| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 100.0, | |
| "eval_steps": 500, | |
| "global_step": 9600, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 1.4137675762176514, | |
| "learning_rate": 4.9500000000000004e-05, | |
| "loss": 1.1489, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_LOCATION_f1": 0.0, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.0, | |
| "eval_LOCATION_recall": 0.0, | |
| "eval_ORGANIZATION_f1": 0.0, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.0, | |
| "eval_ORGANIZATION_recall": 0.0, | |
| "eval_PERSON_f1": 0.0, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.0, | |
| "eval_PERSON_recall": 0.0, | |
| "eval_loss": 0.6808387637138367, | |
| "eval_overall_accuracy": 0.8434547908232118, | |
| "eval_overall_f1": 0.0, | |
| "eval_overall_precision": 0.0, | |
| "eval_overall_recall": 0.0, | |
| "eval_runtime": 0.278, | |
| "eval_samples_per_second": 611.441, | |
| "eval_steps_per_second": 10.79, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.9978224039077759, | |
| "learning_rate": 4.9e-05, | |
| "loss": 0.6648, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_LOCATION_f1": 0.0, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.0, | |
| "eval_LOCATION_recall": 0.0, | |
| "eval_ORGANIZATION_f1": 0.01111111111111111, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.5, | |
| "eval_ORGANIZATION_recall": 0.0056179775280898875, | |
| "eval_PERSON_f1": 0.0, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.0, | |
| "eval_PERSON_recall": 0.0, | |
| "eval_loss": 0.5507592558860779, | |
| "eval_overall_accuracy": 0.8437246963562753, | |
| "eval_overall_f1": 0.005063291139240506, | |
| "eval_overall_precision": 0.3333333333333333, | |
| "eval_overall_recall": 0.002551020408163265, | |
| "eval_runtime": 0.2793, | |
| "eval_samples_per_second": 608.59, | |
| "eval_steps_per_second": 10.74, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 1.2066327333450317, | |
| "learning_rate": 4.85e-05, | |
| "loss": 0.5545, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_LOCATION_f1": 0.0, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.0, | |
| "eval_LOCATION_recall": 0.0, | |
| "eval_ORGANIZATION_f1": 0.10628019323671496, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.3793103448275862, | |
| "eval_ORGANIZATION_recall": 0.06179775280898876, | |
| "eval_PERSON_f1": 0.15950920245398775, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.37142857142857144, | |
| "eval_PERSON_recall": 0.1015625, | |
| "eval_loss": 0.4323981702327728, | |
| "eval_overall_accuracy": 0.854251012145749, | |
| "eval_overall_f1": 0.10480349344978165, | |
| "eval_overall_precision": 0.36363636363636365, | |
| "eval_overall_recall": 0.061224489795918366, | |
| "eval_runtime": 0.2802, | |
| "eval_samples_per_second": 606.765, | |
| "eval_steps_per_second": 10.708, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 0.8178198933601379, | |
| "learning_rate": 4.8e-05, | |
| "loss": 0.4347, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_LOCATION_f1": 0.08080808080808081, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.3076923076923077, | |
| "eval_LOCATION_recall": 0.046511627906976744, | |
| "eval_ORGANIZATION_f1": 0.32573289902280134, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.3875968992248062, | |
| "eval_ORGANIZATION_recall": 0.2808988764044944, | |
| "eval_PERSON_f1": 0.45774647887323944, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.4166666666666667, | |
| "eval_PERSON_recall": 0.5078125, | |
| "eval_loss": 0.31846487522125244, | |
| "eval_overall_accuracy": 0.8909581646423752, | |
| "eval_overall_f1": 0.34492753623188405, | |
| "eval_overall_precision": 0.39932885906040266, | |
| "eval_overall_recall": 0.30357142857142855, | |
| "eval_runtime": 0.2827, | |
| "eval_samples_per_second": 601.322, | |
| "eval_steps_per_second": 10.612, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 0.9346233606338501, | |
| "learning_rate": 4.75e-05, | |
| "loss": 0.3178, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_LOCATION_f1": 0.45070422535211263, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.5714285714285714, | |
| "eval_LOCATION_recall": 0.37209302325581395, | |
| "eval_ORGANIZATION_f1": 0.5927835051546392, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.5476190476190477, | |
| "eval_ORGANIZATION_recall": 0.6460674157303371, | |
| "eval_PERSON_f1": 0.6597938144329896, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.588957055214724, | |
| "eval_PERSON_recall": 0.75, | |
| "eval_loss": 0.23492121696472168, | |
| "eval_overall_accuracy": 0.9319838056680162, | |
| "eval_overall_f1": 0.5919610231425092, | |
| "eval_overall_precision": 0.5664335664335665, | |
| "eval_overall_recall": 0.6198979591836735, | |
| "eval_runtime": 0.2837, | |
| "eval_samples_per_second": 599.31, | |
| "eval_steps_per_second": 10.576, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 1.3035882711410522, | |
| "learning_rate": 4.7e-05, | |
| "loss": 0.2406, | |
| "step": 576 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_LOCATION_f1": 0.7185628742514969, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.7407407407407407, | |
| "eval_LOCATION_recall": 0.6976744186046512, | |
| "eval_ORGANIZATION_f1": 0.712401055408971, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.6716417910447762, | |
| "eval_ORGANIZATION_recall": 0.7584269662921348, | |
| "eval_PERSON_f1": 0.8057553956834532, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.7466666666666667, | |
| "eval_PERSON_recall": 0.875, | |
| "eval_loss": 0.18347080051898956, | |
| "eval_overall_accuracy": 0.9535762483130904, | |
| "eval_overall_f1": 0.7451456310679612, | |
| "eval_overall_precision": 0.7106481481481481, | |
| "eval_overall_recall": 0.7831632653061225, | |
| "eval_runtime": 0.2844, | |
| "eval_samples_per_second": 597.709, | |
| "eval_steps_per_second": 10.548, | |
| "step": 576 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "grad_norm": 1.0643693208694458, | |
| "learning_rate": 4.6500000000000005e-05, | |
| "loss": 0.1942, | |
| "step": 672 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_LOCATION_f1": 0.7745664739884394, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.7701149425287356, | |
| "eval_LOCATION_recall": 0.7790697674418605, | |
| "eval_ORGANIZATION_f1": 0.7546174142480211, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.7114427860696517, | |
| "eval_ORGANIZATION_recall": 0.8033707865168539, | |
| "eval_PERSON_f1": 0.917910447761194, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.8785714285714286, | |
| "eval_PERSON_recall": 0.9609375, | |
| "eval_loss": 0.15194177627563477, | |
| "eval_overall_accuracy": 0.9624831309041836, | |
| "eval_overall_f1": 0.8121951219512196, | |
| "eval_overall_precision": 0.7780373831775701, | |
| "eval_overall_recall": 0.8494897959183674, | |
| "eval_runtime": 0.284, | |
| "eval_samples_per_second": 598.684, | |
| "eval_steps_per_second": 10.565, | |
| "step": 672 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 1.0617378950119019, | |
| "learning_rate": 4.600000000000001e-05, | |
| "loss": 0.1647, | |
| "step": 768 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_LOCATION_f1": 0.7836257309941521, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.788235294117647, | |
| "eval_LOCATION_recall": 0.7790697674418605, | |
| "eval_ORGANIZATION_f1": 0.7750677506775068, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.7486910994764397, | |
| "eval_ORGANIZATION_recall": 0.8033707865168539, | |
| "eval_PERSON_f1": 0.9323308270676692, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.8985507246376812, | |
| "eval_PERSON_recall": 0.96875, | |
| "eval_loss": 0.127915620803833, | |
| "eval_overall_accuracy": 0.965991902834008, | |
| "eval_overall_f1": 0.8287841191066998, | |
| "eval_overall_precision": 0.8067632850241546, | |
| "eval_overall_recall": 0.8520408163265306, | |
| "eval_runtime": 0.2813, | |
| "eval_samples_per_second": 604.319, | |
| "eval_steps_per_second": 10.664, | |
| "step": 768 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "grad_norm": 0.8089593052864075, | |
| "learning_rate": 4.55e-05, | |
| "loss": 0.1479, | |
| "step": 864 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_LOCATION_f1": 0.8114285714285714, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.797752808988764, | |
| "eval_LOCATION_recall": 0.8255813953488372, | |
| "eval_ORGANIZATION_f1": 0.7967914438502675, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.7602040816326531, | |
| "eval_ORGANIZATION_recall": 0.8370786516853933, | |
| "eval_PERSON_f1": 0.9393939393939394, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.9117647058823529, | |
| "eval_PERSON_recall": 0.96875, | |
| "eval_loss": 0.11303041875362396, | |
| "eval_overall_accuracy": 0.9689608636977058, | |
| "eval_overall_f1": 0.8462484624846248, | |
| "eval_overall_precision": 0.8171021377672208, | |
| "eval_overall_recall": 0.8775510204081632, | |
| "eval_runtime": 0.2848, | |
| "eval_samples_per_second": 596.814, | |
| "eval_steps_per_second": 10.532, | |
| "step": 864 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 3.2614407539367676, | |
| "learning_rate": 4.5e-05, | |
| "loss": 0.135, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_LOCATION_f1": 0.8, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.7659574468085106, | |
| "eval_LOCATION_recall": 0.8372093023255814, | |
| "eval_ORGANIZATION_f1": 0.8128342245989305, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.7755102040816326, | |
| "eval_ORGANIZATION_recall": 0.8539325842696629, | |
| "eval_PERSON_f1": 0.9389312977099238, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.917910447761194, | |
| "eval_PERSON_recall": 0.9609375, | |
| "eval_loss": 0.10374683886766434, | |
| "eval_overall_accuracy": 0.9681511470985156, | |
| "eval_overall_f1": 0.8504901960784313, | |
| "eval_overall_precision": 0.8183962264150944, | |
| "eval_overall_recall": 0.8852040816326531, | |
| "eval_runtime": 0.2808, | |
| "eval_samples_per_second": 605.48, | |
| "eval_steps_per_second": 10.685, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "grad_norm": 1.1339415311813354, | |
| "learning_rate": 4.4500000000000004e-05, | |
| "loss": 0.1317, | |
| "step": 1056 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_LOCATION_f1": 0.8202247191011235, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.7934782608695652, | |
| "eval_LOCATION_recall": 0.8488372093023255, | |
| "eval_ORGANIZATION_f1": 0.8383561643835616, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.8181818181818182, | |
| "eval_ORGANIZATION_recall": 0.8595505617977528, | |
| "eval_PERSON_f1": 0.9575289575289575, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.9465648854961832, | |
| "eval_PERSON_recall": 0.96875, | |
| "eval_loss": 0.09509219974279404, | |
| "eval_overall_accuracy": 0.9732793522267207, | |
| "eval_overall_f1": 0.8728179551122195, | |
| "eval_overall_precision": 0.8536585365853658, | |
| "eval_overall_recall": 0.8928571428571429, | |
| "eval_runtime": 0.2793, | |
| "eval_samples_per_second": 608.56, | |
| "eval_steps_per_second": 10.739, | |
| "step": 1056 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "grad_norm": 0.7799615263938904, | |
| "learning_rate": 4.4000000000000006e-05, | |
| "loss": 0.1196, | |
| "step": 1152 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_LOCATION_f1": 0.8131868131868132, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.7708333333333334, | |
| "eval_LOCATION_recall": 0.8604651162790697, | |
| "eval_ORGANIZATION_f1": 0.8633879781420766, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.8404255319148937, | |
| "eval_ORGANIZATION_recall": 0.8876404494382022, | |
| "eval_PERSON_f1": 0.9541984732824427, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.9328358208955224, | |
| "eval_PERSON_recall": 0.9765625, | |
| "eval_loss": 0.09041129052639008, | |
| "eval_overall_accuracy": 0.9748987854251012, | |
| "eval_overall_f1": 0.8814814814814814, | |
| "eval_overall_precision": 0.854066985645933, | |
| "eval_overall_recall": 0.9107142857142857, | |
| "eval_runtime": 0.2835, | |
| "eval_samples_per_second": 599.551, | |
| "eval_steps_per_second": 10.58, | |
| "step": 1152 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "grad_norm": 2.4215242862701416, | |
| "learning_rate": 4.35e-05, | |
| "loss": 0.1108, | |
| "step": 1248 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_LOCATION_f1": 0.8333333333333334, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.7978723404255319, | |
| "eval_LOCATION_recall": 0.872093023255814, | |
| "eval_ORGANIZATION_f1": 0.871934604904632, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.8465608465608465, | |
| "eval_ORGANIZATION_recall": 0.898876404494382, | |
| "eval_PERSON_f1": 0.9575289575289575, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.9465648854961832, | |
| "eval_PERSON_recall": 0.96875, | |
| "eval_loss": 0.08236891031265259, | |
| "eval_overall_accuracy": 0.9767881241565453, | |
| "eval_overall_f1": 0.8908188585607941, | |
| "eval_overall_precision": 0.8671497584541062, | |
| "eval_overall_recall": 0.9158163265306123, | |
| "eval_runtime": 0.281, | |
| "eval_samples_per_second": 604.972, | |
| "eval_steps_per_second": 10.676, | |
| "step": 1248 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "grad_norm": 0.8359857797622681, | |
| "learning_rate": 4.3e-05, | |
| "loss": 0.107, | |
| "step": 1344 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_LOCATION_f1": 0.839779005524862, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.8, | |
| "eval_LOCATION_recall": 0.8837209302325582, | |
| "eval_ORGANIZATION_f1": 0.8802228412256268, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.8729281767955801, | |
| "eval_ORGANIZATION_recall": 0.8876404494382022, | |
| "eval_PERSON_f1": 0.9538461538461539, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.9393939393939394, | |
| "eval_PERSON_recall": 0.96875, | |
| "eval_loss": 0.07973363250494003, | |
| "eval_overall_accuracy": 0.9781376518218623, | |
| "eval_overall_f1": 0.895, | |
| "eval_overall_precision": 0.8774509803921569, | |
| "eval_overall_recall": 0.9132653061224489, | |
| "eval_runtime": 0.2799, | |
| "eval_samples_per_second": 607.303, | |
| "eval_steps_per_second": 10.717, | |
| "step": 1344 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "grad_norm": 1.4929579496383667, | |
| "learning_rate": 4.25e-05, | |
| "loss": 0.1063, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_LOCATION_f1": 0.8222222222222222, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.7872340425531915, | |
| "eval_LOCATION_recall": 0.8604651162790697, | |
| "eval_ORGANIZATION_f1": 0.8821917808219177, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.8609625668449198, | |
| "eval_ORGANIZATION_recall": 0.9044943820224719, | |
| "eval_PERSON_f1": 0.9538461538461539, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.9393939393939394, | |
| "eval_PERSON_recall": 0.96875, | |
| "eval_loss": 0.07602919638156891, | |
| "eval_overall_accuracy": 0.9775978407557355, | |
| "eval_overall_f1": 0.8919254658385093, | |
| "eval_overall_precision": 0.8692493946731235, | |
| "eval_overall_recall": 0.9158163265306123, | |
| "eval_runtime": 0.2828, | |
| "eval_samples_per_second": 601.037, | |
| "eval_steps_per_second": 10.607, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "grad_norm": 1.2506853342056274, | |
| "learning_rate": 4.2e-05, | |
| "loss": 0.1, | |
| "step": 1536 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_LOCATION_f1": 0.8700564971751413, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.8461538461538461, | |
| "eval_LOCATION_recall": 0.8953488372093024, | |
| "eval_ORGANIZATION_f1": 0.8870523415977961, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.8702702702702703, | |
| "eval_ORGANIZATION_recall": 0.9044943820224719, | |
| "eval_PERSON_f1": 0.9612403100775193, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.9538461538461539, | |
| "eval_PERSON_recall": 0.96875, | |
| "eval_loss": 0.07240239530801773, | |
| "eval_overall_accuracy": 0.9794871794871794, | |
| "eval_overall_f1": 0.9072681704260652, | |
| "eval_overall_precision": 0.8916256157635468, | |
| "eval_overall_recall": 0.923469387755102, | |
| "eval_runtime": 0.2817, | |
| "eval_samples_per_second": 603.532, | |
| "eval_steps_per_second": 10.651, | |
| "step": 1536 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "grad_norm": 0.9440656304359436, | |
| "learning_rate": 4.15e-05, | |
| "loss": 0.095, | |
| "step": 1632 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_LOCATION_f1": 0.853932584269663, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.8260869565217391, | |
| "eval_LOCATION_recall": 0.8837209302325582, | |
| "eval_ORGANIZATION_f1": 0.8901098901098902, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.8709677419354839, | |
| "eval_ORGANIZATION_recall": 0.9101123595505618, | |
| "eval_PERSON_f1": 0.9575289575289575, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.9465648854961832, | |
| "eval_PERSON_recall": 0.96875, | |
| "eval_loss": 0.07051108777523041, | |
| "eval_overall_accuracy": 0.9789473684210527, | |
| "eval_overall_f1": 0.9038701622971286, | |
| "eval_overall_precision": 0.8850855745721271, | |
| "eval_overall_recall": 0.923469387755102, | |
| "eval_runtime": 0.2795, | |
| "eval_samples_per_second": 608.264, | |
| "eval_steps_per_second": 10.734, | |
| "step": 1632 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "grad_norm": 0.6154165267944336, | |
| "learning_rate": 4.1e-05, | |
| "loss": 0.0932, | |
| "step": 1728 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_LOCATION_f1": 0.8651685393258426, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.8369565217391305, | |
| "eval_LOCATION_recall": 0.8953488372093024, | |
| "eval_ORGANIZATION_f1": 0.8994413407821229, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.8944444444444445, | |
| "eval_ORGANIZATION_recall": 0.9044943820224719, | |
| "eval_PERSON_f1": 0.9575289575289575, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.9465648854961832, | |
| "eval_PERSON_recall": 0.96875, | |
| "eval_loss": 0.0697602704167366, | |
| "eval_overall_accuracy": 0.9802968960863697, | |
| "eval_overall_f1": 0.9106918238993711, | |
| "eval_overall_precision": 0.8982630272952854, | |
| "eval_overall_recall": 0.923469387755102, | |
| "eval_runtime": 0.2838, | |
| "eval_samples_per_second": 598.992, | |
| "eval_steps_per_second": 10.57, | |
| "step": 1728 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "grad_norm": 1.5888150930404663, | |
| "learning_rate": 4.05e-05, | |
| "loss": 0.0871, | |
| "step": 1824 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_LOCATION_f1": 0.8715083798882681, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.8387096774193549, | |
| "eval_LOCATION_recall": 0.9069767441860465, | |
| "eval_ORGANIZATION_f1": 0.8994413407821229, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.8944444444444445, | |
| "eval_ORGANIZATION_recall": 0.9044943820224719, | |
| "eval_PERSON_f1": 0.9575289575289575, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.9465648854961832, | |
| "eval_PERSON_recall": 0.96875, | |
| "eval_loss": 0.0672474279999733, | |
| "eval_overall_accuracy": 0.9800269905533063, | |
| "eval_overall_f1": 0.9120603015075376, | |
| "eval_overall_precision": 0.8985148514851485, | |
| "eval_overall_recall": 0.9260204081632653, | |
| "eval_runtime": 0.2792, | |
| "eval_samples_per_second": 608.919, | |
| "eval_steps_per_second": 10.746, | |
| "step": 1824 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "grad_norm": 0.6971399784088135, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0883, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_LOCATION_f1": 0.8666666666666666, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.8297872340425532, | |
| "eval_LOCATION_recall": 0.9069767441860465, | |
| "eval_ORGANIZATION_f1": 0.8994413407821229, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.8944444444444445, | |
| "eval_ORGANIZATION_recall": 0.9044943820224719, | |
| "eval_PERSON_f1": 0.9649805447470817, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.9612403100775194, | |
| "eval_PERSON_recall": 0.96875, | |
| "eval_loss": 0.06501375138759613, | |
| "eval_overall_accuracy": 0.9802968960863697, | |
| "eval_overall_f1": 0.9132075471698112, | |
| "eval_overall_precision": 0.9007444168734491, | |
| "eval_overall_recall": 0.9260204081632653, | |
| "eval_runtime": 0.2806, | |
| "eval_samples_per_second": 605.941, | |
| "eval_steps_per_second": 10.693, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "grad_norm": 0.7672743797302246, | |
| "learning_rate": 3.9500000000000005e-05, | |
| "loss": 0.0832, | |
| "step": 2016 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_LOCATION_f1": 0.8666666666666666, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.8297872340425532, | |
| "eval_LOCATION_recall": 0.9069767441860465, | |
| "eval_ORGANIZATION_f1": 0.9019607843137254, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.8994413407821229, | |
| "eval_ORGANIZATION_recall": 0.9044943820224719, | |
| "eval_PERSON_f1": 0.9649805447470817, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.9612403100775194, | |
| "eval_PERSON_recall": 0.96875, | |
| "eval_loss": 0.06505837291479111, | |
| "eval_overall_accuracy": 0.9811066126855601, | |
| "eval_overall_f1": 0.9143576826196474, | |
| "eval_overall_precision": 0.9029850746268657, | |
| "eval_overall_recall": 0.9260204081632653, | |
| "eval_runtime": 0.283, | |
| "eval_samples_per_second": 600.694, | |
| "eval_steps_per_second": 10.6, | |
| "step": 2016 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "grad_norm": 1.2235254049301147, | |
| "learning_rate": 3.9000000000000006e-05, | |
| "loss": 0.0829, | |
| "step": 2112 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_LOCATION_f1": 0.8571428571428572, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.8125, | |
| "eval_LOCATION_recall": 0.9069767441860465, | |
| "eval_ORGANIZATION_f1": 0.8876712328767122, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.8663101604278075, | |
| "eval_ORGANIZATION_recall": 0.9101123595505618, | |
| "eval_PERSON_f1": 0.9575289575289575, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.9465648854961832, | |
| "eval_PERSON_recall": 0.96875, | |
| "eval_loss": 0.06451266258955002, | |
| "eval_overall_accuracy": 0.9786774628879892, | |
| "eval_overall_f1": 0.9032258064516129, | |
| "eval_overall_precision": 0.8792270531400966, | |
| "eval_overall_recall": 0.9285714285714286, | |
| "eval_runtime": 0.2828, | |
| "eval_samples_per_second": 601.12, | |
| "eval_steps_per_second": 10.608, | |
| "step": 2112 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "grad_norm": 0.933464527130127, | |
| "learning_rate": 3.85e-05, | |
| "loss": 0.0789, | |
| "step": 2208 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_LOCATION_f1": 0.861878453038674, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.8210526315789474, | |
| "eval_LOCATION_recall": 0.9069767441860465, | |
| "eval_ORGANIZATION_f1": 0.9019607843137254, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.8994413407821229, | |
| "eval_ORGANIZATION_recall": 0.9044943820224719, | |
| "eval_PERSON_f1": 0.9765625, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.9765625, | |
| "eval_PERSON_recall": 0.9765625, | |
| "eval_loss": 0.06014208123087883, | |
| "eval_overall_accuracy": 0.9819163292847504, | |
| "eval_overall_f1": 0.9168765743073048, | |
| "eval_overall_precision": 0.9054726368159204, | |
| "eval_overall_recall": 0.9285714285714286, | |
| "eval_runtime": 0.2819, | |
| "eval_samples_per_second": 603.138, | |
| "eval_steps_per_second": 10.644, | |
| "step": 2208 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "grad_norm": 0.9433938264846802, | |
| "learning_rate": 3.8e-05, | |
| "loss": 0.078, | |
| "step": 2304 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_LOCATION_f1": 0.861878453038674, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.8210526315789474, | |
| "eval_LOCATION_recall": 0.9069767441860465, | |
| "eval_ORGANIZATION_f1": 0.8901408450704225, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.8926553672316384, | |
| "eval_ORGANIZATION_recall": 0.8876404494382022, | |
| "eval_PERSON_f1": 0.9765625, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.9765625, | |
| "eval_PERSON_recall": 0.9765625, | |
| "eval_loss": 0.061247795820236206, | |
| "eval_overall_accuracy": 0.9805668016194332, | |
| "eval_overall_f1": 0.9116161616161615, | |
| "eval_overall_precision": 0.9025, | |
| "eval_overall_recall": 0.9209183673469388, | |
| "eval_runtime": 0.2813, | |
| "eval_samples_per_second": 604.352, | |
| "eval_steps_per_second": 10.665, | |
| "step": 2304 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "grad_norm": 1.3498409986495972, | |
| "learning_rate": 3.7500000000000003e-05, | |
| "loss": 0.0756, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_LOCATION_f1": 0.8666666666666666, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.8297872340425532, | |
| "eval_LOCATION_recall": 0.9069767441860465, | |
| "eval_ORGANIZATION_f1": 0.9044943820224719, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.9044943820224719, | |
| "eval_ORGANIZATION_recall": 0.9044943820224719, | |
| "eval_PERSON_f1": 0.9689922480620154, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.9615384615384616, | |
| "eval_PERSON_recall": 0.9765625, | |
| "eval_loss": 0.059408556669950485, | |
| "eval_overall_accuracy": 0.9805668016194332, | |
| "eval_overall_f1": 0.9168765743073048, | |
| "eval_overall_precision": 0.9054726368159204, | |
| "eval_overall_recall": 0.9285714285714286, | |
| "eval_runtime": 0.2825, | |
| "eval_samples_per_second": 601.695, | |
| "eval_steps_per_second": 10.618, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "grad_norm": 0.35765427350997925, | |
| "learning_rate": 3.7e-05, | |
| "loss": 0.0767, | |
| "step": 2496 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_LOCATION_f1": 0.8449197860962566, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.7821782178217822, | |
| "eval_LOCATION_recall": 0.9186046511627907, | |
| "eval_ORGANIZATION_f1": 0.8831908831908832, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.8959537572254336, | |
| "eval_ORGANIZATION_recall": 0.8707865168539326, | |
| "eval_PERSON_f1": 0.9765625, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.9765625, | |
| "eval_PERSON_recall": 0.9765625, | |
| "eval_loss": 0.05880308896303177, | |
| "eval_overall_accuracy": 0.9800269905533063, | |
| "eval_overall_f1": 0.9042821158690176, | |
| "eval_overall_precision": 0.8930348258706468, | |
| "eval_overall_recall": 0.9158163265306123, | |
| "eval_runtime": 0.283, | |
| "eval_samples_per_second": 600.655, | |
| "eval_steps_per_second": 10.6, | |
| "step": 2496 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "grad_norm": 1.1899181604385376, | |
| "learning_rate": 3.65e-05, | |
| "loss": 0.0721, | |
| "step": 2592 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_LOCATION_f1": 0.8571428571428572, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.8125, | |
| "eval_LOCATION_recall": 0.9069767441860465, | |
| "eval_ORGANIZATION_f1": 0.8975069252077562, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.8852459016393442, | |
| "eval_ORGANIZATION_recall": 0.9101123595505618, | |
| "eval_PERSON_f1": 0.9765625, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.9765625, | |
| "eval_PERSON_recall": 0.9765625, | |
| "eval_loss": 0.05609607696533203, | |
| "eval_overall_accuracy": 0.9813765182186235, | |
| "eval_overall_f1": 0.9136420525657072, | |
| "eval_overall_precision": 0.8968058968058968, | |
| "eval_overall_recall": 0.9311224489795918, | |
| "eval_runtime": 0.2825, | |
| "eval_samples_per_second": 601.838, | |
| "eval_steps_per_second": 10.621, | |
| "step": 2592 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "grad_norm": 1.2701897621154785, | |
| "learning_rate": 3.6e-05, | |
| "loss": 0.0719, | |
| "step": 2688 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_LOCATION_f1": 0.8777777777777779, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.8404255319148937, | |
| "eval_LOCATION_recall": 0.9186046511627907, | |
| "eval_ORGANIZATION_f1": 0.9014084507042253, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.903954802259887, | |
| "eval_ORGANIZATION_recall": 0.898876404494382, | |
| "eval_PERSON_f1": 0.9765625, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.9765625, | |
| "eval_PERSON_recall": 0.9765625, | |
| "eval_loss": 0.05588143318891525, | |
| "eval_overall_accuracy": 0.9819163292847504, | |
| "eval_overall_f1": 0.9203539823008849, | |
| "eval_overall_precision": 0.9122807017543859, | |
| "eval_overall_recall": 0.9285714285714286, | |
| "eval_runtime": 0.2802, | |
| "eval_samples_per_second": 606.797, | |
| "eval_steps_per_second": 10.708, | |
| "step": 2688 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "grad_norm": 1.3545186519622803, | |
| "learning_rate": 3.55e-05, | |
| "loss": 0.0702, | |
| "step": 2784 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_LOCATION_f1": 0.8764044943820224, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.8478260869565217, | |
| "eval_LOCATION_recall": 0.9069767441860465, | |
| "eval_ORGANIZATION_f1": 0.9141274238227147, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.9016393442622951, | |
| "eval_ORGANIZATION_recall": 0.9269662921348315, | |
| "eval_PERSON_f1": 0.9765625, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.9765625, | |
| "eval_PERSON_recall": 0.9765625, | |
| "eval_loss": 0.05434948578476906, | |
| "eval_overall_accuracy": 0.9816464237516869, | |
| "eval_overall_f1": 0.9257861635220126, | |
| "eval_overall_precision": 0.913151364764268, | |
| "eval_overall_recall": 0.9387755102040817, | |
| "eval_runtime": 0.2819, | |
| "eval_samples_per_second": 603.148, | |
| "eval_steps_per_second": 10.644, | |
| "step": 2784 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "grad_norm": 0.36313942074775696, | |
| "learning_rate": 3.5e-05, | |
| "loss": 0.0711, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_LOCATION_f1": 0.8863636363636364, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.8666666666666667, | |
| "eval_LOCATION_recall": 0.9069767441860465, | |
| "eval_ORGANIZATION_f1": 0.9166666666666666, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.9065934065934066, | |
| "eval_ORGANIZATION_recall": 0.9269662921348315, | |
| "eval_PERSON_f1": 0.9727626459143969, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.9689922480620154, | |
| "eval_PERSON_recall": 0.9765625, | |
| "eval_loss": 0.05385398864746094, | |
| "eval_overall_accuracy": 0.9819163292847504, | |
| "eval_overall_f1": 0.9281210592686003, | |
| "eval_overall_precision": 0.9177057356608479, | |
| "eval_overall_recall": 0.9387755102040817, | |
| "eval_runtime": 0.2813, | |
| "eval_samples_per_second": 604.362, | |
| "eval_steps_per_second": 10.665, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "grad_norm": 1.1205620765686035, | |
| "learning_rate": 3.45e-05, | |
| "loss": 0.067, | |
| "step": 2976 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_LOCATION_f1": 0.858695652173913, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.8061224489795918, | |
| "eval_LOCATION_recall": 0.9186046511627907, | |
| "eval_ORGANIZATION_f1": 0.9101123595505618, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.9101123595505618, | |
| "eval_ORGANIZATION_recall": 0.9101123595505618, | |
| "eval_PERSON_f1": 0.9765625, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.9765625, | |
| "eval_PERSON_recall": 0.9765625, | |
| "eval_loss": 0.05762900039553642, | |
| "eval_overall_accuracy": 0.9819163292847504, | |
| "eval_overall_f1": 0.9195979899497488, | |
| "eval_overall_precision": 0.905940594059406, | |
| "eval_overall_recall": 0.9336734693877551, | |
| "eval_runtime": 0.2839, | |
| "eval_samples_per_second": 598.882, | |
| "eval_steps_per_second": 10.569, | |
| "step": 2976 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "grad_norm": 0.6993715167045593, | |
| "learning_rate": 3.4000000000000007e-05, | |
| "loss": 0.0664, | |
| "step": 3072 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_LOCATION_f1": 0.861878453038674, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.8210526315789474, | |
| "eval_LOCATION_recall": 0.9069767441860465, | |
| "eval_ORGANIZATION_f1": 0.9111111111111112, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.9010989010989011, | |
| "eval_ORGANIZATION_recall": 0.9213483146067416, | |
| "eval_PERSON_f1": 0.9727626459143969, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.9689922480620154, | |
| "eval_PERSON_recall": 0.9765625, | |
| "eval_loss": 0.05667094141244888, | |
| "eval_overall_accuracy": 0.9813765182186235, | |
| "eval_overall_f1": 0.9197994987468671, | |
| "eval_overall_precision": 0.9039408866995073, | |
| "eval_overall_recall": 0.9362244897959183, | |
| "eval_runtime": 0.2807, | |
| "eval_samples_per_second": 605.552, | |
| "eval_steps_per_second": 10.686, | |
| "step": 3072 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "grad_norm": 3.8367385864257812, | |
| "learning_rate": 3.35e-05, | |
| "loss": 0.0642, | |
| "step": 3168 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_LOCATION_f1": 0.8729281767955801, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.8315789473684211, | |
| "eval_LOCATION_recall": 0.9186046511627907, | |
| "eval_ORGANIZATION_f1": 0.9070422535211267, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.9096045197740112, | |
| "eval_ORGANIZATION_recall": 0.9044943820224719, | |
| "eval_PERSON_f1": 0.9765625, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.9765625, | |
| "eval_PERSON_recall": 0.9765625, | |
| "eval_loss": 0.055755291134119034, | |
| "eval_overall_accuracy": 0.9824561403508771, | |
| "eval_overall_f1": 0.9217171717171717, | |
| "eval_overall_precision": 0.9125, | |
| "eval_overall_recall": 0.9311224489795918, | |
| "eval_runtime": 0.2821, | |
| "eval_samples_per_second": 602.531, | |
| "eval_steps_per_second": 10.633, | |
| "step": 3168 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "grad_norm": 0.8335817456245422, | |
| "learning_rate": 3.3e-05, | |
| "loss": 0.0642, | |
| "step": 3264 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_LOCATION_f1": 0.8876404494382023, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.8586956521739131, | |
| "eval_LOCATION_recall": 0.9186046511627907, | |
| "eval_ORGANIZATION_f1": 0.9157303370786517, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.9157303370786517, | |
| "eval_ORGANIZATION_recall": 0.9157303370786517, | |
| "eval_PERSON_f1": 0.9765625, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.9765625, | |
| "eval_PERSON_recall": 0.9765625, | |
| "eval_loss": 0.05453602224588394, | |
| "eval_overall_accuracy": 0.9835357624831309, | |
| "eval_overall_f1": 0.929113924050633, | |
| "eval_overall_precision": 0.9221105527638191, | |
| "eval_overall_recall": 0.9362244897959183, | |
| "eval_runtime": 0.2794, | |
| "eval_samples_per_second": 608.461, | |
| "eval_steps_per_second": 10.738, | |
| "step": 3264 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "grad_norm": 1.6749961376190186, | |
| "learning_rate": 3.2500000000000004e-05, | |
| "loss": 0.0624, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_LOCATION_f1": 0.8926553672316384, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.8681318681318682, | |
| "eval_LOCATION_recall": 0.9186046511627907, | |
| "eval_ORGANIZATION_f1": 0.9162011173184358, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.9111111111111111, | |
| "eval_ORGANIZATION_recall": 0.9213483146067416, | |
| "eval_PERSON_f1": 0.9765625, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.9765625, | |
| "eval_PERSON_recall": 0.9765625, | |
| "eval_loss": 0.05416334420442581, | |
| "eval_overall_accuracy": 0.982995951417004, | |
| "eval_overall_f1": 0.9304677623261693, | |
| "eval_overall_precision": 0.9223057644110275, | |
| "eval_overall_recall": 0.9387755102040817, | |
| "eval_runtime": 0.2801, | |
| "eval_samples_per_second": 606.951, | |
| "eval_steps_per_second": 10.711, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "grad_norm": 1.6614550352096558, | |
| "learning_rate": 3.2000000000000005e-05, | |
| "loss": 0.0651, | |
| "step": 3456 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_LOCATION_f1": 0.8977272727272728, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.8777777777777778, | |
| "eval_LOCATION_recall": 0.9186046511627907, | |
| "eval_ORGANIZATION_f1": 0.9213483146067416, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.9213483146067416, | |
| "eval_ORGANIZATION_recall": 0.9213483146067416, | |
| "eval_PERSON_f1": 0.9727626459143969, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.9689922480620154, | |
| "eval_PERSON_recall": 0.9765625, | |
| "eval_loss": 0.053541768342256546, | |
| "eval_overall_accuracy": 0.9832658569500675, | |
| "eval_overall_f1": 0.9328263624841572, | |
| "eval_overall_precision": 0.9269521410579346, | |
| "eval_overall_recall": 0.9387755102040817, | |
| "eval_runtime": 0.2829, | |
| "eval_samples_per_second": 600.914, | |
| "eval_steps_per_second": 10.604, | |
| "step": 3456 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "grad_norm": 3.9047365188598633, | |
| "learning_rate": 3.15e-05, | |
| "loss": 0.0635, | |
| "step": 3552 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_LOCATION_f1": 0.896551724137931, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.8863636363636364, | |
| "eval_LOCATION_recall": 0.9069767441860465, | |
| "eval_ORGANIZATION_f1": 0.9162011173184358, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.9111111111111111, | |
| "eval_ORGANIZATION_recall": 0.9213483146067416, | |
| "eval_PERSON_f1": 0.9765625, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.9765625, | |
| "eval_PERSON_recall": 0.9765625, | |
| "eval_loss": 0.052303437143564224, | |
| "eval_overall_accuracy": 0.9832658569500675, | |
| "eval_overall_f1": 0.9314720812182741, | |
| "eval_overall_precision": 0.9267676767676768, | |
| "eval_overall_recall": 0.9362244897959183, | |
| "eval_runtime": 0.2809, | |
| "eval_samples_per_second": 605.215, | |
| "eval_steps_per_second": 10.68, | |
| "step": 3552 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "grad_norm": 0.4264446198940277, | |
| "learning_rate": 3.1e-05, | |
| "loss": 0.0617, | |
| "step": 3648 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_LOCATION_f1": 0.8876404494382023, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.8586956521739131, | |
| "eval_LOCATION_recall": 0.9186046511627907, | |
| "eval_ORGANIZATION_f1": 0.9157303370786517, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.9157303370786517, | |
| "eval_ORGANIZATION_recall": 0.9157303370786517, | |
| "eval_PERSON_f1": 0.9765625, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.9765625, | |
| "eval_PERSON_recall": 0.9765625, | |
| "eval_loss": 0.052760832011699677, | |
| "eval_overall_accuracy": 0.9838056680161943, | |
| "eval_overall_f1": 0.929113924050633, | |
| "eval_overall_precision": 0.9221105527638191, | |
| "eval_overall_recall": 0.9362244897959183, | |
| "eval_runtime": 0.2812, | |
| "eval_samples_per_second": 604.578, | |
| "eval_steps_per_second": 10.669, | |
| "step": 3648 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "grad_norm": 0.7656244039535522, | |
| "learning_rate": 3.05e-05, | |
| "loss": 0.0581, | |
| "step": 3744 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_LOCATION_f1": 0.858695652173913, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.8061224489795918, | |
| "eval_LOCATION_recall": 0.9186046511627907, | |
| "eval_ORGANIZATION_f1": 0.9039548022598869, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.9090909090909091, | |
| "eval_ORGANIZATION_recall": 0.898876404494382, | |
| "eval_PERSON_f1": 0.9765625, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.9765625, | |
| "eval_PERSON_recall": 0.9765625, | |
| "eval_loss": 0.05475260689854622, | |
| "eval_overall_accuracy": 0.9827260458839406, | |
| "eval_overall_f1": 0.9168765743073048, | |
| "eval_overall_precision": 0.9054726368159204, | |
| "eval_overall_recall": 0.9285714285714286, | |
| "eval_runtime": 0.2823, | |
| "eval_samples_per_second": 602.161, | |
| "eval_steps_per_second": 10.626, | |
| "step": 3744 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "grad_norm": 0.5649272203445435, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0597, | |
| "step": 3840 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_LOCATION_f1": 0.8977272727272728, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.8777777777777778, | |
| "eval_LOCATION_recall": 0.9186046511627907, | |
| "eval_ORGANIZATION_f1": 0.9269662921348315, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.9269662921348315, | |
| "eval_ORGANIZATION_recall": 0.9269662921348315, | |
| "eval_PERSON_f1": 0.9765625, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.9765625, | |
| "eval_PERSON_recall": 0.9765625, | |
| "eval_loss": 0.051006708294153214, | |
| "eval_overall_accuracy": 0.9846153846153847, | |
| "eval_overall_f1": 0.9365482233502538, | |
| "eval_overall_precision": 0.9318181818181818, | |
| "eval_overall_recall": 0.9413265306122449, | |
| "eval_runtime": 0.2793, | |
| "eval_samples_per_second": 608.712, | |
| "eval_steps_per_second": 10.742, | |
| "step": 3840 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "grad_norm": 0.19076836109161377, | |
| "learning_rate": 2.95e-05, | |
| "loss": 0.0569, | |
| "step": 3936 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_LOCATION_f1": 0.8977272727272728, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.8777777777777778, | |
| "eval_LOCATION_recall": 0.9186046511627907, | |
| "eval_ORGANIZATION_f1": 0.9269662921348315, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.9269662921348315, | |
| "eval_ORGANIZATION_recall": 0.9269662921348315, | |
| "eval_PERSON_f1": 0.9765625, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.9765625, | |
| "eval_PERSON_recall": 0.9765625, | |
| "eval_loss": 0.0505344495177269, | |
| "eval_overall_accuracy": 0.9848852901484481, | |
| "eval_overall_f1": 0.9365482233502538, | |
| "eval_overall_precision": 0.9318181818181818, | |
| "eval_overall_recall": 0.9413265306122449, | |
| "eval_runtime": 0.2814, | |
| "eval_samples_per_second": 604.17, | |
| "eval_steps_per_second": 10.662, | |
| "step": 3936 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "grad_norm": 2.5419020652770996, | |
| "learning_rate": 2.9e-05, | |
| "loss": 0.0579, | |
| "step": 4032 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_LOCATION_f1": 0.8977272727272728, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.8777777777777778, | |
| "eval_LOCATION_recall": 0.9186046511627907, | |
| "eval_ORGANIZATION_f1": 0.9269662921348315, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.9269662921348315, | |
| "eval_ORGANIZATION_recall": 0.9269662921348315, | |
| "eval_PERSON_f1": 0.9765625, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.9765625, | |
| "eval_PERSON_recall": 0.9765625, | |
| "eval_loss": 0.050377897918224335, | |
| "eval_overall_accuracy": 0.9843454790823212, | |
| "eval_overall_f1": 0.9365482233502538, | |
| "eval_overall_precision": 0.9318181818181818, | |
| "eval_overall_recall": 0.9413265306122449, | |
| "eval_runtime": 0.2812, | |
| "eval_samples_per_second": 604.567, | |
| "eval_steps_per_second": 10.669, | |
| "step": 4032 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "grad_norm": 0.1431387960910797, | |
| "learning_rate": 2.8499999999999998e-05, | |
| "loss": 0.0564, | |
| "step": 4128 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_LOCATION_f1": 0.8926553672316384, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.8681318681318682, | |
| "eval_LOCATION_recall": 0.9186046511627907, | |
| "eval_ORGANIZATION_f1": 0.9131652661064427, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.9106145251396648, | |
| "eval_ORGANIZATION_recall": 0.9157303370786517, | |
| "eval_PERSON_f1": 0.9803921568627452, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.984251968503937, | |
| "eval_PERSON_recall": 0.9765625, | |
| "eval_loss": 0.050585947930812836, | |
| "eval_overall_accuracy": 0.9843454790823212, | |
| "eval_overall_f1": 0.9302915082382762, | |
| "eval_overall_precision": 0.924433249370277, | |
| "eval_overall_recall": 0.9362244897959183, | |
| "eval_runtime": 0.2833, | |
| "eval_samples_per_second": 600.171, | |
| "eval_steps_per_second": 10.591, | |
| "step": 4128 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "grad_norm": 1.1703745126724243, | |
| "learning_rate": 2.8000000000000003e-05, | |
| "loss": 0.0572, | |
| "step": 4224 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_LOCATION_f1": 0.8926553672316384, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.8681318681318682, | |
| "eval_LOCATION_recall": 0.9186046511627907, | |
| "eval_ORGANIZATION_f1": 0.9192200557103065, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.9116022099447514, | |
| "eval_ORGANIZATION_recall": 0.9269662921348315, | |
| "eval_PERSON_f1": 0.9803921568627452, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.984251968503937, | |
| "eval_PERSON_recall": 0.9765625, | |
| "eval_loss": 0.04985123872756958, | |
| "eval_overall_accuracy": 0.9848852901484481, | |
| "eval_overall_f1": 0.9329962073324906, | |
| "eval_overall_precision": 0.924812030075188, | |
| "eval_overall_recall": 0.9413265306122449, | |
| "eval_runtime": 0.2812, | |
| "eval_samples_per_second": 604.526, | |
| "eval_steps_per_second": 10.668, | |
| "step": 4224 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "grad_norm": 1.3757704496383667, | |
| "learning_rate": 2.7500000000000004e-05, | |
| "loss": 0.0563, | |
| "step": 4320 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_LOCATION_f1": 0.8926553672316384, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.8681318681318682, | |
| "eval_LOCATION_recall": 0.9186046511627907, | |
| "eval_ORGANIZATION_f1": 0.9213483146067416, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.9213483146067416, | |
| "eval_ORGANIZATION_recall": 0.9213483146067416, | |
| "eval_PERSON_f1": 0.9803921568627452, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.984251968503937, | |
| "eval_PERSON_recall": 0.9765625, | |
| "eval_loss": 0.04884723946452141, | |
| "eval_overall_accuracy": 0.9843454790823212, | |
| "eval_overall_f1": 0.934010152284264, | |
| "eval_overall_precision": 0.9292929292929293, | |
| "eval_overall_recall": 0.9387755102040817, | |
| "eval_runtime": 0.2837, | |
| "eval_samples_per_second": 599.302, | |
| "eval_steps_per_second": 10.576, | |
| "step": 4320 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "grad_norm": 2.0719878673553467, | |
| "learning_rate": 2.7000000000000002e-05, | |
| "loss": 0.0594, | |
| "step": 4416 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_LOCATION_f1": 0.8926553672316384, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.8681318681318682, | |
| "eval_LOCATION_recall": 0.9186046511627907, | |
| "eval_ORGANIZATION_f1": 0.9217877094972067, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.9166666666666666, | |
| "eval_ORGANIZATION_recall": 0.9269662921348315, | |
| "eval_PERSON_f1": 0.9765625, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.9765625, | |
| "eval_PERSON_recall": 0.9765625, | |
| "eval_loss": 0.0507470928132534, | |
| "eval_overall_accuracy": 0.9840755735492578, | |
| "eval_overall_f1": 0.9329962073324906, | |
| "eval_overall_precision": 0.924812030075188, | |
| "eval_overall_recall": 0.9413265306122449, | |
| "eval_runtime": 0.2845, | |
| "eval_samples_per_second": 597.493, | |
| "eval_steps_per_second": 10.544, | |
| "step": 4416 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "grad_norm": 0.6790814399719238, | |
| "learning_rate": 2.6500000000000004e-05, | |
| "loss": 0.0545, | |
| "step": 4512 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_LOCATION_f1": 0.8926553672316384, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.8681318681318682, | |
| "eval_LOCATION_recall": 0.9186046511627907, | |
| "eval_ORGANIZATION_f1": 0.9187675070028011, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.9162011173184358, | |
| "eval_ORGANIZATION_recall": 0.9213483146067416, | |
| "eval_PERSON_f1": 0.9765625, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.9765625, | |
| "eval_PERSON_recall": 0.9765625, | |
| "eval_loss": 0.04966941103339195, | |
| "eval_overall_accuracy": 0.9846153846153847, | |
| "eval_overall_f1": 0.9316455696202531, | |
| "eval_overall_precision": 0.9246231155778895, | |
| "eval_overall_recall": 0.9387755102040817, | |
| "eval_runtime": 0.2818, | |
| "eval_samples_per_second": 603.305, | |
| "eval_steps_per_second": 10.647, | |
| "step": 4512 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "grad_norm": 1.4126778841018677, | |
| "learning_rate": 2.6000000000000002e-05, | |
| "loss": 0.0536, | |
| "step": 4608 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_LOCATION_f1": 0.8926553672316384, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.8681318681318682, | |
| "eval_LOCATION_recall": 0.9186046511627907, | |
| "eval_ORGANIZATION_f1": 0.9187675070028011, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.9162011173184358, | |
| "eval_ORGANIZATION_recall": 0.9213483146067416, | |
| "eval_PERSON_f1": 0.9765625, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.9765625, | |
| "eval_PERSON_recall": 0.9765625, | |
| "eval_loss": 0.04870031401515007, | |
| "eval_overall_accuracy": 0.9848852901484481, | |
| "eval_overall_f1": 0.9316455696202531, | |
| "eval_overall_precision": 0.9246231155778895, | |
| "eval_overall_recall": 0.9387755102040817, | |
| "eval_runtime": 0.2829, | |
| "eval_samples_per_second": 600.855, | |
| "eval_steps_per_second": 10.603, | |
| "step": 4608 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "grad_norm": 0.6721929907798767, | |
| "learning_rate": 2.5500000000000003e-05, | |
| "loss": 0.0556, | |
| "step": 4704 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_LOCATION_f1": 0.8926553672316384, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.8681318681318682, | |
| "eval_LOCATION_recall": 0.9186046511627907, | |
| "eval_ORGANIZATION_f1": 0.9070422535211267, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.9096045197740112, | |
| "eval_ORGANIZATION_recall": 0.9044943820224719, | |
| "eval_PERSON_f1": 0.9765625, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.9765625, | |
| "eval_PERSON_recall": 0.9765625, | |
| "eval_loss": 0.0500752292573452, | |
| "eval_overall_accuracy": 0.9832658569500675, | |
| "eval_overall_f1": 0.9263959390862943, | |
| "eval_overall_precision": 0.9217171717171717, | |
| "eval_overall_recall": 0.9311224489795918, | |
| "eval_runtime": 0.2821, | |
| "eval_samples_per_second": 602.659, | |
| "eval_steps_per_second": 10.635, | |
| "step": 4704 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "grad_norm": 1.7530306577682495, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.0522, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_LOCATION_f1": 0.9039548022598871, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.8791208791208791, | |
| "eval_LOCATION_recall": 0.9302325581395349, | |
| "eval_ORGANIZATION_f1": 0.9187675070028011, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.9162011173184358, | |
| "eval_ORGANIZATION_recall": 0.9213483146067416, | |
| "eval_PERSON_f1": 0.9765625, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.9765625, | |
| "eval_PERSON_recall": 0.9765625, | |
| "eval_loss": 0.05056515708565712, | |
| "eval_overall_accuracy": 0.9854251012145749, | |
| "eval_overall_f1": 0.9341772151898734, | |
| "eval_overall_precision": 0.9271356783919598, | |
| "eval_overall_recall": 0.9413265306122449, | |
| "eval_runtime": 0.2897, | |
| "eval_samples_per_second": 586.89, | |
| "eval_steps_per_second": 10.357, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "grad_norm": 0.5993042588233948, | |
| "learning_rate": 2.45e-05, | |
| "loss": 0.0527, | |
| "step": 4896 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_LOCATION_f1": 0.9039548022598871, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.8791208791208791, | |
| "eval_LOCATION_recall": 0.9302325581395349, | |
| "eval_ORGANIZATION_f1": 0.9265536723163842, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.9318181818181818, | |
| "eval_ORGANIZATION_recall": 0.9213483146067416, | |
| "eval_PERSON_f1": 0.9765625, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.9765625, | |
| "eval_PERSON_recall": 0.9765625, | |
| "eval_loss": 0.049558304250240326, | |
| "eval_overall_accuracy": 0.9851551956815114, | |
| "eval_overall_f1": 0.9377382465057178, | |
| "eval_overall_precision": 0.9341772151898734, | |
| "eval_overall_recall": 0.9413265306122449, | |
| "eval_runtime": 0.2824, | |
| "eval_samples_per_second": 601.901, | |
| "eval_steps_per_second": 10.622, | |
| "step": 4896 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "grad_norm": 0.8313167691230774, | |
| "learning_rate": 2.4e-05, | |
| "loss": 0.0529, | |
| "step": 4992 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_LOCATION_f1": 0.9039548022598871, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.8791208791208791, | |
| "eval_LOCATION_recall": 0.9302325581395349, | |
| "eval_ORGANIZATION_f1": 0.9239436619718311, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.9265536723163842, | |
| "eval_ORGANIZATION_recall": 0.9213483146067416, | |
| "eval_PERSON_f1": 0.96875, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.96875, | |
| "eval_PERSON_recall": 0.96875, | |
| "eval_loss": 0.049007900059223175, | |
| "eval_overall_accuracy": 0.9851551956815114, | |
| "eval_overall_f1": 0.934010152284264, | |
| "eval_overall_precision": 0.9292929292929293, | |
| "eval_overall_recall": 0.9387755102040817, | |
| "eval_runtime": 0.2818, | |
| "eval_samples_per_second": 603.306, | |
| "eval_steps_per_second": 10.647, | |
| "step": 4992 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "grad_norm": 0.9506852626800537, | |
| "learning_rate": 2.35e-05, | |
| "loss": 0.0522, | |
| "step": 5088 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_LOCATION_f1": 0.9039548022598871, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.8791208791208791, | |
| "eval_LOCATION_recall": 0.9302325581395349, | |
| "eval_ORGANIZATION_f1": 0.9157303370786517, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.9157303370786517, | |
| "eval_ORGANIZATION_recall": 0.9157303370786517, | |
| "eval_PERSON_f1": 0.9765625, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.9765625, | |
| "eval_PERSON_recall": 0.9765625, | |
| "eval_loss": 0.04938499256968498, | |
| "eval_overall_accuracy": 0.9846153846153847, | |
| "eval_overall_f1": 0.9328263624841572, | |
| "eval_overall_precision": 0.9269521410579346, | |
| "eval_overall_recall": 0.9387755102040817, | |
| "eval_runtime": 0.281, | |
| "eval_samples_per_second": 605.019, | |
| "eval_steps_per_second": 10.677, | |
| "step": 5088 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "grad_norm": 2.244389533996582, | |
| "learning_rate": 2.3000000000000003e-05, | |
| "loss": 0.0525, | |
| "step": 5184 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_LOCATION_f1": 0.9090909090909092, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.8888888888888888, | |
| "eval_LOCATION_recall": 0.9302325581395349, | |
| "eval_ORGANIZATION_f1": 0.9269662921348315, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.9269662921348315, | |
| "eval_ORGANIZATION_recall": 0.9269662921348315, | |
| "eval_PERSON_f1": 0.9765625, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.9765625, | |
| "eval_PERSON_recall": 0.9765625, | |
| "eval_loss": 0.04819142818450928, | |
| "eval_overall_accuracy": 0.9859649122807017, | |
| "eval_overall_f1": 0.9390862944162437, | |
| "eval_overall_precision": 0.9343434343434344, | |
| "eval_overall_recall": 0.9438775510204082, | |
| "eval_runtime": 0.2815, | |
| "eval_samples_per_second": 603.971, | |
| "eval_steps_per_second": 10.658, | |
| "step": 5184 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "grad_norm": 2.14715838432312, | |
| "learning_rate": 2.25e-05, | |
| "loss": 0.0512, | |
| "step": 5280 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "eval_LOCATION_f1": 0.898876404494382, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.8695652173913043, | |
| "eval_LOCATION_recall": 0.9302325581395349, | |
| "eval_ORGANIZATION_f1": 0.9265536723163842, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.9318181818181818, | |
| "eval_ORGANIZATION_recall": 0.9213483146067416, | |
| "eval_PERSON_f1": 0.9765625, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.9765625, | |
| "eval_PERSON_recall": 0.9765625, | |
| "eval_loss": 0.04878583922982216, | |
| "eval_overall_accuracy": 0.9854251012145749, | |
| "eval_overall_f1": 0.9365482233502538, | |
| "eval_overall_precision": 0.9318181818181818, | |
| "eval_overall_recall": 0.9413265306122449, | |
| "eval_runtime": 0.2814, | |
| "eval_samples_per_second": 604.171, | |
| "eval_steps_per_second": 10.662, | |
| "step": 5280 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "grad_norm": 0.8252633810043335, | |
| "learning_rate": 2.2000000000000003e-05, | |
| "loss": 0.053, | |
| "step": 5376 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_LOCATION_f1": 0.9039548022598871, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.8791208791208791, | |
| "eval_LOCATION_recall": 0.9302325581395349, | |
| "eval_ORGANIZATION_f1": 0.9152542372881356, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.9204545454545454, | |
| "eval_ORGANIZATION_recall": 0.9101123595505618, | |
| "eval_PERSON_f1": 0.9765625, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.9765625, | |
| "eval_PERSON_recall": 0.9765625, | |
| "eval_loss": 0.048739928752183914, | |
| "eval_overall_accuracy": 0.9848852901484481, | |
| "eval_overall_f1": 0.9326556543837357, | |
| "eval_overall_precision": 0.9291139240506329, | |
| "eval_overall_recall": 0.9362244897959183, | |
| "eval_runtime": 0.2812, | |
| "eval_samples_per_second": 604.511, | |
| "eval_steps_per_second": 10.668, | |
| "step": 5376 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "grad_norm": 0.5691685080528259, | |
| "learning_rate": 2.15e-05, | |
| "loss": 0.0498, | |
| "step": 5472 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "eval_LOCATION_f1": 0.9039548022598871, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.8791208791208791, | |
| "eval_LOCATION_recall": 0.9302325581395349, | |
| "eval_ORGANIZATION_f1": 0.9183098591549295, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.9209039548022598, | |
| "eval_ORGANIZATION_recall": 0.9157303370786517, | |
| "eval_PERSON_f1": 0.9765625, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.9765625, | |
| "eval_PERSON_recall": 0.9765625, | |
| "eval_loss": 0.04863953962922096, | |
| "eval_overall_accuracy": 0.9846153846153847, | |
| "eval_overall_f1": 0.934010152284264, | |
| "eval_overall_precision": 0.9292929292929293, | |
| "eval_overall_recall": 0.9387755102040817, | |
| "eval_runtime": 0.2835, | |
| "eval_samples_per_second": 599.591, | |
| "eval_steps_per_second": 10.581, | |
| "step": 5472 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "grad_norm": 0.9249998331069946, | |
| "learning_rate": 2.1e-05, | |
| "loss": 0.0504, | |
| "step": 5568 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_LOCATION_f1": 0.898876404494382, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.8695652173913043, | |
| "eval_LOCATION_recall": 0.9302325581395349, | |
| "eval_ORGANIZATION_f1": 0.9265536723163842, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.9318181818181818, | |
| "eval_ORGANIZATION_recall": 0.9213483146067416, | |
| "eval_PERSON_f1": 0.9765625, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.9765625, | |
| "eval_PERSON_recall": 0.9765625, | |
| "eval_loss": 0.04887806251645088, | |
| "eval_overall_accuracy": 0.9854251012145749, | |
| "eval_overall_f1": 0.9365482233502538, | |
| "eval_overall_precision": 0.9318181818181818, | |
| "eval_overall_recall": 0.9413265306122449, | |
| "eval_runtime": 0.2821, | |
| "eval_samples_per_second": 602.584, | |
| "eval_steps_per_second": 10.634, | |
| "step": 5568 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "grad_norm": 0.7708175778388977, | |
| "learning_rate": 2.05e-05, | |
| "loss": 0.0456, | |
| "step": 5664 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "eval_LOCATION_f1": 0.898876404494382, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.8695652173913043, | |
| "eval_LOCATION_recall": 0.9302325581395349, | |
| "eval_ORGANIZATION_f1": 0.9096045197740114, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.9147727272727273, | |
| "eval_ORGANIZATION_recall": 0.9044943820224719, | |
| "eval_PERSON_f1": 0.9765625, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.9765625, | |
| "eval_PERSON_recall": 0.9765625, | |
| "eval_loss": 0.04921862483024597, | |
| "eval_overall_accuracy": 0.9846153846153847, | |
| "eval_overall_f1": 0.9289340101522842, | |
| "eval_overall_precision": 0.9242424242424242, | |
| "eval_overall_recall": 0.9336734693877551, | |
| "eval_runtime": 0.2809, | |
| "eval_samples_per_second": 605.172, | |
| "eval_steps_per_second": 10.68, | |
| "step": 5664 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "grad_norm": 0.6520349383354187, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0504, | |
| "step": 5760 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_LOCATION_f1": 0.8926553672316384, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.8681318681318682, | |
| "eval_LOCATION_recall": 0.9186046511627907, | |
| "eval_ORGANIZATION_f1": 0.9126760563380282, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.9152542372881356, | |
| "eval_ORGANIZATION_recall": 0.9101123595505618, | |
| "eval_PERSON_f1": 0.9765625, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.9765625, | |
| "eval_PERSON_recall": 0.9765625, | |
| "eval_loss": 0.04753315821290016, | |
| "eval_overall_accuracy": 0.9848852901484481, | |
| "eval_overall_f1": 0.9289340101522842, | |
| "eval_overall_precision": 0.9242424242424242, | |
| "eval_overall_recall": 0.9336734693877551, | |
| "eval_runtime": 0.2828, | |
| "eval_samples_per_second": 601.158, | |
| "eval_steps_per_second": 10.609, | |
| "step": 5760 | |
| }, | |
| { | |
| "epoch": 61.0, | |
| "grad_norm": 0.622580349445343, | |
| "learning_rate": 1.9500000000000003e-05, | |
| "loss": 0.0494, | |
| "step": 5856 | |
| }, | |
| { | |
| "epoch": 61.0, | |
| "eval_LOCATION_f1": 0.8926553672316384, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.8681318681318682, | |
| "eval_LOCATION_recall": 0.9186046511627907, | |
| "eval_ORGANIZATION_f1": 0.9235127478753541, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.9314285714285714, | |
| "eval_ORGANIZATION_recall": 0.9157303370786517, | |
| "eval_PERSON_f1": 0.9765625, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.9765625, | |
| "eval_PERSON_recall": 0.9765625, | |
| "eval_loss": 0.04764934256672859, | |
| "eval_overall_accuracy": 0.9851551956815114, | |
| "eval_overall_f1": 0.9338422391857506, | |
| "eval_overall_precision": 0.9314720812182741, | |
| "eval_overall_recall": 0.9362244897959183, | |
| "eval_runtime": 0.2804, | |
| "eval_samples_per_second": 606.327, | |
| "eval_steps_per_second": 10.7, | |
| "step": 5856 | |
| }, | |
| { | |
| "epoch": 62.0, | |
| "grad_norm": 0.6881121397018433, | |
| "learning_rate": 1.9e-05, | |
| "loss": 0.046, | |
| "step": 5952 | |
| }, | |
| { | |
| "epoch": 62.0, | |
| "eval_LOCATION_f1": 0.9152542372881357, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.8901098901098901, | |
| "eval_LOCATION_recall": 0.9418604651162791, | |
| "eval_ORGANIZATION_f1": 0.9265536723163842, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.9318181818181818, | |
| "eval_ORGANIZATION_recall": 0.9213483146067416, | |
| "eval_PERSON_f1": 0.9803921568627452, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.984251968503937, | |
| "eval_PERSON_recall": 0.9765625, | |
| "eval_loss": 0.0477934405207634, | |
| "eval_overall_accuracy": 0.9859649122807017, | |
| "eval_overall_f1": 0.94147582697201, | |
| "eval_overall_precision": 0.9390862944162437, | |
| "eval_overall_recall": 0.9438775510204082, | |
| "eval_runtime": 0.2805, | |
| "eval_samples_per_second": 606.123, | |
| "eval_steps_per_second": 10.696, | |
| "step": 5952 | |
| }, | |
| { | |
| "epoch": 63.0, | |
| "grad_norm": 1.6825617551803589, | |
| "learning_rate": 1.85e-05, | |
| "loss": 0.0463, | |
| "step": 6048 | |
| }, | |
| { | |
| "epoch": 63.0, | |
| "eval_LOCATION_f1": 0.898876404494382, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.8695652173913043, | |
| "eval_LOCATION_recall": 0.9302325581395349, | |
| "eval_ORGANIZATION_f1": 0.9187675070028011, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.9162011173184358, | |
| "eval_ORGANIZATION_recall": 0.9213483146067416, | |
| "eval_PERSON_f1": 0.96875, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.96875, | |
| "eval_PERSON_recall": 0.96875, | |
| "eval_loss": 0.048465996980667114, | |
| "eval_overall_accuracy": 0.9848852901484481, | |
| "eval_overall_f1": 0.9304677623261693, | |
| "eval_overall_precision": 0.9223057644110275, | |
| "eval_overall_recall": 0.9387755102040817, | |
| "eval_runtime": 0.2808, | |
| "eval_samples_per_second": 605.457, | |
| "eval_steps_per_second": 10.685, | |
| "step": 6048 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "grad_norm": 0.2234792858362198, | |
| "learning_rate": 1.8e-05, | |
| "loss": 0.0452, | |
| "step": 6144 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "eval_LOCATION_f1": 0.9039548022598871, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.8791208791208791, | |
| "eval_LOCATION_recall": 0.9302325581395349, | |
| "eval_ORGANIZATION_f1": 0.9213483146067416, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.9213483146067416, | |
| "eval_ORGANIZATION_recall": 0.9213483146067416, | |
| "eval_PERSON_f1": 0.9765625, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.9765625, | |
| "eval_PERSON_recall": 0.9765625, | |
| "eval_loss": 0.04815259948372841, | |
| "eval_overall_accuracy": 0.9851551956815114, | |
| "eval_overall_f1": 0.935361216730038, | |
| "eval_overall_precision": 0.929471032745592, | |
| "eval_overall_recall": 0.9413265306122449, | |
| "eval_runtime": 0.2856, | |
| "eval_samples_per_second": 595.299, | |
| "eval_steps_per_second": 10.505, | |
| "step": 6144 | |
| }, | |
| { | |
| "epoch": 65.0, | |
| "grad_norm": 0.7405194044113159, | |
| "learning_rate": 1.75e-05, | |
| "loss": 0.0446, | |
| "step": 6240 | |
| }, | |
| { | |
| "epoch": 65.0, | |
| "eval_LOCATION_f1": 0.9039548022598871, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.8791208791208791, | |
| "eval_LOCATION_recall": 0.9302325581395349, | |
| "eval_ORGANIZATION_f1": 0.9162011173184358, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.9111111111111111, | |
| "eval_ORGANIZATION_recall": 0.9213483146067416, | |
| "eval_PERSON_f1": 0.9803921568627452, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.984251968503937, | |
| "eval_PERSON_recall": 0.9765625, | |
| "eval_loss": 0.04923372343182564, | |
| "eval_overall_accuracy": 0.9854251012145749, | |
| "eval_overall_f1": 0.9341772151898734, | |
| "eval_overall_precision": 0.9271356783919598, | |
| "eval_overall_recall": 0.9413265306122449, | |
| "eval_runtime": 0.2832, | |
| "eval_samples_per_second": 600.188, | |
| "eval_steps_per_second": 10.592, | |
| "step": 6240 | |
| }, | |
| { | |
| "epoch": 66.0, | |
| "grad_norm": 1.1158796548843384, | |
| "learning_rate": 1.7000000000000003e-05, | |
| "loss": 0.0463, | |
| "step": 6336 | |
| }, | |
| { | |
| "epoch": 66.0, | |
| "eval_LOCATION_f1": 0.8876404494382023, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.8586956521739131, | |
| "eval_LOCATION_recall": 0.9186046511627907, | |
| "eval_ORGANIZATION_f1": 0.9101123595505618, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.9101123595505618, | |
| "eval_ORGANIZATION_recall": 0.9101123595505618, | |
| "eval_PERSON_f1": 0.9765625, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.9765625, | |
| "eval_PERSON_recall": 0.9765625, | |
| "eval_loss": 0.04949327930808067, | |
| "eval_overall_accuracy": 0.9843454790823212, | |
| "eval_overall_f1": 0.9265822784810125, | |
| "eval_overall_precision": 0.9195979899497487, | |
| "eval_overall_recall": 0.9336734693877551, | |
| "eval_runtime": 0.2821, | |
| "eval_samples_per_second": 602.567, | |
| "eval_steps_per_second": 10.634, | |
| "step": 6336 | |
| }, | |
| { | |
| "epoch": 67.0, | |
| "grad_norm": 0.48084917664527893, | |
| "learning_rate": 1.65e-05, | |
| "loss": 0.0466, | |
| "step": 6432 | |
| }, | |
| { | |
| "epoch": 67.0, | |
| "eval_LOCATION_f1": 0.9039548022598871, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.8791208791208791, | |
| "eval_LOCATION_recall": 0.9302325581395349, | |
| "eval_ORGANIZATION_f1": 0.9101123595505618, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.9101123595505618, | |
| "eval_ORGANIZATION_recall": 0.9101123595505618, | |
| "eval_PERSON_f1": 0.9765625, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.9765625, | |
| "eval_PERSON_recall": 0.9765625, | |
| "eval_loss": 0.04914508014917374, | |
| "eval_overall_accuracy": 0.9846153846153847, | |
| "eval_overall_f1": 0.9302915082382762, | |
| "eval_overall_precision": 0.924433249370277, | |
| "eval_overall_recall": 0.9362244897959183, | |
| "eval_runtime": 0.2844, | |
| "eval_samples_per_second": 597.737, | |
| "eval_steps_per_second": 10.548, | |
| "step": 6432 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "grad_norm": 1.0782126188278198, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 0.0451, | |
| "step": 6528 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "eval_LOCATION_f1": 0.9039548022598871, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.8791208791208791, | |
| "eval_LOCATION_recall": 0.9302325581395349, | |
| "eval_ORGANIZATION_f1": 0.9162011173184358, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.9111111111111111, | |
| "eval_ORGANIZATION_recall": 0.9213483146067416, | |
| "eval_PERSON_f1": 0.9765625, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.9765625, | |
| "eval_PERSON_recall": 0.9765625, | |
| "eval_loss": 0.04990832507610321, | |
| "eval_overall_accuracy": 0.9851551956815114, | |
| "eval_overall_f1": 0.9329962073324906, | |
| "eval_overall_precision": 0.924812030075188, | |
| "eval_overall_recall": 0.9413265306122449, | |
| "eval_runtime": 0.2832, | |
| "eval_samples_per_second": 600.234, | |
| "eval_steps_per_second": 10.592, | |
| "step": 6528 | |
| }, | |
| { | |
| "epoch": 69.0, | |
| "grad_norm": 1.2592836618423462, | |
| "learning_rate": 1.55e-05, | |
| "loss": 0.047, | |
| "step": 6624 | |
| }, | |
| { | |
| "epoch": 69.0, | |
| "eval_LOCATION_f1": 0.898876404494382, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.8695652173913043, | |
| "eval_LOCATION_recall": 0.9302325581395349, | |
| "eval_ORGANIZATION_f1": 0.9183098591549295, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.9209039548022598, | |
| "eval_ORGANIZATION_recall": 0.9157303370786517, | |
| "eval_PERSON_f1": 0.9765625, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.9765625, | |
| "eval_PERSON_recall": 0.9765625, | |
| "eval_loss": 0.04929433763027191, | |
| "eval_overall_accuracy": 0.9851551956815114, | |
| "eval_overall_f1": 0.9328263624841572, | |
| "eval_overall_precision": 0.9269521410579346, | |
| "eval_overall_recall": 0.9387755102040817, | |
| "eval_runtime": 0.2807, | |
| "eval_samples_per_second": 605.579, | |
| "eval_steps_per_second": 10.687, | |
| "step": 6624 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "grad_norm": 0.7667045593261719, | |
| "learning_rate": 1.5e-05, | |
| "loss": 0.0435, | |
| "step": 6720 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "eval_LOCATION_f1": 0.9039548022598871, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.8791208791208791, | |
| "eval_LOCATION_recall": 0.9302325581395349, | |
| "eval_ORGANIZATION_f1": 0.9157303370786517, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.9157303370786517, | |
| "eval_ORGANIZATION_recall": 0.9157303370786517, | |
| "eval_PERSON_f1": 0.9765625, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.9765625, | |
| "eval_PERSON_recall": 0.9765625, | |
| "eval_loss": 0.048545148223638535, | |
| "eval_overall_accuracy": 0.9848852901484481, | |
| "eval_overall_f1": 0.9328263624841572, | |
| "eval_overall_precision": 0.9269521410579346, | |
| "eval_overall_recall": 0.9387755102040817, | |
| "eval_runtime": 0.2848, | |
| "eval_samples_per_second": 596.917, | |
| "eval_steps_per_second": 10.534, | |
| "step": 6720 | |
| }, | |
| { | |
| "epoch": 71.0, | |
| "grad_norm": 1.8045178651809692, | |
| "learning_rate": 1.45e-05, | |
| "loss": 0.045, | |
| "step": 6816 | |
| }, | |
| { | |
| "epoch": 71.0, | |
| "eval_LOCATION_f1": 0.9039548022598871, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.8791208791208791, | |
| "eval_LOCATION_recall": 0.9302325581395349, | |
| "eval_ORGANIZATION_f1": 0.9162011173184358, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.9111111111111111, | |
| "eval_ORGANIZATION_recall": 0.9213483146067416, | |
| "eval_PERSON_f1": 0.9765625, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.9765625, | |
| "eval_PERSON_recall": 0.9765625, | |
| "eval_loss": 0.04896879196166992, | |
| "eval_overall_accuracy": 0.9851551956815114, | |
| "eval_overall_f1": 0.9329962073324906, | |
| "eval_overall_precision": 0.924812030075188, | |
| "eval_overall_recall": 0.9413265306122449, | |
| "eval_runtime": 0.2818, | |
| "eval_samples_per_second": 603.174, | |
| "eval_steps_per_second": 10.644, | |
| "step": 6816 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "grad_norm": 0.6001482009887695, | |
| "learning_rate": 1.4000000000000001e-05, | |
| "loss": 0.0458, | |
| "step": 6912 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "eval_LOCATION_f1": 0.9152542372881357, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.8901098901098901, | |
| "eval_LOCATION_recall": 0.9418604651162791, | |
| "eval_ORGANIZATION_f1": 0.9178470254957507, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.9257142857142857, | |
| "eval_ORGANIZATION_recall": 0.9101123595505618, | |
| "eval_PERSON_f1": 0.9765625, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.9765625, | |
| "eval_PERSON_recall": 0.9765625, | |
| "eval_loss": 0.04974735528230667, | |
| "eval_overall_accuracy": 0.9848852901484481, | |
| "eval_overall_f1": 0.9363867684478372, | |
| "eval_overall_precision": 0.934010152284264, | |
| "eval_overall_recall": 0.9387755102040817, | |
| "eval_runtime": 0.2833, | |
| "eval_samples_per_second": 600.101, | |
| "eval_steps_per_second": 10.59, | |
| "step": 6912 | |
| }, | |
| { | |
| "epoch": 73.0, | |
| "grad_norm": 1.2454522848129272, | |
| "learning_rate": 1.3500000000000001e-05, | |
| "loss": 0.0442, | |
| "step": 7008 | |
| }, | |
| { | |
| "epoch": 73.0, | |
| "eval_LOCATION_f1": 0.9152542372881357, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.8901098901098901, | |
| "eval_LOCATION_recall": 0.9418604651162791, | |
| "eval_ORGANIZATION_f1": 0.9157303370786517, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.9157303370786517, | |
| "eval_ORGANIZATION_recall": 0.9157303370786517, | |
| "eval_PERSON_f1": 0.9765625, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.9765625, | |
| "eval_PERSON_recall": 0.9765625, | |
| "eval_loss": 0.0495486781001091, | |
| "eval_overall_accuracy": 0.9854251012145749, | |
| "eval_overall_f1": 0.935361216730038, | |
| "eval_overall_precision": 0.929471032745592, | |
| "eval_overall_recall": 0.9413265306122449, | |
| "eval_runtime": 0.2816, | |
| "eval_samples_per_second": 603.673, | |
| "eval_steps_per_second": 10.653, | |
| "step": 7008 | |
| }, | |
| { | |
| "epoch": 74.0, | |
| "grad_norm": 2.512705087661743, | |
| "learning_rate": 1.3000000000000001e-05, | |
| "loss": 0.0442, | |
| "step": 7104 | |
| }, | |
| { | |
| "epoch": 74.0, | |
| "eval_LOCATION_f1": 0.9152542372881357, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.8901098901098901, | |
| "eval_LOCATION_recall": 0.9418604651162791, | |
| "eval_ORGANIZATION_f1": 0.9126760563380282, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.9152542372881356, | |
| "eval_ORGANIZATION_recall": 0.9101123595505618, | |
| "eval_PERSON_f1": 0.9765625, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.9765625, | |
| "eval_PERSON_recall": 0.9765625, | |
| "eval_loss": 0.04903655871748924, | |
| "eval_overall_accuracy": 0.9851551956815114, | |
| "eval_overall_f1": 0.934010152284264, | |
| "eval_overall_precision": 0.9292929292929293, | |
| "eval_overall_recall": 0.9387755102040817, | |
| "eval_runtime": 0.2798, | |
| "eval_samples_per_second": 607.495, | |
| "eval_steps_per_second": 10.72, | |
| "step": 7104 | |
| }, | |
| { | |
| "epoch": 75.0, | |
| "grad_norm": 0.993471086025238, | |
| "learning_rate": 1.25e-05, | |
| "loss": 0.0437, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 75.0, | |
| "eval_LOCATION_f1": 0.8926553672316384, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.8681318681318682, | |
| "eval_LOCATION_recall": 0.9186046511627907, | |
| "eval_ORGANIZATION_f1": 0.9183098591549295, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.9209039548022598, | |
| "eval_ORGANIZATION_recall": 0.9157303370786517, | |
| "eval_PERSON_f1": 0.9765625, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.9765625, | |
| "eval_PERSON_recall": 0.9765625, | |
| "eval_loss": 0.04867413640022278, | |
| "eval_overall_accuracy": 0.9840755735492578, | |
| "eval_overall_f1": 0.9314720812182741, | |
| "eval_overall_precision": 0.9267676767676768, | |
| "eval_overall_recall": 0.9362244897959183, | |
| "eval_runtime": 0.2828, | |
| "eval_samples_per_second": 601.141, | |
| "eval_steps_per_second": 10.608, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 76.0, | |
| "grad_norm": 0.7063285112380981, | |
| "learning_rate": 1.2e-05, | |
| "loss": 0.0458, | |
| "step": 7296 | |
| }, | |
| { | |
| "epoch": 76.0, | |
| "eval_LOCATION_f1": 0.9039548022598871, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.8791208791208791, | |
| "eval_LOCATION_recall": 0.9302325581395349, | |
| "eval_ORGANIZATION_f1": 0.9183098591549295, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.9209039548022598, | |
| "eval_ORGANIZATION_recall": 0.9157303370786517, | |
| "eval_PERSON_f1": 0.9803921568627452, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.984251968503937, | |
| "eval_PERSON_recall": 0.9765625, | |
| "eval_loss": 0.04928082972764969, | |
| "eval_overall_accuracy": 0.9843454790823212, | |
| "eval_overall_f1": 0.9351969504447268, | |
| "eval_overall_precision": 0.9316455696202531, | |
| "eval_overall_recall": 0.9387755102040817, | |
| "eval_runtime": 0.2811, | |
| "eval_samples_per_second": 604.715, | |
| "eval_steps_per_second": 10.671, | |
| "step": 7296 | |
| }, | |
| { | |
| "epoch": 77.0, | |
| "grad_norm": 1.6234911680221558, | |
| "learning_rate": 1.1500000000000002e-05, | |
| "loss": 0.0448, | |
| "step": 7392 | |
| }, | |
| { | |
| "epoch": 77.0, | |
| "eval_LOCATION_f1": 0.8926553672316384, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.8681318681318682, | |
| "eval_LOCATION_recall": 0.9186046511627907, | |
| "eval_ORGANIZATION_f1": 0.9126760563380282, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.9152542372881356, | |
| "eval_ORGANIZATION_recall": 0.9101123595505618, | |
| "eval_PERSON_f1": 0.9803921568627452, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.984251968503937, | |
| "eval_PERSON_recall": 0.9765625, | |
| "eval_loss": 0.04873611778020859, | |
| "eval_overall_accuracy": 0.9838056680161943, | |
| "eval_overall_f1": 0.9301143583227446, | |
| "eval_overall_precision": 0.9265822784810127, | |
| "eval_overall_recall": 0.9336734693877551, | |
| "eval_runtime": 0.2824, | |
| "eval_samples_per_second": 602.033, | |
| "eval_steps_per_second": 10.624, | |
| "step": 7392 | |
| }, | |
| { | |
| "epoch": 78.0, | |
| "grad_norm": 0.894944965839386, | |
| "learning_rate": 1.1000000000000001e-05, | |
| "loss": 0.0451, | |
| "step": 7488 | |
| }, | |
| { | |
| "epoch": 78.0, | |
| "eval_LOCATION_f1": 0.9039548022598871, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.8791208791208791, | |
| "eval_LOCATION_recall": 0.9302325581395349, | |
| "eval_ORGANIZATION_f1": 0.9183098591549295, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.9209039548022598, | |
| "eval_ORGANIZATION_recall": 0.9157303370786517, | |
| "eval_PERSON_f1": 0.9765625, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.9765625, | |
| "eval_PERSON_recall": 0.9765625, | |
| "eval_loss": 0.049469735473394394, | |
| "eval_overall_accuracy": 0.9843454790823212, | |
| "eval_overall_f1": 0.934010152284264, | |
| "eval_overall_precision": 0.9292929292929293, | |
| "eval_overall_recall": 0.9387755102040817, | |
| "eval_runtime": 0.2811, | |
| "eval_samples_per_second": 604.745, | |
| "eval_steps_per_second": 10.672, | |
| "step": 7488 | |
| }, | |
| { | |
| "epoch": 79.0, | |
| "grad_norm": 0.6182302236557007, | |
| "learning_rate": 1.05e-05, | |
| "loss": 0.0449, | |
| "step": 7584 | |
| }, | |
| { | |
| "epoch": 79.0, | |
| "eval_LOCATION_f1": 0.9039548022598871, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.8791208791208791, | |
| "eval_LOCATION_recall": 0.9302325581395349, | |
| "eval_ORGANIZATION_f1": 0.9213483146067416, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.9213483146067416, | |
| "eval_ORGANIZATION_recall": 0.9213483146067416, | |
| "eval_PERSON_f1": 0.9803921568627452, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.984251968503937, | |
| "eval_PERSON_recall": 0.9765625, | |
| "eval_loss": 0.04977456107735634, | |
| "eval_overall_accuracy": 0.9846153846153847, | |
| "eval_overall_f1": 0.9365482233502538, | |
| "eval_overall_precision": 0.9318181818181818, | |
| "eval_overall_recall": 0.9413265306122449, | |
| "eval_runtime": 0.2824, | |
| "eval_samples_per_second": 601.942, | |
| "eval_steps_per_second": 10.622, | |
| "step": 7584 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "grad_norm": 0.9781434535980225, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0436, | |
| "step": 7680 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "eval_LOCATION_f1": 0.898876404494382, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.8695652173913043, | |
| "eval_LOCATION_recall": 0.9302325581395349, | |
| "eval_ORGANIZATION_f1": 0.9152542372881356, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.9204545454545454, | |
| "eval_ORGANIZATION_recall": 0.9101123595505618, | |
| "eval_PERSON_f1": 0.9803921568627452, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.984251968503937, | |
| "eval_PERSON_recall": 0.9765625, | |
| "eval_loss": 0.049282483756542206, | |
| "eval_overall_accuracy": 0.9843454790823212, | |
| "eval_overall_f1": 0.9326556543837357, | |
| "eval_overall_precision": 0.9291139240506329, | |
| "eval_overall_recall": 0.9362244897959183, | |
| "eval_runtime": 0.2832, | |
| "eval_samples_per_second": 600.22, | |
| "eval_steps_per_second": 10.592, | |
| "step": 7680 | |
| }, | |
| { | |
| "epoch": 81.0, | |
| "grad_norm": 1.0374711751937866, | |
| "learning_rate": 9.5e-06, | |
| "loss": 0.044, | |
| "step": 7776 | |
| }, | |
| { | |
| "epoch": 81.0, | |
| "eval_LOCATION_f1": 0.9101123595505618, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.8804347826086957, | |
| "eval_LOCATION_recall": 0.9418604651162791, | |
| "eval_ORGANIZATION_f1": 0.9183098591549295, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.9209039548022598, | |
| "eval_ORGANIZATION_recall": 0.9157303370786517, | |
| "eval_PERSON_f1": 0.9803921568627452, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.984251968503937, | |
| "eval_PERSON_recall": 0.9765625, | |
| "eval_loss": 0.049396924674510956, | |
| "eval_overall_accuracy": 0.9851551956815114, | |
| "eval_overall_f1": 0.9365482233502538, | |
| "eval_overall_precision": 0.9318181818181818, | |
| "eval_overall_recall": 0.9413265306122449, | |
| "eval_runtime": 0.2821, | |
| "eval_samples_per_second": 602.607, | |
| "eval_steps_per_second": 10.634, | |
| "step": 7776 | |
| }, | |
| { | |
| "epoch": 82.0, | |
| "grad_norm": 1.2461556196212769, | |
| "learning_rate": 9e-06, | |
| "loss": 0.0438, | |
| "step": 7872 | |
| }, | |
| { | |
| "epoch": 82.0, | |
| "eval_LOCATION_f1": 0.898876404494382, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.8695652173913043, | |
| "eval_LOCATION_recall": 0.9302325581395349, | |
| "eval_ORGANIZATION_f1": 0.9178470254957507, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.9257142857142857, | |
| "eval_ORGANIZATION_recall": 0.9101123595505618, | |
| "eval_PERSON_f1": 0.9765625, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.9765625, | |
| "eval_PERSON_recall": 0.9765625, | |
| "eval_loss": 0.04848863556981087, | |
| "eval_overall_accuracy": 0.9846153846153847, | |
| "eval_overall_f1": 0.9326556543837357, | |
| "eval_overall_precision": 0.9291139240506329, | |
| "eval_overall_recall": 0.9362244897959183, | |
| "eval_runtime": 0.2815, | |
| "eval_samples_per_second": 604.004, | |
| "eval_steps_per_second": 10.659, | |
| "step": 7872 | |
| }, | |
| { | |
| "epoch": 83.0, | |
| "grad_norm": 2.299999475479126, | |
| "learning_rate": 8.500000000000002e-06, | |
| "loss": 0.0434, | |
| "step": 7968 | |
| }, | |
| { | |
| "epoch": 83.0, | |
| "eval_LOCATION_f1": 0.9152542372881357, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.8901098901098901, | |
| "eval_LOCATION_recall": 0.9418604651162791, | |
| "eval_ORGANIZATION_f1": 0.9187675070028011, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.9162011173184358, | |
| "eval_ORGANIZATION_recall": 0.9213483146067416, | |
| "eval_PERSON_f1": 0.9765625, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.9765625, | |
| "eval_PERSON_recall": 0.9765625, | |
| "eval_loss": 0.04818493500351906, | |
| "eval_overall_accuracy": 0.9856950067476383, | |
| "eval_overall_f1": 0.9367088607594937, | |
| "eval_overall_precision": 0.9296482412060302, | |
| "eval_overall_recall": 0.9438775510204082, | |
| "eval_runtime": 0.283, | |
| "eval_samples_per_second": 600.663, | |
| "eval_steps_per_second": 10.6, | |
| "step": 7968 | |
| }, | |
| { | |
| "epoch": 84.0, | |
| "grad_norm": 2.182854413986206, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 0.0418, | |
| "step": 8064 | |
| }, | |
| { | |
| "epoch": 84.0, | |
| "eval_LOCATION_f1": 0.898876404494382, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.8695652173913043, | |
| "eval_LOCATION_recall": 0.9302325581395349, | |
| "eval_ORGANIZATION_f1": 0.9101123595505618, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.9101123595505618, | |
| "eval_ORGANIZATION_recall": 0.9101123595505618, | |
| "eval_PERSON_f1": 0.9765625, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.9765625, | |
| "eval_PERSON_recall": 0.9765625, | |
| "eval_loss": 0.04847468063235283, | |
| "eval_overall_accuracy": 0.9846153846153847, | |
| "eval_overall_f1": 0.929113924050633, | |
| "eval_overall_precision": 0.9221105527638191, | |
| "eval_overall_recall": 0.9362244897959183, | |
| "eval_runtime": 0.282, | |
| "eval_samples_per_second": 602.885, | |
| "eval_steps_per_second": 10.639, | |
| "step": 8064 | |
| }, | |
| { | |
| "epoch": 85.0, | |
| "grad_norm": 1.2896052598953247, | |
| "learning_rate": 7.5e-06, | |
| "loss": 0.0424, | |
| "step": 8160 | |
| }, | |
| { | |
| "epoch": 85.0, | |
| "eval_LOCATION_f1": 0.9152542372881357, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.8901098901098901, | |
| "eval_LOCATION_recall": 0.9418604651162791, | |
| "eval_ORGANIZATION_f1": 0.9204545454545454, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.9310344827586207, | |
| "eval_ORGANIZATION_recall": 0.9101123595505618, | |
| "eval_PERSON_f1": 0.9765625, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.9765625, | |
| "eval_PERSON_recall": 0.9765625, | |
| "eval_loss": 0.048406198620796204, | |
| "eval_overall_accuracy": 0.9848852901484481, | |
| "eval_overall_f1": 0.937579617834395, | |
| "eval_overall_precision": 0.9363867684478372, | |
| "eval_overall_recall": 0.9387755102040817, | |
| "eval_runtime": 0.2817, | |
| "eval_samples_per_second": 603.389, | |
| "eval_steps_per_second": 10.648, | |
| "step": 8160 | |
| }, | |
| { | |
| "epoch": 86.0, | |
| "grad_norm": 0.4105066657066345, | |
| "learning_rate": 7.000000000000001e-06, | |
| "loss": 0.042, | |
| "step": 8256 | |
| }, | |
| { | |
| "epoch": 86.0, | |
| "eval_LOCATION_f1": 0.9152542372881357, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.8901098901098901, | |
| "eval_LOCATION_recall": 0.9418604651162791, | |
| "eval_ORGANIZATION_f1": 0.9239436619718311, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.9265536723163842, | |
| "eval_ORGANIZATION_recall": 0.9213483146067416, | |
| "eval_PERSON_f1": 0.9803921568627452, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.984251968503937, | |
| "eval_PERSON_recall": 0.9765625, | |
| "eval_loss": 0.048215754330158234, | |
| "eval_overall_accuracy": 0.9856950067476383, | |
| "eval_overall_f1": 0.9402795425667091, | |
| "eval_overall_precision": 0.9367088607594937, | |
| "eval_overall_recall": 0.9438775510204082, | |
| "eval_runtime": 0.2835, | |
| "eval_samples_per_second": 599.717, | |
| "eval_steps_per_second": 10.583, | |
| "step": 8256 | |
| }, | |
| { | |
| "epoch": 87.0, | |
| "grad_norm": 0.5451318025588989, | |
| "learning_rate": 6.5000000000000004e-06, | |
| "loss": 0.0431, | |
| "step": 8352 | |
| }, | |
| { | |
| "epoch": 87.0, | |
| "eval_LOCATION_f1": 0.9101123595505618, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.8804347826086957, | |
| "eval_LOCATION_recall": 0.9418604651162791, | |
| "eval_ORGANIZATION_f1": 0.9178470254957507, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.9257142857142857, | |
| "eval_ORGANIZATION_recall": 0.9101123595505618, | |
| "eval_PERSON_f1": 0.9803921568627452, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.984251968503937, | |
| "eval_PERSON_recall": 0.9765625, | |
| "eval_loss": 0.04817402362823486, | |
| "eval_overall_accuracy": 0.9851551956815114, | |
| "eval_overall_f1": 0.9363867684478372, | |
| "eval_overall_precision": 0.934010152284264, | |
| "eval_overall_recall": 0.9387755102040817, | |
| "eval_runtime": 0.2829, | |
| "eval_samples_per_second": 600.903, | |
| "eval_steps_per_second": 10.604, | |
| "step": 8352 | |
| }, | |
| { | |
| "epoch": 88.0, | |
| "grad_norm": 0.7700179219245911, | |
| "learning_rate": 6e-06, | |
| "loss": 0.0417, | |
| "step": 8448 | |
| }, | |
| { | |
| "epoch": 88.0, | |
| "eval_LOCATION_f1": 0.9152542372881357, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.8901098901098901, | |
| "eval_LOCATION_recall": 0.9418604651162791, | |
| "eval_ORGANIZATION_f1": 0.9178470254957507, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.9257142857142857, | |
| "eval_ORGANIZATION_recall": 0.9101123595505618, | |
| "eval_PERSON_f1": 0.9803921568627452, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.984251968503937, | |
| "eval_PERSON_recall": 0.9765625, | |
| "eval_loss": 0.0481853149831295, | |
| "eval_overall_accuracy": 0.9848852901484481, | |
| "eval_overall_f1": 0.937579617834395, | |
| "eval_overall_precision": 0.9363867684478372, | |
| "eval_overall_recall": 0.9387755102040817, | |
| "eval_runtime": 0.2822, | |
| "eval_samples_per_second": 602.399, | |
| "eval_steps_per_second": 10.631, | |
| "step": 8448 | |
| }, | |
| { | |
| "epoch": 89.0, | |
| "grad_norm": 0.48494595289230347, | |
| "learning_rate": 5.500000000000001e-06, | |
| "loss": 0.0421, | |
| "step": 8544 | |
| }, | |
| { | |
| "epoch": 89.0, | |
| "eval_LOCATION_f1": 0.9152542372881357, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.8901098901098901, | |
| "eval_LOCATION_recall": 0.9418604651162791, | |
| "eval_ORGANIZATION_f1": 0.92090395480226, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.9261363636363636, | |
| "eval_ORGANIZATION_recall": 0.9157303370786517, | |
| "eval_PERSON_f1": 0.9803921568627452, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.984251968503937, | |
| "eval_PERSON_recall": 0.9765625, | |
| "eval_loss": 0.04823269695043564, | |
| "eval_overall_accuracy": 0.9854251012145749, | |
| "eval_overall_f1": 0.9389312977099236, | |
| "eval_overall_precision": 0.9365482233502538, | |
| "eval_overall_recall": 0.9413265306122449, | |
| "eval_runtime": 0.2832, | |
| "eval_samples_per_second": 600.189, | |
| "eval_steps_per_second": 10.592, | |
| "step": 8544 | |
| }, | |
| { | |
| "epoch": 90.0, | |
| "grad_norm": 1.2131330966949463, | |
| "learning_rate": 5e-06, | |
| "loss": 0.0412, | |
| "step": 8640 | |
| }, | |
| { | |
| "epoch": 90.0, | |
| "eval_LOCATION_f1": 0.9152542372881357, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.8901098901098901, | |
| "eval_LOCATION_recall": 0.9418604651162791, | |
| "eval_ORGANIZATION_f1": 0.9178470254957507, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.9257142857142857, | |
| "eval_ORGANIZATION_recall": 0.9101123595505618, | |
| "eval_PERSON_f1": 0.9803921568627452, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.984251968503937, | |
| "eval_PERSON_recall": 0.9765625, | |
| "eval_loss": 0.048506613820791245, | |
| "eval_overall_accuracy": 0.9851551956815114, | |
| "eval_overall_f1": 0.937579617834395, | |
| "eval_overall_precision": 0.9363867684478372, | |
| "eval_overall_recall": 0.9387755102040817, | |
| "eval_runtime": 0.2827, | |
| "eval_samples_per_second": 601.369, | |
| "eval_steps_per_second": 10.612, | |
| "step": 8640 | |
| }, | |
| { | |
| "epoch": 91.0, | |
| "grad_norm": 1.6268497705459595, | |
| "learning_rate": 4.5e-06, | |
| "loss": 0.0407, | |
| "step": 8736 | |
| }, | |
| { | |
| "epoch": 91.0, | |
| "eval_LOCATION_f1": 0.9152542372881357, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.8901098901098901, | |
| "eval_LOCATION_recall": 0.9418604651162791, | |
| "eval_ORGANIZATION_f1": 0.9204545454545454, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.9310344827586207, | |
| "eval_ORGANIZATION_recall": 0.9101123595505618, | |
| "eval_PERSON_f1": 0.9803921568627452, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.984251968503937, | |
| "eval_PERSON_recall": 0.9765625, | |
| "eval_loss": 0.0484403595328331, | |
| "eval_overall_accuracy": 0.9848852901484481, | |
| "eval_overall_f1": 0.9387755102040817, | |
| "eval_overall_precision": 0.9387755102040817, | |
| "eval_overall_recall": 0.9387755102040817, | |
| "eval_runtime": 0.2823, | |
| "eval_samples_per_second": 602.132, | |
| "eval_steps_per_second": 10.626, | |
| "step": 8736 | |
| }, | |
| { | |
| "epoch": 92.0, | |
| "grad_norm": 0.282482773065567, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.0405, | |
| "step": 8832 | |
| }, | |
| { | |
| "epoch": 92.0, | |
| "eval_LOCATION_f1": 0.9204545454545455, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.9, | |
| "eval_LOCATION_recall": 0.9418604651162791, | |
| "eval_ORGANIZATION_f1": 0.9230769230769231, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.9364161849710982, | |
| "eval_ORGANIZATION_recall": 0.9101123595505618, | |
| "eval_PERSON_f1": 0.9803921568627452, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.984251968503937, | |
| "eval_PERSON_recall": 0.9765625, | |
| "eval_loss": 0.04866935685276985, | |
| "eval_overall_accuracy": 0.9846153846153847, | |
| "eval_overall_f1": 0.9411764705882353, | |
| "eval_overall_precision": 0.9435897435897436, | |
| "eval_overall_recall": 0.9387755102040817, | |
| "eval_runtime": 0.2824, | |
| "eval_samples_per_second": 601.955, | |
| "eval_steps_per_second": 10.623, | |
| "step": 8832 | |
| }, | |
| { | |
| "epoch": 93.0, | |
| "grad_norm": 1.4597584009170532, | |
| "learning_rate": 3.5000000000000004e-06, | |
| "loss": 0.0447, | |
| "step": 8928 | |
| }, | |
| { | |
| "epoch": 93.0, | |
| "eval_LOCATION_f1": 0.9204545454545455, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.9, | |
| "eval_LOCATION_recall": 0.9418604651162791, | |
| "eval_ORGANIZATION_f1": 0.9230769230769231, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.9364161849710982, | |
| "eval_ORGANIZATION_recall": 0.9101123595505618, | |
| "eval_PERSON_f1": 0.9803921568627452, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.984251968503937, | |
| "eval_PERSON_recall": 0.9765625, | |
| "eval_loss": 0.04870360717177391, | |
| "eval_overall_accuracy": 0.9846153846153847, | |
| "eval_overall_f1": 0.9411764705882353, | |
| "eval_overall_precision": 0.9435897435897436, | |
| "eval_overall_recall": 0.9387755102040817, | |
| "eval_runtime": 0.2828, | |
| "eval_samples_per_second": 601.209, | |
| "eval_steps_per_second": 10.61, | |
| "step": 8928 | |
| }, | |
| { | |
| "epoch": 94.0, | |
| "grad_norm": 0.4648018777370453, | |
| "learning_rate": 3e-06, | |
| "loss": 0.0402, | |
| "step": 9024 | |
| }, | |
| { | |
| "epoch": 94.0, | |
| "eval_LOCATION_f1": 0.9204545454545455, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.9, | |
| "eval_LOCATION_recall": 0.9418604651162791, | |
| "eval_ORGANIZATION_f1": 0.9204545454545454, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.9310344827586207, | |
| "eval_ORGANIZATION_recall": 0.9101123595505618, | |
| "eval_PERSON_f1": 0.9803921568627452, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.984251968503937, | |
| "eval_PERSON_recall": 0.9765625, | |
| "eval_loss": 0.048693280667066574, | |
| "eval_overall_accuracy": 0.9848852901484481, | |
| "eval_overall_f1": 0.9399744572158366, | |
| "eval_overall_precision": 0.9411764705882353, | |
| "eval_overall_recall": 0.9387755102040817, | |
| "eval_runtime": 0.2803, | |
| "eval_samples_per_second": 606.45, | |
| "eval_steps_per_second": 10.702, | |
| "step": 9024 | |
| }, | |
| { | |
| "epoch": 95.0, | |
| "grad_norm": 0.9228402376174927, | |
| "learning_rate": 2.5e-06, | |
| "loss": 0.0406, | |
| "step": 9120 | |
| }, | |
| { | |
| "epoch": 95.0, | |
| "eval_LOCATION_f1": 0.9204545454545455, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.9, | |
| "eval_LOCATION_recall": 0.9418604651162791, | |
| "eval_ORGANIZATION_f1": 0.9230769230769231, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.9364161849710982, | |
| "eval_ORGANIZATION_recall": 0.9101123595505618, | |
| "eval_PERSON_f1": 0.9803921568627452, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.984251968503937, | |
| "eval_PERSON_recall": 0.9765625, | |
| "eval_loss": 0.048481784760951996, | |
| "eval_overall_accuracy": 0.9846153846153847, | |
| "eval_overall_f1": 0.9411764705882353, | |
| "eval_overall_precision": 0.9435897435897436, | |
| "eval_overall_recall": 0.9387755102040817, | |
| "eval_runtime": 0.2827, | |
| "eval_samples_per_second": 601.417, | |
| "eval_steps_per_second": 10.613, | |
| "step": 9120 | |
| }, | |
| { | |
| "epoch": 96.0, | |
| "grad_norm": 0.3986660838127136, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 0.0413, | |
| "step": 9216 | |
| }, | |
| { | |
| "epoch": 96.0, | |
| "eval_LOCATION_f1": 0.9204545454545455, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.9, | |
| "eval_LOCATION_recall": 0.9418604651162791, | |
| "eval_ORGANIZATION_f1": 0.9230769230769231, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.9364161849710982, | |
| "eval_ORGANIZATION_recall": 0.9101123595505618, | |
| "eval_PERSON_f1": 0.9803921568627452, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.984251968503937, | |
| "eval_PERSON_recall": 0.9765625, | |
| "eval_loss": 0.04846182465553284, | |
| "eval_overall_accuracy": 0.9846153846153847, | |
| "eval_overall_f1": 0.9411764705882353, | |
| "eval_overall_precision": 0.9435897435897436, | |
| "eval_overall_recall": 0.9387755102040817, | |
| "eval_runtime": 0.2821, | |
| "eval_samples_per_second": 602.684, | |
| "eval_steps_per_second": 10.636, | |
| "step": 9216 | |
| }, | |
| { | |
| "epoch": 97.0, | |
| "grad_norm": 0.8940658569335938, | |
| "learning_rate": 1.5e-06, | |
| "loss": 0.0404, | |
| "step": 9312 | |
| }, | |
| { | |
| "epoch": 97.0, | |
| "eval_LOCATION_f1": 0.9204545454545455, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.9, | |
| "eval_LOCATION_recall": 0.9418604651162791, | |
| "eval_ORGANIZATION_f1": 0.9261363636363636, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.9367816091954023, | |
| "eval_ORGANIZATION_recall": 0.9157303370786517, | |
| "eval_PERSON_f1": 0.9803921568627452, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.984251968503937, | |
| "eval_PERSON_recall": 0.9765625, | |
| "eval_loss": 0.04837748035788536, | |
| "eval_overall_accuracy": 0.9851551956815114, | |
| "eval_overall_f1": 0.9425287356321839, | |
| "eval_overall_precision": 0.9437340153452686, | |
| "eval_overall_recall": 0.9413265306122449, | |
| "eval_runtime": 0.2813, | |
| "eval_samples_per_second": 604.426, | |
| "eval_steps_per_second": 10.666, | |
| "step": 9312 | |
| }, | |
| { | |
| "epoch": 98.0, | |
| "grad_norm": 1.2582430839538574, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 0.0403, | |
| "step": 9408 | |
| }, | |
| { | |
| "epoch": 98.0, | |
| "eval_LOCATION_f1": 0.9204545454545455, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.9, | |
| "eval_LOCATION_recall": 0.9418604651162791, | |
| "eval_ORGANIZATION_f1": 0.9230769230769231, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.9364161849710982, | |
| "eval_ORGANIZATION_recall": 0.9101123595505618, | |
| "eval_PERSON_f1": 0.9803921568627452, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.984251968503937, | |
| "eval_PERSON_recall": 0.9765625, | |
| "eval_loss": 0.04847470298409462, | |
| "eval_overall_accuracy": 0.9846153846153847, | |
| "eval_overall_f1": 0.9411764705882353, | |
| "eval_overall_precision": 0.9435897435897436, | |
| "eval_overall_recall": 0.9387755102040817, | |
| "eval_runtime": 0.2833, | |
| "eval_samples_per_second": 600.008, | |
| "eval_steps_per_second": 10.588, | |
| "step": 9408 | |
| }, | |
| { | |
| "epoch": 99.0, | |
| "grad_norm": 1.0658987760543823, | |
| "learning_rate": 5.000000000000001e-07, | |
| "loss": 0.0403, | |
| "step": 9504 | |
| }, | |
| { | |
| "epoch": 99.0, | |
| "eval_LOCATION_f1": 0.9204545454545455, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.9, | |
| "eval_LOCATION_recall": 0.9418604651162791, | |
| "eval_ORGANIZATION_f1": 0.9230769230769231, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.9364161849710982, | |
| "eval_ORGANIZATION_recall": 0.9101123595505618, | |
| "eval_PERSON_f1": 0.9803921568627452, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.984251968503937, | |
| "eval_PERSON_recall": 0.9765625, | |
| "eval_loss": 0.048433490097522736, | |
| "eval_overall_accuracy": 0.9846153846153847, | |
| "eval_overall_f1": 0.9411764705882353, | |
| "eval_overall_precision": 0.9435897435897436, | |
| "eval_overall_recall": 0.9387755102040817, | |
| "eval_runtime": 0.2829, | |
| "eval_samples_per_second": 600.968, | |
| "eval_steps_per_second": 10.605, | |
| "step": 9504 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "grad_norm": 1.2720928192138672, | |
| "learning_rate": 0.0, | |
| "loss": 0.0417, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "eval_LOCATION_f1": 0.9204545454545455, | |
| "eval_LOCATION_number": 86, | |
| "eval_LOCATION_precision": 0.9, | |
| "eval_LOCATION_recall": 0.9418604651162791, | |
| "eval_ORGANIZATION_f1": 0.9230769230769231, | |
| "eval_ORGANIZATION_number": 178, | |
| "eval_ORGANIZATION_precision": 0.9364161849710982, | |
| "eval_ORGANIZATION_recall": 0.9101123595505618, | |
| "eval_PERSON_f1": 0.9803921568627452, | |
| "eval_PERSON_number": 128, | |
| "eval_PERSON_precision": 0.984251968503937, | |
| "eval_PERSON_recall": 0.9765625, | |
| "eval_loss": 0.048419199883937836, | |
| "eval_overall_accuracy": 0.9846153846153847, | |
| "eval_overall_f1": 0.9411764705882353, | |
| "eval_overall_precision": 0.9435897435897436, | |
| "eval_overall_recall": 0.9387755102040817, | |
| "eval_runtime": 0.2819, | |
| "eval_samples_per_second": 602.959, | |
| "eval_steps_per_second": 10.64, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "step": 9600, | |
| "total_flos": 3881337493223460.0, | |
| "train_loss": 0.0924897667268912, | |
| "train_runtime": 512.434, | |
| "train_samples_per_second": 298.77, | |
| "train_steps_per_second": 18.734 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 9600, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 100, | |
| "save_steps": 500, | |
| "total_flos": 3881337493223460.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |