| { | |
| "best_metric": 0.5932047750229569, | |
| "best_model_checkpoint": "convnextv2-base-22k-224-finetuned-tekno24/checkpoint-614", | |
| "epoch": 11.956043956043956, | |
| "eval_steps": 500, | |
| "global_step": 816, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.14652014652014653, | |
| "grad_norm": 16.747648239135742, | |
| "learning_rate": 6.0975609756097564e-06, | |
| "loss": 1.4185, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.29304029304029305, | |
| "grad_norm": 14.544577598571777, | |
| "learning_rate": 1.2195121951219513e-05, | |
| "loss": 1.4153, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.43956043956043955, | |
| "grad_norm": 12.55716323852539, | |
| "learning_rate": 1.8292682926829268e-05, | |
| "loss": 1.3581, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5860805860805861, | |
| "grad_norm": 16.329694747924805, | |
| "learning_rate": 2.378048780487805e-05, | |
| "loss": 1.3421, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.7326007326007326, | |
| "grad_norm": 9.924437522888184, | |
| "learning_rate": 2.9878048780487805e-05, | |
| "loss": 1.3174, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.8791208791208791, | |
| "grad_norm": 8.243997573852539, | |
| "learning_rate": 3.597560975609756e-05, | |
| "loss": 1.2755, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.9963369963369964, | |
| "eval_accuracy": 0.4903581267217631, | |
| "eval_f1": 0.39101576597192117, | |
| "eval_loss": 1.2008219957351685, | |
| "eval_precision": 0.45771669331368264, | |
| "eval_recall": 0.4903581267217631, | |
| "eval_runtime": 10.5546, | |
| "eval_samples_per_second": 103.178, | |
| "eval_steps_per_second": 6.537, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 1.0256410256410255, | |
| "grad_norm": 13.558063507080078, | |
| "learning_rate": 4.207317073170732e-05, | |
| "loss": 1.2711, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.1721611721611722, | |
| "grad_norm": 27.544034957885742, | |
| "learning_rate": 4.817073170731707e-05, | |
| "loss": 1.2731, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.3186813186813187, | |
| "grad_norm": 12.061452865600586, | |
| "learning_rate": 4.952316076294278e-05, | |
| "loss": 1.2582, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.4652014652014653, | |
| "grad_norm": 13.313647270202637, | |
| "learning_rate": 4.884196185286104e-05, | |
| "loss": 1.2729, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.6117216117216118, | |
| "grad_norm": 8.85893440246582, | |
| "learning_rate": 4.816076294277929e-05, | |
| "loss": 1.2093, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.7582417582417582, | |
| "grad_norm": 7.619632244110107, | |
| "learning_rate": 4.747956403269755e-05, | |
| "loss": 1.2445, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.9047619047619047, | |
| "grad_norm": 9.313189506530762, | |
| "learning_rate": 4.6798365122615805e-05, | |
| "loss": 1.1711, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.9926739926739927, | |
| "eval_accuracy": 0.5353535353535354, | |
| "eval_f1": 0.47656758341858724, | |
| "eval_loss": 1.0650511980056763, | |
| "eval_precision": 0.48653241546321574, | |
| "eval_recall": 0.5353535353535354, | |
| "eval_runtime": 10.5232, | |
| "eval_samples_per_second": 103.486, | |
| "eval_steps_per_second": 6.557, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 2.051282051282051, | |
| "grad_norm": 9.400361061096191, | |
| "learning_rate": 4.6117166212534065e-05, | |
| "loss": 1.1145, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.197802197802198, | |
| "grad_norm": 5.284915924072266, | |
| "learning_rate": 4.543596730245232e-05, | |
| "loss": 1.1809, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.3443223443223444, | |
| "grad_norm": 10.18017292022705, | |
| "learning_rate": 4.475476839237057e-05, | |
| "loss": 1.1668, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.490842490842491, | |
| "grad_norm": 7.79976224899292, | |
| "learning_rate": 4.407356948228883e-05, | |
| "loss": 1.1582, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.6373626373626373, | |
| "grad_norm": 8.457806587219238, | |
| "learning_rate": 4.339237057220708e-05, | |
| "loss": 1.1628, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.7838827838827838, | |
| "grad_norm": 6.220970630645752, | |
| "learning_rate": 4.271117166212534e-05, | |
| "loss": 1.2035, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 2.9304029304029307, | |
| "grad_norm": 7.159059524536133, | |
| "learning_rate": 4.20299727520436e-05, | |
| "loss": 1.1599, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.989010989010989, | |
| "eval_accuracy": 0.54178145087236, | |
| "eval_f1": 0.5077316365087595, | |
| "eval_loss": 1.0533095598220825, | |
| "eval_precision": 0.5274645952658832, | |
| "eval_recall": 0.54178145087236, | |
| "eval_runtime": 10.5408, | |
| "eval_samples_per_second": 103.313, | |
| "eval_steps_per_second": 6.546, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 3.076923076923077, | |
| "grad_norm": 5.542409896850586, | |
| "learning_rate": 4.1348773841961855e-05, | |
| "loss": 1.1692, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 3.2234432234432235, | |
| "grad_norm": 7.356290340423584, | |
| "learning_rate": 4.066757493188011e-05, | |
| "loss": 1.1176, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 3.36996336996337, | |
| "grad_norm": 6.849288463592529, | |
| "learning_rate": 3.998637602179837e-05, | |
| "loss": 1.1335, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 3.5164835164835164, | |
| "grad_norm": 11.968345642089844, | |
| "learning_rate": 3.930517711171662e-05, | |
| "loss": 1.14, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 3.663003663003663, | |
| "grad_norm": 8.681733131408691, | |
| "learning_rate": 3.862397820163488e-05, | |
| "loss": 1.1195, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 3.8095238095238093, | |
| "grad_norm": 8.258611679077148, | |
| "learning_rate": 3.794277929155314e-05, | |
| "loss": 1.1578, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 3.956043956043956, | |
| "grad_norm": 9.197736740112305, | |
| "learning_rate": 3.726158038147139e-05, | |
| "loss": 1.1595, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.5454545454545454, | |
| "eval_f1": 0.5413509466694156, | |
| "eval_loss": 1.0423349142074585, | |
| "eval_precision": 0.5690587889084956, | |
| "eval_recall": 0.5454545454545454, | |
| "eval_runtime": 10.5435, | |
| "eval_samples_per_second": 103.286, | |
| "eval_steps_per_second": 6.544, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 4.102564102564102, | |
| "grad_norm": 7.987867832183838, | |
| "learning_rate": 3.6580381471389645e-05, | |
| "loss": 1.0988, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 4.249084249084249, | |
| "grad_norm": 6.383251667022705, | |
| "learning_rate": 3.5899182561307905e-05, | |
| "loss": 1.1338, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 4.395604395604396, | |
| "grad_norm": 7.749887943267822, | |
| "learning_rate": 3.521798365122616e-05, | |
| "loss": 1.1635, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 4.542124542124542, | |
| "grad_norm": 9.830282211303711, | |
| "learning_rate": 3.453678474114442e-05, | |
| "loss": 1.0912, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 4.688644688644689, | |
| "grad_norm": 9.785733222961426, | |
| "learning_rate": 3.385558583106267e-05, | |
| "loss": 1.1293, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 4.835164835164835, | |
| "grad_norm": 9.794586181640625, | |
| "learning_rate": 3.317438692098093e-05, | |
| "loss": 1.0867, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 4.981684981684982, | |
| "grad_norm": 5.60059928894043, | |
| "learning_rate": 3.249318801089918e-05, | |
| "loss": 1.096, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 4.996336996336996, | |
| "eval_accuracy": 0.5610651974288338, | |
| "eval_f1": 0.5462709659715219, | |
| "eval_loss": 1.0159707069396973, | |
| "eval_precision": 0.5419035604614381, | |
| "eval_recall": 0.5610651974288338, | |
| "eval_runtime": 10.5161, | |
| "eval_samples_per_second": 103.556, | |
| "eval_steps_per_second": 6.561, | |
| "step": 341 | |
| }, | |
| { | |
| "epoch": 5.128205128205128, | |
| "grad_norm": 6.809742450714111, | |
| "learning_rate": 3.181198910081744e-05, | |
| "loss": 1.071, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 5.274725274725275, | |
| "grad_norm": 7.61679744720459, | |
| "learning_rate": 3.1130790190735695e-05, | |
| "loss": 1.1031, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 5.4212454212454215, | |
| "grad_norm": 7.127725601196289, | |
| "learning_rate": 3.0449591280653955e-05, | |
| "loss": 1.0971, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 5.5677655677655675, | |
| "grad_norm": 6.362829685211182, | |
| "learning_rate": 2.9768392370572208e-05, | |
| "loss": 1.1078, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 5.714285714285714, | |
| "grad_norm": 8.149834632873535, | |
| "learning_rate": 2.9087193460490464e-05, | |
| "loss": 1.0871, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 5.860805860805861, | |
| "grad_norm": 8.003039360046387, | |
| "learning_rate": 2.840599455040872e-05, | |
| "loss": 1.0592, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 5.992673992673993, | |
| "eval_accuracy": 0.5766758494031221, | |
| "eval_f1": 0.5414852771503386, | |
| "eval_loss": 0.9847236275672913, | |
| "eval_precision": 0.5484837093262834, | |
| "eval_recall": 0.5766758494031221, | |
| "eval_runtime": 10.5345, | |
| "eval_samples_per_second": 103.374, | |
| "eval_steps_per_second": 6.55, | |
| "step": 409 | |
| }, | |
| { | |
| "epoch": 6.007326007326007, | |
| "grad_norm": 9.939899444580078, | |
| "learning_rate": 2.772479564032698e-05, | |
| "loss": 1.0573, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 6.153846153846154, | |
| "grad_norm": 8.810173988342285, | |
| "learning_rate": 2.7043596730245236e-05, | |
| "loss": 1.038, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 6.3003663003663, | |
| "grad_norm": 9.228567123413086, | |
| "learning_rate": 2.6362397820163485e-05, | |
| "loss": 1.0441, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 6.446886446886447, | |
| "grad_norm": 10.357806205749512, | |
| "learning_rate": 2.5681198910081745e-05, | |
| "loss": 1.0313, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 6.593406593406593, | |
| "grad_norm": 6.874061584472656, | |
| "learning_rate": 2.5e-05, | |
| "loss": 1.0667, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 6.73992673992674, | |
| "grad_norm": 10.741703987121582, | |
| "learning_rate": 2.4318801089918257e-05, | |
| "loss": 1.0353, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 6.886446886446887, | |
| "grad_norm": 7.215301513671875, | |
| "learning_rate": 2.3637602179836514e-05, | |
| "loss": 1.0706, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 6.989010989010989, | |
| "eval_accuracy": 0.588613406795225, | |
| "eval_f1": 0.5835655659113839, | |
| "eval_loss": 0.9867706894874573, | |
| "eval_precision": 0.5861531495568983, | |
| "eval_recall": 0.588613406795225, | |
| "eval_runtime": 10.5429, | |
| "eval_samples_per_second": 103.292, | |
| "eval_steps_per_second": 6.545, | |
| "step": 477 | |
| }, | |
| { | |
| "epoch": 7.032967032967033, | |
| "grad_norm": 9.452975273132324, | |
| "learning_rate": 2.295640326975477e-05, | |
| "loss": 1.1093, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 7.17948717948718, | |
| "grad_norm": 5.909883499145508, | |
| "learning_rate": 2.2275204359673023e-05, | |
| "loss": 1.0628, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 7.326007326007326, | |
| "grad_norm": 8.430510520935059, | |
| "learning_rate": 2.1594005449591282e-05, | |
| "loss": 1.0175, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 7.472527472527473, | |
| "grad_norm": 11.566703796386719, | |
| "learning_rate": 2.091280653950954e-05, | |
| "loss": 0.9975, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 7.619047619047619, | |
| "grad_norm": 8.561046600341797, | |
| "learning_rate": 2.023160762942779e-05, | |
| "loss": 1.057, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 7.7655677655677655, | |
| "grad_norm": 9.214874267578125, | |
| "learning_rate": 1.955040871934605e-05, | |
| "loss": 1.0085, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 7.912087912087912, | |
| "grad_norm": 7.050257682800293, | |
| "learning_rate": 1.8869209809264307e-05, | |
| "loss": 1.0404, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.5867768595041323, | |
| "eval_f1": 0.5736657074074295, | |
| "eval_loss": 0.9758484363555908, | |
| "eval_precision": 0.5694509571644558, | |
| "eval_recall": 0.5867768595041323, | |
| "eval_runtime": 10.5054, | |
| "eval_samples_per_second": 103.661, | |
| "eval_steps_per_second": 6.568, | |
| "step": 546 | |
| }, | |
| { | |
| "epoch": 8.058608058608058, | |
| "grad_norm": 9.406164169311523, | |
| "learning_rate": 1.818801089918256e-05, | |
| "loss": 1.0564, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 8.205128205128204, | |
| "grad_norm": 8.063167572021484, | |
| "learning_rate": 1.750681198910082e-05, | |
| "loss": 1.0381, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 8.351648351648352, | |
| "grad_norm": 7.877150535583496, | |
| "learning_rate": 1.6825613079019073e-05, | |
| "loss": 0.9996, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 8.498168498168498, | |
| "grad_norm": 10.49506664276123, | |
| "learning_rate": 1.614441416893733e-05, | |
| "loss": 0.9723, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 8.644688644688644, | |
| "grad_norm": 8.74528694152832, | |
| "learning_rate": 1.546321525885559e-05, | |
| "loss": 1.0267, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 8.791208791208792, | |
| "grad_norm": 7.0554962158203125, | |
| "learning_rate": 1.4782016348773841e-05, | |
| "loss": 1.0251, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 8.937728937728938, | |
| "grad_norm": 7.974668502807617, | |
| "learning_rate": 1.41008174386921e-05, | |
| "loss": 1.0059, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 8.996336996336996, | |
| "eval_accuracy": 0.5932047750229569, | |
| "eval_f1": 0.5674291939014156, | |
| "eval_loss": 0.9468401074409485, | |
| "eval_precision": 0.5709384462011384, | |
| "eval_recall": 0.5932047750229569, | |
| "eval_runtime": 10.4878, | |
| "eval_samples_per_second": 103.835, | |
| "eval_steps_per_second": 6.579, | |
| "step": 614 | |
| }, | |
| { | |
| "epoch": 9.084249084249084, | |
| "grad_norm": 8.571954727172852, | |
| "learning_rate": 1.3419618528610356e-05, | |
| "loss": 0.9878, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 9.23076923076923, | |
| "grad_norm": 8.298359870910645, | |
| "learning_rate": 1.273841961852861e-05, | |
| "loss": 1.0056, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 9.377289377289378, | |
| "grad_norm": 7.087368965148926, | |
| "learning_rate": 1.2057220708446868e-05, | |
| "loss": 1.037, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 9.523809523809524, | |
| "grad_norm": 7.409104347229004, | |
| "learning_rate": 1.1376021798365123e-05, | |
| "loss": 0.9326, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 9.67032967032967, | |
| "grad_norm": 7.1452531814575195, | |
| "learning_rate": 1.0694822888283379e-05, | |
| "loss": 0.9723, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 9.816849816849818, | |
| "grad_norm": 8.340729713439941, | |
| "learning_rate": 1.0013623978201635e-05, | |
| "loss": 0.9914, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 9.963369963369964, | |
| "grad_norm": 10.698880195617676, | |
| "learning_rate": 9.332425068119891e-06, | |
| "loss": 0.965, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 9.992673992673993, | |
| "eval_accuracy": 0.5932047750229569, | |
| "eval_f1": 0.5804462637419235, | |
| "eval_loss": 0.9565483331680298, | |
| "eval_precision": 0.5857538351608745, | |
| "eval_recall": 0.5932047750229569, | |
| "eval_runtime": 10.4791, | |
| "eval_samples_per_second": 103.921, | |
| "eval_steps_per_second": 6.585, | |
| "step": 682 | |
| }, | |
| { | |
| "epoch": 10.10989010989011, | |
| "grad_norm": 10.67618465423584, | |
| "learning_rate": 8.651226158038147e-06, | |
| "loss": 0.9732, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 10.256410256410255, | |
| "grad_norm": 9.102426528930664, | |
| "learning_rate": 7.970027247956404e-06, | |
| "loss": 0.9804, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 10.402930402930403, | |
| "grad_norm": 11.115556716918945, | |
| "learning_rate": 7.288828337874659e-06, | |
| "loss": 0.9855, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 10.54945054945055, | |
| "grad_norm": 11.00426197052002, | |
| "learning_rate": 6.607629427792916e-06, | |
| "loss": 0.9691, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 10.695970695970695, | |
| "grad_norm": 10.043339729309082, | |
| "learning_rate": 5.9264305177111724e-06, | |
| "loss": 0.9365, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 10.842490842490843, | |
| "grad_norm": 11.518232345581055, | |
| "learning_rate": 5.245231607629428e-06, | |
| "loss": 0.9659, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 10.989010989010989, | |
| "grad_norm": 9.314995765686035, | |
| "learning_rate": 4.564032697547684e-06, | |
| "loss": 0.9362, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 10.989010989010989, | |
| "eval_accuracy": 0.588613406795225, | |
| "eval_f1": 0.5778239696801104, | |
| "eval_loss": 0.9466218948364258, | |
| "eval_precision": 0.5767647827506791, | |
| "eval_recall": 0.588613406795225, | |
| "eval_runtime": 10.5258, | |
| "eval_samples_per_second": 103.46, | |
| "eval_steps_per_second": 6.555, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 11.135531135531135, | |
| "grad_norm": 10.667020797729492, | |
| "learning_rate": 3.88283378746594e-06, | |
| "loss": 0.9564, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 11.282051282051283, | |
| "grad_norm": 10.923125267028809, | |
| "learning_rate": 3.2016348773841965e-06, | |
| "loss": 0.9177, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 11.428571428571429, | |
| "grad_norm": 9.893692016601562, | |
| "learning_rate": 2.5204359673024523e-06, | |
| "loss": 0.9732, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 11.575091575091575, | |
| "grad_norm": 8.784825325012207, | |
| "learning_rate": 1.8392370572207086e-06, | |
| "loss": 0.9558, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 11.72161172161172, | |
| "grad_norm": 8.990778923034668, | |
| "learning_rate": 1.1580381471389646e-06, | |
| "loss": 0.9656, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 11.868131868131869, | |
| "grad_norm": 8.444221496582031, | |
| "learning_rate": 4.768392370572207e-07, | |
| "loss": 0.9334, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 11.956043956043956, | |
| "eval_accuracy": 0.5858585858585859, | |
| "eval_f1": 0.5699572730591373, | |
| "eval_loss": 0.9441593885421753, | |
| "eval_precision": 0.5692451226403554, | |
| "eval_recall": 0.5858585858585859, | |
| "eval_runtime": 10.5926, | |
| "eval_samples_per_second": 102.808, | |
| "eval_steps_per_second": 6.514, | |
| "step": 816 | |
| }, | |
| { | |
| "epoch": 11.956043956043956, | |
| "step": 816, | |
| "total_flos": 4.123334853511373e+18, | |
| "train_loss": 1.090085435147379, | |
| "train_runtime": 2115.1144, | |
| "train_samples_per_second": 24.697, | |
| "train_steps_per_second": 0.386 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 816, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 12, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.123334853511373e+18, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |