-05, |
| "loss": 0.0375, |
| "step": 1380 |
| }, |
| { |
| "epoch": 1.1, |
| "learning_rate": 3e-05, |
| "loss": 0.0333, |
| "step": 1390 |
| }, |
| { |
| "epoch": 1.11, |
| "learning_rate": 3e-05, |
| "loss": 0.0418, |
| "step": 1400 |
| }, |
| { |
| "epoch": 1.11, |
| "eval_accuracy": 0.7962264150943397, |
| "eval_f1_macro": 0.6910242491250081, |
| "eval_f1_micro": 0.7962264150943396, |
| "eval_loss": 0.0368194542825222, |
| "eval_precision_macro": 0.7114033533579757, |
| "eval_precision_micro": 0.7962264150943397, |
| "eval_recall_macro": 0.6942176996685531, |
| "eval_recall_micro": 0.7962264150943397, |
| "eval_runtime": 66.8832, |
| "eval_samples_per_second": 15.849, |
| "eval_steps_per_second": 3.962, |
| "step": 1400 |
| }, |
| { |
| "epoch": 1.12, |
| "learning_rate": 3e-05, |
| "loss": 0.0414, |
| "step": 1410 |
| }, |
| { |
| "epoch": 1.13, |
| "learning_rate": 3e-05, |
| "loss": 0.0357, |
| "step": 1420 |
| }, |
| { |
| "epoch": 1.14, |
| "learning_rate": 3e-05, |
| "loss": 0.0272, |
| "step": 1430 |
| }, |
| { |
| "epoch": 1.14, |
| "learning_rate": 3e-05, |
| "loss": 0.0323, |
| "step": 1440 |
| }, |
| { |
| "epoch": 1.15, |
| "learning_rate": 3e-05, |
| "loss": 0.0293, |
| "step": 1450 |
| }, |
| { |
| "epoch": 1.15, |
| "eval_accuracy": 0.8141509433962264, |
| "eval_f1_macro": 0.7097996478763092, |
| "eval_f1_micro": 0.8141509433962264, |
| "eval_loss": 0.035770244896411896, |
| "eval_precision_macro": 0.7222302630120379, |
| "eval_precision_micro": 0.8141509433962264, |
| "eval_recall_macro": 0.7125706602249756, |
| "eval_recall_micro": 0.8141509433962264, |
| "eval_runtime": 67.0694, |
| "eval_samples_per_second": 15.805, |
| "eval_steps_per_second": 3.951, |
| "step": 1450 |
| }, |
| { |
| "epoch": 1.15, |
| "step": 1450, |
| "total_flos": 3.612646182806976e+17, |
| "train_loss": 0.07879953698865298, |
| "train_runtime": 5948.326, |
| "train_samples_per_second": 3.9, |
| "train_steps_per_second": 0.244 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 1450, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "save_steps": 250, |
| "total_flos": 3.612646182806976e+17, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
