| { |
| "best_metric": 1.2530498504638672, |
| "best_model_checkpoint": "./ckpt/2312201705_trained_train+val_added_continue-recommend/checkpoint-2775", |
| "epoch": 2500.0, |
| "eval_steps": 25, |
| "global_step": 5000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 12.5, |
| "learning_rate": 1.9950000000000004e-05, |
| "loss": 2.1851, |
| "step": 25 |
| }, |
| { |
| "epoch": 12.5, |
| "eval_accuracy": 0.33, |
| "eval_f1": 0.04962406015037594, |
| "eval_loss": 2.1281986236572266, |
| "eval_precision": 0.033, |
| "eval_recall": 0.1, |
| "eval_runtime": 0.2178, |
| "eval_samples_per_second": 918.12, |
| "eval_steps_per_second": 4.591, |
| "step": 25 |
| }, |
| { |
| "epoch": 25.0, |
| "learning_rate": 1.9900000000000003e-05, |
| "loss": 2.0291, |
| "step": 50 |
| }, |
| { |
| "epoch": 25.0, |
| "eval_accuracy": 0.33, |
| "eval_f1": 0.04962406015037594, |
| "eval_loss": 2.0157577991485596, |
| "eval_precision": 0.033, |
| "eval_recall": 0.1, |
| "eval_runtime": 0.115, |
| "eval_samples_per_second": 1739.325, |
| "eval_steps_per_second": 8.697, |
| "step": 50 |
| }, |
| { |
| "epoch": 37.5, |
| "learning_rate": 1.985e-05, |
| "loss": 1.8942, |
| "step": 75 |
| }, |
| { |
| "epoch": 37.5, |
| "eval_accuracy": 0.33, |
| "eval_f1": 0.04962406015037594, |
| "eval_loss": 1.9294581413269043, |
| "eval_precision": 0.033, |
| "eval_recall": 0.1, |
| "eval_runtime": 0.1082, |
| "eval_samples_per_second": 1848.252, |
| "eval_steps_per_second": 9.241, |
| "step": 75 |
| }, |
| { |
| "epoch": 50.0, |
| "learning_rate": 1.98e-05, |
| "loss": 1.7909, |
| "step": 100 |
| }, |
| { |
| "epoch": 50.0, |
| "eval_accuracy": 0.33, |
| "eval_f1": 0.04962406015037594, |
| "eval_loss": 1.873355746269226, |
| "eval_precision": 0.033, |
| "eval_recall": 0.1, |
| "eval_runtime": 0.1081, |
| "eval_samples_per_second": 1849.597, |
| "eval_steps_per_second": 9.248, |
| "step": 100 |
| }, |
| { |
| "epoch": 62.5, |
| "learning_rate": 1.9750000000000002e-05, |
| "loss": 1.7185, |
| "step": 125 |
| }, |
| { |
| "epoch": 62.5, |
| "eval_accuracy": 0.33, |
| "eval_f1": 0.04962406015037594, |
| "eval_loss": 1.840307354927063, |
| "eval_precision": 0.033, |
| "eval_recall": 0.1, |
| "eval_runtime": 0.1084, |
| "eval_samples_per_second": 1844.761, |
| "eval_steps_per_second": 9.224, |
| "step": 125 |
| }, |
| { |
| "epoch": 75.0, |
| "learning_rate": 1.97e-05, |
| "loss": 1.6607, |
| "step": 150 |
| }, |
| { |
| "epoch": 75.0, |
| "eval_accuracy": 0.33, |
| "eval_f1": 0.04962406015037594, |
| "eval_loss": 1.814700961112976, |
| "eval_precision": 0.033, |
| "eval_recall": 0.1, |
| "eval_runtime": 0.1086, |
| "eval_samples_per_second": 1840.951, |
| "eval_steps_per_second": 9.205, |
| "step": 150 |
| }, |
| { |
| "epoch": 87.5, |
| "learning_rate": 1.9650000000000003e-05, |
| "loss": 1.6153, |
| "step": 175 |
| }, |
| { |
| "epoch": 87.5, |
| "eval_accuracy": 0.33, |
| "eval_f1": 0.04962406015037594, |
| "eval_loss": 1.801851511001587, |
| "eval_precision": 0.033, |
| "eval_recall": 0.1, |
| "eval_runtime": 0.1091, |
| "eval_samples_per_second": 1833.411, |
| "eval_steps_per_second": 9.167, |
| "step": 175 |
| }, |
| { |
| "epoch": 100.0, |
| "learning_rate": 1.9600000000000002e-05, |
| "loss": 1.5799, |
| "step": 200 |
| }, |
| { |
| "epoch": 100.0, |
| "eval_accuracy": 0.36, |
| "eval_f1": 0.0703125, |
| "eval_loss": 1.7845327854156494, |
| "eval_precision": 0.09473684210526316, |
| "eval_recall": 0.11111111111111112, |
| "eval_runtime": 0.1096, |
| "eval_samples_per_second": 1825.126, |
| "eval_steps_per_second": 9.126, |
| "step": 200 |
| }, |
| { |
| "epoch": 112.5, |
| "learning_rate": 1.955e-05, |
| "loss": 1.5655, |
| "step": 225 |
| }, |
| { |
| "epoch": 112.5, |
| "eval_accuracy": 0.385, |
| "eval_f1": 0.08447369940527745, |
| "eval_loss": 1.7618108987808228, |
| "eval_precision": 0.109009009009009, |
| "eval_recall": 0.12037037037037038, |
| "eval_runtime": 0.1092, |
| "eval_samples_per_second": 1830.898, |
| "eval_steps_per_second": 9.154, |
| "step": 225 |
| }, |
| { |
| "epoch": 125.0, |
| "learning_rate": 1.95e-05, |
| "loss": 1.5415, |
| "step": 250 |
| }, |
| { |
| "epoch": 125.0, |
| "eval_accuracy": 0.415, |
| "eval_f1": 0.09921088435374151, |
| "eval_loss": 1.7453179359436035, |
| "eval_precision": 0.11782388933226921, |
| "eval_recall": 0.13148148148148148, |
| "eval_runtime": 0.1082, |
| "eval_samples_per_second": 1848.114, |
| "eval_steps_per_second": 9.241, |
| "step": 250 |
| }, |
| { |
| "epoch": 137.5, |
| "learning_rate": 1.9450000000000002e-05, |
| "loss": 1.5213, |
| "step": 275 |
| }, |
| { |
| "epoch": 137.5, |
| "eval_accuracy": 0.43, |
| "eval_f1": 0.1062451572911824, |
| "eval_loss": 1.7249926328659058, |
| "eval_precision": 0.11535003211303789, |
| "eval_recall": 0.13737373737373737, |
| "eval_runtime": 0.109, |
| "eval_samples_per_second": 1835.562, |
| "eval_steps_per_second": 9.178, |
| "step": 275 |
| }, |
| { |
| "epoch": 150.0, |
| "learning_rate": 1.94e-05, |
| "loss": 1.4994, |
| "step": 300 |
| }, |
| { |
| "epoch": 150.0, |
| "eval_accuracy": 0.44, |
| "eval_f1": 0.10943679599499376, |
| "eval_loss": 1.7063140869140625, |
| "eval_precision": 0.11265508684863523, |
| "eval_recall": 0.14107744107744108, |
| "eval_runtime": 0.1089, |
| "eval_samples_per_second": 1837.101, |
| "eval_steps_per_second": 9.186, |
| "step": 300 |
| }, |
| { |
| "epoch": 162.5, |
| "learning_rate": 1.9350000000000003e-05, |
| "loss": 1.45, |
| "step": 325 |
| }, |
| { |
| "epoch": 162.5, |
| "eval_accuracy": 0.465, |
| "eval_f1": 0.11875325659608735, |
| "eval_loss": 1.685305118560791, |
| "eval_precision": 0.11411052715400541, |
| "eval_recall": 0.15067340067340068, |
| "eval_runtime": 0.133, |
| "eval_samples_per_second": 1503.383, |
| "eval_steps_per_second": 7.517, |
| "step": 325 |
| }, |
| { |
| "epoch": 175.0, |
| "learning_rate": 1.93e-05, |
| "loss": 1.4077, |
| "step": 350 |
| }, |
| { |
| "epoch": 175.0, |
| "eval_accuracy": 0.46, |
| "eval_f1": 0.1170803456517742, |
| "eval_loss": 1.6690095663070679, |
| "eval_precision": 0.10792540792540792, |
| "eval_recall": 0.14949494949494951, |
| "eval_runtime": 0.1125, |
| "eval_samples_per_second": 1777.718, |
| "eval_steps_per_second": 8.889, |
| "step": 350 |
| }, |
| { |
| "epoch": 187.5, |
| "learning_rate": 1.925e-05, |
| "loss": 1.4157, |
| "step": 375 |
| }, |
| { |
| "epoch": 187.5, |
| "eval_accuracy": 0.465, |
| "eval_f1": 0.11800714318007147, |
| "eval_loss": 1.651031494140625, |
| "eval_precision": 0.10648032262550408, |
| "eval_recall": 0.15134680134680134, |
| "eval_runtime": 0.1084, |
| "eval_samples_per_second": 1845.699, |
| "eval_steps_per_second": 9.228, |
| "step": 375 |
| }, |
| { |
| "epoch": 200.0, |
| "learning_rate": 1.9200000000000003e-05, |
| "loss": 1.3774, |
| "step": 400 |
| }, |
| { |
| "epoch": 200.0, |
| "eval_accuracy": 0.47, |
| "eval_f1": 0.11962583198416983, |
| "eval_loss": 1.6357709169387817, |
| "eval_precision": 0.10745614035087718, |
| "eval_recall": 0.1531986531986532, |
| "eval_runtime": 0.1092, |
| "eval_samples_per_second": 1830.834, |
| "eval_steps_per_second": 9.154, |
| "step": 400 |
| }, |
| { |
| "epoch": 212.5, |
| "learning_rate": 1.915e-05, |
| "loss": 1.3508, |
| "step": 425 |
| }, |
| { |
| "epoch": 212.5, |
| "eval_accuracy": 0.47, |
| "eval_f1": 0.11962583198416983, |
| "eval_loss": 1.6214944124221802, |
| "eval_precision": 0.10745614035087718, |
| "eval_recall": 0.1531986531986532, |
| "eval_runtime": 0.108, |
| "eval_samples_per_second": 1852.068, |
| "eval_steps_per_second": 9.26, |
| "step": 425 |
| }, |
| { |
| "epoch": 225.0, |
| "learning_rate": 1.91e-05, |
| "loss": 1.3048, |
| "step": 450 |
| }, |
| { |
| "epoch": 225.0, |
| "eval_accuracy": 0.47, |
| "eval_f1": 0.11962583198416983, |
| "eval_loss": 1.6078141927719116, |
| "eval_precision": 0.10745614035087718, |
| "eval_recall": 0.1531986531986532, |
| "eval_runtime": 0.1077, |
| "eval_samples_per_second": 1857.757, |
| "eval_steps_per_second": 9.289, |
| "step": 450 |
| }, |
| { |
| "epoch": 237.5, |
| "learning_rate": 1.9050000000000002e-05, |
| "loss": 1.3187, |
| "step": 475 |
| }, |
| { |
| "epoch": 237.5, |
| "eval_accuracy": 0.495, |
| "eval_f1": 0.12754467585547197, |
| "eval_loss": 1.5953254699707031, |
| "eval_precision": 0.11115987460815047, |
| "eval_recall": 0.1627946127946128, |
| "eval_runtime": 0.1101, |
| "eval_samples_per_second": 1816.491, |
| "eval_steps_per_second": 9.082, |
| "step": 475 |
| }, |
| { |
| "epoch": 250.0, |
| "learning_rate": 1.9e-05, |
| "loss": 1.2809, |
| "step": 500 |
| }, |
| { |
| "epoch": 250.0, |
| "eval_accuracy": 0.495, |
| "eval_f1": 0.12769176943934227, |
| "eval_loss": 1.5819820165634155, |
| "eval_precision": 0.11023809523809525, |
| "eval_recall": 0.1627946127946128, |
| "eval_runtime": 0.1084, |
| "eval_samples_per_second": 1845.431, |
| "eval_steps_per_second": 9.227, |
| "step": 500 |
| }, |
| { |
| "epoch": 262.5, |
| "learning_rate": 1.8950000000000003e-05, |
| "loss": 1.2529, |
| "step": 525 |
| }, |
| { |
| "epoch": 262.5, |
| "eval_accuracy": 0.505, |
| "eval_f1": 0.13595994937839648, |
| "eval_loss": 1.5695488452911377, |
| "eval_precision": 0.1598529411764706, |
| "eval_recall": 0.16849261849261848, |
| "eval_runtime": 0.1093, |
| "eval_samples_per_second": 1829.181, |
| "eval_steps_per_second": 9.146, |
| "step": 525 |
| }, |
| { |
| "epoch": 275.0, |
| "learning_rate": 1.8900000000000002e-05, |
| "loss": 1.2318, |
| "step": 550 |
| }, |
| { |
| "epoch": 275.0, |
| "eval_accuracy": 0.5, |
| "eval_f1": 0.13480392156862744, |
| "eval_loss": 1.5617371797561646, |
| "eval_precision": 0.15972013993003498, |
| "eval_recall": 0.16664076664076666, |
| "eval_runtime": 0.1249, |
| "eval_samples_per_second": 1600.879, |
| "eval_steps_per_second": 8.004, |
| "step": 550 |
| }, |
| { |
| "epoch": 287.5, |
| "learning_rate": 1.885e-05, |
| "loss": 1.219, |
| "step": 575 |
| }, |
| { |
| "epoch": 287.5, |
| "eval_accuracy": 0.51, |
| "eval_f1": 0.1374045919470968, |
| "eval_loss": 1.5485947132110596, |
| "eval_precision": 0.16075895567698845, |
| "eval_recall": 0.17034447034447034, |
| "eval_runtime": 0.1319, |
| "eval_samples_per_second": 1515.932, |
| "eval_steps_per_second": 7.58, |
| "step": 575 |
| }, |
| { |
| "epoch": 300.0, |
| "learning_rate": 1.88e-05, |
| "loss": 1.2015, |
| "step": 600 |
| }, |
| { |
| "epoch": 300.0, |
| "eval_accuracy": 0.525, |
| "eval_f1": 0.21699974800254962, |
| "eval_loss": 1.540075421333313, |
| "eval_precision": 0.23696635656938958, |
| "eval_recall": 0.2761849261849262, |
| "eval_runtime": 0.1082, |
| "eval_samples_per_second": 1848.126, |
| "eval_steps_per_second": 9.241, |
| "step": 600 |
| }, |
| { |
| "epoch": 312.5, |
| "learning_rate": 1.8750000000000002e-05, |
| "loss": 1.1865, |
| "step": 625 |
| }, |
| { |
| "epoch": 312.5, |
| "eval_accuracy": 0.535, |
| "eval_f1": 0.21488239830345096, |
| "eval_loss": 1.5302218198776245, |
| "eval_precision": 0.2206201550387597, |
| "eval_recall": 0.28188293188293184, |
| "eval_runtime": 0.1121, |
| "eval_samples_per_second": 1784.863, |
| "eval_steps_per_second": 8.924, |
| "step": 625 |
| }, |
| { |
| "epoch": 325.0, |
| "learning_rate": 1.8700000000000004e-05, |
| "loss": 1.1387, |
| "step": 650 |
| }, |
| { |
| "epoch": 325.0, |
| "eval_accuracy": 0.535, |
| "eval_f1": 0.2082144327068185, |
| "eval_loss": 1.5234472751617432, |
| "eval_precision": 0.2157492969063881, |
| "eval_recall": 0.28154623154623154, |
| "eval_runtime": 0.1157, |
| "eval_samples_per_second": 1728.669, |
| "eval_steps_per_second": 8.643, |
| "step": 650 |
| }, |
| { |
| "epoch": 337.5, |
| "learning_rate": 1.8650000000000003e-05, |
| "loss": 1.1487, |
| "step": 675 |
| }, |
| { |
| "epoch": 337.5, |
| "eval_accuracy": 0.52, |
| "eval_f1": 0.1901849150171407, |
| "eval_loss": 1.5094608068466187, |
| "eval_precision": 0.20013505987190197, |
| "eval_recall": 0.273996373996374, |
| "eval_runtime": 0.1083, |
| "eval_samples_per_second": 1847.385, |
| "eval_steps_per_second": 9.237, |
| "step": 675 |
| }, |
| { |
| "epoch": 350.0, |
| "learning_rate": 1.86e-05, |
| "loss": 1.1056, |
| "step": 700 |
| }, |
| { |
| "epoch": 350.0, |
| "eval_accuracy": 0.545, |
| "eval_f1": 0.2018150763446284, |
| "eval_loss": 1.499509572982788, |
| "eval_precision": 0.20997708972819074, |
| "eval_recall": 0.28524993524993525, |
| "eval_runtime": 0.1096, |
| "eval_samples_per_second": 1824.332, |
| "eval_steps_per_second": 9.122, |
| "step": 700 |
| }, |
| { |
| "epoch": 362.5, |
| "learning_rate": 1.855e-05, |
| "loss": 1.0919, |
| "step": 725 |
| }, |
| { |
| "epoch": 362.5, |
| "eval_accuracy": 0.55, |
| "eval_f1": 0.21087738984074916, |
| "eval_loss": 1.488194227218628, |
| "eval_precision": 0.2161290322580645, |
| "eval_recall": 0.29142709142709144, |
| "eval_runtime": 0.11, |
| "eval_samples_per_second": 1818.566, |
| "eval_steps_per_second": 9.093, |
| "step": 725 |
| }, |
| { |
| "epoch": 375.0, |
| "learning_rate": 1.8500000000000002e-05, |
| "loss": 1.0648, |
| "step": 750 |
| }, |
| { |
| "epoch": 375.0, |
| "eval_accuracy": 0.55, |
| "eval_f1": 0.21114873002341034, |
| "eval_loss": 1.4815982580184937, |
| "eval_precision": 0.21680661068905768, |
| "eval_recall": 0.29142709142709144, |
| "eval_runtime": 0.1103, |
| "eval_samples_per_second": 1812.601, |
| "eval_steps_per_second": 9.063, |
| "step": 750 |
| }, |
| { |
| "epoch": 387.5, |
| "learning_rate": 1.845e-05, |
| "loss": 1.057, |
| "step": 775 |
| }, |
| { |
| "epoch": 387.5, |
| "eval_accuracy": 0.555, |
| "eval_f1": 0.21278195529706112, |
| "eval_loss": 1.4760266542434692, |
| "eval_precision": 0.2190915254237288, |
| "eval_recall": 0.29294224294224297, |
| "eval_runtime": 0.1083, |
| "eval_samples_per_second": 1847.06, |
| "eval_steps_per_second": 9.235, |
| "step": 775 |
| }, |
| { |
| "epoch": 400.0, |
| "learning_rate": 1.8400000000000003e-05, |
| "loss": 1.028, |
| "step": 800 |
| }, |
| { |
| "epoch": 400.0, |
| "eval_accuracy": 0.55, |
| "eval_f1": 0.2104499695650138, |
| "eval_loss": 1.4676929712295532, |
| "eval_precision": 0.20408502135868817, |
| "eval_recall": 0.29142709142709144, |
| "eval_runtime": 0.1093, |
| "eval_samples_per_second": 1829.457, |
| "eval_steps_per_second": 9.147, |
| "step": 800 |
| }, |
| { |
| "epoch": 412.5, |
| "learning_rate": 1.8350000000000002e-05, |
| "loss": 1.0263, |
| "step": 825 |
| }, |
| { |
| "epoch": 412.5, |
| "eval_accuracy": 0.56, |
| "eval_f1": 0.21367276887871856, |
| "eval_loss": 1.4615812301635742, |
| "eval_precision": 0.2066949152542373, |
| "eval_recall": 0.2991193991193991, |
| "eval_runtime": 0.1094, |
| "eval_samples_per_second": 1828.799, |
| "eval_steps_per_second": 9.144, |
| "step": 825 |
| }, |
| { |
| "epoch": 425.0, |
| "learning_rate": 1.83e-05, |
| "loss": 1.014, |
| "step": 850 |
| }, |
| { |
| "epoch": 425.0, |
| "eval_accuracy": 0.55, |
| "eval_f1": 0.20480680883988586, |
| "eval_loss": 1.4569095373153687, |
| "eval_precision": 0.1928015487337521, |
| "eval_recall": 0.29375809375809375, |
| "eval_runtime": 0.1097, |
| "eval_samples_per_second": 1823.163, |
| "eval_steps_per_second": 9.116, |
| "step": 850 |
| }, |
| { |
| "epoch": 437.5, |
| "learning_rate": 1.825e-05, |
| "loss": 0.9689, |
| "step": 875 |
| }, |
| { |
| "epoch": 437.5, |
| "eval_accuracy": 0.555, |
| "eval_f1": 0.20607287449392714, |
| "eval_loss": 1.4516905546188354, |
| "eval_precision": 0.1958133971291866, |
| "eval_recall": 0.2956099456099456, |
| "eval_runtime": 0.1098, |
| "eval_samples_per_second": 1821.207, |
| "eval_steps_per_second": 9.106, |
| "step": 875 |
| }, |
| { |
| "epoch": 450.0, |
| "learning_rate": 1.8200000000000002e-05, |
| "loss": 0.981, |
| "step": 900 |
| }, |
| { |
| "epoch": 450.0, |
| "eval_accuracy": 0.55, |
| "eval_f1": 0.2031474674560661, |
| "eval_loss": 1.441676378250122, |
| "eval_precision": 0.1841098484848485, |
| "eval_recall": 0.2940947940947941, |
| "eval_runtime": 0.1119, |
| "eval_samples_per_second": 1787.842, |
| "eval_steps_per_second": 8.939, |
| "step": 900 |
| }, |
| { |
| "epoch": 462.5, |
| "learning_rate": 1.815e-05, |
| "loss": 0.9571, |
| "step": 925 |
| }, |
| { |
| "epoch": 462.5, |
| "eval_accuracy": 0.55, |
| "eval_f1": 0.20385623739556324, |
| "eval_loss": 1.4357507228851318, |
| "eval_precision": 0.1875270562770563, |
| "eval_recall": 0.2940947940947941, |
| "eval_runtime": 0.1137, |
| "eval_samples_per_second": 1758.891, |
| "eval_steps_per_second": 8.794, |
| "step": 925 |
| }, |
| { |
| "epoch": 475.0, |
| "learning_rate": 1.8100000000000003e-05, |
| "loss": 0.9526, |
| "step": 950 |
| }, |
| { |
| "epoch": 475.0, |
| "eval_accuracy": 0.555, |
| "eval_f1": 0.2074794809710064, |
| "eval_loss": 1.427919626235962, |
| "eval_precision": 0.18793525854879067, |
| "eval_recall": 0.29794094794094794, |
| "eval_runtime": 0.1128, |
| "eval_samples_per_second": 1773.25, |
| "eval_steps_per_second": 8.866, |
| "step": 950 |
| }, |
| { |
| "epoch": 487.5, |
| "learning_rate": 1.805e-05, |
| "loss": 0.9566, |
| "step": 975 |
| }, |
| { |
| "epoch": 487.5, |
| "eval_accuracy": 0.545, |
| "eval_f1": 0.20249975688028785, |
| "eval_loss": 1.425557255744934, |
| "eval_precision": 0.1877025662823442, |
| "eval_recall": 0.29190624190624187, |
| "eval_runtime": 0.1095, |
| "eval_samples_per_second": 1827.253, |
| "eval_steps_per_second": 9.136, |
| "step": 975 |
| }, |
| { |
| "epoch": 500.0, |
| "learning_rate": 1.8e-05, |
| "loss": 0.9239, |
| "step": 1000 |
| }, |
| { |
| "epoch": 500.0, |
| "eval_accuracy": 0.555, |
| "eval_f1": 0.2074794809710064, |
| "eval_loss": 1.4146395921707153, |
| "eval_precision": 0.18793525854879067, |
| "eval_recall": 0.29794094794094794, |
| "eval_runtime": 0.1096, |
| "eval_samples_per_second": 1824.126, |
| "eval_steps_per_second": 9.121, |
| "step": 1000 |
| }, |
| { |
| "epoch": 512.5, |
| "learning_rate": 1.795e-05, |
| "loss": 0.9073, |
| "step": 1025 |
| }, |
| { |
| "epoch": 512.5, |
| "eval_accuracy": 0.555, |
| "eval_f1": 0.2074794809710064, |
| "eval_loss": 1.4115307331085205, |
| "eval_precision": 0.18793525854879067, |
| "eval_recall": 0.29794094794094794, |
| "eval_runtime": 0.1316, |
| "eval_samples_per_second": 1519.67, |
| "eval_steps_per_second": 7.598, |
| "step": 1025 |
| }, |
| { |
| "epoch": 525.0, |
| "learning_rate": 1.79e-05, |
| "loss": 0.8995, |
| "step": 1050 |
| }, |
| { |
| "epoch": 525.0, |
| "eval_accuracy": 0.555, |
| "eval_f1": 0.2074794809710064, |
| "eval_loss": 1.4043453931808472, |
| "eval_precision": 0.18793525854879067, |
| "eval_recall": 0.29794094794094794, |
| "eval_runtime": 0.1086, |
| "eval_samples_per_second": 1841.602, |
| "eval_steps_per_second": 9.208, |
| "step": 1050 |
| }, |
| { |
| "epoch": 537.5, |
| "learning_rate": 1.785e-05, |
| "loss": 0.884, |
| "step": 1075 |
| }, |
| { |
| "epoch": 537.5, |
| "eval_accuracy": 0.56, |
| "eval_f1": 0.21142602366517654, |
| "eval_loss": 1.3939542770385742, |
| "eval_precision": 0.19087856618367888, |
| "eval_recall": 0.3017871017871018, |
| "eval_runtime": 0.1097, |
| "eval_samples_per_second": 1823.174, |
| "eval_steps_per_second": 9.116, |
| "step": 1075 |
| }, |
| { |
| "epoch": 550.0, |
| "learning_rate": 1.7800000000000002e-05, |
| "loss": 0.858, |
| "step": 1100 |
| }, |
| { |
| "epoch": 550.0, |
| "eval_accuracy": 0.555, |
| "eval_f1": 0.20726879611260948, |
| "eval_loss": 1.3932217359542847, |
| "eval_precision": 0.18742683242683242, |
| "eval_recall": 0.29794094794094794, |
| "eval_runtime": 0.1094, |
| "eval_samples_per_second": 1828.54, |
| "eval_steps_per_second": 9.143, |
| "step": 1100 |
| }, |
| { |
| "epoch": 562.5, |
| "learning_rate": 1.775e-05, |
| "loss": 0.8826, |
| "step": 1125 |
| }, |
| { |
| "epoch": 562.5, |
| "eval_accuracy": 0.565, |
| "eval_f1": 0.21541666268068455, |
| "eval_loss": 1.3876113891601562, |
| "eval_precision": 0.19401313571124895, |
| "eval_recall": 0.3056332556332556, |
| "eval_runtime": 0.1275, |
| "eval_samples_per_second": 1568.897, |
| "eval_steps_per_second": 7.844, |
| "step": 1125 |
| }, |
| { |
| "epoch": 575.0, |
| "learning_rate": 1.77e-05, |
| "loss": 0.8439, |
| "step": 1150 |
| }, |
| { |
| "epoch": 575.0, |
| "eval_accuracy": 0.565, |
| "eval_f1": 0.21561830938729143, |
| "eval_loss": 1.3830856084823608, |
| "eval_precision": 0.1945025606532616, |
| "eval_recall": 0.3056332556332556, |
| "eval_runtime": 0.1104, |
| "eval_samples_per_second": 1811.243, |
| "eval_steps_per_second": 9.056, |
| "step": 1150 |
| }, |
| { |
| "epoch": 587.5, |
| "learning_rate": 1.7650000000000002e-05, |
| "loss": 0.8425, |
| "step": 1175 |
| }, |
| { |
| "epoch": 587.5, |
| "eval_accuracy": 0.565, |
| "eval_f1": 0.21561830938729143, |
| "eval_loss": 1.374933123588562, |
| "eval_precision": 0.1945025606532616, |
| "eval_recall": 0.3056332556332556, |
| "eval_runtime": 0.1123, |
| "eval_samples_per_second": 1780.182, |
| "eval_steps_per_second": 8.901, |
| "step": 1175 |
| }, |
| { |
| "epoch": 600.0, |
| "learning_rate": 1.76e-05, |
| "loss": 0.8336, |
| "step": 1200 |
| }, |
| { |
| "epoch": 600.0, |
| "eval_accuracy": 0.565, |
| "eval_f1": 0.21500476705443203, |
| "eval_loss": 1.3735445737838745, |
| "eval_precision": 0.19209877448767718, |
| "eval_recall": 0.3056332556332556, |
| "eval_runtime": 0.1262, |
| "eval_samples_per_second": 1585.407, |
| "eval_steps_per_second": 7.927, |
| "step": 1200 |
| }, |
| { |
| "epoch": 612.5, |
| "learning_rate": 1.755e-05, |
| "loss": 0.8106, |
| "step": 1225 |
| }, |
| { |
| "epoch": 612.5, |
| "eval_accuracy": 0.56, |
| "eval_f1": 0.20927161132127625, |
| "eval_loss": 1.3722925186157227, |
| "eval_precision": 0.18795204402515725, |
| "eval_recall": 0.3017871017871018, |
| "eval_runtime": 0.1096, |
| "eval_samples_per_second": 1824.566, |
| "eval_steps_per_second": 9.123, |
| "step": 1225 |
| }, |
| { |
| "epoch": 625.0, |
| "learning_rate": 1.7500000000000002e-05, |
| "loss": 0.8052, |
| "step": 1250 |
| }, |
| { |
| "epoch": 625.0, |
| "eval_accuracy": 0.56, |
| "eval_f1": 0.21128928542721645, |
| "eval_loss": 1.3651293516159058, |
| "eval_precision": 0.18947811447811447, |
| "eval_recall": 0.3017871017871018, |
| "eval_runtime": 0.1099, |
| "eval_samples_per_second": 1819.193, |
| "eval_steps_per_second": 9.096, |
| "step": 1250 |
| }, |
| { |
| "epoch": 637.5, |
| "learning_rate": 1.7450000000000004e-05, |
| "loss": 0.7897, |
| "step": 1275 |
| }, |
| { |
| "epoch": 637.5, |
| "eval_accuracy": 0.565, |
| "eval_f1": 0.2152166394940961, |
| "eval_loss": 1.3617373704910278, |
| "eval_precision": 0.1926202507117411, |
| "eval_recall": 0.3056332556332556, |
| "eval_runtime": 0.1094, |
| "eval_samples_per_second": 1828.105, |
| "eval_steps_per_second": 9.141, |
| "step": 1275 |
| }, |
| { |
| "epoch": 650.0, |
| "learning_rate": 1.7400000000000003e-05, |
| "loss": 0.7708, |
| "step": 1300 |
| }, |
| { |
| "epoch": 650.0, |
| "eval_accuracy": 0.565, |
| "eval_f1": 0.2152166394940961, |
| "eval_loss": 1.3592756986618042, |
| "eval_precision": 0.1926202507117411, |
| "eval_recall": 0.3056332556332556, |
| "eval_runtime": 0.1094, |
| "eval_samples_per_second": 1827.484, |
| "eval_steps_per_second": 9.137, |
| "step": 1300 |
| }, |
| { |
| "epoch": 662.5, |
| "learning_rate": 1.735e-05, |
| "loss": 0.7629, |
| "step": 1325 |
| }, |
| { |
| "epoch": 662.5, |
| "eval_accuracy": 0.565, |
| "eval_f1": 0.21500476705443203, |
| "eval_loss": 1.3498928546905518, |
| "eval_precision": 0.19209877448767718, |
| "eval_recall": 0.3056332556332556, |
| "eval_runtime": 0.1096, |
| "eval_samples_per_second": 1824.082, |
| "eval_steps_per_second": 9.12, |
| "step": 1325 |
| }, |
| { |
| "epoch": 675.0, |
| "learning_rate": 1.73e-05, |
| "loss": 0.7761, |
| "step": 1350 |
| }, |
| { |
| "epoch": 675.0, |
| "eval_accuracy": 0.565, |
| "eval_f1": 0.2152166394940961, |
| "eval_loss": 1.3434274196624756, |
| "eval_precision": 0.1926202507117411, |
| "eval_recall": 0.3056332556332556, |
| "eval_runtime": 0.1091, |
| "eval_samples_per_second": 1833.656, |
| "eval_steps_per_second": 9.168, |
| "step": 1350 |
| }, |
| { |
| "epoch": 687.5, |
| "learning_rate": 1.7250000000000003e-05, |
| "loss": 0.7407, |
| "step": 1375 |
| }, |
| { |
| "epoch": 687.5, |
| "eval_accuracy": 0.565, |
| "eval_f1": 0.24286010713756379, |
| "eval_loss": 1.3476942777633667, |
| "eval_precision": 0.2934414689671699, |
| "eval_recall": 0.3217871017871018, |
| "eval_runtime": 0.1103, |
| "eval_samples_per_second": 1813.859, |
| "eval_steps_per_second": 9.069, |
| "step": 1375 |
| }, |
| { |
| "epoch": 700.0, |
| "learning_rate": 1.72e-05, |
| "loss": 0.7352, |
| "step": 1400 |
| }, |
| { |
| "epoch": 700.0, |
| "eval_accuracy": 0.56, |
| "eval_f1": 0.20853009606336664, |
| "eval_loss": 1.3470566272735596, |
| "eval_precision": 0.1901326454377581, |
| "eval_recall": 0.3017871017871018, |
| "eval_runtime": 0.1093, |
| "eval_samples_per_second": 1830.259, |
| "eval_steps_per_second": 9.151, |
| "step": 1400 |
| }, |
| { |
| "epoch": 712.5, |
| "learning_rate": 1.7150000000000004e-05, |
| "loss": 0.7218, |
| "step": 1425 |
| }, |
| { |
| "epoch": 712.5, |
| "eval_accuracy": 0.565, |
| "eval_f1": 0.21402893830639497, |
| "eval_loss": 1.3459302186965942, |
| "eval_precision": 0.19402907580477674, |
| "eval_recall": 0.3056332556332556, |
| "eval_runtime": 0.1094, |
| "eval_samples_per_second": 1827.436, |
| "eval_steps_per_second": 9.137, |
| "step": 1425 |
| }, |
| { |
| "epoch": 725.0, |
| "learning_rate": 1.7100000000000002e-05, |
| "loss": 0.7367, |
| "step": 1450 |
| }, |
| { |
| "epoch": 725.0, |
| "eval_accuracy": 0.57, |
| "eval_f1": 0.2180585228441659, |
| "eval_loss": 1.3345229625701904, |
| "eval_precision": 0.19691717273954118, |
| "eval_recall": 0.30947940947940944, |
| "eval_runtime": 0.1156, |
| "eval_samples_per_second": 1730.802, |
| "eval_steps_per_second": 8.654, |
| "step": 1450 |
| }, |
| { |
| "epoch": 737.5, |
| "learning_rate": 1.705e-05, |
| "loss": 0.6962, |
| "step": 1475 |
| }, |
| { |
| "epoch": 737.5, |
| "eval_accuracy": 0.57, |
| "eval_f1": 0.21826103720840564, |
| "eval_loss": 1.3321415185928345, |
| "eval_precision": 0.1974185463659148, |
| "eval_recall": 0.30947940947940944, |
| "eval_runtime": 0.113, |
| "eval_samples_per_second": 1770.171, |
| "eval_steps_per_second": 8.851, |
| "step": 1475 |
| }, |
| { |
| "epoch": 750.0, |
| "learning_rate": 1.7e-05, |
| "loss": 0.7072, |
| "step": 1500 |
| }, |
| { |
| "epoch": 750.0, |
| "eval_accuracy": 0.565, |
| "eval_f1": 0.21296938641440022, |
| "eval_loss": 1.3314956426620483, |
| "eval_precision": 0.19549352215487065, |
| "eval_recall": 0.3056332556332556, |
| "eval_runtime": 0.1151, |
| "eval_samples_per_second": 1737.178, |
| "eval_steps_per_second": 8.686, |
| "step": 1500 |
| }, |
| { |
| "epoch": 762.5, |
| "learning_rate": 1.6950000000000002e-05, |
| "loss": 0.6969, |
| "step": 1525 |
| }, |
| { |
| "epoch": 762.5, |
| "eval_accuracy": 0.57, |
| "eval_f1": 0.2478113362502301, |
| "eval_loss": 1.32610285282135, |
| "eval_precision": 0.2997000915750916, |
| "eval_recall": 0.3256332556332556, |
| "eval_runtime": 0.1099, |
| "eval_samples_per_second": 1819.678, |
| "eval_steps_per_second": 9.098, |
| "step": 1525 |
| }, |
| { |
| "epoch": 775.0, |
| "learning_rate": 1.69e-05, |
| "loss": 0.6914, |
| "step": 1550 |
| }, |
| { |
| "epoch": 775.0, |
| "eval_accuracy": 0.57, |
| "eval_f1": 0.2478113362502301, |
| "eval_loss": 1.3198169469833374, |
| "eval_precision": 0.2997000915750916, |
| "eval_recall": 0.3256332556332556, |
| "eval_runtime": 0.1088, |
| "eval_samples_per_second": 1837.87, |
| "eval_steps_per_second": 9.189, |
| "step": 1550 |
| }, |
| { |
| "epoch": 787.5, |
| "learning_rate": 1.6850000000000003e-05, |
| "loss": 0.6931, |
| "step": 1575 |
| }, |
| { |
| "epoch": 787.5, |
| "eval_accuracy": 0.58, |
| "eval_f1": 0.2542068800764453, |
| "eval_loss": 1.3169305324554443, |
| "eval_precision": 0.299894419306184, |
| "eval_recall": 0.3333255633255633, |
| "eval_runtime": 0.1155, |
| "eval_samples_per_second": 1731.688, |
| "eval_steps_per_second": 8.658, |
| "step": 1575 |
| }, |
| { |
| "epoch": 800.0, |
| "learning_rate": 1.6800000000000002e-05, |
| "loss": 0.6557, |
| "step": 1600 |
| }, |
| { |
| "epoch": 800.0, |
| "eval_accuracy": 0.575, |
| "eval_f1": 0.2517609960815229, |
| "eval_loss": 1.3166579008102417, |
| "eval_precision": 0.30244626696832577, |
| "eval_recall": 0.32947940947940946, |
| "eval_runtime": 0.1302, |
| "eval_samples_per_second": 1535.948, |
| "eval_steps_per_second": 7.68, |
| "step": 1600 |
| }, |
| { |
| "epoch": 812.5, |
| "learning_rate": 1.675e-05, |
| "loss": 0.6566, |
| "step": 1625 |
| }, |
| { |
| "epoch": 812.5, |
| "eval_accuracy": 0.58, |
| "eval_f1": 0.2562470211231619, |
| "eval_loss": 1.3132545948028564, |
| "eval_precision": 0.302731114801567, |
| "eval_recall": 0.3333255633255633, |
| "eval_runtime": 0.1166, |
| "eval_samples_per_second": 1715.981, |
| "eval_steps_per_second": 8.58, |
| "step": 1625 |
| }, |
| { |
| "epoch": 825.0, |
| "learning_rate": 1.67e-05, |
| "loss": 0.6422, |
| "step": 1650 |
| }, |
| { |
| "epoch": 825.0, |
| "eval_accuracy": 0.585, |
| "eval_f1": 0.2608462489547957, |
| "eval_loss": 1.3107500076293945, |
| "eval_precision": 0.30355471734148204, |
| "eval_recall": 0.3371717171717171, |
| "eval_runtime": 0.1098, |
| "eval_samples_per_second": 1820.895, |
| "eval_steps_per_second": 9.104, |
| "step": 1650 |
| }, |
| { |
| "epoch": 837.5, |
| "learning_rate": 1.665e-05, |
| "loss": 0.6384, |
| "step": 1675 |
| }, |
| { |
| "epoch": 837.5, |
| "eval_accuracy": 0.575, |
| "eval_f1": 0.2517609960815229, |
| "eval_loss": 1.3102846145629883, |
| "eval_precision": 0.30244626696832577, |
| "eval_recall": 0.32947940947940946, |
| "eval_runtime": 0.1105, |
| "eval_samples_per_second": 1809.165, |
| "eval_steps_per_second": 9.046, |
| "step": 1675 |
| }, |
| { |
| "epoch": 850.0, |
| "learning_rate": 1.66e-05, |
| "loss": 0.6504, |
| "step": 1700 |
| }, |
| { |
| "epoch": 850.0, |
| "eval_accuracy": 0.58, |
| "eval_f1": 0.2547578692493947, |
| "eval_loss": 1.303167462348938, |
| "eval_precision": 0.30201064737635946, |
| "eval_recall": 0.3333255633255633, |
| "eval_runtime": 0.1154, |
| "eval_samples_per_second": 1733.531, |
| "eval_steps_per_second": 8.668, |
| "step": 1700 |
| }, |
| { |
| "epoch": 862.5, |
| "learning_rate": 1.6550000000000002e-05, |
| "loss": 0.6137, |
| "step": 1725 |
| }, |
| { |
| "epoch": 862.5, |
| "eval_accuracy": 0.575, |
| "eval_f1": 0.2517609960815229, |
| "eval_loss": 1.303627371788025, |
| "eval_precision": 0.30244626696832577, |
| "eval_recall": 0.32947940947940946, |
| "eval_runtime": 0.1101, |
| "eval_samples_per_second": 1817.258, |
| "eval_steps_per_second": 9.086, |
| "step": 1725 |
| }, |
| { |
| "epoch": 875.0, |
| "learning_rate": 1.65e-05, |
| "loss": 0.6172, |
| "step": 1750 |
| }, |
| { |
| "epoch": 875.0, |
| "eval_accuracy": 0.58, |
| "eval_f1": 0.2504165518841252, |
| "eval_loss": 1.2991704940795898, |
| "eval_precision": 0.2525833517056159, |
| "eval_recall": 0.3333255633255633, |
| "eval_runtime": 0.1222, |
| "eval_samples_per_second": 1636.335, |
| "eval_steps_per_second": 8.182, |
| "step": 1750 |
| }, |
| { |
| "epoch": 887.5, |
| "learning_rate": 1.645e-05, |
| "loss": 0.6178, |
| "step": 1775 |
| }, |
| { |
| "epoch": 887.5, |
| "eval_accuracy": 0.58, |
| "eval_f1": 0.2547578692493947, |
| "eval_loss": 1.3013752698898315, |
| "eval_precision": 0.30201064737635946, |
| "eval_recall": 0.3333255633255633, |
| "eval_runtime": 0.1275, |
| "eval_samples_per_second": 1568.888, |
| "eval_steps_per_second": 7.844, |
| "step": 1775 |
| }, |
| { |
| "epoch": 900.0, |
| "learning_rate": 1.64e-05, |
| "loss": 0.5967, |
| "step": 1800 |
| }, |
| { |
| "epoch": 900.0, |
| "eval_accuracy": 0.58, |
| "eval_f1": 0.2547578692493947, |
| "eval_loss": 1.3014745712280273, |
| "eval_precision": 0.30201064737635946, |
| "eval_recall": 0.3333255633255633, |
| "eval_runtime": 0.1102, |
| "eval_samples_per_second": 1815.59, |
| "eval_steps_per_second": 9.078, |
| "step": 1800 |
| }, |
| { |
| "epoch": 912.5, |
| "learning_rate": 1.635e-05, |
| "loss": 0.6192, |
| "step": 1825 |
| }, |
| { |
| "epoch": 912.5, |
| "eval_accuracy": 0.59, |
| "eval_f1": 0.2532499208108964, |
| "eval_loss": 1.2941592931747437, |
| "eval_precision": 0.25441823354515536, |
| "eval_recall": 0.33702926702926705, |
| "eval_runtime": 0.1095, |
| "eval_samples_per_second": 1827.042, |
| "eval_steps_per_second": 9.135, |
| "step": 1825 |
| }, |
| { |
| "epoch": 925.0, |
| "learning_rate": 1.63e-05, |
| "loss": 0.6046, |
| "step": 1850 |
| }, |
| { |
| "epoch": 925.0, |
| "eval_accuracy": 0.58, |
| "eval_f1": 0.2504165518841252, |
| "eval_loss": 1.29150390625, |
| "eval_precision": 0.2525833517056159, |
| "eval_recall": 0.3333255633255633, |
| "eval_runtime": 0.1315, |
| "eval_samples_per_second": 1520.877, |
| "eval_steps_per_second": 7.604, |
| "step": 1850 |
| }, |
| { |
| "epoch": 937.5, |
| "learning_rate": 1.6250000000000002e-05, |
| "loss": 0.5819, |
| "step": 1875 |
| }, |
| { |
| "epoch": 937.5, |
| "eval_accuracy": 0.59, |
| "eval_f1": 0.2532499208108964, |
| "eval_loss": 1.2836596965789795, |
| "eval_precision": 0.25441823354515536, |
| "eval_recall": 0.33702926702926705, |
| "eval_runtime": 0.1096, |
| "eval_samples_per_second": 1824.158, |
| "eval_steps_per_second": 9.121, |
| "step": 1875 |
| }, |
| { |
| "epoch": 950.0, |
| "learning_rate": 1.62e-05, |
| "loss": 0.575, |
| "step": 1900 |
| }, |
| { |
| "epoch": 950.0, |
| "eval_accuracy": 0.585, |
| "eval_f1": 0.2762730207645462, |
| "eval_loss": 1.2920979261398315, |
| "eval_precision": 0.3037634697174171, |
| "eval_recall": 0.34999222999222995, |
| "eval_runtime": 0.109, |
| "eval_samples_per_second": 1834.101, |
| "eval_steps_per_second": 9.171, |
| "step": 1900 |
| }, |
| { |
| "epoch": 962.5, |
| "learning_rate": 1.6150000000000003e-05, |
| "loss": 0.5715, |
| "step": 1925 |
| }, |
| { |
| "epoch": 962.5, |
| "eval_accuracy": 0.59, |
| "eval_f1": 0.2777915556466489, |
| "eval_loss": 1.2907838821411133, |
| "eval_precision": 0.3049004379079567, |
| "eval_recall": 0.3518440818440819, |
| "eval_runtime": 0.1103, |
| "eval_samples_per_second": 1813.044, |
| "eval_steps_per_second": 9.065, |
| "step": 1925 |
| }, |
| { |
| "epoch": 975.0, |
| "learning_rate": 1.6100000000000002e-05, |
| "loss": 0.5698, |
| "step": 1950 |
| }, |
| { |
| "epoch": 975.0, |
| "eval_accuracy": 0.59, |
| "eval_f1": 0.27914934563073396, |
| "eval_loss": 1.2832599878311157, |
| "eval_precision": 0.3040582482993197, |
| "eval_recall": 0.3518440818440819, |
| "eval_runtime": 0.1106, |
| "eval_samples_per_second": 1808.864, |
| "eval_steps_per_second": 9.044, |
| "step": 1950 |
| }, |
| { |
| "epoch": 987.5, |
| "learning_rate": 1.605e-05, |
| "loss": 0.5578, |
| "step": 1975 |
| }, |
| { |
| "epoch": 987.5, |
| "eval_accuracy": 0.585, |
| "eval_f1": 0.2762730207645462, |
| "eval_loss": 1.283950686454773, |
| "eval_precision": 0.3037634697174171, |
| "eval_recall": 0.34999222999222995, |
| "eval_runtime": 0.1107, |
| "eval_samples_per_second": 1806.986, |
| "eval_steps_per_second": 9.035, |
| "step": 1975 |
| }, |
| { |
| "epoch": 1000.0, |
| "learning_rate": 1.6000000000000003e-05, |
| "loss": 0.5468, |
| "step": 2000 |
| }, |
| { |
| "epoch": 1000.0, |
| "eval_accuracy": 0.595, |
| "eval_f1": 0.2995061728395062, |
| "eval_loss": 1.2839480638504028, |
| "eval_precision": 0.3218190252729726, |
| "eval_recall": 0.37184408184408185, |
| "eval_runtime": 0.1101, |
| "eval_samples_per_second": 1817.289, |
| "eval_steps_per_second": 9.086, |
| "step": 2000 |
| }, |
| { |
| "epoch": 1012.5, |
| "learning_rate": 1.595e-05, |
| "loss": 0.5584, |
| "step": 2025 |
| }, |
| { |
| "epoch": 1012.5, |
| "eval_accuracy": 0.585, |
| "eval_f1": 0.2788626459972715, |
| "eval_loss": 1.283686637878418, |
| "eval_precision": 0.351051282051282, |
| "eval_recall": 0.34999222999222995, |
| "eval_runtime": 0.1104, |
| "eval_samples_per_second": 1811.763, |
| "eval_steps_per_second": 9.059, |
| "step": 2025 |
| }, |
| { |
| "epoch": 1025.0, |
| "learning_rate": 1.5900000000000004e-05, |
| "loss": 0.5448, |
| "step": 2050 |
| }, |
| { |
| "epoch": 1025.0, |
| "eval_accuracy": 0.59, |
| "eval_f1": 0.29649185854859617, |
| "eval_loss": 1.2762924432754517, |
| "eval_precision": 0.3019345238095238, |
| "eval_recall": 0.36999222999222997, |
| "eval_runtime": 0.127, |
| "eval_samples_per_second": 1575.115, |
| "eval_steps_per_second": 7.876, |
| "step": 2050 |
| }, |
| { |
| "epoch": 1037.5, |
| "learning_rate": 1.5850000000000002e-05, |
| "loss": 0.5269, |
| "step": 2075 |
| }, |
| { |
| "epoch": 1037.5, |
| "eval_accuracy": 0.595, |
| "eval_f1": 0.30101933558392, |
| "eval_loss": 1.280715823173523, |
| "eval_precision": 0.32134557560137456, |
| "eval_recall": 0.37184408184408185, |
| "eval_runtime": 0.1328, |
| "eval_samples_per_second": 1506.32, |
| "eval_steps_per_second": 7.532, |
| "step": 2075 |
| }, |
| { |
| "epoch": 1050.0, |
| "learning_rate": 1.58e-05, |
| "loss": 0.549, |
| "step": 2100 |
| }, |
| { |
| "epoch": 1050.0, |
| "eval_accuracy": 0.59, |
| "eval_f1": 0.29649185854859617, |
| "eval_loss": 1.276688575744629, |
| "eval_precision": 0.3019345238095238, |
| "eval_recall": 0.36999222999222997, |
| "eval_runtime": 0.1234, |
| "eval_samples_per_second": 1620.705, |
| "eval_steps_per_second": 8.104, |
| "step": 2100 |
| }, |
| { |
| "epoch": 1062.5, |
| "learning_rate": 1.575e-05, |
| "loss": 0.5262, |
| "step": 2125 |
| }, |
| { |
| "epoch": 1062.5, |
| "eval_accuracy": 0.59, |
| "eval_f1": 0.29715507366881067, |
| "eval_loss": 1.2787173986434937, |
| "eval_precision": 0.3041580756013746, |
| "eval_recall": 0.36999222999222997, |
| "eval_runtime": 0.1106, |
| "eval_samples_per_second": 1807.512, |
| "eval_steps_per_second": 9.038, |
| "step": 2125 |
| }, |
| { |
| "epoch": 1075.0, |
| "learning_rate": 1.5700000000000002e-05, |
| "loss": 0.5263, |
| "step": 2150 |
| }, |
| { |
| "epoch": 1075.0, |
| "eval_accuracy": 0.59, |
| "eval_f1": 0.2944310848199276, |
| "eval_loss": 1.2766177654266357, |
| "eval_precision": 0.3002577356853673, |
| "eval_recall": 0.36999222999222997, |
| "eval_runtime": 0.1091, |
| "eval_samples_per_second": 1832.458, |
| "eval_steps_per_second": 9.162, |
| "step": 2150 |
| }, |
| { |
| "epoch": 1087.5, |
| "learning_rate": 1.565e-05, |
| "loss": 0.5181, |
| "step": 2175 |
| }, |
| { |
| "epoch": 1087.5, |
| "eval_accuracy": 0.6, |
| "eval_f1": 0.30507075081227625, |
| "eval_loss": 1.2711414098739624, |
| "eval_precision": 0.307442340846018, |
| "eval_recall": 0.37768453768453764, |
| "eval_runtime": 0.1096, |
| "eval_samples_per_second": 1825.158, |
| "eval_steps_per_second": 9.126, |
| "step": 2175 |
| }, |
| { |
| "epoch": 1100.0, |
| "learning_rate": 1.5600000000000003e-05, |
| "loss": 0.491, |
| "step": 2200 |
| }, |
| { |
| "epoch": 1100.0, |
| "eval_accuracy": 0.59, |
| "eval_f1": 0.2985336489224917, |
| "eval_loss": 1.2738006114959717, |
| "eval_precision": 0.3030549384825701, |
| "eval_recall": 0.36999222999222997, |
| "eval_runtime": 0.1087, |
| "eval_samples_per_second": 1840.293, |
| "eval_steps_per_second": 9.201, |
| "step": 2200 |
| }, |
| { |
| "epoch": 1112.5, |
| "learning_rate": 1.5550000000000002e-05, |
| "loss": 0.4932, |
| "step": 2225 |
| }, |
| { |
| "epoch": 1112.5, |
| "eval_accuracy": 0.59, |
| "eval_f1": 0.29964373217873586, |
| "eval_loss": 1.2712461948394775, |
| "eval_precision": 0.305912081339713, |
| "eval_recall": 0.36999222999222997, |
| "eval_runtime": 0.1303, |
| "eval_samples_per_second": 1534.95, |
| "eval_steps_per_second": 7.675, |
| "step": 2225 |
| }, |
| { |
| "epoch": 1125.0, |
| "learning_rate": 1.55e-05, |
| "loss": 0.4929, |
| "step": 2250 |
| }, |
| { |
| "epoch": 1125.0, |
| "eval_accuracy": 0.595, |
| "eval_f1": 0.3010492404077871, |
| "eval_loss": 1.2729893922805786, |
| "eval_precision": 0.3069623860182371, |
| "eval_recall": 0.3738383838383838, |
| "eval_runtime": 0.1331, |
| "eval_samples_per_second": 1502.909, |
| "eval_steps_per_second": 7.515, |
| "step": 2250 |
| }, |
| { |
| "epoch": 1137.5, |
| "learning_rate": 1.545e-05, |
| "loss": 0.4922, |
| "step": 2275 |
| }, |
| { |
| "epoch": 1137.5, |
| "eval_accuracy": 0.595, |
| "eval_f1": 0.3010492404077871, |
| "eval_loss": 1.2685459852218628, |
| "eval_precision": 0.3069623860182371, |
| "eval_recall": 0.3738383838383838, |
| "eval_runtime": 0.1097, |
| "eval_samples_per_second": 1822.881, |
| "eval_steps_per_second": 9.114, |
| "step": 2275 |
| }, |
| { |
| "epoch": 1150.0, |
| "learning_rate": 1.54e-05, |
| "loss": 0.472, |
| "step": 2300 |
| }, |
| { |
| "epoch": 1150.0, |
| "eval_accuracy": 0.59, |
| "eval_f1": 0.30051229615646796, |
| "eval_loss": 1.2717591524124146, |
| "eval_precision": 0.3088311218533682, |
| "eval_recall": 0.36999222999222997, |
| "eval_runtime": 0.1097, |
| "eval_samples_per_second": 1822.64, |
| "eval_steps_per_second": 9.113, |
| "step": 2300 |
| }, |
| { |
| "epoch": 1162.5, |
| "learning_rate": 1.535e-05, |
| "loss": 0.4734, |
| "step": 2325 |
| }, |
| { |
| "epoch": 1162.5, |
| "eval_accuracy": 0.595, |
| "eval_f1": 0.30324704260558927, |
| "eval_loss": 1.2703065872192383, |
| "eval_precision": 0.3084775375333886, |
| "eval_recall": 0.3738383838383838, |
| "eval_runtime": 0.1097, |
| "eval_samples_per_second": 1822.731, |
| "eval_steps_per_second": 9.114, |
| "step": 2325 |
| }, |
| { |
| "epoch": 1175.0, |
| "learning_rate": 1.5300000000000003e-05, |
| "loss": 0.4736, |
| "step": 2350 |
| }, |
| { |
| "epoch": 1175.0, |
| "eval_accuracy": 0.595, |
| "eval_f1": 0.30324704260558927, |
| "eval_loss": 1.2648420333862305, |
| "eval_precision": 0.3084775375333886, |
| "eval_recall": 0.3738383838383838, |
| "eval_runtime": 0.1099, |
| "eval_samples_per_second": 1820.227, |
| "eval_steps_per_second": 9.101, |
| "step": 2350 |
| }, |
| { |
| "epoch": 1187.5, |
| "learning_rate": 1.525e-05, |
| "loss": 0.4553, |
| "step": 2375 |
| }, |
| { |
| "epoch": 1187.5, |
| "eval_accuracy": 0.59, |
| "eval_f1": 0.29891747807414976, |
| "eval_loss": 1.2696685791015625, |
| "eval_precision": 0.29717368935535315, |
| "eval_recall": 0.371986531986532, |
| "eval_runtime": 0.1097, |
| "eval_samples_per_second": 1822.727, |
| "eval_steps_per_second": 9.114, |
| "step": 2375 |
| }, |
| { |
| "epoch": 1200.0, |
| "learning_rate": 1.5200000000000002e-05, |
| "loss": 0.4576, |
| "step": 2400 |
| }, |
| { |
| "epoch": 1200.0, |
| "eval_accuracy": 0.595, |
| "eval_f1": 0.30324704260558927, |
| "eval_loss": 1.265201210975647, |
| "eval_precision": 0.3084775375333886, |
| "eval_recall": 0.3738383838383838, |
| "eval_runtime": 0.1093, |
| "eval_samples_per_second": 1829.832, |
| "eval_steps_per_second": 9.149, |
| "step": 2400 |
| }, |
| { |
| "epoch": 1212.5, |
| "learning_rate": 1.515e-05, |
| "loss": 0.4643, |
| "step": 2425 |
| }, |
| { |
| "epoch": 1212.5, |
| "eval_accuracy": 0.595, |
| "eval_f1": 0.30324704260558927, |
| "eval_loss": 1.264267921447754, |
| "eval_precision": 0.3084775375333886, |
| "eval_recall": 0.3738383838383838, |
| "eval_runtime": 0.1098, |
| "eval_samples_per_second": 1821.532, |
| "eval_steps_per_second": 9.108, |
| "step": 2425 |
| }, |
| { |
| "epoch": 1225.0, |
| "learning_rate": 1.5100000000000001e-05, |
| "loss": 0.4541, |
| "step": 2450 |
| }, |
| { |
| "epoch": 1225.0, |
| "eval_accuracy": 0.585, |
| "eval_f1": 0.29912982463363835, |
| "eval_loss": 1.263696312904358, |
| "eval_precision": 0.2991982032304613, |
| "eval_recall": 0.37047138047138045, |
| "eval_runtime": 0.1094, |
| "eval_samples_per_second": 1827.874, |
| "eval_steps_per_second": 9.139, |
| "step": 2450 |
| }, |
| { |
| "epoch": 1237.5, |
| "learning_rate": 1.505e-05, |
| "loss": 0.4488, |
| "step": 2475 |
| }, |
| { |
| "epoch": 1237.5, |
| "eval_accuracy": 0.59, |
| "eval_f1": 0.29992384979087106, |
| "eval_loss": 1.2690153121948242, |
| "eval_precision": 0.29959856927942036, |
| "eval_recall": 0.371986531986532, |
| "eval_runtime": 0.1409, |
| "eval_samples_per_second": 1419.923, |
| "eval_steps_per_second": 7.1, |
| "step": 2475 |
| }, |
| { |
| "epoch": 1250.0, |
| "learning_rate": 1.5000000000000002e-05, |
| "loss": 0.4395, |
| "step": 2500 |
| }, |
| { |
| "epoch": 1250.0, |
| "eval_accuracy": 0.59, |
| "eval_f1": 0.3000699603436533, |
| "eval_loss": 1.2683618068695068, |
| "eval_precision": 0.29998754216920603, |
| "eval_recall": 0.371986531986532, |
| "eval_runtime": 0.1104, |
| "eval_samples_per_second": 1812.045, |
| "eval_steps_per_second": 9.06, |
| "step": 2500 |
| }, |
| { |
| "epoch": 1262.5, |
| "learning_rate": 1.4950000000000003e-05, |
| "loss": 0.4448, |
| "step": 2525 |
| }, |
| { |
| "epoch": 1262.5, |
| "eval_accuracy": 0.585, |
| "eval_f1": 0.2984390890403549, |
| "eval_loss": 1.259466290473938, |
| "eval_precision": 0.2970622372796286, |
| "eval_recall": 0.37047138047138045, |
| "eval_runtime": 0.11, |
| "eval_samples_per_second": 1818.404, |
| "eval_steps_per_second": 9.092, |
| "step": 2525 |
| }, |
| { |
| "epoch": 1275.0, |
| "learning_rate": 1.4900000000000001e-05, |
| "loss": 0.4394, |
| "step": 2550 |
| }, |
| { |
| "epoch": 1275.0, |
| "eval_accuracy": 0.585, |
| "eval_f1": 0.29912982463363835, |
| "eval_loss": 1.2657842636108398, |
| "eval_precision": 0.2991982032304613, |
| "eval_recall": 0.37047138047138045, |
| "eval_runtime": 0.1098, |
| "eval_samples_per_second": 1821.654, |
| "eval_steps_per_second": 9.108, |
| "step": 2550 |
| }, |
| { |
| "epoch": 1287.5, |
| "learning_rate": 1.4850000000000002e-05, |
| "loss": 0.4352, |
| "step": 2575 |
| }, |
| { |
| "epoch": 1287.5, |
| "eval_accuracy": 0.585, |
| "eval_f1": 0.2973336468634842, |
| "eval_loss": 1.2618379592895508, |
| "eval_precision": 0.29449306731915426, |
| "eval_recall": 0.37047138047138045, |
| "eval_runtime": 0.136, |
| "eval_samples_per_second": 1470.512, |
| "eval_steps_per_second": 7.353, |
| "step": 2575 |
| }, |
| { |
| "epoch": 1300.0, |
| "learning_rate": 1.48e-05, |
| "loss": 0.4378, |
| "step": 2600 |
| }, |
| { |
| "epoch": 1300.0, |
| "eval_accuracy": 0.585, |
| "eval_f1": 0.2984390890403549, |
| "eval_loss": 1.2561547756195068, |
| "eval_precision": 0.2970622372796286, |
| "eval_recall": 0.37047138047138045, |
| "eval_runtime": 0.1097, |
| "eval_samples_per_second": 1822.957, |
| "eval_steps_per_second": 9.115, |
| "step": 2600 |
| }, |
| { |
| "epoch": 1312.5, |
| "learning_rate": 1.4750000000000003e-05, |
| "loss": 0.4343, |
| "step": 2625 |
| }, |
| { |
| "epoch": 1312.5, |
| "eval_accuracy": 0.585, |
| "eval_f1": 0.2984390890403549, |
| "eval_loss": 1.255575180053711, |
| "eval_precision": 0.2970622372796286, |
| "eval_recall": 0.37047138047138045, |
| "eval_runtime": 0.1172, |
| "eval_samples_per_second": 1706.156, |
| "eval_steps_per_second": 8.531, |
| "step": 2625 |
| }, |
| { |
| "epoch": 1325.0, |
| "learning_rate": 1.4700000000000002e-05, |
| "loss": 0.4199, |
| "step": 2650 |
| }, |
| { |
| "epoch": 1325.0, |
| "eval_accuracy": 0.59, |
| "eval_f1": 0.299235203999355, |
| "eval_loss": 1.2637606859207153, |
| "eval_precision": 0.29745961923381276, |
| "eval_recall": 0.371986531986532, |
| "eval_runtime": 0.1208, |
| "eval_samples_per_second": 1655.358, |
| "eval_steps_per_second": 8.277, |
| "step": 2650 |
| }, |
| { |
| "epoch": 1337.5, |
| "learning_rate": 1.4650000000000002e-05, |
| "loss": 0.4187, |
| "step": 2675 |
| }, |
| { |
| "epoch": 1337.5, |
| "eval_accuracy": 0.585, |
| "eval_f1": 0.2973937691120562, |
| "eval_loss": 1.260729193687439, |
| "eval_precision": 0.2983609385783299, |
| "eval_recall": 0.37047138047138045, |
| "eval_runtime": 0.1093, |
| "eval_samples_per_second": 1830.139, |
| "eval_steps_per_second": 9.151, |
| "step": 2675 |
| }, |
| { |
| "epoch": 1350.0, |
| "learning_rate": 1.46e-05, |
| "loss": 0.3977, |
| "step": 2700 |
| }, |
| { |
| "epoch": 1350.0, |
| "eval_accuracy": 0.59, |
| "eval_f1": 0.2981898840710563, |
| "eval_loss": 1.2641257047653198, |
| "eval_precision": 0.29875832053251405, |
| "eval_recall": 0.371986531986532, |
| "eval_runtime": 0.1094, |
| "eval_samples_per_second": 1828.536, |
| "eval_steps_per_second": 9.143, |
| "step": 2700 |
| }, |
| { |
| "epoch": 1362.5, |
| "learning_rate": 1.4550000000000001e-05, |
| "loss": 0.409, |
| "step": 2725 |
| }, |
| { |
| "epoch": 1362.5, |
| "eval_accuracy": 0.585, |
| "eval_f1": 0.2984390890403549, |
| "eval_loss": 1.2626018524169922, |
| "eval_precision": 0.2970622372796286, |
| "eval_recall": 0.37047138047138045, |
| "eval_runtime": 0.1105, |
| "eval_samples_per_second": 1810.516, |
| "eval_steps_per_second": 9.053, |
| "step": 2725 |
| }, |
| { |
| "epoch": 1375.0, |
| "learning_rate": 1.45e-05, |
| "loss": 0.4106, |
| "step": 2750 |
| }, |
| { |
| "epoch": 1375.0, |
| "eval_accuracy": 0.59, |
| "eval_f1": 0.3093365249377908, |
| "eval_loss": 1.2577816247940063, |
| "eval_precision": 0.31554708576447704, |
| "eval_recall": 0.37602693602693604, |
| "eval_runtime": 0.1092, |
| "eval_samples_per_second": 1830.994, |
| "eval_steps_per_second": 9.155, |
| "step": 2750 |
| }, |
| { |
| "epoch": 1387.5, |
| "learning_rate": 1.4450000000000002e-05, |
| "loss": 0.4044, |
| "step": 2775 |
| }, |
| { |
| "epoch": 1387.5, |
| "eval_accuracy": 0.585, |
| "eval_f1": 0.30590035472502486, |
| "eval_loss": 1.2530498504638672, |
| "eval_precision": 0.3112180814354727, |
| "eval_recall": 0.3721807821807822, |
| "eval_runtime": 0.1106, |
| "eval_samples_per_second": 1808.693, |
| "eval_steps_per_second": 9.043, |
| "step": 2775 |
| }, |
| { |
| "epoch": 1400.0, |
| "learning_rate": 1.4400000000000001e-05, |
| "loss": 0.4062, |
| "step": 2800 |
| }, |
| { |
| "epoch": 1400.0, |
| "eval_accuracy": 0.59, |
| "eval_f1": 0.3093365249377908, |
| "eval_loss": 1.255041480064392, |
| "eval_precision": 0.31554708576447704, |
| "eval_recall": 0.37602693602693604, |
| "eval_runtime": 0.1087, |
| "eval_samples_per_second": 1839.74, |
| "eval_steps_per_second": 9.199, |
| "step": 2800 |
| }, |
| { |
| "epoch": 1412.5, |
| "learning_rate": 1.4350000000000002e-05, |
| "loss": 0.3867, |
| "step": 2825 |
| }, |
| { |
| "epoch": 1412.5, |
| "eval_accuracy": 0.595, |
| "eval_f1": 0.34818573128699715, |
| "eval_loss": 1.2607990503311157, |
| "eval_precision": 0.4215438959718136, |
| "eval_recall": 0.401026936026936, |
| "eval_runtime": 0.11, |
| "eval_samples_per_second": 1818.877, |
| "eval_steps_per_second": 9.094, |
| "step": 2825 |
| }, |
| { |
| "epoch": 1425.0, |
| "learning_rate": 1.43e-05, |
| "loss": 0.3963, |
| "step": 2850 |
| }, |
| { |
| "epoch": 1425.0, |
| "eval_accuracy": 0.59, |
| "eval_f1": 0.34100319160445747, |
| "eval_loss": 1.2606894969940186, |
| "eval_precision": 0.39888041909781036, |
| "eval_recall": 0.3954713804713804, |
| "eval_runtime": 0.1109, |
| "eval_samples_per_second": 1803.075, |
| "eval_steps_per_second": 9.015, |
| "step": 2850 |
| }, |
| { |
| "epoch": 1437.5, |
| "learning_rate": 1.425e-05, |
| "loss": 0.3911, |
| "step": 2875 |
| }, |
| { |
| "epoch": 1437.5, |
| "eval_accuracy": 0.59, |
| "eval_f1": 0.3456057557070215, |
| "eval_loss": 1.2616832256317139, |
| "eval_precision": 0.41541493721127587, |
| "eval_recall": 0.3971807821807822, |
| "eval_runtime": 0.1097, |
| "eval_samples_per_second": 1823.9, |
| "eval_steps_per_second": 9.119, |
| "step": 2875 |
| }, |
| { |
| "epoch": 1450.0, |
| "learning_rate": 1.4200000000000001e-05, |
| "loss": 0.3873, |
| "step": 2900 |
| }, |
| { |
| "epoch": 1450.0, |
| "eval_accuracy": 0.59, |
| "eval_f1": 0.34100319160445747, |
| "eval_loss": 1.2619085311889648, |
| "eval_precision": 0.39888041909781036, |
| "eval_recall": 0.3954713804713804, |
| "eval_runtime": 0.1101, |
| "eval_samples_per_second": 1816.101, |
| "eval_steps_per_second": 9.081, |
| "step": 2900 |
| }, |
| { |
| "epoch": 1462.5, |
| "learning_rate": 1.4150000000000002e-05, |
| "loss": 0.3842, |
| "step": 2925 |
| }, |
| { |
| "epoch": 1462.5, |
| "eval_accuracy": 0.595, |
| "eval_f1": 0.35048900720729437, |
| "eval_loss": 1.2598904371261597, |
| "eval_precision": 0.4183609385783299, |
| "eval_recall": 0.401026936026936, |
| "eval_runtime": 0.1096, |
| "eval_samples_per_second": 1824.789, |
| "eval_steps_per_second": 9.124, |
| "step": 2925 |
| }, |
| { |
| "epoch": 1475.0, |
| "learning_rate": 1.41e-05, |
| "loss": 0.3739, |
| "step": 2950 |
| }, |
| { |
| "epoch": 1475.0, |
| "eval_accuracy": 0.595, |
| "eval_f1": 0.35048900720729437, |
| "eval_loss": 1.2582826614379883, |
| "eval_precision": 0.4183609385783299, |
| "eval_recall": 0.401026936026936, |
| "eval_runtime": 0.1161, |
| "eval_samples_per_second": 1722.284, |
| "eval_steps_per_second": 8.611, |
| "step": 2950 |
| }, |
| { |
| "epoch": 1487.5, |
| "learning_rate": 1.4050000000000001e-05, |
| "loss": 0.3728, |
| "step": 2975 |
| }, |
| { |
| "epoch": 1487.5, |
| "eval_accuracy": 0.59, |
| "eval_f1": 0.34701043798126907, |
| "eval_loss": 1.2598789930343628, |
| "eval_precision": 0.4140752242926157, |
| "eval_recall": 0.3971807821807822, |
| "eval_runtime": 0.1109, |
| "eval_samples_per_second": 1804.11, |
| "eval_steps_per_second": 9.021, |
| "step": 2975 |
| }, |
| { |
| "epoch": 1500.0, |
| "learning_rate": 1.4e-05, |
| "loss": 0.3717, |
| "step": 3000 |
| }, |
| { |
| "epoch": 1500.0, |
| "eval_accuracy": 0.59, |
| "eval_f1": 0.3456057557070215, |
| "eval_loss": 1.2592926025390625, |
| "eval_precision": 0.41541493721127587, |
| "eval_recall": 0.3971807821807822, |
| "eval_runtime": 0.1089, |
| "eval_samples_per_second": 1837.29, |
| "eval_steps_per_second": 9.186, |
| "step": 3000 |
| }, |
| { |
| "epoch": 1512.5, |
| "learning_rate": 1.3950000000000002e-05, |
| "loss": 0.3732, |
| "step": 3025 |
| }, |
| { |
| "epoch": 1512.5, |
| "eval_accuracy": 0.59, |
| "eval_f1": 0.3456057557070215, |
| "eval_loss": 1.2535885572433472, |
| "eval_precision": 0.41541493721127587, |
| "eval_recall": 0.3971807821807822, |
| "eval_runtime": 0.1093, |
| "eval_samples_per_second": 1829.521, |
| "eval_steps_per_second": 9.148, |
| "step": 3025 |
| }, |
| { |
| "epoch": 1525.0, |
| "learning_rate": 1.39e-05, |
| "loss": 0.3547, |
| "step": 3050 |
| }, |
| { |
| "epoch": 1525.0, |
| "eval_accuracy": 0.59, |
| "eval_f1": 0.3456057557070215, |
| "eval_loss": 1.2632359266281128, |
| "eval_precision": 0.41541493721127587, |
| "eval_recall": 0.3971807821807822, |
| "eval_runtime": 0.1101, |
| "eval_samples_per_second": 1816.9, |
| "eval_steps_per_second": 9.084, |
| "step": 3050 |
| }, |
| { |
| "epoch": 1537.5, |
| "learning_rate": 1.3850000000000001e-05, |
| "loss": 0.3492, |
| "step": 3075 |
| }, |
| { |
| "epoch": 1537.5, |
| "eval_accuracy": 0.595, |
| "eval_f1": 0.34818573128699715, |
| "eval_loss": 1.2610071897506714, |
| "eval_precision": 0.4215438959718136, |
| "eval_recall": 0.401026936026936, |
| "eval_runtime": 0.1093, |
| "eval_samples_per_second": 1830.187, |
| "eval_steps_per_second": 9.151, |
| "step": 3075 |
| }, |
| { |
| "epoch": 1550.0, |
| "learning_rate": 1.38e-05, |
| "loss": 0.3581, |
| "step": 3100 |
| }, |
| { |
| "epoch": 1550.0, |
| "eval_accuracy": 0.595, |
| "eval_f1": 0.35048900720729437, |
| "eval_loss": 1.2602499723434448, |
| "eval_precision": 0.4183609385783299, |
| "eval_recall": 0.401026936026936, |
| "eval_runtime": 0.1101, |
| "eval_samples_per_second": 1816.526, |
| "eval_steps_per_second": 9.083, |
| "step": 3100 |
| }, |
| { |
| "epoch": 1562.5, |
| "learning_rate": 1.375e-05, |
| "loss": 0.3492, |
| "step": 3125 |
| }, |
| { |
| "epoch": 1562.5, |
| "eval_accuracy": 0.59, |
| "eval_f1": 0.3456057557070215, |
| "eval_loss": 1.2612745761871338, |
| "eval_precision": 0.41541493721127587, |
| "eval_recall": 0.3971807821807822, |
| "eval_runtime": 0.1097, |
| "eval_samples_per_second": 1823.115, |
| "eval_steps_per_second": 9.116, |
| "step": 3125 |
| }, |
| { |
| "epoch": 1575.0, |
| "learning_rate": 1.3700000000000003e-05, |
| "loss": 0.3586, |
| "step": 3150 |
| }, |
| { |
| "epoch": 1575.0, |
| "eval_accuracy": 0.595, |
| "eval_f1": 0.35048900720729437, |
| "eval_loss": 1.2579611539840698, |
| "eval_precision": 0.4183609385783299, |
| "eval_recall": 0.401026936026936, |
| "eval_runtime": 0.1106, |
| "eval_samples_per_second": 1808.993, |
| "eval_steps_per_second": 9.045, |
| "step": 3150 |
| }, |
| { |
| "epoch": 1587.5, |
| "learning_rate": 1.3650000000000001e-05, |
| "loss": 0.3439, |
| "step": 3175 |
| }, |
| { |
| "epoch": 1587.5, |
| "eval_accuracy": 0.595, |
| "eval_f1": 0.35048900720729437, |
| "eval_loss": 1.2570867538452148, |
| "eval_precision": 0.4183609385783299, |
| "eval_recall": 0.401026936026936, |
| "eval_runtime": 0.1098, |
| "eval_samples_per_second": 1820.832, |
| "eval_steps_per_second": 9.104, |
| "step": 3175 |
| }, |
| { |
| "epoch": 1600.0, |
| "learning_rate": 1.3600000000000002e-05, |
| "loss": 0.3435, |
| "step": 3200 |
| }, |
| { |
| "epoch": 1600.0, |
| "eval_accuracy": 0.595, |
| "eval_f1": 0.34912749483745636, |
| "eval_loss": 1.2599965333938599, |
| "eval_precision": 0.41963799485538616, |
| "eval_recall": 0.401026936026936, |
| "eval_runtime": 0.1119, |
| "eval_samples_per_second": 1787.922, |
| "eval_steps_per_second": 8.94, |
| "step": 3200 |
| }, |
| { |
| "epoch": 1612.5, |
| "learning_rate": 1.355e-05, |
| "loss": 0.3443, |
| "step": 3225 |
| }, |
| { |
| "epoch": 1612.5, |
| "eval_accuracy": 0.6, |
| "eval_f1": 0.35028592863703617, |
| "eval_loss": 1.2632455825805664, |
| "eval_precision": 0.4233687101429037, |
| "eval_recall": 0.4025420875420876, |
| "eval_runtime": 0.1096, |
| "eval_samples_per_second": 1824.106, |
| "eval_steps_per_second": 9.121, |
| "step": 3225 |
| }, |
| { |
| "epoch": 1625.0, |
| "learning_rate": 1.3500000000000001e-05, |
| "loss": 0.3372, |
| "step": 3250 |
| }, |
| { |
| "epoch": 1625.0, |
| "eval_accuracy": 0.595, |
| "eval_f1": 0.34912749483745636, |
| "eval_loss": 1.2614706754684448, |
| "eval_precision": 0.41963799485538616, |
| "eval_recall": 0.401026936026936, |
| "eval_runtime": 0.1096, |
| "eval_samples_per_second": 1824.205, |
| "eval_steps_per_second": 9.121, |
| "step": 3250 |
| }, |
| { |
| "epoch": 1637.5, |
| "learning_rate": 1.3450000000000002e-05, |
| "loss": 0.3379, |
| "step": 3275 |
| }, |
| { |
| "epoch": 1637.5, |
| "eval_accuracy": 0.595, |
| "eval_f1": 0.34912749483745636, |
| "eval_loss": 1.2629131078720093, |
| "eval_precision": 0.41963799485538616, |
| "eval_recall": 0.401026936026936, |
| "eval_runtime": 0.1103, |
| "eval_samples_per_second": 1813.537, |
| "eval_steps_per_second": 9.068, |
| "step": 3275 |
| }, |
| { |
| "epoch": 1650.0, |
| "learning_rate": 1.3400000000000002e-05, |
| "loss": 0.3273, |
| "step": 3300 |
| }, |
| { |
| "epoch": 1650.0, |
| "eval_accuracy": 0.595, |
| "eval_f1": 0.34912749483745636, |
| "eval_loss": 1.2596778869628906, |
| "eval_precision": 0.41963799485538616, |
| "eval_recall": 0.401026936026936, |
| "eval_runtime": 0.1097, |
| "eval_samples_per_second": 1823.547, |
| "eval_steps_per_second": 9.118, |
| "step": 3300 |
| }, |
| { |
| "epoch": 1662.5, |
| "learning_rate": 1.3350000000000001e-05, |
| "loss": 0.3372, |
| "step": 3325 |
| }, |
| { |
| "epoch": 1662.5, |
| "eval_accuracy": 0.615, |
| "eval_f1": 0.4529699088032402, |
| "eval_loss": 1.2613047361373901, |
| "eval_precision": 0.5227730989226936, |
| "eval_recall": 0.5010269360269362, |
| "eval_runtime": 0.1097, |
| "eval_samples_per_second": 1822.897, |
| "eval_steps_per_second": 9.114, |
| "step": 3325 |
| }, |
| { |
| "epoch": 1675.0, |
| "learning_rate": 1.3300000000000001e-05, |
| "loss": 0.3289, |
| "step": 3350 |
| }, |
| { |
| "epoch": 1675.0, |
| "eval_accuracy": 0.615, |
| "eval_f1": 0.45160839643340217, |
| "eval_loss": 1.2596044540405273, |
| "eval_precision": 0.5240501551997498, |
| "eval_recall": 0.5010269360269362, |
| "eval_runtime": 0.11, |
| "eval_samples_per_second": 1818.668, |
| "eval_steps_per_second": 9.093, |
| "step": 3350 |
| }, |
| { |
| "epoch": 1687.5, |
| "learning_rate": 1.325e-05, |
| "loss": 0.3281, |
| "step": 3375 |
| }, |
| { |
| "epoch": 1687.5, |
| "eval_accuracy": 0.6, |
| "eval_f1": 0.35069609422943626, |
| "eval_loss": 1.263865351676941, |
| "eval_precision": 0.4208764152514153, |
| "eval_recall": 0.40287878787878795, |
| "eval_runtime": 0.1096, |
| "eval_samples_per_second": 1824.709, |
| "eval_steps_per_second": 9.124, |
| "step": 3375 |
| }, |
| { |
| "epoch": 1700.0, |
| "learning_rate": 1.3200000000000002e-05, |
| "loss": 0.3216, |
| "step": 3400 |
| }, |
| { |
| "epoch": 1700.0, |
| "eval_accuracy": 0.615, |
| "eval_f1": 0.45160839643340217, |
| "eval_loss": 1.2669954299926758, |
| "eval_precision": 0.5240501551997498, |
| "eval_recall": 0.5010269360269362, |
| "eval_runtime": 0.1094, |
| "eval_samples_per_second": 1827.81, |
| "eval_steps_per_second": 9.139, |
| "step": 3400 |
| }, |
| { |
| "epoch": 1712.5, |
| "learning_rate": 1.3150000000000001e-05, |
| "loss": 0.3144, |
| "step": 3425 |
| }, |
| { |
| "epoch": 1712.5, |
| "eval_accuracy": 0.61, |
| "eval_f1": 0.4471009763172864, |
| "eval_loss": 1.2653799057006836, |
| "eval_precision": 0.5218207179703127, |
| "eval_recall": 0.49718078218078227, |
| "eval_runtime": 0.1124, |
| "eval_samples_per_second": 1779.034, |
| "eval_steps_per_second": 8.895, |
| "step": 3425 |
| }, |
| { |
| "epoch": 1725.0, |
| "learning_rate": 1.3100000000000002e-05, |
| "loss": 0.3047, |
| "step": 3450 |
| }, |
| { |
| "epoch": 1725.0, |
| "eval_accuracy": 0.615, |
| "eval_f1": 0.45160839643340217, |
| "eval_loss": 1.26544988155365, |
| "eval_precision": 0.5240501551997498, |
| "eval_recall": 0.5010269360269362, |
| "eval_runtime": 0.1249, |
| "eval_samples_per_second": 1601.041, |
| "eval_steps_per_second": 8.005, |
| "step": 3450 |
| }, |
| { |
| "epoch": 1737.5, |
| "learning_rate": 1.305e-05, |
| "loss": 0.3072, |
| "step": 3475 |
| }, |
| { |
| "epoch": 1737.5, |
| "eval_accuracy": 0.615, |
| "eval_f1": 0.45160839643340217, |
| "eval_loss": 1.2732189893722534, |
| "eval_precision": 0.5240501551997498, |
| "eval_recall": 0.5010269360269362, |
| "eval_runtime": 0.1091, |
| "eval_samples_per_second": 1832.634, |
| "eval_steps_per_second": 9.163, |
| "step": 3475 |
| }, |
| { |
| "epoch": 1750.0, |
| "learning_rate": 1.3000000000000001e-05, |
| "loss": 0.3185, |
| "step": 3500 |
| }, |
| { |
| "epoch": 1750.0, |
| "eval_accuracy": 0.615, |
| "eval_f1": 0.45087343503862154, |
| "eval_loss": 1.2701507806777954, |
| "eval_precision": 0.521647702579906, |
| "eval_recall": 0.5010269360269362, |
| "eval_runtime": 0.1098, |
| "eval_samples_per_second": 1820.915, |
| "eval_steps_per_second": 9.105, |
| "step": 3500 |
| }, |
| { |
| "epoch": 1762.5, |
| "learning_rate": 1.295e-05, |
| "loss": 0.3168, |
| "step": 3525 |
| }, |
| { |
| "epoch": 1762.5, |
| "eval_accuracy": 0.62, |
| "eval_f1": 0.4527668302329819, |
| "eval_loss": 1.267295479774475, |
| "eval_precision": 0.5277808704872674, |
| "eval_recall": 0.5025420875420876, |
| "eval_runtime": 0.1097, |
| "eval_samples_per_second": 1823.432, |
| "eval_steps_per_second": 9.117, |
| "step": 3525 |
| }, |
| { |
| "epoch": 1775.0, |
| "learning_rate": 1.2900000000000002e-05, |
| "loss": 0.3094, |
| "step": 3550 |
| }, |
| { |
| "epoch": 1775.0, |
| "eval_accuracy": 0.615, |
| "eval_f1": 0.4529699088032402, |
| "eval_loss": 1.2606223821640015, |
| "eval_precision": 0.5227730989226936, |
| "eval_recall": 0.5010269360269362, |
| "eval_runtime": 0.1096, |
| "eval_samples_per_second": 1825.571, |
| "eval_steps_per_second": 9.128, |
| "step": 3550 |
| }, |
| { |
| "epoch": 1787.5, |
| "learning_rate": 1.285e-05, |
| "loss": 0.2951, |
| "step": 3575 |
| }, |
| { |
| "epoch": 1787.5, |
| "eval_accuracy": 0.615, |
| "eval_f1": 0.4496721249473512, |
| "eval_loss": 1.2645279169082642, |
| "eval_precision": 0.5210283576073049, |
| "eval_recall": 0.4990326340326341, |
| "eval_runtime": 0.1106, |
| "eval_samples_per_second": 1808.33, |
| "eval_steps_per_second": 9.042, |
| "step": 3575 |
| }, |
| { |
| "epoch": 1800.0, |
| "learning_rate": 1.2800000000000001e-05, |
| "loss": 0.3003, |
| "step": 3600 |
| }, |
| { |
| "epoch": 1800.0, |
| "eval_accuracy": 0.615, |
| "eval_f1": 0.4496721249473512, |
| "eval_loss": 1.2622060775756836, |
| "eval_precision": 0.5210283576073049, |
| "eval_recall": 0.4990326340326341, |
| "eval_runtime": 0.1107, |
| "eval_samples_per_second": 1807.286, |
| "eval_steps_per_second": 9.036, |
| "step": 3600 |
| }, |
| { |
| "epoch": 1812.5, |
| "learning_rate": 1.275e-05, |
| "loss": 0.2975, |
| "step": 3625 |
| }, |
| { |
| "epoch": 1812.5, |
| "eval_accuracy": 0.61, |
| "eval_f1": 0.44873457133583716, |
| "eval_loss": 1.2640191316604614, |
| "eval_precision": 0.5210252273043245, |
| "eval_recall": 0.49718078218078227, |
| "eval_runtime": 0.1097, |
| "eval_samples_per_second": 1822.378, |
| "eval_steps_per_second": 9.112, |
| "step": 3625 |
| }, |
| { |
| "epoch": 1825.0, |
| "learning_rate": 1.27e-05, |
| "loss": 0.2992, |
| "step": 3650 |
| }, |
| { |
| "epoch": 1825.0, |
| "eval_accuracy": 0.615, |
| "eval_f1": 0.4522563104662719, |
| "eval_loss": 1.2694511413574219, |
| "eval_precision": 0.5252482849484348, |
| "eval_recall": 0.5010269360269362, |
| "eval_runtime": 0.1246, |
| "eval_samples_per_second": 1604.965, |
| "eval_steps_per_second": 8.025, |
| "step": 3650 |
| }, |
| { |
| "epoch": 1837.5, |
| "learning_rate": 1.2650000000000001e-05, |
| "loss": 0.2993, |
| "step": 3675 |
| }, |
| { |
| "epoch": 1837.5, |
| "eval_accuracy": 0.62, |
| "eval_f1": 0.4527668302329819, |
| "eval_loss": 1.2768322229385376, |
| "eval_precision": 0.5277808704872674, |
| "eval_recall": 0.5025420875420876, |
| "eval_runtime": 0.1097, |
| "eval_samples_per_second": 1823.218, |
| "eval_steps_per_second": 9.116, |
| "step": 3675 |
| }, |
| { |
| "epoch": 1850.0, |
| "learning_rate": 1.2600000000000001e-05, |
| "loss": 0.2948, |
| "step": 3700 |
| }, |
| { |
| "epoch": 1850.0, |
| "eval_accuracy": 0.615, |
| "eval_f1": 0.45160839643340217, |
| "eval_loss": 1.2783905267715454, |
| "eval_precision": 0.5240501551997498, |
| "eval_recall": 0.5010269360269362, |
| "eval_runtime": 0.1097, |
| "eval_samples_per_second": 1822.933, |
| "eval_steps_per_second": 9.115, |
| "step": 3700 |
| }, |
| { |
| "epoch": 1862.5, |
| "learning_rate": 1.255e-05, |
| "loss": 0.2842, |
| "step": 3725 |
| }, |
| { |
| "epoch": 1862.5, |
| "eval_accuracy": 0.62, |
| "eval_f1": 0.45341474426585177, |
| "eval_loss": 1.2781866788864136, |
| "eval_precision": 0.5289790002359525, |
| "eval_recall": 0.5025420875420876, |
| "eval_runtime": 0.1093, |
| "eval_samples_per_second": 1830.547, |
| "eval_steps_per_second": 9.153, |
| "step": 3725 |
| }, |
| { |
| "epoch": 1875.0, |
| "learning_rate": 1.25e-05, |
| "loss": 0.2872, |
| "step": 3750 |
| }, |
| { |
| "epoch": 1875.0, |
| "eval_accuracy": 0.61, |
| "eval_f1": 0.44808665730296743, |
| "eval_loss": 1.2730449438095093, |
| "eval_precision": 0.5198270975556396, |
| "eval_recall": 0.49718078218078227, |
| "eval_runtime": 0.1098, |
| "eval_samples_per_second": 1821.361, |
| "eval_steps_per_second": 9.107, |
| "step": 3750 |
| }, |
| { |
| "epoch": 1887.5, |
| "learning_rate": 1.2450000000000003e-05, |
| "loss": 0.2893, |
| "step": 3775 |
| }, |
| { |
| "epoch": 1887.5, |
| "eval_accuracy": 0.615, |
| "eval_f1": 0.4522563104662719, |
| "eval_loss": 1.2721458673477173, |
| "eval_precision": 0.5252482849484348, |
| "eval_recall": 0.5010269360269362, |
| "eval_runtime": 0.1092, |
| "eval_samples_per_second": 1831.098, |
| "eval_steps_per_second": 9.155, |
| "step": 3775 |
| }, |
| { |
| "epoch": 1900.0, |
| "learning_rate": 1.2400000000000002e-05, |
| "loss": 0.2869, |
| "step": 3800 |
| }, |
| { |
| "epoch": 1900.0, |
| "eval_accuracy": 0.615, |
| "eval_f1": 0.4522563104662719, |
| "eval_loss": 1.2688474655151367, |
| "eval_precision": 0.5252482849484348, |
| "eval_recall": 0.5010269360269362, |
| "eval_runtime": 0.139, |
| "eval_samples_per_second": 1438.364, |
| "eval_steps_per_second": 7.192, |
| "step": 3800 |
| }, |
| { |
| "epoch": 1912.5, |
| "learning_rate": 1.2350000000000002e-05, |
| "loss": 0.2811, |
| "step": 3825 |
| }, |
| { |
| "epoch": 1912.5, |
| "eval_accuracy": 0.61, |
| "eval_f1": 0.44873457133583716, |
| "eval_loss": 1.266568899154663, |
| "eval_precision": 0.5210252273043245, |
| "eval_recall": 0.49718078218078227, |
| "eval_runtime": 0.1098, |
| "eval_samples_per_second": 1822.129, |
| "eval_steps_per_second": 9.111, |
| "step": 3825 |
| }, |
| { |
| "epoch": 1925.0, |
| "learning_rate": 1.23e-05, |
| "loss": 0.2839, |
| "step": 3850 |
| }, |
| { |
| "epoch": 1925.0, |
| "eval_accuracy": 0.61, |
| "eval_f1": 0.44873457133583716, |
| "eval_loss": 1.2698582410812378, |
| "eval_precision": 0.5210252273043245, |
| "eval_recall": 0.49718078218078227, |
| "eval_runtime": 0.1142, |
| "eval_samples_per_second": 1751.005, |
| "eval_steps_per_second": 8.755, |
| "step": 3850 |
| }, |
| { |
| "epoch": 1937.5, |
| "learning_rate": 1.2250000000000001e-05, |
| "loss": 0.2763, |
| "step": 3875 |
| }, |
| { |
| "epoch": 1937.5, |
| "eval_accuracy": 0.61, |
| "eval_f1": 0.44873457133583716, |
| "eval_loss": 1.2797365188598633, |
| "eval_precision": 0.5210252273043245, |
| "eval_recall": 0.49718078218078227, |
| "eval_runtime": 0.11, |
| "eval_samples_per_second": 1818.582, |
| "eval_steps_per_second": 9.093, |
| "step": 3875 |
| }, |
| { |
| "epoch": 1950.0, |
| "learning_rate": 1.22e-05, |
| "loss": 0.2714, |
| "step": 3900 |
| }, |
| { |
| "epoch": 1950.0, |
| "eval_accuracy": 0.625, |
| "eval_f1": 0.4700311244819254, |
| "eval_loss": 1.2719074487686157, |
| "eval_precision": 0.540959595959596, |
| "eval_recall": 0.5195454545454545, |
| "eval_runtime": 0.1104, |
| "eval_samples_per_second": 1811.161, |
| "eval_steps_per_second": 9.056, |
| "step": 3900 |
| }, |
| { |
| "epoch": 1962.5, |
| "learning_rate": 1.2150000000000002e-05, |
| "loss": 0.2684, |
| "step": 3925 |
| }, |
| { |
| "epoch": 1962.5, |
| "eval_accuracy": 0.62, |
| "eval_f1": 0.45341474426585177, |
| "eval_loss": 1.2820361852645874, |
| "eval_precision": 0.5289790002359525, |
| "eval_recall": 0.5025420875420876, |
| "eval_runtime": 0.1275, |
| "eval_samples_per_second": 1568.377, |
| "eval_steps_per_second": 7.842, |
| "step": 3925 |
| }, |
| { |
| "epoch": 1975.0, |
| "learning_rate": 1.2100000000000001e-05, |
| "loss": 0.2626, |
| "step": 3950 |
| }, |
| { |
| "epoch": 1975.0, |
| "eval_accuracy": 0.62, |
| "eval_f1": 0.45341474426585177, |
| "eval_loss": 1.2908936738967896, |
| "eval_precision": 0.5289790002359525, |
| "eval_recall": 0.5025420875420876, |
| "eval_runtime": 0.1287, |
| "eval_samples_per_second": 1553.958, |
| "eval_steps_per_second": 7.77, |
| "step": 3950 |
| }, |
| { |
| "epoch": 1987.5, |
| "learning_rate": 1.2050000000000002e-05, |
| "loss": 0.2688, |
| "step": 3975 |
| }, |
| { |
| "epoch": 1987.5, |
| "eval_accuracy": 0.615, |
| "eval_f1": 0.45152134907149144, |
| "eval_loss": 1.2801417112350464, |
| "eval_precision": 0.5228458323285909, |
| "eval_recall": 0.5010269360269362, |
| "eval_runtime": 0.1089, |
| "eval_samples_per_second": 1836.454, |
| "eval_steps_per_second": 9.182, |
| "step": 3975 |
| }, |
| { |
| "epoch": 2000.0, |
| "learning_rate": 1.2e-05, |
| "loss": 0.2746, |
| "step": 4000 |
| }, |
| { |
| "epoch": 2000.0, |
| "eval_accuracy": 0.61, |
| "eval_f1": 0.44873457133583716, |
| "eval_loss": 1.2783504724502563, |
| "eval_precision": 0.5210252273043245, |
| "eval_recall": 0.49718078218078227, |
| "eval_runtime": 0.1264, |
| "eval_samples_per_second": 1582.296, |
| "eval_steps_per_second": 7.911, |
| "step": 4000 |
| }, |
| { |
| "epoch": 2012.5, |
| "learning_rate": 1.195e-05, |
| "loss": 0.2741, |
| "step": 4025 |
| }, |
| { |
| "epoch": 2012.5, |
| "eval_accuracy": 0.61, |
| "eval_f1": 0.44873457133583716, |
| "eval_loss": 1.278936505317688, |
| "eval_precision": 0.5210252273043245, |
| "eval_recall": 0.49718078218078227, |
| "eval_runtime": 0.1104, |
| "eval_samples_per_second": 1811.571, |
| "eval_steps_per_second": 9.058, |
| "step": 4025 |
| }, |
| { |
| "epoch": 2025.0, |
| "learning_rate": 1.1900000000000001e-05, |
| "loss": 0.2671, |
| "step": 4050 |
| }, |
| { |
| "epoch": 2025.0, |
| "eval_accuracy": 0.62, |
| "eval_f1": 0.45384593673731094, |
| "eval_loss": 1.280784249305725, |
| "eval_precision": 0.5264378559293814, |
| "eval_recall": 0.5028787878787879, |
| "eval_runtime": 0.109, |
| "eval_samples_per_second": 1835.208, |
| "eval_steps_per_second": 9.176, |
| "step": 4050 |
| }, |
| { |
| "epoch": 2037.5, |
| "learning_rate": 1.1850000000000002e-05, |
| "loss": 0.2667, |
| "step": 4075 |
| }, |
| { |
| "epoch": 2037.5, |
| "eval_accuracy": 0.615, |
| "eval_f1": 0.4522563104662719, |
| "eval_loss": 1.281556248664856, |
| "eval_precision": 0.5252482849484348, |
| "eval_recall": 0.5010269360269362, |
| "eval_runtime": 0.1321, |
| "eval_samples_per_second": 1513.484, |
| "eval_steps_per_second": 7.567, |
| "step": 4075 |
| }, |
| { |
| "epoch": 2050.0, |
| "learning_rate": 1.18e-05, |
| "loss": 0.2501, |
| "step": 4100 |
| }, |
| { |
| "epoch": 2050.0, |
| "eval_accuracy": 0.62, |
| "eval_f1": 0.45341474426585177, |
| "eval_loss": 1.289035677909851, |
| "eval_precision": 0.5289790002359525, |
| "eval_recall": 0.5025420875420876, |
| "eval_runtime": 0.1274, |
| "eval_samples_per_second": 1569.851, |
| "eval_steps_per_second": 7.849, |
| "step": 4100 |
| }, |
| { |
| "epoch": 2062.5, |
| "learning_rate": 1.1750000000000001e-05, |
| "loss": 0.2537, |
| "step": 4125 |
| }, |
| { |
| "epoch": 2062.5, |
| "eval_accuracy": 0.61, |
| "eval_f1": 0.44873457133583716, |
| "eval_loss": 1.2851228713989258, |
| "eval_precision": 0.5210252273043245, |
| "eval_recall": 0.49718078218078227, |
| "eval_runtime": 0.1098, |
| "eval_samples_per_second": 1821.773, |
| "eval_steps_per_second": 9.109, |
| "step": 4125 |
| }, |
| { |
| "epoch": 2075.0, |
| "learning_rate": 1.17e-05, |
| "loss": 0.2564, |
| "step": 4150 |
| }, |
| { |
| "epoch": 2075.0, |
| "eval_accuracy": 0.62, |
| "eval_f1": 0.45341474426585177, |
| "eval_loss": 1.2925108671188354, |
| "eval_precision": 0.5289790002359525, |
| "eval_recall": 0.5025420875420876, |
| "eval_runtime": 0.11, |
| "eval_samples_per_second": 1817.939, |
| "eval_steps_per_second": 9.09, |
| "step": 4150 |
| }, |
| { |
| "epoch": 2087.5, |
| "learning_rate": 1.1650000000000002e-05, |
| "loss": 0.2505, |
| "step": 4175 |
| }, |
| { |
| "epoch": 2087.5, |
| "eval_accuracy": 0.625, |
| "eval_f1": 0.48265456127158257, |
| "eval_loss": 1.2837164402008057, |
| "eval_precision": 0.5497941824257614, |
| "eval_recall": 0.5343602693602694, |
| "eval_runtime": 0.1099, |
| "eval_samples_per_second": 1820.046, |
| "eval_steps_per_second": 9.1, |
| "step": 4175 |
| }, |
| { |
| "epoch": 2100.0, |
| "learning_rate": 1.16e-05, |
| "loss": 0.2473, |
| "step": 4200 |
| }, |
| { |
| "epoch": 2100.0, |
| "eval_accuracy": 0.63, |
| "eval_f1": 0.509683546778829, |
| "eval_loss": 1.2851536273956299, |
| "eval_precision": 0.5531275157590947, |
| "eval_recall": 0.5593602693602694, |
| "eval_runtime": 0.1157, |
| "eval_samples_per_second": 1728.441, |
| "eval_steps_per_second": 8.642, |
| "step": 4200 |
| }, |
| { |
| "epoch": 2112.5, |
| "learning_rate": 1.1550000000000001e-05, |
| "loss": 0.2486, |
| "step": 4225 |
| }, |
| { |
| "epoch": 2112.5, |
| "eval_accuracy": 0.63, |
| "eval_f1": 0.4973100120389608, |
| "eval_loss": 1.2886310815811157, |
| "eval_precision": 0.5496685748035073, |
| "eval_recall": 0.5442087542087541, |
| "eval_runtime": 0.1104, |
| "eval_samples_per_second": 1811.0, |
| "eval_steps_per_second": 9.055, |
| "step": 4225 |
| }, |
| { |
| "epoch": 2125.0, |
| "learning_rate": 1.15e-05, |
| "loss": 0.2524, |
| "step": 4250 |
| }, |
| { |
| "epoch": 2125.0, |
| "eval_accuracy": 0.625, |
| "eval_f1": 0.4706831971414503, |
| "eval_loss": 1.2821846008300781, |
| "eval_precision": 0.5421460366375621, |
| "eval_recall": 0.5195454545454545, |
| "eval_runtime": 0.1095, |
| "eval_samples_per_second": 1826.704, |
| "eval_steps_per_second": 9.134, |
| "step": 4250 |
| }, |
| { |
| "epoch": 2137.5, |
| "learning_rate": 1.145e-05, |
| "loss": 0.2487, |
| "step": 4275 |
| }, |
| { |
| "epoch": 2137.5, |
| "eval_accuracy": 0.63, |
| "eval_f1": 0.48932588916459885, |
| "eval_loss": 1.2815427780151367, |
| "eval_precision": 0.5605887120146178, |
| "eval_recall": 0.537921522921523, |
| "eval_runtime": 0.1103, |
| "eval_samples_per_second": 1813.784, |
| "eval_steps_per_second": 9.069, |
| "step": 4275 |
| }, |
| { |
| "epoch": 2150.0, |
| "learning_rate": 1.14e-05, |
| "loss": 0.2474, |
| "step": 4300 |
| }, |
| { |
| "epoch": 2150.0, |
| "eval_accuracy": 0.63, |
| "eval_f1": 0.48454404025125, |
| "eval_loss": 1.2901078462600708, |
| "eval_precision": 0.555908744192497, |
| "eval_recall": 0.5358754208754208, |
| "eval_runtime": 0.1109, |
| "eval_samples_per_second": 1803.052, |
| "eval_steps_per_second": 9.015, |
| "step": 4300 |
| }, |
| { |
| "epoch": 2162.5, |
| "learning_rate": 1.1350000000000001e-05, |
| "loss": 0.2314, |
| "step": 4325 |
| }, |
| { |
| "epoch": 2162.5, |
| "eval_accuracy": 0.63, |
| "eval_f1": 0.4973100120389608, |
| "eval_loss": 1.291297197341919, |
| "eval_precision": 0.5496685748035073, |
| "eval_recall": 0.5442087542087541, |
| "eval_runtime": 0.1095, |
| "eval_samples_per_second": 1826.437, |
| "eval_steps_per_second": 9.132, |
| "step": 4325 |
| }, |
| { |
| "epoch": 2175.0, |
| "learning_rate": 1.13e-05, |
| "loss": 0.2382, |
| "step": 4350 |
| }, |
| { |
| "epoch": 2175.0, |
| "eval_accuracy": 0.635, |
| "eval_f1": 0.5116059638349126, |
| "eval_loss": 1.2974814176559448, |
| "eval_precision": 0.560908744192497, |
| "eval_recall": 0.5608754208754209, |
| "eval_runtime": 0.1091, |
| "eval_samples_per_second": 1833.756, |
| "eval_steps_per_second": 9.169, |
| "step": 4350 |
| }, |
| { |
| "epoch": 2187.5, |
| "learning_rate": 1.125e-05, |
| "loss": 0.243, |
| "step": 4375 |
| }, |
| { |
| "epoch": 2187.5, |
| "eval_accuracy": 0.64, |
| "eval_f1": 0.5197463883634097, |
| "eval_loss": 1.2825735807418823, |
| "eval_precision": 0.5684094640991193, |
| "eval_recall": 0.5667676767676768, |
| "eval_runtime": 0.1101, |
| "eval_samples_per_second": 1816.542, |
| "eval_steps_per_second": 9.083, |
| "step": 4375 |
| }, |
| { |
| "epoch": 2200.0, |
| "learning_rate": 1.1200000000000001e-05, |
| "loss": 0.2363, |
| "step": 4400 |
| }, |
| { |
| "epoch": 2200.0, |
| "eval_accuracy": 0.625, |
| "eval_f1": 0.4833835274253441, |
| "eval_loss": 1.2903591394424438, |
| "eval_precision": 0.5521812398128187, |
| "eval_recall": 0.5343602693602694, |
| "eval_runtime": 0.1096, |
| "eval_samples_per_second": 1825.627, |
| "eval_steps_per_second": 9.128, |
| "step": 4400 |
| }, |
| { |
| "epoch": 2212.5, |
| "learning_rate": 1.1150000000000002e-05, |
| "loss": 0.2377, |
| "step": 4425 |
| }, |
| { |
| "epoch": 2212.5, |
| "eval_accuracy": 0.63, |
| "eval_f1": 0.5104125129325905, |
| "eval_loss": 1.2953640222549438, |
| "eval_precision": 0.555514573146152, |
| "eval_recall": 0.5593602693602694, |
| "eval_runtime": 0.1091, |
| "eval_samples_per_second": 1832.906, |
| "eval_steps_per_second": 9.165, |
| "step": 4425 |
| }, |
| { |
| "epoch": 2225.0, |
| "learning_rate": 1.1100000000000002e-05, |
| "loss": 0.2404, |
| "step": 4450 |
| }, |
| { |
| "epoch": 2225.0, |
| "eval_accuracy": 0.625, |
| "eval_f1": 0.4833835274253441, |
| "eval_loss": 1.2943035364151, |
| "eval_precision": 0.5521812398128187, |
| "eval_recall": 0.5343602693602694, |
| "eval_runtime": 0.1101, |
| "eval_samples_per_second": 1817.108, |
| "eval_steps_per_second": 9.086, |
| "step": 4450 |
| }, |
| { |
| "epoch": 2237.5, |
| "learning_rate": 1.1050000000000001e-05, |
| "loss": 0.2403, |
| "step": 4475 |
| }, |
| { |
| "epoch": 2237.5, |
| "eval_accuracy": 0.625, |
| "eval_f1": 0.4833835274253441, |
| "eval_loss": 1.2905778884887695, |
| "eval_precision": 0.5521812398128187, |
| "eval_recall": 0.5343602693602694, |
| "eval_runtime": 0.1096, |
| "eval_samples_per_second": 1824.32, |
| "eval_steps_per_second": 9.122, |
| "step": 4475 |
| }, |
| { |
| "epoch": 2250.0, |
| "learning_rate": 1.1000000000000001e-05, |
| "loss": 0.2343, |
| "step": 4500 |
| }, |
| { |
| "epoch": 2250.0, |
| "eval_accuracy": 0.63, |
| "eval_f1": 0.48454404025125, |
| "eval_loss": 1.3000606298446655, |
| "eval_precision": 0.555908744192497, |
| "eval_recall": 0.5358754208754208, |
| "eval_runtime": 0.13, |
| "eval_samples_per_second": 1538.596, |
| "eval_steps_per_second": 7.693, |
| "step": 4500 |
| }, |
| { |
| "epoch": 2262.5, |
| "learning_rate": 1.095e-05, |
| "loss": 0.2405, |
| "step": 4525 |
| }, |
| { |
| "epoch": 2262.5, |
| "eval_accuracy": 0.625, |
| "eval_f1": 0.4833835274253441, |
| "eval_loss": 1.2946971654891968, |
| "eval_precision": 0.5521812398128187, |
| "eval_recall": 0.5343602693602694, |
| "eval_runtime": 0.11, |
| "eval_samples_per_second": 1817.825, |
| "eval_steps_per_second": 9.089, |
| "step": 4525 |
| }, |
| { |
| "epoch": 2275.0, |
| "learning_rate": 1.0900000000000002e-05, |
| "loss": 0.2285, |
| "step": 4550 |
| }, |
| { |
| "epoch": 2275.0, |
| "eval_accuracy": 0.63, |
| "eval_f1": 0.486042628071414, |
| "eval_loss": 1.288519024848938, |
| "eval_precision": 0.5465890431407673, |
| "eval_recall": 0.5402525252525253, |
| "eval_runtime": 0.1101, |
| "eval_samples_per_second": 1816.825, |
| "eval_steps_per_second": 9.084, |
| "step": 4550 |
| }, |
| { |
| "epoch": 2287.5, |
| "learning_rate": 1.0850000000000001e-05, |
| "loss": 0.23, |
| "step": 4575 |
| }, |
| { |
| "epoch": 2287.5, |
| "eval_accuracy": 0.63, |
| "eval_f1": 0.509683546778829, |
| "eval_loss": 1.2907253503799438, |
| "eval_precision": 0.5531275157590947, |
| "eval_recall": 0.5593602693602694, |
| "eval_runtime": 0.1149, |
| "eval_samples_per_second": 1741.061, |
| "eval_steps_per_second": 8.705, |
| "step": 4575 |
| }, |
| { |
| "epoch": 2300.0, |
| "learning_rate": 1.0800000000000002e-05, |
| "loss": 0.2223, |
| "step": 4600 |
| }, |
| { |
| "epoch": 2300.0, |
| "eval_accuracy": 0.635, |
| "eval_f1": 0.5112894082234001, |
| "eval_loss": 1.2937698364257812, |
| "eval_precision": 0.5543355791825377, |
| "eval_recall": 0.5612121212121213, |
| "eval_runtime": 0.1116, |
| "eval_samples_per_second": 1791.347, |
| "eval_steps_per_second": 8.957, |
| "step": 4600 |
| }, |
| { |
| "epoch": 2312.5, |
| "learning_rate": 1.075e-05, |
| "loss": 0.2226, |
| "step": 4625 |
| }, |
| { |
| "epoch": 2312.5, |
| "eval_accuracy": 0.625, |
| "eval_f1": 0.4833835274253441, |
| "eval_loss": 1.2982170581817627, |
| "eval_precision": 0.5521812398128187, |
| "eval_recall": 0.5343602693602694, |
| "eval_runtime": 0.1435, |
| "eval_samples_per_second": 1394.2, |
| "eval_steps_per_second": 6.971, |
| "step": 4625 |
| }, |
| { |
| "epoch": 2325.0, |
| "learning_rate": 1.0700000000000001e-05, |
| "loss": 0.2255, |
| "step": 4650 |
| }, |
| { |
| "epoch": 2325.0, |
| "eval_accuracy": 0.635, |
| "eval_f1": 0.4924130550300763, |
| "eval_loss": 1.2945975065231323, |
| "eval_precision": 0.5636475593372146, |
| "eval_recall": 0.5417676767676768, |
| "eval_runtime": 0.1102, |
| "eval_samples_per_second": 1815.547, |
| "eval_steps_per_second": 9.078, |
| "step": 4650 |
| }, |
| { |
| "epoch": 2337.5, |
| "learning_rate": 1.065e-05, |
| "loss": 0.227, |
| "step": 4675 |
| }, |
| { |
| "epoch": 2337.5, |
| "eval_accuracy": 0.625, |
| "eval_f1": 0.4833835274253441, |
| "eval_loss": 1.2982064485549927, |
| "eval_precision": 0.5521812398128187, |
| "eval_recall": 0.5343602693602694, |
| "eval_runtime": 0.1103, |
| "eval_samples_per_second": 1813.404, |
| "eval_steps_per_second": 9.067, |
| "step": 4675 |
| }, |
| { |
| "epoch": 2350.0, |
| "learning_rate": 1.0600000000000002e-05, |
| "loss": 0.2266, |
| "step": 4700 |
| }, |
| { |
| "epoch": 2350.0, |
| "eval_accuracy": 0.63, |
| "eval_f1": 0.48932588916459885, |
| "eval_loss": 1.2912367582321167, |
| "eval_precision": 0.5605887120146178, |
| "eval_recall": 0.537921522921523, |
| "eval_runtime": 0.1105, |
| "eval_samples_per_second": 1810.617, |
| "eval_steps_per_second": 9.053, |
| "step": 4700 |
| }, |
| { |
| "epoch": 2362.5, |
| "learning_rate": 1.055e-05, |
| "loss": 0.222, |
| "step": 4725 |
| }, |
| { |
| "epoch": 2362.5, |
| "eval_accuracy": 0.625, |
| "eval_f1": 0.48762996246867213, |
| "eval_loss": 1.2941089868545532, |
| "eval_precision": 0.5573269656947953, |
| "eval_recall": 0.5360696710696711, |
| "eval_runtime": 0.1095, |
| "eval_samples_per_second": 1826.27, |
| "eval_steps_per_second": 9.131, |
| "step": 4725 |
| }, |
| { |
| "epoch": 2375.0, |
| "learning_rate": 1.0500000000000001e-05, |
| "loss": 0.2225, |
| "step": 4750 |
| }, |
| { |
| "epoch": 2375.0, |
| "eval_accuracy": 0.635, |
| "eval_f1": 0.4922899885540687, |
| "eval_loss": 1.2936097383499146, |
| "eval_precision": 0.5608337065233616, |
| "eval_recall": 0.5417676767676768, |
| "eval_runtime": 0.1189, |
| "eval_samples_per_second": 1681.923, |
| "eval_steps_per_second": 8.41, |
| "step": 4750 |
| }, |
| { |
| "epoch": 2387.5, |
| "learning_rate": 1.045e-05, |
| "loss": 0.2235, |
| "step": 4775 |
| }, |
| { |
| "epoch": 2387.5, |
| "eval_accuracy": 0.625, |
| "eval_f1": 0.48762996246867213, |
| "eval_loss": 1.2959061861038208, |
| "eval_precision": 0.5573269656947953, |
| "eval_recall": 0.5360696710696711, |
| "eval_runtime": 0.1108, |
| "eval_samples_per_second": 1805.66, |
| "eval_steps_per_second": 9.028, |
| "step": 4775 |
| }, |
| { |
| "epoch": 2400.0, |
| "learning_rate": 1.04e-05, |
| "loss": 0.2171, |
| "step": 4800 |
| }, |
| { |
| "epoch": 2400.0, |
| "eval_accuracy": 0.635, |
| "eval_f1": 0.49300026060895624, |
| "eval_loss": 1.2970188856124878, |
| "eval_precision": 0.563171368861024, |
| "eval_recall": 0.5417676767676768, |
| "eval_runtime": 0.1098, |
| "eval_samples_per_second": 1821.65, |
| "eval_steps_per_second": 9.108, |
| "step": 4800 |
| }, |
| { |
| "epoch": 2412.5, |
| "learning_rate": 1.0350000000000001e-05, |
| "loss": 0.221, |
| "step": 4825 |
| }, |
| { |
| "epoch": 2412.5, |
| "eval_accuracy": 0.635, |
| "eval_f1": 0.5188571514658472, |
| "eval_loss": 1.304814338684082, |
| "eval_precision": 0.5695560871876661, |
| "eval_recall": 0.5649158249158249, |
| "eval_runtime": 0.1095, |
| "eval_samples_per_second": 1827.209, |
| "eval_steps_per_second": 9.136, |
| "step": 4825 |
| }, |
| { |
| "epoch": 2425.0, |
| "learning_rate": 1.0300000000000001e-05, |
| "loss": 0.2168, |
| "step": 4850 |
| }, |
| { |
| "epoch": 2425.0, |
| "eval_accuracy": 0.625, |
| "eval_f1": 0.4838571514658471, |
| "eval_loss": 1.3051663637161255, |
| "eval_precision": 0.5528894205209994, |
| "eval_recall": 0.5343602693602694, |
| "eval_runtime": 0.1084, |
| "eval_samples_per_second": 1844.883, |
| "eval_steps_per_second": 9.224, |
| "step": 4850 |
| }, |
| { |
| "epoch": 2437.5, |
| "learning_rate": 1.025e-05, |
| "loss": 0.2135, |
| "step": 4875 |
| }, |
| { |
| "epoch": 2437.5, |
| "eval_accuracy": 0.63, |
| "eval_f1": 0.4849053731694533, |
| "eval_loss": 1.297641634941101, |
| "eval_precision": 0.5501194208090759, |
| "eval_recall": 0.5362121212121213, |
| "eval_runtime": 0.11, |
| "eval_samples_per_second": 1817.715, |
| "eval_steps_per_second": 9.089, |
| "step": 4875 |
| }, |
| { |
| "epoch": 2450.0, |
| "learning_rate": 1.02e-05, |
| "loss": 0.213, |
| "step": 4900 |
| }, |
| { |
| "epoch": 2450.0, |
| "eval_accuracy": 0.635, |
| "eval_f1": 0.4922899885540687, |
| "eval_loss": 1.2998266220092773, |
| "eval_precision": 0.5608337065233616, |
| "eval_recall": 0.5417676767676768, |
| "eval_runtime": 0.1118, |
| "eval_samples_per_second": 1788.307, |
| "eval_steps_per_second": 8.942, |
| "step": 4900 |
| }, |
| { |
| "epoch": 2462.5, |
| "learning_rate": 1.015e-05, |
| "loss": 0.2084, |
| "step": 4925 |
| }, |
| { |
| "epoch": 2462.5, |
| "eval_accuracy": 0.63, |
| "eval_f1": 0.48454404025125, |
| "eval_loss": 1.3060911893844604, |
| "eval_precision": 0.555908744192497, |
| "eval_recall": 0.5358754208754208, |
| "eval_runtime": 0.1095, |
| "eval_samples_per_second": 1826.895, |
| "eval_steps_per_second": 9.134, |
| "step": 4925 |
| }, |
| { |
| "epoch": 2475.0, |
| "learning_rate": 1.0100000000000002e-05, |
| "loss": 0.2141, |
| "step": 4950 |
| }, |
| { |
| "epoch": 2475.0, |
| "eval_accuracy": 0.63, |
| "eval_f1": 0.49152381813251383, |
| "eval_loss": 1.3060494661331177, |
| "eval_precision": 0.5647941824257614, |
| "eval_recall": 0.5399158249158249, |
| "eval_runtime": 0.1187, |
| "eval_samples_per_second": 1685.4, |
| "eval_steps_per_second": 8.427, |
| "step": 4950 |
| }, |
| { |
| "epoch": 2487.5, |
| "learning_rate": 1.005e-05, |
| "loss": 0.1981, |
| "step": 4975 |
| }, |
| { |
| "epoch": 2487.5, |
| "eval_accuracy": 0.63, |
| "eval_f1": 0.48932588916459885, |
| "eval_loss": 1.3027862310409546, |
| "eval_precision": 0.5605887120146178, |
| "eval_recall": 0.537921522921523, |
| "eval_runtime": 0.111, |
| "eval_samples_per_second": 1801.561, |
| "eval_steps_per_second": 9.008, |
| "step": 4975 |
| }, |
| { |
| "epoch": 2500.0, |
| "learning_rate": 1e-05, |
| "loss": 0.2055, |
| "step": 5000 |
| }, |
| { |
| "epoch": 2500.0, |
| "eval_accuracy": 0.625, |
| "eval_f1": 0.4833835274253441, |
| "eval_loss": 1.3091175556182861, |
| "eval_precision": 0.5521812398128187, |
| "eval_recall": 0.5343602693602694, |
| "eval_runtime": 0.1089, |
| "eval_samples_per_second": 1835.77, |
| "eval_steps_per_second": 9.179, |
| "step": 5000 |
| } |
| ], |
| "logging_steps": 25, |
| "max_steps": 10000, |
| "num_train_epochs": 5000, |
| "save_steps": 25, |
| "total_flos": 1.1141670670365e+16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
