| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "global_step": 2188, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 4.997714808043876e-05, | |
| "loss": 6.9866, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.9017367458866546e-05, | |
| "loss": 3.9852, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_accuracy": 0.5429333333333334, | |
| "eval_f1": 0.6712696586114307, | |
| "eval_loss": 1.4847679138183594, | |
| "eval_precision": 0.5241090146750524, | |
| "eval_recall": 0.9333333333333333, | |
| "eval_runtime": 305.136, | |
| "eval_samples_per_second": 12.29, | |
| "eval_steps_per_second": 1.537, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.8034734917733096e-05, | |
| "loss": 2.6079, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_accuracy": 0.5717333333333333, | |
| "eval_f1": 0.6556603773584906, | |
| "eval_loss": 0.8047523498535156, | |
| "eval_precision": 0.5482251703119397, | |
| "eval_recall": 0.8154666666666667, | |
| "eval_runtime": 305.1856, | |
| "eval_samples_per_second": 12.288, | |
| "eval_steps_per_second": 1.537, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.705210237659964e-05, | |
| "loss": 1.0141, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_accuracy": 0.5896, | |
| "eval_f1": 0.6892792247122956, | |
| "eval_loss": 0.7188379764556885, | |
| "eval_precision": 0.5545808966861598, | |
| "eval_recall": 0.9104, | |
| "eval_runtime": 305.1209, | |
| "eval_samples_per_second": 12.29, | |
| "eval_steps_per_second": 1.537, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.606946983546618e-05, | |
| "loss": 0.8023, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_accuracy": 0.49733333333333335, | |
| "eval_f1": 0.11874707807386631, | |
| "eval_loss": 2.954312801361084, | |
| "eval_precision": 0.4810606060606061, | |
| "eval_recall": 0.06773333333333334, | |
| "eval_runtime": 305.0816, | |
| "eval_samples_per_second": 12.292, | |
| "eval_steps_per_second": 1.537, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.5086837294332726e-05, | |
| "loss": 2.4517, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_accuracy": 0.6850666666666667, | |
| "eval_f1": 0.7327449649241911, | |
| "eval_loss": 0.6679351925849915, | |
| "eval_precision": 0.6363993710691824, | |
| "eval_recall": 0.8634666666666667, | |
| "eval_runtime": 304.8754, | |
| "eval_samples_per_second": 12.3, | |
| "eval_steps_per_second": 1.538, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.410420475319927e-05, | |
| "loss": 1.6579, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_accuracy": 0.8109333333333333, | |
| "eval_f1": 0.7899259259259258, | |
| "eval_loss": 0.7148910164833069, | |
| "eval_precision": 0.8886666666666667, | |
| "eval_recall": 0.7109333333333333, | |
| "eval_runtime": 305.6713, | |
| "eval_samples_per_second": 12.268, | |
| "eval_steps_per_second": 1.534, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.312157221206581e-05, | |
| "loss": 1.3412, | |
| "step": 301 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_accuracy": 0.4938666666666667, | |
| "eval_f1": 0.6546579330422125, | |
| "eval_loss": 3.249486207962036, | |
| "eval_precision": 0.4968240817453742, | |
| "eval_recall": 0.9594666666666667, | |
| "eval_runtime": 304.7083, | |
| "eval_samples_per_second": 12.307, | |
| "eval_steps_per_second": 1.539, | |
| "step": 301 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.213893967093236e-05, | |
| "loss": 1.6235, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_accuracy": 0.8013333333333333, | |
| "eval_f1": 0.797719250610915, | |
| "eval_loss": 0.4983011782169342, | |
| "eval_precision": 0.8125, | |
| "eval_recall": 0.7834666666666666, | |
| "eval_runtime": 304.8657, | |
| "eval_samples_per_second": 12.3, | |
| "eval_steps_per_second": 1.538, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.1156307129798905e-05, | |
| "loss": 0.7822, | |
| "step": 387 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_accuracy": 0.856, | |
| "eval_f1": 0.8429319371727749, | |
| "eval_loss": 0.8706910014152527, | |
| "eval_precision": 0.927063339731286, | |
| "eval_recall": 0.7728, | |
| "eval_runtime": 305.1415, | |
| "eval_samples_per_second": 12.289, | |
| "eval_steps_per_second": 1.537, | |
| "step": 387 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.017367458866545e-05, | |
| "loss": 1.0922, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_accuracy": 0.8034666666666667, | |
| "eval_f1": 0.7738570113531757, | |
| "eval_loss": 0.667508602142334, | |
| "eval_precision": 0.9111271676300579, | |
| "eval_recall": 0.6725333333333333, | |
| "eval_runtime": 305.5394, | |
| "eval_samples_per_second": 12.273, | |
| "eval_steps_per_second": 1.535, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 3.919104204753199e-05, | |
| "loss": 0.5747, | |
| "step": 473 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_accuracy": 0.88, | |
| "eval_f1": 0.8822605965463108, | |
| "eval_loss": 0.4237947165966034, | |
| "eval_precision": 0.8659476117103235, | |
| "eval_recall": 0.8992, | |
| "eval_runtime": 305.7145, | |
| "eval_samples_per_second": 12.266, | |
| "eval_steps_per_second": 1.534, | |
| "step": 473 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 3.820840950639854e-05, | |
| "loss": 0.5248, | |
| "step": 516 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_accuracy": 0.8424, | |
| "eval_f1": 0.8570737605804112, | |
| "eval_loss": 1.081692099571228, | |
| "eval_precision": 0.784070796460177, | |
| "eval_recall": 0.9450666666666667, | |
| "eval_runtime": 305.0927, | |
| "eval_samples_per_second": 12.291, | |
| "eval_steps_per_second": 1.537, | |
| "step": 516 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 3.7225776965265085e-05, | |
| "loss": 0.6488, | |
| "step": 559 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "eval_accuracy": 0.8365333333333334, | |
| "eval_f1": 0.8115585613280049, | |
| "eval_loss": 0.5578557252883911, | |
| "eval_precision": 0.9579100145137881, | |
| "eval_recall": 0.704, | |
| "eval_runtime": 305.0779, | |
| "eval_samples_per_second": 12.292, | |
| "eval_steps_per_second": 1.537, | |
| "step": 559 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 3.624314442413163e-05, | |
| "loss": 0.9679, | |
| "step": 602 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_accuracy": 0.6829333333333333, | |
| "eval_f1": 0.5987175160310497, | |
| "eval_loss": 0.9434438943862915, | |
| "eval_precision": 0.8152573529411765, | |
| "eval_recall": 0.4730666666666667, | |
| "eval_runtime": 304.9674, | |
| "eval_samples_per_second": 12.296, | |
| "eval_steps_per_second": 1.538, | |
| "step": 602 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 3.526051188299818e-05, | |
| "loss": 0.4584, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "eval_accuracy": 0.8458666666666667, | |
| "eval_f1": 0.8547008547008548, | |
| "eval_loss": 0.44859734177589417, | |
| "eval_precision": 0.8083689966714218, | |
| "eval_recall": 0.9066666666666666, | |
| "eval_runtime": 304.9696, | |
| "eval_samples_per_second": 12.296, | |
| "eval_steps_per_second": 1.538, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 3.4277879341864715e-05, | |
| "loss": 0.418, | |
| "step": 688 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "eval_accuracy": 0.8901333333333333, | |
| "eval_f1": 0.892931392931393, | |
| "eval_loss": 0.5646004676818848, | |
| "eval_precision": 0.8707551951343132, | |
| "eval_recall": 0.9162666666666667, | |
| "eval_runtime": 304.779, | |
| "eval_samples_per_second": 12.304, | |
| "eval_steps_per_second": 1.539, | |
| "step": 688 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 3.329524680073126e-05, | |
| "loss": 0.5809, | |
| "step": 731 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_accuracy": 0.8773333333333333, | |
| "eval_f1": 0.8847117794486216, | |
| "eval_loss": 0.4200115501880646, | |
| "eval_precision": 0.83451536643026, | |
| "eval_recall": 0.9413333333333334, | |
| "eval_runtime": 304.7969, | |
| "eval_samples_per_second": 12.303, | |
| "eval_steps_per_second": 1.539, | |
| "step": 731 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 3.231261425959781e-05, | |
| "loss": 0.4702, | |
| "step": 774 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "eval_accuracy": 0.7117333333333333, | |
| "eval_f1": 0.7615265828369733, | |
| "eval_loss": 0.5946761965751648, | |
| "eval_precision": 0.6493604213694507, | |
| "eval_recall": 0.9205333333333333, | |
| "eval_runtime": 304.8632, | |
| "eval_samples_per_second": 12.301, | |
| "eval_steps_per_second": 1.538, | |
| "step": 774 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 3.132998171846435e-05, | |
| "loss": 0.3684, | |
| "step": 817 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "eval_accuracy": 0.8965333333333333, | |
| "eval_f1": 0.8914381645215446, | |
| "eval_loss": 0.30674976110458374, | |
| "eval_precision": 0.9376103590347263, | |
| "eval_recall": 0.8496, | |
| "eval_runtime": 304.8468, | |
| "eval_samples_per_second": 12.301, | |
| "eval_steps_per_second": 1.538, | |
| "step": 817 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 3.03473491773309e-05, | |
| "loss": 0.5431, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "eval_accuracy": 0.8762666666666666, | |
| "eval_f1": 0.8831234256926952, | |
| "eval_loss": 0.8089134693145752, | |
| "eval_precision": 0.8367541766109785, | |
| "eval_recall": 0.9349333333333333, | |
| "eval_runtime": 304.976, | |
| "eval_samples_per_second": 12.296, | |
| "eval_steps_per_second": 1.538, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 2.9364716636197442e-05, | |
| "loss": 0.4287, | |
| "step": 903 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_accuracy": 0.8466666666666667, | |
| "eval_f1": 0.822366388631449, | |
| "eval_loss": 0.49679452180862427, | |
| "eval_precision": 0.9772393538913363, | |
| "eval_recall": 0.7098666666666666, | |
| "eval_runtime": 306.5019, | |
| "eval_samples_per_second": 12.235, | |
| "eval_steps_per_second": 1.53, | |
| "step": 903 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 2.838208409506399e-05, | |
| "loss": 0.4942, | |
| "step": 946 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_accuracy": 0.9157333333333333, | |
| "eval_f1": 0.9138025095471904, | |
| "eval_loss": 0.23615875840187073, | |
| "eval_precision": 0.9352317141261864, | |
| "eval_recall": 0.8933333333333333, | |
| "eval_runtime": 305.2275, | |
| "eval_samples_per_second": 12.286, | |
| "eval_steps_per_second": 1.537, | |
| "step": 946 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 2.739945155393053e-05, | |
| "loss": 0.3997, | |
| "step": 989 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "eval_accuracy": 0.8874666666666666, | |
| "eval_f1": 0.8867418142780461, | |
| "eval_loss": 0.6193059086799622, | |
| "eval_precision": 0.8924905456509995, | |
| "eval_recall": 0.8810666666666667, | |
| "eval_runtime": 304.7962, | |
| "eval_samples_per_second": 12.303, | |
| "eval_steps_per_second": 1.539, | |
| "step": 989 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 2.641681901279708e-05, | |
| "loss": 0.3862, | |
| "step": 1032 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_accuracy": 0.8712, | |
| "eval_f1": 0.8817625458996328, | |
| "eval_loss": 0.6541677713394165, | |
| "eval_precision": 0.8149321266968326, | |
| "eval_recall": 0.9605333333333334, | |
| "eval_runtime": 305.7101, | |
| "eval_samples_per_second": 12.267, | |
| "eval_steps_per_second": 1.534, | |
| "step": 1032 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 2.5434186471663625e-05, | |
| "loss": 0.4199, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "eval_accuracy": 0.8778666666666667, | |
| "eval_f1": 0.8674768518518517, | |
| "eval_loss": 0.5205650329589844, | |
| "eval_precision": 0.948134092346616, | |
| "eval_recall": 0.7994666666666667, | |
| "eval_runtime": 306.2355, | |
| "eval_samples_per_second": 12.245, | |
| "eval_steps_per_second": 1.532, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 2.4451553930530165e-05, | |
| "loss": 0.4922, | |
| "step": 1118 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_accuracy": 0.8664, | |
| "eval_f1": 0.8587538765153652, | |
| "eval_loss": 0.3552885353565216, | |
| "eval_precision": 0.9108851674641149, | |
| "eval_recall": 0.8122666666666667, | |
| "eval_runtime": 305.1994, | |
| "eval_samples_per_second": 12.287, | |
| "eval_steps_per_second": 1.537, | |
| "step": 1118 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 2.346892138939671e-05, | |
| "loss": 0.3303, | |
| "step": 1161 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_accuracy": 0.9082666666666667, | |
| "eval_f1": 0.9038569032979319, | |
| "eval_loss": 0.38709646463394165, | |
| "eval_precision": 0.9495008807985907, | |
| "eval_recall": 0.8624, | |
| "eval_runtime": 305.1281, | |
| "eval_samples_per_second": 12.29, | |
| "eval_steps_per_second": 1.537, | |
| "step": 1161 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 2.2486288848263255e-05, | |
| "loss": 0.2829, | |
| "step": 1204 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_accuracy": 0.9104, | |
| "eval_f1": 0.9114391143911439, | |
| "eval_loss": 0.3015682101249695, | |
| "eval_precision": 0.900990099009901, | |
| "eval_recall": 0.9221333333333334, | |
| "eval_runtime": 305.3174, | |
| "eval_samples_per_second": 12.282, | |
| "eval_steps_per_second": 1.536, | |
| "step": 1204 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 2.1503656307129798e-05, | |
| "loss": 0.5477, | |
| "step": 1247 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "eval_accuracy": 0.8509333333333333, | |
| "eval_f1": 0.8479738917595866, | |
| "eval_loss": 0.5632778406143188, | |
| "eval_precision": 0.865149833518313, | |
| "eval_recall": 0.8314666666666667, | |
| "eval_runtime": 305.058, | |
| "eval_samples_per_second": 12.293, | |
| "eval_steps_per_second": 1.537, | |
| "step": 1247 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 2.0521023765996345e-05, | |
| "loss": 0.4431, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_accuracy": 0.9082666666666667, | |
| "eval_f1": 0.9050248481501934, | |
| "eval_loss": 0.42895591259002686, | |
| "eval_precision": 0.9381797366914711, | |
| "eval_recall": 0.8741333333333333, | |
| "eval_runtime": 305.0347, | |
| "eval_samples_per_second": 12.294, | |
| "eval_steps_per_second": 1.538, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 1.953839122486289e-05, | |
| "loss": 0.3335, | |
| "step": 1333 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "eval_accuracy": 0.9069333333333334, | |
| "eval_f1": 0.90008588605783, | |
| "eval_loss": 0.32379406690597534, | |
| "eval_precision": 0.9715698393077874, | |
| "eval_recall": 0.8384, | |
| "eval_runtime": 306.6476, | |
| "eval_samples_per_second": 12.229, | |
| "eval_steps_per_second": 1.529, | |
| "step": 1333 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 1.8555758683729435e-05, | |
| "loss": 0.3255, | |
| "step": 1376 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "eval_accuracy": 0.9152, | |
| "eval_f1": 0.9159619450317126, | |
| "eval_loss": 0.3898433446884155, | |
| "eval_precision": 0.9078051335777895, | |
| "eval_recall": 0.9242666666666667, | |
| "eval_runtime": 305.4671, | |
| "eval_samples_per_second": 12.276, | |
| "eval_steps_per_second": 1.535, | |
| "step": 1376 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 1.7573126142595978e-05, | |
| "loss": 0.3103, | |
| "step": 1419 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_accuracy": 0.9189333333333334, | |
| "eval_f1": 0.9140271493212669, | |
| "eval_loss": 0.25054827332496643, | |
| "eval_precision": 0.9729078868151716, | |
| "eval_recall": 0.8618666666666667, | |
| "eval_runtime": 304.9946, | |
| "eval_samples_per_second": 12.295, | |
| "eval_steps_per_second": 1.538, | |
| "step": 1419 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 1.659049360146252e-05, | |
| "loss": 0.2878, | |
| "step": 1462 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_accuracy": 0.9208, | |
| "eval_f1": 0.9207788743664976, | |
| "eval_loss": 0.29952123761177063, | |
| "eval_precision": 0.9210245464247598, | |
| "eval_recall": 0.9205333333333333, | |
| "eval_runtime": 304.6679, | |
| "eval_samples_per_second": 12.308, | |
| "eval_steps_per_second": 1.539, | |
| "step": 1462 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 1.5607861060329068e-05, | |
| "loss": 0.3426, | |
| "step": 1505 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_accuracy": 0.9248, | |
| "eval_f1": 0.9255936675461741, | |
| "eval_loss": 0.3102300763130188, | |
| "eval_precision": 0.9159268929503916, | |
| "eval_recall": 0.9354666666666667, | |
| "eval_runtime": 305.1368, | |
| "eval_samples_per_second": 12.29, | |
| "eval_steps_per_second": 1.537, | |
| "step": 1505 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 1.4625228519195613e-05, | |
| "loss": 0.2799, | |
| "step": 1548 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_accuracy": 0.9226666666666666, | |
| "eval_f1": 0.9236440231700894, | |
| "eval_loss": 0.32980650663375854, | |
| "eval_precision": 0.9121164846593863, | |
| "eval_recall": 0.9354666666666667, | |
| "eval_runtime": 305.2653, | |
| "eval_samples_per_second": 12.284, | |
| "eval_steps_per_second": 1.536, | |
| "step": 1548 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 1.3642595978062158e-05, | |
| "loss": 0.4076, | |
| "step": 1591 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "eval_accuracy": 0.9277333333333333, | |
| "eval_f1": 0.9256515775034294, | |
| "eval_loss": 0.29825451970100403, | |
| "eval_precision": 0.9531073446327684, | |
| "eval_recall": 0.8997333333333334, | |
| "eval_runtime": 304.9271, | |
| "eval_samples_per_second": 12.298, | |
| "eval_steps_per_second": 1.538, | |
| "step": 1591 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.2659963436928701e-05, | |
| "loss": 0.2303, | |
| "step": 1634 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_accuracy": 0.9168, | |
| "eval_f1": 0.9147540983606557, | |
| "eval_loss": 0.27176761627197266, | |
| "eval_precision": 0.9378151260504202, | |
| "eval_recall": 0.8928, | |
| "eval_runtime": 305.6751, | |
| "eval_samples_per_second": 12.268, | |
| "eval_steps_per_second": 1.534, | |
| "step": 1634 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.1677330895795248e-05, | |
| "loss": 0.2793, | |
| "step": 1677 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "eval_accuracy": 0.9229333333333334, | |
| "eval_f1": 0.9229949373834265, | |
| "eval_loss": 0.34073972702026367, | |
| "eval_precision": 0.9222577209797657, | |
| "eval_recall": 0.9237333333333333, | |
| "eval_runtime": 305.4396, | |
| "eval_samples_per_second": 12.277, | |
| "eval_steps_per_second": 1.535, | |
| "step": 1677 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1.0694698354661791e-05, | |
| "loss": 0.226, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "eval_accuracy": 0.9290666666666667, | |
| "eval_f1": 0.9279132791327913, | |
| "eval_loss": 0.34017863869667053, | |
| "eval_precision": 0.9432506887052342, | |
| "eval_recall": 0.9130666666666667, | |
| "eval_runtime": 304.4994, | |
| "eval_samples_per_second": 12.315, | |
| "eval_steps_per_second": 1.54, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 9.712065813528338e-06, | |
| "loss": 0.5583, | |
| "step": 1763 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "eval_accuracy": 0.92, | |
| "eval_f1": 0.9220779220779222, | |
| "eval_loss": 0.26789960265159607, | |
| "eval_precision": 0.8987341772151899, | |
| "eval_recall": 0.9466666666666667, | |
| "eval_runtime": 304.5833, | |
| "eval_samples_per_second": 12.312, | |
| "eval_steps_per_second": 1.54, | |
| "step": 1763 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 8.729433272394881e-06, | |
| "loss": 0.2609, | |
| "step": 1806 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "eval_accuracy": 0.9293333333333333, | |
| "eval_f1": 0.928436402916554, | |
| "eval_loss": 0.3069748878479004, | |
| "eval_precision": 0.9403719912472648, | |
| "eval_recall": 0.9168, | |
| "eval_runtime": 305.3926, | |
| "eval_samples_per_second": 12.279, | |
| "eval_steps_per_second": 1.536, | |
| "step": 1806 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 7.746800731261426e-06, | |
| "loss": 0.3392, | |
| "step": 1849 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "eval_accuracy": 0.9309333333333333, | |
| "eval_f1": 0.928748280605227, | |
| "eval_loss": 0.24878720939159393, | |
| "eval_precision": 0.9590909090909091, | |
| "eval_recall": 0.9002666666666667, | |
| "eval_runtime": 305.0861, | |
| "eval_samples_per_second": 12.292, | |
| "eval_steps_per_second": 1.537, | |
| "step": 1849 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 6.764168190127972e-06, | |
| "loss": 0.3378, | |
| "step": 1892 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "eval_accuracy": 0.9272, | |
| "eval_f1": 0.9248554913294799, | |
| "eval_loss": 0.2940199077129364, | |
| "eval_precision": 0.9556313993174061, | |
| "eval_recall": 0.896, | |
| "eval_runtime": 304.8472, | |
| "eval_samples_per_second": 12.301, | |
| "eval_steps_per_second": 1.538, | |
| "step": 1892 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 5.781535648994515e-06, | |
| "loss": 0.2271, | |
| "step": 1935 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "eval_accuracy": 0.9349333333333333, | |
| "eval_f1": 0.934654525977504, | |
| "eval_loss": 0.23414117097854614, | |
| "eval_precision": 0.9386767079074771, | |
| "eval_recall": 0.9306666666666666, | |
| "eval_runtime": 304.8432, | |
| "eval_samples_per_second": 12.301, | |
| "eval_steps_per_second": 1.538, | |
| "step": 1935 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 4.798903107861061e-06, | |
| "loss": 0.4284, | |
| "step": 1978 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "eval_accuracy": 0.9325333333333333, | |
| "eval_f1": 0.9310438811665304, | |
| "eval_loss": 0.30585160851478577, | |
| "eval_precision": 0.9520624303232998, | |
| "eval_recall": 0.9109333333333334, | |
| "eval_runtime": 304.8244, | |
| "eval_samples_per_second": 12.302, | |
| "eval_steps_per_second": 1.539, | |
| "step": 1978 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 3.816270566727605e-06, | |
| "loss": 0.2887, | |
| "step": 2021 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "eval_accuracy": 0.9341333333333334, | |
| "eval_f1": 0.9327158812312721, | |
| "eval_loss": 0.27199041843414307, | |
| "eval_precision": 0.9532293986636972, | |
| "eval_recall": 0.9130666666666667, | |
| "eval_runtime": 305.2967, | |
| "eval_samples_per_second": 12.283, | |
| "eval_steps_per_second": 1.536, | |
| "step": 2021 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 2.83363802559415e-06, | |
| "loss": 0.2287, | |
| "step": 2064 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "eval_accuracy": 0.9362666666666667, | |
| "eval_f1": 0.9355273806312382, | |
| "eval_loss": 0.3032676577568054, | |
| "eval_precision": 0.9465065502183406, | |
| "eval_recall": 0.9248, | |
| "eval_runtime": 305.4791, | |
| "eval_samples_per_second": 12.276, | |
| "eval_steps_per_second": 1.535, | |
| "step": 2064 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 1.851005484460695e-06, | |
| "loss": 0.3379, | |
| "step": 2107 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_accuracy": 0.9362666666666667, | |
| "eval_f1": 0.9354577369700243, | |
| "eval_loss": 0.25949496030807495, | |
| "eval_precision": 0.9474835886214442, | |
| "eval_recall": 0.9237333333333333, | |
| "eval_runtime": 305.1987, | |
| "eval_samples_per_second": 12.287, | |
| "eval_steps_per_second": 1.537, | |
| "step": 2107 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 8.683729433272396e-07, | |
| "loss": 0.2405, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "eval_accuracy": 0.9354666666666667, | |
| "eval_f1": 0.9345238095238096, | |
| "eval_loss": 0.2737696170806885, | |
| "eval_precision": 0.9483800109829764, | |
| "eval_recall": 0.9210666666666667, | |
| "eval_runtime": 304.727, | |
| "eval_samples_per_second": 12.306, | |
| "eval_steps_per_second": 1.539, | |
| "step": 2150 | |
| } | |
| ], | |
| "max_steps": 2188, | |
| "num_train_epochs": 1, | |
| "total_flos": 6.497491746816e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |