| { | |
| "best_metric": 0.5543531726512543, | |
| "best_model_checkpoint": "fr-FR/wav2vec2-xls-r-300m/checkpoint-2610", | |
| "epoch": 30.0, | |
| "eval_steps": 100, | |
| "global_step": 2700, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.5555555555555556, | |
| "grad_norm": 0.6311665773391724, | |
| "learning_rate": 1.814814814814815e-05, | |
| "loss": 4.0831, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.05017215937038859, | |
| "eval_f1": 0.0016194974794585797, | |
| "eval_loss": 3.921128511428833, | |
| "eval_runtime": 20.2481, | |
| "eval_samples_per_second": 100.404, | |
| "eval_steps_per_second": 1.58, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.1111111111111112, | |
| "grad_norm": 0.6617798805236816, | |
| "learning_rate": 3.6666666666666666e-05, | |
| "loss": 3.9927, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.6666666666666665, | |
| "grad_norm": 0.8150258660316467, | |
| "learning_rate": 5.518518518518519e-05, | |
| "loss": 3.8256, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.06443679291687161, | |
| "eval_f1": 0.00205206930041668, | |
| "eval_loss": 3.73803973197937, | |
| "eval_runtime": 20.3477, | |
| "eval_samples_per_second": 99.913, | |
| "eval_steps_per_second": 1.573, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.2222222222222223, | |
| "grad_norm": 0.8914035558700562, | |
| "learning_rate": 7.37037037037037e-05, | |
| "loss": 3.7727, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.7777777777777777, | |
| "grad_norm": 0.93168705701828, | |
| "learning_rate": 9.222222222222223e-05, | |
| "loss": 3.7519, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.07181505164781112, | |
| "eval_f1": 0.005259036785425362, | |
| "eval_loss": 3.7302937507629395, | |
| "eval_runtime": 20.203, | |
| "eval_samples_per_second": 100.629, | |
| "eval_steps_per_second": 1.584, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 3.3333333333333335, | |
| "grad_norm": 0.8782232999801636, | |
| "learning_rate": 9.880658436213992e-05, | |
| "loss": 3.7506, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.888888888888889, | |
| "grad_norm": 1.1496119499206543, | |
| "learning_rate": 9.674897119341564e-05, | |
| "loss": 3.7476, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.06443679291687161, | |
| "eval_f1": 0.00205206930041668, | |
| "eval_loss": 3.709669351577759, | |
| "eval_runtime": 20.1865, | |
| "eval_samples_per_second": 100.711, | |
| "eval_steps_per_second": 1.585, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 4.444444444444445, | |
| "grad_norm": 0.9949362277984619, | |
| "learning_rate": 9.469135802469137e-05, | |
| "loss": 3.7454, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 1.1786142587661743, | |
| "learning_rate": 9.263374485596709e-05, | |
| "loss": 3.7098, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.09591736350221347, | |
| "eval_f1": 0.005725705609705114, | |
| "eval_loss": 3.690065622329712, | |
| "eval_runtime": 20.1867, | |
| "eval_samples_per_second": 100.71, | |
| "eval_steps_per_second": 1.585, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 5.555555555555555, | |
| "grad_norm": 1.3047127723693848, | |
| "learning_rate": 9.057613168724281e-05, | |
| "loss": 3.6858, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.09886866699458928, | |
| "eval_f1": 0.007264866491847572, | |
| "eval_loss": 3.6419930458068848, | |
| "eval_runtime": 20.0133, | |
| "eval_samples_per_second": 101.582, | |
| "eval_steps_per_second": 1.599, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 6.111111111111111, | |
| "grad_norm": 1.4781264066696167, | |
| "learning_rate": 8.851851851851852e-05, | |
| "loss": 3.6583, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 6.666666666666667, | |
| "grad_norm": 1.342982292175293, | |
| "learning_rate": 8.646090534979425e-05, | |
| "loss": 3.6096, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.11264141662567634, | |
| "eval_f1": 0.012811569793871857, | |
| "eval_loss": 3.566227674484253, | |
| "eval_runtime": 20.2051, | |
| "eval_samples_per_second": 100.618, | |
| "eval_steps_per_second": 1.584, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 7.222222222222222, | |
| "grad_norm": 1.2319382429122925, | |
| "learning_rate": 8.452674897119341e-05, | |
| "loss": 3.6427, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 7.777777777777778, | |
| "grad_norm": 1.120038628578186, | |
| "learning_rate": 8.246913580246915e-05, | |
| "loss": 3.5484, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.12985735366453516, | |
| "eval_f1": 0.01639035591982137, | |
| "eval_loss": 3.5015017986297607, | |
| "eval_runtime": 20.2258, | |
| "eval_samples_per_second": 100.515, | |
| "eval_steps_per_second": 1.582, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 8.333333333333334, | |
| "grad_norm": 1.6429734230041504, | |
| "learning_rate": 8.041152263374486e-05, | |
| "loss": 3.4963, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 8.88888888888889, | |
| "grad_norm": 2.2033281326293945, | |
| "learning_rate": 7.835390946502059e-05, | |
| "loss": 3.4439, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.12395474667978357, | |
| "eval_f1": 0.019783749206849655, | |
| "eval_loss": 3.391706943511963, | |
| "eval_runtime": 20.2246, | |
| "eval_samples_per_second": 100.521, | |
| "eval_steps_per_second": 1.582, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 9.444444444444445, | |
| "grad_norm": 2.9443519115448, | |
| "learning_rate": 7.62962962962963e-05, | |
| "loss": 3.3565, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 2.37030029296875, | |
| "learning_rate": 7.423868312757202e-05, | |
| "loss": 3.2907, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.1736350221347762, | |
| "eval_f1": 0.03961650753233977, | |
| "eval_loss": 3.2812328338623047, | |
| "eval_runtime": 20.1829, | |
| "eval_samples_per_second": 100.729, | |
| "eval_steps_per_second": 1.585, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 10.555555555555555, | |
| "grad_norm": 3.3137433528900146, | |
| "learning_rate": 7.218106995884773e-05, | |
| "loss": 3.1707, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.1751106738809641, | |
| "eval_f1": 0.04082360136597588, | |
| "eval_loss": 3.1738343238830566, | |
| "eval_runtime": 20.1847, | |
| "eval_samples_per_second": 100.72, | |
| "eval_steps_per_second": 1.585, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 11.11111111111111, | |
| "grad_norm": 4.893256664276123, | |
| "learning_rate": 7.012345679012346e-05, | |
| "loss": 3.093, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 11.666666666666666, | |
| "grad_norm": 2.7285029888153076, | |
| "learning_rate": 6.806584362139918e-05, | |
| "loss": 3.0034, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.23266109198229218, | |
| "eval_f1": 0.07458858219754078, | |
| "eval_loss": 2.987241744995117, | |
| "eval_runtime": 20.172, | |
| "eval_samples_per_second": 100.783, | |
| "eval_steps_per_second": 1.586, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 12.222222222222221, | |
| "grad_norm": 2.4686148166656494, | |
| "learning_rate": 6.60082304526749e-05, | |
| "loss": 2.8933, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 12.777777777777779, | |
| "grad_norm": 4.950862884521484, | |
| "learning_rate": 6.395061728395062e-05, | |
| "loss": 2.7734, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.26512543039842595, | |
| "eval_f1": 0.09626588280325074, | |
| "eval_loss": 2.8068132400512695, | |
| "eval_runtime": 20.1739, | |
| "eval_samples_per_second": 100.774, | |
| "eval_steps_per_second": 1.586, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 13.333333333333334, | |
| "grad_norm": 3.508140802383423, | |
| "learning_rate": 6.189300411522633e-05, | |
| "loss": 2.6421, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 13.88888888888889, | |
| "grad_norm": 2.7219550609588623, | |
| "learning_rate": 5.983539094650206e-05, | |
| "loss": 2.5912, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.2951303492375799, | |
| "eval_f1": 0.12066140989612666, | |
| "eval_loss": 2.687779188156128, | |
| "eval_runtime": 20.1345, | |
| "eval_samples_per_second": 100.971, | |
| "eval_steps_per_second": 1.589, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 14.444444444444445, | |
| "grad_norm": 3.374047040939331, | |
| "learning_rate": 5.7777777777777776e-05, | |
| "loss": 2.4899, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "grad_norm": 4.324727535247803, | |
| "learning_rate": 5.57201646090535e-05, | |
| "loss": 2.4839, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.32611903590752583, | |
| "eval_f1": 0.16030752546112262, | |
| "eval_loss": 2.6126816272735596, | |
| "eval_runtime": 20.1788, | |
| "eval_samples_per_second": 100.749, | |
| "eval_steps_per_second": 1.586, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 15.555555555555555, | |
| "grad_norm": 3.545776128768921, | |
| "learning_rate": 5.366255144032922e-05, | |
| "loss": 2.3293, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.3453025086079685, | |
| "eval_f1": 0.17236182167002215, | |
| "eval_loss": 2.5199337005615234, | |
| "eval_runtime": 20.1733, | |
| "eval_samples_per_second": 100.777, | |
| "eval_steps_per_second": 1.586, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 16.11111111111111, | |
| "grad_norm": 5.616283893585205, | |
| "learning_rate": 5.160493827160494e-05, | |
| "loss": 2.2367, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 16.666666666666668, | |
| "grad_norm": 5.327425479888916, | |
| "learning_rate": 4.9547325102880656e-05, | |
| "loss": 2.169, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.36399409739301525, | |
| "eval_f1": 0.2078663996139009, | |
| "eval_loss": 2.4475929737091064, | |
| "eval_runtime": 20.1551, | |
| "eval_samples_per_second": 100.868, | |
| "eval_steps_per_second": 1.588, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 17.22222222222222, | |
| "grad_norm": 5.141805171966553, | |
| "learning_rate": 4.748971193415638e-05, | |
| "loss": 2.1224, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 17.77777777777778, | |
| "grad_norm": 3.864804744720459, | |
| "learning_rate": 4.54320987654321e-05, | |
| "loss": 2.0474, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.3954746679783571, | |
| "eval_f1": 0.2329830407945391, | |
| "eval_loss": 2.3817105293273926, | |
| "eval_runtime": 20.1551, | |
| "eval_samples_per_second": 100.868, | |
| "eval_steps_per_second": 1.588, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 18.333333333333332, | |
| "grad_norm": 5.070396423339844, | |
| "learning_rate": 4.337448559670782e-05, | |
| "loss": 1.986, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 18.88888888888889, | |
| "grad_norm": 3.915616035461426, | |
| "learning_rate": 4.1316872427983537e-05, | |
| "loss": 1.9385, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.43433349729463844, | |
| "eval_f1": 0.26422232789593036, | |
| "eval_loss": 2.2753679752349854, | |
| "eval_runtime": 20.1569, | |
| "eval_samples_per_second": 100.859, | |
| "eval_steps_per_second": 1.588, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 19.444444444444443, | |
| "grad_norm": 4.9511399269104, | |
| "learning_rate": 3.925925925925926e-05, | |
| "loss": 1.833, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "grad_norm": 8.35456657409668, | |
| "learning_rate": 3.720164609053498e-05, | |
| "loss": 1.8169, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.45696015740285295, | |
| "eval_f1": 0.3069655313049267, | |
| "eval_loss": 2.233362913131714, | |
| "eval_runtime": 20.1609, | |
| "eval_samples_per_second": 100.839, | |
| "eval_steps_per_second": 1.587, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 20.555555555555557, | |
| "grad_norm": 4.3977885246276855, | |
| "learning_rate": 3.51440329218107e-05, | |
| "loss": 1.7037, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.4864731923266109, | |
| "eval_f1": 0.32092427700938486, | |
| "eval_loss": 2.1784141063690186, | |
| "eval_runtime": 20.146, | |
| "eval_samples_per_second": 100.913, | |
| "eval_steps_per_second": 1.588, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 21.11111111111111, | |
| "grad_norm": 4.727329730987549, | |
| "learning_rate": 3.308641975308642e-05, | |
| "loss": 1.6356, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 21.666666666666668, | |
| "grad_norm": 8.652691841125488, | |
| "learning_rate": 3.102880658436214e-05, | |
| "loss": 1.5998, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.5081160846040335, | |
| "eval_f1": 0.3454217533127742, | |
| "eval_loss": 2.1258203983306885, | |
| "eval_runtime": 20.1442, | |
| "eval_samples_per_second": 100.922, | |
| "eval_steps_per_second": 1.589, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 22.22222222222222, | |
| "grad_norm": 10.133247375488281, | |
| "learning_rate": 2.897119341563786e-05, | |
| "loss": 1.549, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 22.77777777777778, | |
| "grad_norm": 4.033301830291748, | |
| "learning_rate": 2.6913580246913585e-05, | |
| "loss": 1.51, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.5081160846040335, | |
| "eval_f1": 0.3574234127712544, | |
| "eval_loss": 2.0932371616363525, | |
| "eval_runtime": 20.1291, | |
| "eval_samples_per_second": 100.998, | |
| "eval_steps_per_second": 1.59, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 23.333333333333332, | |
| "grad_norm": 3.8187780380249023, | |
| "learning_rate": 2.4855967078189303e-05, | |
| "loss": 1.4493, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 23.88888888888889, | |
| "grad_norm": 3.596712589263916, | |
| "learning_rate": 2.279835390946502e-05, | |
| "loss": 1.4407, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.5164781111657649, | |
| "eval_f1": 0.37192680141832524, | |
| "eval_loss": 2.098966121673584, | |
| "eval_runtime": 20.1169, | |
| "eval_samples_per_second": 101.059, | |
| "eval_steps_per_second": 1.591, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 24.444444444444443, | |
| "grad_norm": 4.555119037628174, | |
| "learning_rate": 2.074074074074074e-05, | |
| "loss": 1.415, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "grad_norm": 4.245804786682129, | |
| "learning_rate": 1.868312757201646e-05, | |
| "loss": 1.3468, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.5366453516969996, | |
| "eval_f1": 0.38983496988780386, | |
| "eval_loss": 2.0432238578796387, | |
| "eval_runtime": 20.0898, | |
| "eval_samples_per_second": 101.195, | |
| "eval_steps_per_second": 1.593, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 25.555555555555557, | |
| "grad_norm": 4.591546058654785, | |
| "learning_rate": 1.662551440329218e-05, | |
| "loss": 1.2885, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.5391047712739794, | |
| "eval_f1": 0.40537387724487417, | |
| "eval_loss": 2.01814866065979, | |
| "eval_runtime": 20.1408, | |
| "eval_samples_per_second": 100.939, | |
| "eval_steps_per_second": 1.589, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 26.11111111111111, | |
| "grad_norm": 3.095262050628662, | |
| "learning_rate": 1.4567901234567902e-05, | |
| "loss": 1.2853, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 26.666666666666668, | |
| "grad_norm": 3.832343339920044, | |
| "learning_rate": 1.2510288065843623e-05, | |
| "loss": 1.2539, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.5479586817511067, | |
| "eval_f1": 0.41006063615437155, | |
| "eval_loss": 2.021588087081909, | |
| "eval_runtime": 20.1524, | |
| "eval_samples_per_second": 100.881, | |
| "eval_steps_per_second": 1.588, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 27.22222222222222, | |
| "grad_norm": 4.070197105407715, | |
| "learning_rate": 1.0452674897119343e-05, | |
| "loss": 1.2327, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 27.77777777777778, | |
| "grad_norm": 3.290456533432007, | |
| "learning_rate": 8.395061728395062e-06, | |
| "loss": 1.21, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.5484505656665027, | |
| "eval_f1": 0.41472217066308065, | |
| "eval_loss": 2.0198214054107666, | |
| "eval_runtime": 20.1563, | |
| "eval_samples_per_second": 100.862, | |
| "eval_steps_per_second": 1.588, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 28.333333333333332, | |
| "grad_norm": 3.003391981124878, | |
| "learning_rate": 6.337448559670782e-06, | |
| "loss": 1.2188, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 28.88888888888889, | |
| "grad_norm": 5.390565395355225, | |
| "learning_rate": 4.2798353909465025e-06, | |
| "loss": 1.1995, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.5543531726512543, | |
| "eval_f1": 0.4205878734286696, | |
| "eval_loss": 2.0205445289611816, | |
| "eval_runtime": 20.1392, | |
| "eval_samples_per_second": 100.947, | |
| "eval_steps_per_second": 1.589, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 29.444444444444443, | |
| "grad_norm": 3.9864342212677, | |
| "learning_rate": 2.2222222222222225e-06, | |
| "loss": 1.197, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "grad_norm": 3.8882803916931152, | |
| "learning_rate": 1.646090534979424e-07, | |
| "loss": 1.1697, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.5528775209050664, | |
| "eval_f1": 0.4185233692128861, | |
| "eval_loss": 2.020263910293579, | |
| "eval_runtime": 20.0868, | |
| "eval_samples_per_second": 101.211, | |
| "eval_steps_per_second": 1.593, | |
| "step": 2700 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 2700, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 30, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.0469261495692793e+20, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |