| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "global_step": 1750, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 4.9971428571428576e-05, | |
| "loss": 18.0539, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.9e-05, | |
| "loss": 4.1309, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_accuracy": 0.8826666666666667, | |
| "eval_f1": 0.8778625954198473, | |
| "eval_loss": 0.34147411584854126, | |
| "eval_precision": 0.9153400868306801, | |
| "eval_recall": 0.8433333333333334, | |
| "eval_runtime": 463.3794, | |
| "eval_samples_per_second": 6.474, | |
| "eval_steps_per_second": 0.809, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.8e-05, | |
| "loss": 0.6366, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_accuracy": 0.9403333333333334, | |
| "eval_f1": 0.9423881557772771, | |
| "eval_loss": 0.139574334025383, | |
| "eval_precision": 0.911014312383323, | |
| "eval_recall": 0.976, | |
| "eval_runtime": 463.7246, | |
| "eval_samples_per_second": 6.469, | |
| "eval_steps_per_second": 0.809, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.7e-05, | |
| "loss": 0.8166, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_accuracy": 0.8373333333333334, | |
| "eval_f1": 0.8576429404900816, | |
| "eval_loss": 0.8452138900756836, | |
| "eval_precision": 0.7624481327800829, | |
| "eval_recall": 0.98, | |
| "eval_runtime": 463.2546, | |
| "eval_samples_per_second": 6.476, | |
| "eval_steps_per_second": 0.809, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.600000000000001e-05, | |
| "loss": 1.8141, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_accuracy": 0.8703333333333333, | |
| "eval_f1": 0.8838459241564646, | |
| "eval_loss": 2.6052372455596924, | |
| "eval_precision": 0.8004326663061114, | |
| "eval_recall": 0.9866666666666667, | |
| "eval_runtime": 463.8217, | |
| "eval_samples_per_second": 6.468, | |
| "eval_steps_per_second": 0.809, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.5e-05, | |
| "loss": 0.994, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_accuracy": 0.8933333333333333, | |
| "eval_f1": 0.9029714978775015, | |
| "eval_loss": 0.5267955660820007, | |
| "eval_precision": 0.8281423804226918, | |
| "eval_recall": 0.9926666666666667, | |
| "eval_runtime": 463.9594, | |
| "eval_samples_per_second": 6.466, | |
| "eval_steps_per_second": 0.808, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.4000000000000006e-05, | |
| "loss": 0.3827, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_accuracy": 0.9343333333333333, | |
| "eval_f1": 0.9345297441010303, | |
| "eval_loss": 0.296316534280777, | |
| "eval_precision": 0.9317428760768721, | |
| "eval_recall": 0.9373333333333334, | |
| "eval_runtime": 463.5088, | |
| "eval_samples_per_second": 6.472, | |
| "eval_steps_per_second": 0.809, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.3e-05, | |
| "loss": 0.5048, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_accuracy": 0.9526666666666667, | |
| "eval_f1": 0.9523489932885906, | |
| "eval_loss": 0.2187061905860901, | |
| "eval_precision": 0.9587837837837838, | |
| "eval_recall": 0.946, | |
| "eval_runtime": 467.9247, | |
| "eval_samples_per_second": 6.411, | |
| "eval_steps_per_second": 0.801, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.2e-05, | |
| "loss": 0.2841, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_accuracy": 0.8916666666666667, | |
| "eval_f1": 0.8787765759045133, | |
| "eval_loss": 1.027541160583496, | |
| "eval_precision": 0.9974597798475868, | |
| "eval_recall": 0.7853333333333333, | |
| "eval_runtime": 463.3965, | |
| "eval_samples_per_second": 6.474, | |
| "eval_steps_per_second": 0.809, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.1e-05, | |
| "loss": 0.3962, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_accuracy": 0.9496666666666667, | |
| "eval_f1": 0.948656919415165, | |
| "eval_loss": 0.3296962380409241, | |
| "eval_precision": 0.9680777238029147, | |
| "eval_recall": 0.93, | |
| "eval_runtime": 463.326, | |
| "eval_samples_per_second": 6.475, | |
| "eval_steps_per_second": 0.809, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4e-05, | |
| "loss": 0.488, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_accuracy": 0.9443333333333334, | |
| "eval_f1": 0.9429839535677706, | |
| "eval_loss": 0.4798208773136139, | |
| "eval_precision": 0.966410076976907, | |
| "eval_recall": 0.9206666666666666, | |
| "eval_runtime": 463.3936, | |
| "eval_samples_per_second": 6.474, | |
| "eval_steps_per_second": 0.809, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 3.9000000000000006e-05, | |
| "loss": 0.4094, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_accuracy": 0.9096666666666666, | |
| "eval_f1": 0.9166922840454964, | |
| "eval_loss": 0.5374864339828491, | |
| "eval_precision": 0.8505419281232174, | |
| "eval_recall": 0.994, | |
| "eval_runtime": 463.4888, | |
| "eval_samples_per_second": 6.473, | |
| "eval_steps_per_second": 0.809, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 3.8e-05, | |
| "loss": 0.2203, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_accuracy": 0.957, | |
| "eval_f1": 0.958130477117819, | |
| "eval_loss": 0.18050691485404968, | |
| "eval_precision": 0.9335863377609108, | |
| "eval_recall": 0.984, | |
| "eval_runtime": 463.3488, | |
| "eval_samples_per_second": 6.475, | |
| "eval_steps_per_second": 0.809, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 3.7e-05, | |
| "loss": 0.2526, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "eval_accuracy": 0.9566666666666667, | |
| "eval_f1": 0.9579288025889968, | |
| "eval_loss": 0.32805779576301575, | |
| "eval_precision": 0.9308176100628931, | |
| "eval_recall": 0.9866666666666667, | |
| "eval_runtime": 464.3941, | |
| "eval_samples_per_second": 6.46, | |
| "eval_steps_per_second": 0.808, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 3.6e-05, | |
| "loss": 0.1888, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_accuracy": 0.972, | |
| "eval_f1": 0.9723502304147466, | |
| "eval_loss": 0.15383633971214294, | |
| "eval_precision": 0.9603381014304291, | |
| "eval_recall": 0.9846666666666667, | |
| "eval_runtime": 463.4989, | |
| "eval_samples_per_second": 6.473, | |
| "eval_steps_per_second": 0.809, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 3.5e-05, | |
| "loss": 0.1859, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_accuracy": 0.9783333333333334, | |
| "eval_f1": 0.9781659388646288, | |
| "eval_loss": 0.11581222712993622, | |
| "eval_precision": 0.985781990521327, | |
| "eval_recall": 0.9706666666666667, | |
| "eval_runtime": 463.5881, | |
| "eval_samples_per_second": 6.471, | |
| "eval_steps_per_second": 0.809, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 3.4000000000000007e-05, | |
| "loss": 0.1007, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_accuracy": 0.9753333333333334, | |
| "eval_f1": 0.9755129053606882, | |
| "eval_loss": 0.14892521500587463, | |
| "eval_precision": 0.9684625492772667, | |
| "eval_recall": 0.9826666666666667, | |
| "eval_runtime": 463.553, | |
| "eval_samples_per_second": 6.472, | |
| "eval_steps_per_second": 0.809, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 3.3e-05, | |
| "loss": 0.1065, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_accuracy": 0.9726666666666667, | |
| "eval_f1": 0.9720327421555252, | |
| "eval_loss": 0.15965215861797333, | |
| "eval_precision": 0.9951117318435754, | |
| "eval_recall": 0.95, | |
| "eval_runtime": 463.6429, | |
| "eval_samples_per_second": 6.47, | |
| "eval_steps_per_second": 0.809, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 3.2000000000000005e-05, | |
| "loss": 0.2868, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_accuracy": 0.9806666666666667, | |
| "eval_f1": 0.9807180851063829, | |
| "eval_loss": 0.08715511113405228, | |
| "eval_precision": 0.9781167108753316, | |
| "eval_recall": 0.9833333333333333, | |
| "eval_runtime": 463.4149, | |
| "eval_samples_per_second": 6.474, | |
| "eval_steps_per_second": 0.809, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 3.1e-05, | |
| "loss": 0.1818, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_accuracy": 0.9796666666666667, | |
| "eval_f1": 0.9795781720790091, | |
| "eval_loss": 0.12202201038599014, | |
| "eval_precision": 0.9838601210490922, | |
| "eval_recall": 0.9753333333333334, | |
| "eval_runtime": 464.4798, | |
| "eval_samples_per_second": 6.459, | |
| "eval_steps_per_second": 0.807, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 3e-05, | |
| "loss": 0.3238, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_accuracy": 0.9786666666666667, | |
| "eval_f1": 0.9784221173297369, | |
| "eval_loss": 0.16317808628082275, | |
| "eval_precision": 0.9897680763983628, | |
| "eval_recall": 0.9673333333333334, | |
| "eval_runtime": 463.2126, | |
| "eval_samples_per_second": 6.477, | |
| "eval_steps_per_second": 0.81, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 2.9e-05, | |
| "loss": 0.125, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_accuracy": 0.9796666666666667, | |
| "eval_f1": 0.9796054831160146, | |
| "eval_loss": 0.1086646318435669, | |
| "eval_precision": 0.9825620389000671, | |
| "eval_recall": 0.9766666666666667, | |
| "eval_runtime": 464.4048, | |
| "eval_samples_per_second": 6.46, | |
| "eval_steps_per_second": 0.807, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 2.8000000000000003e-05, | |
| "loss": 0.1361, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_accuracy": 0.976, | |
| "eval_f1": 0.9754935330156569, | |
| "eval_loss": 0.15513776242733002, | |
| "eval_precision": 0.9965229485396384, | |
| "eval_recall": 0.9553333333333334, | |
| "eval_runtime": 463.6268, | |
| "eval_samples_per_second": 6.471, | |
| "eval_steps_per_second": 0.809, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 2.7000000000000002e-05, | |
| "loss": 0.1276, | |
| "step": 805 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "eval_accuracy": 0.9683333333333334, | |
| "eval_f1": 0.9673875729488499, | |
| "eval_loss": 0.20085427165031433, | |
| "eval_precision": 0.997169143665959, | |
| "eval_recall": 0.9393333333333334, | |
| "eval_runtime": 463.7219, | |
| "eval_samples_per_second": 6.469, | |
| "eval_steps_per_second": 0.809, | |
| "step": 805 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 2.6000000000000002e-05, | |
| "loss": 0.1618, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_accuracy": 0.9766666666666667, | |
| "eval_f1": 0.9762066621346024, | |
| "eval_loss": 0.12355328351259232, | |
| "eval_precision": 0.9958391123439667, | |
| "eval_recall": 0.9573333333333334, | |
| "eval_runtime": 464.5376, | |
| "eval_samples_per_second": 6.458, | |
| "eval_steps_per_second": 0.807, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.2574, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_accuracy": 0.9806666666666667, | |
| "eval_f1": 0.9804054054054054, | |
| "eval_loss": 0.126968115568161, | |
| "eval_precision": 0.9938356164383562, | |
| "eval_recall": 0.9673333333333334, | |
| "eval_runtime": 465.883, | |
| "eval_samples_per_second": 6.439, | |
| "eval_steps_per_second": 0.805, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 2.4e-05, | |
| "loss": 0.1482, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "eval_accuracy": 0.9576666666666667, | |
| "eval_f1": 0.9558874609239321, | |
| "eval_loss": 0.2774529755115509, | |
| "eval_precision": 0.9978245105148659, | |
| "eval_recall": 0.9173333333333333, | |
| "eval_runtime": 465.4264, | |
| "eval_samples_per_second": 6.446, | |
| "eval_steps_per_second": 0.806, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 2.3000000000000003e-05, | |
| "loss": 0.1156, | |
| "step": 945 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "eval_accuracy": 0.9856666666666667, | |
| "eval_f1": 0.9855849815621857, | |
| "eval_loss": 0.1439618021249771, | |
| "eval_precision": 0.9912339851652057, | |
| "eval_recall": 0.98, | |
| "eval_runtime": 466.4591, | |
| "eval_samples_per_second": 6.431, | |
| "eval_steps_per_second": 0.804, | |
| "step": 945 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 2.2000000000000003e-05, | |
| "loss": 0.2393, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_accuracy": 0.9406666666666667, | |
| "eval_f1": 0.9369688385269122, | |
| "eval_loss": 0.37739551067352295, | |
| "eval_precision": 0.9992447129909365, | |
| "eval_recall": 0.882, | |
| "eval_runtime": 465.7379, | |
| "eval_samples_per_second": 6.441, | |
| "eval_steps_per_second": 0.805, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 2.1e-05, | |
| "loss": 0.2364, | |
| "step": 1015 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_accuracy": 0.984, | |
| "eval_f1": 0.9838601210490923, | |
| "eval_loss": 0.0981753021478653, | |
| "eval_precision": 0.9925373134328358, | |
| "eval_recall": 0.9753333333333334, | |
| "eval_runtime": 464.4225, | |
| "eval_samples_per_second": 6.46, | |
| "eval_steps_per_second": 0.807, | |
| "step": 1015 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 2e-05, | |
| "loss": 0.1246, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_accuracy": 0.985, | |
| "eval_f1": 0.9848637739656912, | |
| "eval_loss": 0.08204901963472366, | |
| "eval_precision": 0.9938900203665988, | |
| "eval_recall": 0.976, | |
| "eval_runtime": 466.5569, | |
| "eval_samples_per_second": 6.43, | |
| "eval_steps_per_second": 0.804, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 1.9e-05, | |
| "loss": 0.1411, | |
| "step": 1085 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "eval_accuracy": 0.9873333333333333, | |
| "eval_f1": 0.9872824631860776, | |
| "eval_loss": 0.05377618223428726, | |
| "eval_precision": 0.991263440860215, | |
| "eval_recall": 0.9833333333333333, | |
| "eval_runtime": 464.6089, | |
| "eval_samples_per_second": 6.457, | |
| "eval_steps_per_second": 0.807, | |
| "step": 1085 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 1.8e-05, | |
| "loss": 0.2055, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_accuracy": 0.9736666666666667, | |
| "eval_f1": 0.9730099077553809, | |
| "eval_loss": 0.15216030180454254, | |
| "eval_precision": 0.9978976874562018, | |
| "eval_recall": 0.9493333333333334, | |
| "eval_runtime": 465.4747, | |
| "eval_samples_per_second": 6.445, | |
| "eval_steps_per_second": 0.806, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 1.7000000000000003e-05, | |
| "loss": 0.3018, | |
| "step": 1155 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "eval_accuracy": 0.9813333333333333, | |
| "eval_f1": 0.9815059445178336, | |
| "eval_loss": 0.07627255469560623, | |
| "eval_precision": 0.9725130890052356, | |
| "eval_recall": 0.9906666666666667, | |
| "eval_runtime": 464.4389, | |
| "eval_samples_per_second": 6.459, | |
| "eval_steps_per_second": 0.807, | |
| "step": 1155 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 0.1702, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_accuracy": 0.9873333333333333, | |
| "eval_f1": 0.9873586161011311, | |
| "eval_loss": 0.07290682196617126, | |
| "eval_precision": 0.9853917662682603, | |
| "eval_recall": 0.9893333333333333, | |
| "eval_runtime": 464.5835, | |
| "eval_samples_per_second": 6.457, | |
| "eval_steps_per_second": 0.807, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 1.5e-05, | |
| "loss": 0.2085, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "eval_accuracy": 0.986, | |
| "eval_f1": 0.9859060402684564, | |
| "eval_loss": 0.08615541458129883, | |
| "eval_precision": 0.9925675675675676, | |
| "eval_recall": 0.9793333333333333, | |
| "eval_runtime": 464.5251, | |
| "eval_samples_per_second": 6.458, | |
| "eval_steps_per_second": 0.807, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 1.4000000000000001e-05, | |
| "loss": 0.0899, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_accuracy": 0.987, | |
| "eval_f1": 0.9869782971619365, | |
| "eval_loss": 0.07593820989131927, | |
| "eval_precision": 0.988628762541806, | |
| "eval_recall": 0.9853333333333333, | |
| "eval_runtime": 464.4867, | |
| "eval_samples_per_second": 6.459, | |
| "eval_steps_per_second": 0.807, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1.3000000000000001e-05, | |
| "loss": 0.212, | |
| "step": 1295 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "eval_accuracy": 0.9846666666666667, | |
| "eval_f1": 0.9847277556440903, | |
| "eval_loss": 0.08726092427968979, | |
| "eval_precision": 0.9808201058201058, | |
| "eval_recall": 0.9886666666666667, | |
| "eval_runtime": 463.8528, | |
| "eval_samples_per_second": 6.468, | |
| "eval_steps_per_second": 0.808, | |
| "step": 1295 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.2e-05, | |
| "loss": 0.0459, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_accuracy": 0.981, | |
| "eval_f1": 0.9807237064592493, | |
| "eval_loss": 0.11619190126657486, | |
| "eval_precision": 0.9951956074124915, | |
| "eval_recall": 0.9666666666666667, | |
| "eval_runtime": 463.7918, | |
| "eval_samples_per_second": 6.468, | |
| "eval_steps_per_second": 0.809, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.1000000000000001e-05, | |
| "loss": 0.2035, | |
| "step": 1365 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "eval_accuracy": 0.9876666666666667, | |
| "eval_f1": 0.9875797247398456, | |
| "eval_loss": 0.07956338673830032, | |
| "eval_precision": 0.9945909398242055, | |
| "eval_recall": 0.9806666666666667, | |
| "eval_runtime": 464.4206, | |
| "eval_samples_per_second": 6.46, | |
| "eval_steps_per_second": 0.807, | |
| "step": 1365 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0942, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_accuracy": 0.979, | |
| "eval_f1": 0.979269496544916, | |
| "eval_loss": 0.09173166751861572, | |
| "eval_precision": 0.9668615984405458, | |
| "eval_recall": 0.992, | |
| "eval_runtime": 464.6027, | |
| "eval_samples_per_second": 6.457, | |
| "eval_steps_per_second": 0.807, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 9e-06, | |
| "loss": 0.161, | |
| "step": 1435 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "eval_accuracy": 0.9873333333333333, | |
| "eval_f1": 0.9872397582269979, | |
| "eval_loss": 0.06276000291109085, | |
| "eval_precision": 0.9945872801082544, | |
| "eval_recall": 0.98, | |
| "eval_runtime": 463.3979, | |
| "eval_samples_per_second": 6.474, | |
| "eval_steps_per_second": 0.809, | |
| "step": 1435 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 0.0365, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "eval_accuracy": 0.9843333333333333, | |
| "eval_f1": 0.9841162554917202, | |
| "eval_loss": 0.08324441313743591, | |
| "eval_precision": 0.997943797121316, | |
| "eval_recall": 0.9706666666666667, | |
| "eval_runtime": 463.6189, | |
| "eval_samples_per_second": 6.471, | |
| "eval_steps_per_second": 0.809, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 7.000000000000001e-06, | |
| "loss": 0.0508, | |
| "step": 1505 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "eval_accuracy": 0.9843333333333333, | |
| "eval_f1": 0.9841162554917202, | |
| "eval_loss": 0.09412873536348343, | |
| "eval_precision": 0.997943797121316, | |
| "eval_recall": 0.9706666666666667, | |
| "eval_runtime": 466.9343, | |
| "eval_samples_per_second": 6.425, | |
| "eval_steps_per_second": 0.803, | |
| "step": 1505 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 6e-06, | |
| "loss": 0.0597, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "eval_accuracy": 0.9873333333333333, | |
| "eval_f1": 0.9872994652406418, | |
| "eval_loss": 0.05775593966245651, | |
| "eval_precision": 0.989946380697051, | |
| "eval_recall": 0.9846666666666667, | |
| "eval_runtime": 464.2967, | |
| "eval_samples_per_second": 6.461, | |
| "eval_steps_per_second": 0.808, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 5e-06, | |
| "loss": 0.0055, | |
| "step": 1575 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "eval_accuracy": 0.9863333333333333, | |
| "eval_f1": 0.9861813279406809, | |
| "eval_loss": 0.07944045215845108, | |
| "eval_precision": 0.9972733469665985, | |
| "eval_recall": 0.9753333333333334, | |
| "eval_runtime": 464.3973, | |
| "eval_samples_per_second": 6.46, | |
| "eval_steps_per_second": 0.807, | |
| "step": 1575 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.0681, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "eval_accuracy": 0.9873333333333333, | |
| "eval_f1": 0.9872139973082099, | |
| "eval_loss": 0.07313308119773865, | |
| "eval_precision": 0.9966032608695652, | |
| "eval_recall": 0.978, | |
| "eval_runtime": 464.8711, | |
| "eval_samples_per_second": 6.453, | |
| "eval_steps_per_second": 0.807, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 3e-06, | |
| "loss": 0.0978, | |
| "step": 1645 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "eval_accuracy": 0.9883333333333333, | |
| "eval_f1": 0.9883138564273791, | |
| "eval_loss": 0.058573223650455475, | |
| "eval_precision": 0.9899665551839465, | |
| "eval_recall": 0.9866666666666667, | |
| "eval_runtime": 465.0949, | |
| "eval_samples_per_second": 6.45, | |
| "eval_steps_per_second": 0.806, | |
| "step": 1645 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 0.1392, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_accuracy": 0.9883333333333333, | |
| "eval_f1": 0.9883060474440362, | |
| "eval_loss": 0.055864058434963226, | |
| "eval_precision": 0.9906229068988613, | |
| "eval_recall": 0.986, | |
| "eval_runtime": 464.3364, | |
| "eval_samples_per_second": 6.461, | |
| "eval_steps_per_second": 0.808, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 0.0432, | |
| "step": 1715 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "eval_accuracy": 0.9883333333333333, | |
| "eval_f1": 0.9883060474440362, | |
| "eval_loss": 0.055420782417058945, | |
| "eval_precision": 0.9906229068988613, | |
| "eval_recall": 0.986, | |
| "eval_runtime": 464.6017, | |
| "eval_samples_per_second": 6.457, | |
| "eval_steps_per_second": 0.807, | |
| "step": 1715 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.0006, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.988, | |
| "eval_f1": 0.9879679144385026, | |
| "eval_loss": 0.05567142367362976, | |
| "eval_precision": 0.9906166219839142, | |
| "eval_recall": 0.9853333333333333, | |
| "eval_runtime": 464.5424, | |
| "eval_samples_per_second": 6.458, | |
| "eval_steps_per_second": 0.807, | |
| "step": 1750 | |
| } | |
| ], | |
| "max_steps": 1750, | |
| "num_train_epochs": 1, | |
| "total_flos": 1.0151220215808e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |