| { | |
| "best_metric": 2.735139846801758, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-100", | |
| "epoch": 0.01632586425043876, | |
| "eval_steps": 50, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00016325864250438759, | |
| "grad_norm": 0.8632163405418396, | |
| "learning_rate": 3.3333333333333333e-06, | |
| "loss": 2.6076, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00016325864250438759, | |
| "eval_loss": 3.252528667449951, | |
| "eval_runtime": 363.3093, | |
| "eval_samples_per_second": 28.395, | |
| "eval_steps_per_second": 14.197, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00032651728500877517, | |
| "grad_norm": 0.8164938688278198, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 2.7626, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0004897759275131628, | |
| "grad_norm": 1.0135329961776733, | |
| "learning_rate": 1e-05, | |
| "loss": 3.2325, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0006530345700175503, | |
| "grad_norm": 1.0819627046585083, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 3.3302, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0008162932125219379, | |
| "grad_norm": 1.0888584852218628, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 3.2608, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0009795518550263255, | |
| "grad_norm": 1.1022908687591553, | |
| "learning_rate": 2e-05, | |
| "loss": 3.3397, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.001142810497530713, | |
| "grad_norm": 1.0631771087646484, | |
| "learning_rate": 2.3333333333333336e-05, | |
| "loss": 3.2714, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0013060691400351007, | |
| "grad_norm": 1.1249130964279175, | |
| "learning_rate": 2.6666666666666667e-05, | |
| "loss": 3.3009, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0014693277825394882, | |
| "grad_norm": 1.2283929586410522, | |
| "learning_rate": 3e-05, | |
| "loss": 3.3171, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0016325864250438759, | |
| "grad_norm": 1.0188909769058228, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 2.7293, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0017958450675482633, | |
| "grad_norm": 1.2337793111801147, | |
| "learning_rate": 3.6666666666666666e-05, | |
| "loss": 3.0187, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.001959103710052651, | |
| "grad_norm": 1.0160133838653564, | |
| "learning_rate": 4e-05, | |
| "loss": 2.897, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0021223623525570383, | |
| "grad_norm": 0.9511106610298157, | |
| "learning_rate": 4.3333333333333334e-05, | |
| "loss": 3.2403, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.002285620995061426, | |
| "grad_norm": 0.9372708797454834, | |
| "learning_rate": 4.666666666666667e-05, | |
| "loss": 3.0862, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0024488796375658137, | |
| "grad_norm": 0.7635182738304138, | |
| "learning_rate": 5e-05, | |
| "loss": 2.9518, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0026121382800702014, | |
| "grad_norm": 0.9754545092582703, | |
| "learning_rate": 5.333333333333333e-05, | |
| "loss": 2.789, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0027753969225745886, | |
| "grad_norm": 0.8830393552780151, | |
| "learning_rate": 5.666666666666667e-05, | |
| "loss": 2.8314, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0029386555650789763, | |
| "grad_norm": 0.7772381901741028, | |
| "learning_rate": 6e-05, | |
| "loss": 2.6371, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.003101914207583364, | |
| "grad_norm": 1.0107795000076294, | |
| "learning_rate": 6.333333333333333e-05, | |
| "loss": 2.858, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0032651728500877517, | |
| "grad_norm": 1.1810671091079712, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 3.2062, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.003428431492592139, | |
| "grad_norm": 0.9577175378799438, | |
| "learning_rate": 7e-05, | |
| "loss": 3.1488, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0035916901350965267, | |
| "grad_norm": 0.898638904094696, | |
| "learning_rate": 7.333333333333333e-05, | |
| "loss": 3.3016, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0037549487776009144, | |
| "grad_norm": 1.1327389478683472, | |
| "learning_rate": 7.666666666666667e-05, | |
| "loss": 2.8533, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.003918207420105302, | |
| "grad_norm": 0.9358575940132141, | |
| "learning_rate": 8e-05, | |
| "loss": 3.1331, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.00408146606260969, | |
| "grad_norm": 0.9725240468978882, | |
| "learning_rate": 8.333333333333334e-05, | |
| "loss": 2.9826, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.004244724705114077, | |
| "grad_norm": 0.9563072919845581, | |
| "learning_rate": 8.666666666666667e-05, | |
| "loss": 2.9238, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.004407983347618464, | |
| "grad_norm": 0.8429107069969177, | |
| "learning_rate": 9e-05, | |
| "loss": 2.8076, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.004571241990122852, | |
| "grad_norm": 0.938100278377533, | |
| "learning_rate": 9.333333333333334e-05, | |
| "loss": 2.9171, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.00473450063262724, | |
| "grad_norm": 1.0879822969436646, | |
| "learning_rate": 9.666666666666667e-05, | |
| "loss": 3.0946, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.004897759275131627, | |
| "grad_norm": 1.012676477432251, | |
| "learning_rate": 0.0001, | |
| "loss": 2.8535, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.005061017917636015, | |
| "grad_norm": 0.864611029624939, | |
| "learning_rate": 9.994965332706573e-05, | |
| "loss": 2.8619, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.005224276560140403, | |
| "grad_norm": 0.9068366885185242, | |
| "learning_rate": 9.979871469976196e-05, | |
| "loss": 2.7014, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.00538753520264479, | |
| "grad_norm": 1.1143074035644531, | |
| "learning_rate": 9.954748808839674e-05, | |
| "loss": 2.7219, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.005550793845149177, | |
| "grad_norm": 1.0027602910995483, | |
| "learning_rate": 9.919647942993148e-05, | |
| "loss": 3.1337, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.005714052487653565, | |
| "grad_norm": 0.9993074536323547, | |
| "learning_rate": 9.874639560909117e-05, | |
| "loss": 2.906, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.005877311130157953, | |
| "grad_norm": 0.9074757695198059, | |
| "learning_rate": 9.819814303479267e-05, | |
| "loss": 2.7418, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.00604056977266234, | |
| "grad_norm": 1.012048602104187, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 2.594, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.006203828415166728, | |
| "grad_norm": 0.8783692717552185, | |
| "learning_rate": 9.681174353198687e-05, | |
| "loss": 3.0345, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.006367087057671116, | |
| "grad_norm": 1.058866262435913, | |
| "learning_rate": 9.597638862757255e-05, | |
| "loss": 2.9908, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.006530345700175503, | |
| "grad_norm": 0.9666945338249207, | |
| "learning_rate": 9.504844339512095e-05, | |
| "loss": 2.8316, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.00669360434267989, | |
| "grad_norm": 0.8591721653938293, | |
| "learning_rate": 9.40297765928369e-05, | |
| "loss": 2.723, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.006856862985184278, | |
| "grad_norm": 0.9416791796684265, | |
| "learning_rate": 9.292243968009331e-05, | |
| "loss": 2.781, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.007020121627688666, | |
| "grad_norm": 1.2646563053131104, | |
| "learning_rate": 9.172866268606513e-05, | |
| "loss": 2.9002, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.007183380270193053, | |
| "grad_norm": 1.0307127237319946, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 2.8108, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.007346638912697441, | |
| "grad_norm": 1.0498608350753784, | |
| "learning_rate": 8.90915741234015e-05, | |
| "loss": 2.4317, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.007509897555201829, | |
| "grad_norm": 1.1443825960159302, | |
| "learning_rate": 8.765357330018056e-05, | |
| "loss": 2.7738, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.007673156197706216, | |
| "grad_norm": 1.4476778507232666, | |
| "learning_rate": 8.613974319136958e-05, | |
| "loss": 2.6264, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.007836414840210604, | |
| "grad_norm": 1.4269299507141113, | |
| "learning_rate": 8.455313244934324e-05, | |
| "loss": 2.4248, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.007999673482714992, | |
| "grad_norm": 1.6290944814682007, | |
| "learning_rate": 8.289693629698564e-05, | |
| "loss": 2.6149, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.00816293212521938, | |
| "grad_norm": 2.4885928630828857, | |
| "learning_rate": 8.117449009293668e-05, | |
| "loss": 2.1892, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.00816293212521938, | |
| "eval_loss": 2.8629980087280273, | |
| "eval_runtime": 363.5686, | |
| "eval_samples_per_second": 28.374, | |
| "eval_steps_per_second": 14.187, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.008326190767723767, | |
| "grad_norm": 2.1676950454711914, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 2.8331, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.008489449410228153, | |
| "grad_norm": 1.6274971961975098, | |
| "learning_rate": 7.754484907260513e-05, | |
| "loss": 2.6935, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.00865270805273254, | |
| "grad_norm": 1.3204303979873657, | |
| "learning_rate": 7.564496387029532e-05, | |
| "loss": 2.797, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.008815966695236929, | |
| "grad_norm": 1.0049480199813843, | |
| "learning_rate": 7.369343312364993e-05, | |
| "loss": 3.0168, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.008979225337741316, | |
| "grad_norm": 1.075304388999939, | |
| "learning_rate": 7.169418695587791e-05, | |
| "loss": 3.2103, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.009142483980245704, | |
| "grad_norm": 0.8386501669883728, | |
| "learning_rate": 6.965125158269619e-05, | |
| "loss": 3.072, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.009305742622750092, | |
| "grad_norm": 0.8426527976989746, | |
| "learning_rate": 6.756874120406714e-05, | |
| "loss": 2.752, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.00946900126525448, | |
| "grad_norm": 0.8528467416763306, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 2.8089, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.009632259907758867, | |
| "grad_norm": 0.904664158821106, | |
| "learning_rate": 6.330184227833376e-05, | |
| "loss": 2.8771, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.009795518550263255, | |
| "grad_norm": 0.7004697322845459, | |
| "learning_rate": 6.112604669781572e-05, | |
| "loss": 2.6807, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.009958777192767642, | |
| "grad_norm": 0.7690675258636475, | |
| "learning_rate": 5.8927844739931834e-05, | |
| "loss": 2.9141, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.01012203583527203, | |
| "grad_norm": 0.7248542904853821, | |
| "learning_rate": 5.6711663290882776e-05, | |
| "loss": 2.8913, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.010285294477776418, | |
| "grad_norm": 0.617339015007019, | |
| "learning_rate": 5.448196544517168e-05, | |
| "loss": 2.8585, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.010448553120280805, | |
| "grad_norm": 0.7304785251617432, | |
| "learning_rate": 5.2243241517525754e-05, | |
| "loss": 2.6997, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.010611811762785193, | |
| "grad_norm": 0.8117228150367737, | |
| "learning_rate": 5e-05, | |
| "loss": 2.8935, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.01077507040528958, | |
| "grad_norm": 0.7086424827575684, | |
| "learning_rate": 4.775675848247427e-05, | |
| "loss": 2.969, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.010938329047793967, | |
| "grad_norm": 0.715423583984375, | |
| "learning_rate": 4.551803455482833e-05, | |
| "loss": 2.5869, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.011101587690298355, | |
| "grad_norm": 0.7727792263031006, | |
| "learning_rate": 4.328833670911724e-05, | |
| "loss": 2.8389, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.011264846332802742, | |
| "grad_norm": 0.6761236786842346, | |
| "learning_rate": 4.107215526006817e-05, | |
| "loss": 2.709, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.01142810497530713, | |
| "grad_norm": 0.7613105773925781, | |
| "learning_rate": 3.887395330218429e-05, | |
| "loss": 2.8757, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.011591363617811518, | |
| "grad_norm": 0.8669199347496033, | |
| "learning_rate": 3.6698157721666246e-05, | |
| "loss": 3.1531, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.011754622260315905, | |
| "grad_norm": 0.8836479783058167, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 2.7458, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.011917880902820293, | |
| "grad_norm": 0.778107225894928, | |
| "learning_rate": 3.243125879593286e-05, | |
| "loss": 2.7683, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.01208113954532468, | |
| "grad_norm": 0.6686323285102844, | |
| "learning_rate": 3.0348748417303823e-05, | |
| "loss": 2.4992, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.012244398187829068, | |
| "grad_norm": 0.8155844807624817, | |
| "learning_rate": 2.8305813044122097e-05, | |
| "loss": 2.8288, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.012407656830333456, | |
| "grad_norm": 0.7905011773109436, | |
| "learning_rate": 2.630656687635007e-05, | |
| "loss": 2.7207, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.012570915472837844, | |
| "grad_norm": 0.821061372756958, | |
| "learning_rate": 2.43550361297047e-05, | |
| "loss": 2.6178, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.012734174115342231, | |
| "grad_norm": 0.9048423767089844, | |
| "learning_rate": 2.245515092739488e-05, | |
| "loss": 2.8052, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.01289743275784662, | |
| "grad_norm": 0.7810814380645752, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 2.9147, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.013060691400351007, | |
| "grad_norm": 0.887985348701477, | |
| "learning_rate": 1.8825509907063327e-05, | |
| "loss": 2.681, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.013223950042855395, | |
| "grad_norm": 0.8398605585098267, | |
| "learning_rate": 1.7103063703014372e-05, | |
| "loss": 2.7676, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.01338720868535978, | |
| "grad_norm": 0.8217864036560059, | |
| "learning_rate": 1.544686755065677e-05, | |
| "loss": 2.7269, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.013550467327864168, | |
| "grad_norm": 0.9799962639808655, | |
| "learning_rate": 1.3860256808630428e-05, | |
| "loss": 2.7334, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.013713725970368556, | |
| "grad_norm": 0.7503747344017029, | |
| "learning_rate": 1.2346426699819458e-05, | |
| "loss": 2.6707, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.013876984612872944, | |
| "grad_norm": 0.9742613434791565, | |
| "learning_rate": 1.090842587659851e-05, | |
| "loss": 2.6392, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.014040243255377331, | |
| "grad_norm": 0.7584743499755859, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 2.6515, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.014203501897881719, | |
| "grad_norm": 0.7804672718048096, | |
| "learning_rate": 8.271337313934869e-06, | |
| "loss": 2.4738, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.014366760540386107, | |
| "grad_norm": 0.8059239983558655, | |
| "learning_rate": 7.077560319906695e-06, | |
| "loss": 2.494, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.014530019182890494, | |
| "grad_norm": 0.9126543402671814, | |
| "learning_rate": 5.9702234071631e-06, | |
| "loss": 2.6029, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.014693277825394882, | |
| "grad_norm": 0.8912916779518127, | |
| "learning_rate": 4.951556604879048e-06, | |
| "loss": 2.5753, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.01485653646789927, | |
| "grad_norm": 0.9568765163421631, | |
| "learning_rate": 4.023611372427471e-06, | |
| "loss": 2.3926, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.015019795110403657, | |
| "grad_norm": 1.004371166229248, | |
| "learning_rate": 3.18825646801314e-06, | |
| "loss": 2.7712, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.015183053752908045, | |
| "grad_norm": 1.0826361179351807, | |
| "learning_rate": 2.4471741852423237e-06, | |
| "loss": 2.6105, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.015346312395412433, | |
| "grad_norm": 0.9342916011810303, | |
| "learning_rate": 1.8018569652073381e-06, | |
| "loss": 2.3885, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.01550957103791682, | |
| "grad_norm": 1.158676028251648, | |
| "learning_rate": 1.2536043909088191e-06, | |
| "loss": 2.4456, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.015672829680421208, | |
| "grad_norm": 1.0513296127319336, | |
| "learning_rate": 8.035205700685167e-07, | |
| "loss": 2.2801, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.015836088322925594, | |
| "grad_norm": 1.4424023628234863, | |
| "learning_rate": 4.52511911603265e-07, | |
| "loss": 2.6424, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.015999346965429984, | |
| "grad_norm": 1.7463353872299194, | |
| "learning_rate": 2.012853002380466e-07, | |
| "loss": 2.3797, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.01616260560793437, | |
| "grad_norm": 2.0830276012420654, | |
| "learning_rate": 5.0346672934270534e-08, | |
| "loss": 2.5996, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.01632586425043876, | |
| "grad_norm": 2.8903799057006836, | |
| "learning_rate": 0.0, | |
| "loss": 2.8615, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.01632586425043876, | |
| "eval_loss": 2.735139846801758, | |
| "eval_runtime": 363.8754, | |
| "eval_samples_per_second": 28.35, | |
| "eval_steps_per_second": 14.175, | |
| "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": 5, | |
| "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": 2.728250925121536e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |