| { | |
| "best_metric": 1.135526418685913, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-100", | |
| "epoch": 0.6006006006006006, | |
| "eval_steps": 50, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.006006006006006006, | |
| "grad_norm": 1.932458758354187, | |
| "learning_rate": 4e-05, | |
| "loss": 1.7467, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006006006006006006, | |
| "eval_loss": 2.258627414703369, | |
| "eval_runtime": 19.9156, | |
| "eval_samples_per_second": 3.565, | |
| "eval_steps_per_second": 1.808, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.012012012012012012, | |
| "grad_norm": 2.092580556869507, | |
| "learning_rate": 8e-05, | |
| "loss": 1.6174, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.018018018018018018, | |
| "grad_norm": 2.6704134941101074, | |
| "learning_rate": 0.00012, | |
| "loss": 2.0744, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.024024024024024024, | |
| "grad_norm": 2.6446096897125244, | |
| "learning_rate": 0.00016, | |
| "loss": 2.0456, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.03003003003003003, | |
| "grad_norm": 2.992283821105957, | |
| "learning_rate": 0.0002, | |
| "loss": 2.0608, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.036036036036036036, | |
| "grad_norm": 2.878772020339966, | |
| "learning_rate": 0.00019994532573409262, | |
| "loss": 1.8436, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.042042042042042045, | |
| "grad_norm": 2.3450255393981934, | |
| "learning_rate": 0.00019978136272187747, | |
| "loss": 1.5301, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.04804804804804805, | |
| "grad_norm": 2.627563953399658, | |
| "learning_rate": 0.00019950829025450114, | |
| "loss": 1.5067, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.05405405405405406, | |
| "grad_norm": 2.8160147666931152, | |
| "learning_rate": 0.00019912640693269752, | |
| "loss": 1.63, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.06006006006006006, | |
| "grad_norm": 2.9350571632385254, | |
| "learning_rate": 0.00019863613034027224, | |
| "loss": 1.4446, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06606606606606606, | |
| "grad_norm": 3.1540119647979736, | |
| "learning_rate": 0.00019803799658748094, | |
| "loss": 1.546, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.07207207207207207, | |
| "grad_norm": 2.9855709075927734, | |
| "learning_rate": 0.0001973326597248006, | |
| "loss": 1.3291, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.07807807807807808, | |
| "grad_norm": 3.5713071823120117, | |
| "learning_rate": 0.00019652089102773488, | |
| "loss": 1.5786, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.08408408408408409, | |
| "grad_norm": 2.8019843101501465, | |
| "learning_rate": 0.00019560357815343577, | |
| "loss": 1.3472, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.09009009009009009, | |
| "grad_norm": 4.3546671867370605, | |
| "learning_rate": 0.00019458172417006347, | |
| "loss": 1.6172, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0960960960960961, | |
| "grad_norm": 2.810098886489868, | |
| "learning_rate": 0.0001934564464599461, | |
| "loss": 1.3136, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.1021021021021021, | |
| "grad_norm": 3.4647932052612305, | |
| "learning_rate": 0.00019222897549773848, | |
| "loss": 1.5548, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.10810810810810811, | |
| "grad_norm": 3.7336630821228027, | |
| "learning_rate": 0.00019090065350491626, | |
| "loss": 1.1755, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.11411411411411411, | |
| "grad_norm": 4.415683746337891, | |
| "learning_rate": 0.00018947293298207635, | |
| "loss": 0.9405, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.12012012012012012, | |
| "grad_norm": 3.080712080001831, | |
| "learning_rate": 0.0001879473751206489, | |
| "loss": 1.3905, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.12612612612612611, | |
| "grad_norm": 3.236367702484131, | |
| "learning_rate": 0.00018632564809575742, | |
| "loss": 1.3573, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.13213213213213212, | |
| "grad_norm": 5.037254810333252, | |
| "learning_rate": 0.00018460952524209355, | |
| "loss": 1.365, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.13813813813813813, | |
| "grad_norm": 2.8221218585968018, | |
| "learning_rate": 0.00018280088311480201, | |
| "loss": 1.4346, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.14414414414414414, | |
| "grad_norm": 3.3068811893463135, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 1.1536, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.15015015015015015, | |
| "grad_norm": 2.7103137969970703, | |
| "learning_rate": 0.00017891405093963938, | |
| "loss": 1.0335, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.15615615615615616, | |
| "grad_norm": 3.330439567565918, | |
| "learning_rate": 0.00017684011108568592, | |
| "loss": 1.1602, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.16216216216216217, | |
| "grad_norm": 4.12816858291626, | |
| "learning_rate": 0.0001746821476984154, | |
| "loss": 1.1393, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.16816816816816818, | |
| "grad_norm": 4.085017204284668, | |
| "learning_rate": 0.00017244252047910892, | |
| "loss": 1.1626, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.17417417417417416, | |
| "grad_norm": 3.0069985389709473, | |
| "learning_rate": 0.00017012367842724887, | |
| "loss": 1.2041, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.18018018018018017, | |
| "grad_norm": 5.760845184326172, | |
| "learning_rate": 0.00016772815716257412, | |
| "loss": 1.3702, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.18618618618618618, | |
| "grad_norm": 4.769516944885254, | |
| "learning_rate": 0.00016525857615241687, | |
| "loss": 1.3721, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.1921921921921922, | |
| "grad_norm": 4.2040114402771, | |
| "learning_rate": 0.0001627176358473537, | |
| "loss": 1.5594, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.1981981981981982, | |
| "grad_norm": 2.858583927154541, | |
| "learning_rate": 0.00016010811472830252, | |
| "loss": 0.874, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.2042042042042042, | |
| "grad_norm": 2.5151712894439697, | |
| "learning_rate": 0.00015743286626829437, | |
| "loss": 0.9235, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.21021021021021022, | |
| "grad_norm": 5.206013202667236, | |
| "learning_rate": 0.00015469481581224272, | |
| "loss": 1.2918, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.21621621621621623, | |
| "grad_norm": 3.1817026138305664, | |
| "learning_rate": 0.00015189695737812152, | |
| "loss": 1.0485, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.2222222222222222, | |
| "grad_norm": 3.6301400661468506, | |
| "learning_rate": 0.00014904235038305083, | |
| "loss": 1.1451, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.22822822822822822, | |
| "grad_norm": 3.7824904918670654, | |
| "learning_rate": 0.0001461341162978688, | |
| "loss": 1.3248, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.23423423423423423, | |
| "grad_norm": 4.668453216552734, | |
| "learning_rate": 0.00014317543523384928, | |
| "loss": 1.4904, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.24024024024024024, | |
| "grad_norm": 4.5516252517700195, | |
| "learning_rate": 0.00014016954246529696, | |
| "loss": 1.2515, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.24624624624624625, | |
| "grad_norm": 5.962148666381836, | |
| "learning_rate": 0.00013711972489182208, | |
| "loss": 1.563, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.25225225225225223, | |
| "grad_norm": 2.278181314468384, | |
| "learning_rate": 0.00013402931744416433, | |
| "loss": 1.3006, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.25825825825825827, | |
| "grad_norm": 2.05096173286438, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 1.2765, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.26426426426426425, | |
| "grad_norm": 3.696538209915161, | |
| "learning_rate": 0.00012774029087618446, | |
| "loss": 1.3659, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.2702702702702703, | |
| "grad_norm": 4.0726094245910645, | |
| "learning_rate": 0.00012454854871407994, | |
| "loss": 1.7335, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.27627627627627627, | |
| "grad_norm": 2.9776477813720703, | |
| "learning_rate": 0.0001213299630743747, | |
| "loss": 1.3651, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.2822822822822823, | |
| "grad_norm": 1.9622524976730347, | |
| "learning_rate": 0.000118088053433211, | |
| "loss": 1.0952, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.2882882882882883, | |
| "grad_norm": 3.340439796447754, | |
| "learning_rate": 0.0001148263647711842, | |
| "loss": 1.2612, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.29429429429429427, | |
| "grad_norm": 2.5127453804016113, | |
| "learning_rate": 0.00011154846369695863, | |
| "loss": 1.1119, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.3003003003003003, | |
| "grad_norm": 2.534255266189575, | |
| "learning_rate": 0.00010825793454723325, | |
| "loss": 1.1786, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3003003003003003, | |
| "eval_loss": 1.1894547939300537, | |
| "eval_runtime": 20.2258, | |
| "eval_samples_per_second": 3.51, | |
| "eval_steps_per_second": 1.78, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3063063063063063, | |
| "grad_norm": 2.467716932296753, | |
| "learning_rate": 0.00010495837546732224, | |
| "loss": 1.3141, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.3123123123123123, | |
| "grad_norm": 2.7195961475372314, | |
| "learning_rate": 0.00010165339447663587, | |
| "loss": 1.1358, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.3183183183183183, | |
| "grad_norm": 2.4302902221679688, | |
| "learning_rate": 9.834660552336415e-05, | |
| "loss": 1.2766, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.32432432432432434, | |
| "grad_norm": 2.4811532497406006, | |
| "learning_rate": 9.504162453267777e-05, | |
| "loss": 1.2285, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.3303303303303303, | |
| "grad_norm": 2.6031277179718018, | |
| "learning_rate": 9.174206545276677e-05, | |
| "loss": 1.2114, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.33633633633633636, | |
| "grad_norm": 3.0436697006225586, | |
| "learning_rate": 8.845153630304139e-05, | |
| "loss": 1.457, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.34234234234234234, | |
| "grad_norm": 2.756425619125366, | |
| "learning_rate": 8.517363522881579e-05, | |
| "loss": 1.2442, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.3483483483483483, | |
| "grad_norm": 2.9140679836273193, | |
| "learning_rate": 8.191194656678904e-05, | |
| "loss": 1.127, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.35435435435435436, | |
| "grad_norm": 2.6434483528137207, | |
| "learning_rate": 7.867003692562534e-05, | |
| "loss": 1.0603, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.36036036036036034, | |
| "grad_norm": 5.660317897796631, | |
| "learning_rate": 7.54514512859201e-05, | |
| "loss": 1.048, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.3663663663663664, | |
| "grad_norm": 2.662621021270752, | |
| "learning_rate": 7.225970912381556e-05, | |
| "loss": 0.9771, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.37237237237237236, | |
| "grad_norm": 3.0631654262542725, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 1.4288, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.3783783783783784, | |
| "grad_norm": 2.566416025161743, | |
| "learning_rate": 6.59706825558357e-05, | |
| "loss": 0.9023, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.3843843843843844, | |
| "grad_norm": 2.502877712249756, | |
| "learning_rate": 6.28802751081779e-05, | |
| "loss": 0.8202, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.39039039039039036, | |
| "grad_norm": 3.319624662399292, | |
| "learning_rate": 5.983045753470308e-05, | |
| "loss": 1.045, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.3963963963963964, | |
| "grad_norm": 2.7986936569213867, | |
| "learning_rate": 5.6824564766150726e-05, | |
| "loss": 1.295, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.4024024024024024, | |
| "grad_norm": 3.08010196685791, | |
| "learning_rate": 5.386588370213124e-05, | |
| "loss": 1.0989, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.4084084084084084, | |
| "grad_norm": 3.931140899658203, | |
| "learning_rate": 5.095764961694922e-05, | |
| "loss": 0.8769, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.4144144144144144, | |
| "grad_norm": 4.616240978240967, | |
| "learning_rate": 4.810304262187852e-05, | |
| "loss": 1.3225, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.42042042042042044, | |
| "grad_norm": 3.139350652694702, | |
| "learning_rate": 4.530518418775733e-05, | |
| "loss": 1.1953, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.4264264264264264, | |
| "grad_norm": 3.0971598625183105, | |
| "learning_rate": 4.256713373170564e-05, | |
| "loss": 0.9564, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.43243243243243246, | |
| "grad_norm": 4.219956874847412, | |
| "learning_rate": 3.9891885271697496e-05, | |
| "loss": 0.9444, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.43843843843843844, | |
| "grad_norm": 3.592334747314453, | |
| "learning_rate": 3.7282364152646297e-05, | |
| "loss": 1.1826, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.4444444444444444, | |
| "grad_norm": 4.302462577819824, | |
| "learning_rate": 3.4741423847583134e-05, | |
| "loss": 1.0087, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.45045045045045046, | |
| "grad_norm": 2.8837406635284424, | |
| "learning_rate": 3.227184283742591e-05, | |
| "loss": 0.9843, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.45645645645645644, | |
| "grad_norm": 2.9115164279937744, | |
| "learning_rate": 2.9876321572751144e-05, | |
| "loss": 1.013, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.4624624624624625, | |
| "grad_norm": 2.647456645965576, | |
| "learning_rate": 2.7557479520891104e-05, | |
| "loss": 0.9615, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.46846846846846846, | |
| "grad_norm": 2.5124423503875732, | |
| "learning_rate": 2.5317852301584643e-05, | |
| "loss": 0.697, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.4744744744744745, | |
| "grad_norm": 4.744019508361816, | |
| "learning_rate": 2.315988891431412e-05, | |
| "loss": 1.0931, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.4804804804804805, | |
| "grad_norm": 3.7033681869506836, | |
| "learning_rate": 2.1085949060360654e-05, | |
| "loss": 1.0538, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.4864864864864865, | |
| "grad_norm": 3.1618974208831787, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 0.7846, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.4924924924924925, | |
| "grad_norm": 3.4100112915039062, | |
| "learning_rate": 1.7199116885197995e-05, | |
| "loss": 1.1595, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.4984984984984985, | |
| "grad_norm": 2.8490142822265625, | |
| "learning_rate": 1.5390474757906446e-05, | |
| "loss": 1.3412, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.5045045045045045, | |
| "grad_norm": 1.9056596755981445, | |
| "learning_rate": 1.3674351904242611e-05, | |
| "loss": 1.2043, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.5105105105105106, | |
| "grad_norm": 2.0238497257232666, | |
| "learning_rate": 1.2052624879351104e-05, | |
| "loss": 1.1433, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.5165165165165165, | |
| "grad_norm": 2.10072922706604, | |
| "learning_rate": 1.0527067017923654e-05, | |
| "loss": 1.2434, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.5225225225225225, | |
| "grad_norm": 2.534837484359741, | |
| "learning_rate": 9.09934649508375e-06, | |
| "loss": 1.176, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.5285285285285285, | |
| "grad_norm": 2.2539825439453125, | |
| "learning_rate": 7.771024502261526e-06, | |
| "loss": 1.2467, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.5345345345345346, | |
| "grad_norm": 2.548096179962158, | |
| "learning_rate": 6.543553540053926e-06, | |
| "loss": 1.3314, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.5405405405405406, | |
| "grad_norm": 2.4377360343933105, | |
| "learning_rate": 5.418275829936537e-06, | |
| "loss": 1.2026, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.5465465465465466, | |
| "grad_norm": 2.1080400943756104, | |
| "learning_rate": 4.3964218465642355e-06, | |
| "loss": 1.1876, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.5525525525525525, | |
| "grad_norm": 2.250770330429077, | |
| "learning_rate": 3.4791089722651436e-06, | |
| "loss": 1.2981, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.5585585585585585, | |
| "grad_norm": 2.5565848350524902, | |
| "learning_rate": 2.667340275199426e-06, | |
| "loss": 1.031, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.5645645645645646, | |
| "grad_norm": 2.642076015472412, | |
| "learning_rate": 1.9620034125190644e-06, | |
| "loss": 1.1568, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.5705705705705706, | |
| "grad_norm": 2.3764145374298096, | |
| "learning_rate": 1.3638696597277679e-06, | |
| "loss": 1.2446, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.5765765765765766, | |
| "grad_norm": 2.5050697326660156, | |
| "learning_rate": 8.735930673024806e-07, | |
| "loss": 1.0928, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.5825825825825826, | |
| "grad_norm": 2.3315417766571045, | |
| "learning_rate": 4.917097454988584e-07, | |
| "loss": 1.0785, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.5885885885885885, | |
| "grad_norm": 1.9666122198104858, | |
| "learning_rate": 2.1863727812254653e-07, | |
| "loss": 0.9106, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.5945945945945946, | |
| "grad_norm": 2.5268125534057617, | |
| "learning_rate": 5.467426590739511e-08, | |
| "loss": 1.2624, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.6006006006006006, | |
| "grad_norm": 2.017895460128784, | |
| "learning_rate": 0.0, | |
| "loss": 0.8749, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.6006006006006006, | |
| "eval_loss": 1.135526418685913, | |
| "eval_runtime": 20.2206, | |
| "eval_samples_per_second": 3.511, | |
| "eval_steps_per_second": 1.78, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.483774567120896e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |