| { | |
| "best_global_step": 59, | |
| "best_metric": 0.8877551020408163, | |
| "best_model_checkpoint": "efficientnet-b0-accidents/checkpoint-59", | |
| "epoch": 100.0, | |
| "eval_steps": 500, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.7959183673469388, | |
| "eval_loss": 0.4779815375804901, | |
| "eval_runtime": 1.1795, | |
| "eval_samples_per_second": 83.084, | |
| "eval_steps_per_second": 0.848, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.7959183673469388, | |
| "eval_loss": 0.46097320318222046, | |
| "eval_runtime": 1.1909, | |
| "eval_samples_per_second": 82.291, | |
| "eval_steps_per_second": 0.84, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.7755102040816326, | |
| "eval_loss": 0.45180079340934753, | |
| "eval_runtime": 1.1886, | |
| "eval_samples_per_second": 82.451, | |
| "eval_steps_per_second": 0.841, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8163265306122449, | |
| "eval_loss": 0.44495007395744324, | |
| "eval_runtime": 1.1829, | |
| "eval_samples_per_second": 82.845, | |
| "eval_steps_per_second": 0.845, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.826530612244898, | |
| "eval_loss": 0.44236451387405396, | |
| "eval_runtime": 1.1745, | |
| "eval_samples_per_second": 83.437, | |
| "eval_steps_per_second": 0.851, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.7959183673469388, | |
| "eval_loss": 0.44830843806266785, | |
| "eval_runtime": 1.1934, | |
| "eval_samples_per_second": 82.117, | |
| "eval_steps_per_second": 0.838, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.7959183673469388, | |
| "eval_loss": 0.4532928168773651, | |
| "eval_runtime": 1.2016, | |
| "eval_samples_per_second": 81.561, | |
| "eval_steps_per_second": 0.832, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.7959183673469388, | |
| "eval_loss": 0.4556555151939392, | |
| "eval_runtime": 1.1751, | |
| "eval_samples_per_second": 83.399, | |
| "eval_steps_per_second": 0.851, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.826530612244898, | |
| "eval_loss": 0.4555840492248535, | |
| "eval_runtime": 1.1859, | |
| "eval_samples_per_second": 82.637, | |
| "eval_steps_per_second": 0.843, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 0.6532824635505676, | |
| "learning_rate": 9e-05, | |
| "loss": 0.4528, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.8163265306122449, | |
| "eval_loss": 0.4452582001686096, | |
| "eval_runtime": 1.1757, | |
| "eval_samples_per_second": 83.352, | |
| "eval_steps_per_second": 0.851, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.7755102040816326, | |
| "eval_loss": 0.4558465778827667, | |
| "eval_runtime": 1.1787, | |
| "eval_samples_per_second": 83.141, | |
| "eval_steps_per_second": 0.848, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.826530612244898, | |
| "eval_loss": 0.4390490651130676, | |
| "eval_runtime": 1.1827, | |
| "eval_samples_per_second": 82.862, | |
| "eval_steps_per_second": 0.846, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.7959183673469388, | |
| "eval_loss": 0.4321656823158264, | |
| "eval_runtime": 1.1951, | |
| "eval_samples_per_second": 81.999, | |
| "eval_steps_per_second": 0.837, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.8163265306122449, | |
| "eval_loss": 0.4322623908519745, | |
| "eval_runtime": 1.1728, | |
| "eval_samples_per_second": 83.56, | |
| "eval_steps_per_second": 0.853, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.8061224489795918, | |
| "eval_loss": 0.4126739203929901, | |
| "eval_runtime": 1.179, | |
| "eval_samples_per_second": 83.121, | |
| "eval_steps_per_second": 0.848, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.8061224489795918, | |
| "eval_loss": 0.4341281056404114, | |
| "eval_runtime": 1.1827, | |
| "eval_samples_per_second": 82.862, | |
| "eval_steps_per_second": 0.846, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.826530612244898, | |
| "eval_loss": 0.4143841862678528, | |
| "eval_runtime": 1.174, | |
| "eval_samples_per_second": 83.472, | |
| "eval_steps_per_second": 0.852, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.826530612244898, | |
| "eval_loss": 0.4274652302265167, | |
| "eval_runtime": 1.1859, | |
| "eval_samples_per_second": 82.636, | |
| "eval_steps_per_second": 0.843, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.8673469387755102, | |
| "eval_loss": 0.39877012372016907, | |
| "eval_runtime": 1.1702, | |
| "eval_samples_per_second": 83.75, | |
| "eval_steps_per_second": 0.855, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "grad_norm": 0.636593222618103, | |
| "learning_rate": 9e-05, | |
| "loss": 0.4233, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.7959183673469388, | |
| "eval_loss": 0.4209805428981781, | |
| "eval_runtime": 1.1739, | |
| "eval_samples_per_second": 83.481, | |
| "eval_steps_per_second": 0.852, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.7755102040816326, | |
| "eval_loss": 0.42234739661216736, | |
| "eval_runtime": 1.242, | |
| "eval_samples_per_second": 78.908, | |
| "eval_steps_per_second": 0.805, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.826530612244898, | |
| "eval_loss": 0.4287910461425781, | |
| "eval_runtime": 1.1884, | |
| "eval_samples_per_second": 82.462, | |
| "eval_steps_per_second": 0.841, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.8571428571428571, | |
| "eval_loss": 0.3851400911808014, | |
| "eval_runtime": 1.171, | |
| "eval_samples_per_second": 83.691, | |
| "eval_steps_per_second": 0.854, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.8061224489795918, | |
| "eval_loss": 0.3956393897533417, | |
| "eval_runtime": 1.1758, | |
| "eval_samples_per_second": 83.349, | |
| "eval_steps_per_second": 0.85, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.8367346938775511, | |
| "eval_loss": 0.4159245789051056, | |
| "eval_runtime": 1.1679, | |
| "eval_samples_per_second": 83.915, | |
| "eval_steps_per_second": 0.856, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.8163265306122449, | |
| "eval_loss": 0.4054996073246002, | |
| "eval_runtime": 1.1741, | |
| "eval_samples_per_second": 83.467, | |
| "eval_steps_per_second": 0.852, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.8163265306122449, | |
| "eval_loss": 0.3861065208911896, | |
| "eval_runtime": 1.191, | |
| "eval_samples_per_second": 82.286, | |
| "eval_steps_per_second": 0.84, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.8469387755102041, | |
| "eval_loss": 0.3751261532306671, | |
| "eval_runtime": 1.1897, | |
| "eval_samples_per_second": 82.373, | |
| "eval_steps_per_second": 0.841, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.8367346938775511, | |
| "eval_loss": 0.39149540662765503, | |
| "eval_runtime": 1.2043, | |
| "eval_samples_per_second": 81.378, | |
| "eval_steps_per_second": 0.83, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "grad_norm": 0.5932164788246155, | |
| "learning_rate": 7.88888888888889e-05, | |
| "loss": 0.3846, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.8571428571428571, | |
| "eval_loss": 0.3704555332660675, | |
| "eval_runtime": 1.2019, | |
| "eval_samples_per_second": 81.54, | |
| "eval_steps_per_second": 0.832, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_accuracy": 0.8367346938775511, | |
| "eval_loss": 0.3868422508239746, | |
| "eval_runtime": 1.1797, | |
| "eval_samples_per_second": 83.073, | |
| "eval_steps_per_second": 0.848, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.8469387755102041, | |
| "eval_loss": 0.37100356817245483, | |
| "eval_runtime": 1.1859, | |
| "eval_samples_per_second": 82.641, | |
| "eval_steps_per_second": 0.843, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_accuracy": 0.8469387755102041, | |
| "eval_loss": 0.37700414657592773, | |
| "eval_runtime": 1.1948, | |
| "eval_samples_per_second": 82.025, | |
| "eval_steps_per_second": 0.837, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.826530612244898, | |
| "eval_loss": 0.39025142788887024, | |
| "eval_runtime": 1.1986, | |
| "eval_samples_per_second": 81.762, | |
| "eval_steps_per_second": 0.834, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_accuracy": 0.8469387755102041, | |
| "eval_loss": 0.3864216208457947, | |
| "eval_runtime": 1.1828, | |
| "eval_samples_per_second": 82.852, | |
| "eval_steps_per_second": 0.845, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.826530612244898, | |
| "eval_loss": 0.37283435463905334, | |
| "eval_runtime": 1.1824, | |
| "eval_samples_per_second": 82.882, | |
| "eval_steps_per_second": 0.846, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_accuracy": 0.8367346938775511, | |
| "eval_loss": 0.37720832228660583, | |
| "eval_runtime": 1.2152, | |
| "eval_samples_per_second": 80.648, | |
| "eval_steps_per_second": 0.823, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.8163265306122449, | |
| "eval_loss": 0.36333897709846497, | |
| "eval_runtime": 1.1808, | |
| "eval_samples_per_second": 82.993, | |
| "eval_steps_per_second": 0.847, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_accuracy": 0.8469387755102041, | |
| "eval_loss": 0.38240504264831543, | |
| "eval_runtime": 1.1905, | |
| "eval_samples_per_second": 82.317, | |
| "eval_steps_per_second": 0.84, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "grad_norm": 0.6421281099319458, | |
| "learning_rate": 6.777777777777778e-05, | |
| "loss": 0.3714, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.8571428571428571, | |
| "eval_loss": 0.3520002067089081, | |
| "eval_runtime": 1.1819, | |
| "eval_samples_per_second": 82.917, | |
| "eval_steps_per_second": 0.846, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_accuracy": 0.8469387755102041, | |
| "eval_loss": 0.3843795657157898, | |
| "eval_runtime": 1.1866, | |
| "eval_samples_per_second": 82.592, | |
| "eval_steps_per_second": 0.843, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.8469387755102041, | |
| "eval_loss": 0.3564036190509796, | |
| "eval_runtime": 1.1961, | |
| "eval_samples_per_second": 81.93, | |
| "eval_steps_per_second": 0.836, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_accuracy": 0.8673469387755102, | |
| "eval_loss": 0.3747188150882721, | |
| "eval_runtime": 1.1718, | |
| "eval_samples_per_second": 83.63, | |
| "eval_steps_per_second": 0.853, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.8571428571428571, | |
| "eval_loss": 0.33950209617614746, | |
| "eval_runtime": 1.2426, | |
| "eval_samples_per_second": 78.864, | |
| "eval_steps_per_second": 0.805, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_accuracy": 0.8163265306122449, | |
| "eval_loss": 0.38714832067489624, | |
| "eval_runtime": 1.2757, | |
| "eval_samples_per_second": 76.82, | |
| "eval_steps_per_second": 0.784, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 0.8367346938775511, | |
| "eval_loss": 0.348727285861969, | |
| "eval_runtime": 1.1817, | |
| "eval_samples_per_second": 82.933, | |
| "eval_steps_per_second": 0.846, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_accuracy": 0.8163265306122449, | |
| "eval_loss": 0.3797769844532013, | |
| "eval_runtime": 1.1792, | |
| "eval_samples_per_second": 83.105, | |
| "eval_steps_per_second": 0.848, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.8367346938775511, | |
| "eval_loss": 0.38484281301498413, | |
| "eval_runtime": 1.1845, | |
| "eval_samples_per_second": 82.735, | |
| "eval_steps_per_second": 0.844, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_accuracy": 0.826530612244898, | |
| "eval_loss": 0.3978123068809509, | |
| "eval_runtime": 1.1774, | |
| "eval_samples_per_second": 83.238, | |
| "eval_steps_per_second": 0.849, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "grad_norm": 0.7799413204193115, | |
| "learning_rate": 5.666666666666667e-05, | |
| "loss": 0.3618, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 0.8571428571428571, | |
| "eval_loss": 0.33839166164398193, | |
| "eval_runtime": 1.1751, | |
| "eval_samples_per_second": 83.397, | |
| "eval_steps_per_second": 0.851, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_accuracy": 0.826530612244898, | |
| "eval_loss": 0.36474189162254333, | |
| "eval_runtime": 1.1761, | |
| "eval_samples_per_second": 83.326, | |
| "eval_steps_per_second": 0.85, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.8571428571428571, | |
| "eval_loss": 0.35444045066833496, | |
| "eval_runtime": 1.2058, | |
| "eval_samples_per_second": 81.274, | |
| "eval_steps_per_second": 0.829, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_accuracy": 0.8163265306122449, | |
| "eval_loss": 0.42885449528694153, | |
| "eval_runtime": 1.1966, | |
| "eval_samples_per_second": 81.895, | |
| "eval_steps_per_second": 0.836, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_accuracy": 0.8673469387755102, | |
| "eval_loss": 0.3567652404308319, | |
| "eval_runtime": 1.1882, | |
| "eval_samples_per_second": 82.48, | |
| "eval_steps_per_second": 0.842, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "eval_accuracy": 0.8673469387755102, | |
| "eval_loss": 0.37271520495414734, | |
| "eval_runtime": 1.1895, | |
| "eval_samples_per_second": 82.388, | |
| "eval_steps_per_second": 0.841, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.826530612244898, | |
| "eval_loss": 0.3796241879463196, | |
| "eval_runtime": 1.1802, | |
| "eval_samples_per_second": 83.037, | |
| "eval_steps_per_second": 0.847, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "eval_accuracy": 0.8571428571428571, | |
| "eval_loss": 0.36781173944473267, | |
| "eval_runtime": 1.1792, | |
| "eval_samples_per_second": 83.11, | |
| "eval_steps_per_second": 0.848, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_accuracy": 0.8469387755102041, | |
| "eval_loss": 0.3718703091144562, | |
| "eval_runtime": 1.1805, | |
| "eval_samples_per_second": 83.012, | |
| "eval_steps_per_second": 0.847, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "eval_accuracy": 0.8877551020408163, | |
| "eval_loss": 0.38076311349868774, | |
| "eval_runtime": 1.1858, | |
| "eval_samples_per_second": 82.643, | |
| "eval_steps_per_second": 0.843, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "grad_norm": 0.8338537216186523, | |
| "learning_rate": 4.555555555555556e-05, | |
| "loss": 0.327, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_accuracy": 0.8163265306122449, | |
| "eval_loss": 0.3783416748046875, | |
| "eval_runtime": 1.2706, | |
| "eval_samples_per_second": 77.13, | |
| "eval_steps_per_second": 0.787, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 61.0, | |
| "eval_accuracy": 0.8367346938775511, | |
| "eval_loss": 0.363650381565094, | |
| "eval_runtime": 1.2014, | |
| "eval_samples_per_second": 81.574, | |
| "eval_steps_per_second": 0.832, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 62.0, | |
| "eval_accuracy": 0.8367346938775511, | |
| "eval_loss": 0.37426507472991943, | |
| "eval_runtime": 1.1766, | |
| "eval_samples_per_second": 83.293, | |
| "eval_steps_per_second": 0.85, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 63.0, | |
| "eval_accuracy": 0.8571428571428571, | |
| "eval_loss": 0.3553648591041565, | |
| "eval_runtime": 1.1889, | |
| "eval_samples_per_second": 82.429, | |
| "eval_steps_per_second": 0.841, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "eval_accuracy": 0.826530612244898, | |
| "eval_loss": 0.3544183075428009, | |
| "eval_runtime": 1.1948, | |
| "eval_samples_per_second": 82.02, | |
| "eval_steps_per_second": 0.837, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 65.0, | |
| "eval_accuracy": 0.8469387755102041, | |
| "eval_loss": 0.361508309841156, | |
| "eval_runtime": 1.1861, | |
| "eval_samples_per_second": 82.624, | |
| "eval_steps_per_second": 0.843, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 66.0, | |
| "eval_accuracy": 0.8673469387755102, | |
| "eval_loss": 0.3502516448497772, | |
| "eval_runtime": 1.1913, | |
| "eval_samples_per_second": 82.261, | |
| "eval_steps_per_second": 0.839, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 67.0, | |
| "eval_accuracy": 0.7959183673469388, | |
| "eval_loss": 0.39142534136772156, | |
| "eval_runtime": 1.1829, | |
| "eval_samples_per_second": 82.845, | |
| "eval_steps_per_second": 0.845, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "eval_accuracy": 0.8367346938775511, | |
| "eval_loss": 0.3686521351337433, | |
| "eval_runtime": 1.2512, | |
| "eval_samples_per_second": 78.327, | |
| "eval_steps_per_second": 0.799, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 69.0, | |
| "eval_accuracy": 0.8877551020408163, | |
| "eval_loss": 0.3295800983905792, | |
| "eval_runtime": 1.1917, | |
| "eval_samples_per_second": 82.233, | |
| "eval_steps_per_second": 0.839, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "grad_norm": 0.4433494806289673, | |
| "learning_rate": 3.444444444444445e-05, | |
| "loss": 0.3136, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "eval_accuracy": 0.8571428571428571, | |
| "eval_loss": 0.35484427213668823, | |
| "eval_runtime": 1.1759, | |
| "eval_samples_per_second": 83.337, | |
| "eval_steps_per_second": 0.85, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 71.0, | |
| "eval_accuracy": 0.826530612244898, | |
| "eval_loss": 0.3809606730937958, | |
| "eval_runtime": 1.175, | |
| "eval_samples_per_second": 83.406, | |
| "eval_steps_per_second": 0.851, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "eval_accuracy": 0.8469387755102041, | |
| "eval_loss": 0.3522069752216339, | |
| "eval_runtime": 1.169, | |
| "eval_samples_per_second": 83.829, | |
| "eval_steps_per_second": 0.855, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 73.0, | |
| "eval_accuracy": 0.8367346938775511, | |
| "eval_loss": 0.3851645290851593, | |
| "eval_runtime": 1.1768, | |
| "eval_samples_per_second": 83.277, | |
| "eval_steps_per_second": 0.85, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 74.0, | |
| "eval_accuracy": 0.8571428571428571, | |
| "eval_loss": 0.34336620569229126, | |
| "eval_runtime": 1.1784, | |
| "eval_samples_per_second": 83.163, | |
| "eval_steps_per_second": 0.849, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 75.0, | |
| "eval_accuracy": 0.8571428571428571, | |
| "eval_loss": 0.35957837104797363, | |
| "eval_runtime": 1.2169, | |
| "eval_samples_per_second": 80.535, | |
| "eval_steps_per_second": 0.822, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 76.0, | |
| "eval_accuracy": 0.8367346938775511, | |
| "eval_loss": 0.3550688624382019, | |
| "eval_runtime": 1.2477, | |
| "eval_samples_per_second": 78.542, | |
| "eval_steps_per_second": 0.801, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 77.0, | |
| "eval_accuracy": 0.8163265306122449, | |
| "eval_loss": 0.42566972970962524, | |
| "eval_runtime": 1.1764, | |
| "eval_samples_per_second": 83.303, | |
| "eval_steps_per_second": 0.85, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 78.0, | |
| "eval_accuracy": 0.8367346938775511, | |
| "eval_loss": 0.3554403781890869, | |
| "eval_runtime": 1.1844, | |
| "eval_samples_per_second": 82.741, | |
| "eval_steps_per_second": 0.844, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 79.0, | |
| "eval_accuracy": 0.826530612244898, | |
| "eval_loss": 0.3352053165435791, | |
| "eval_runtime": 1.1717, | |
| "eval_samples_per_second": 83.636, | |
| "eval_steps_per_second": 0.853, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "grad_norm": 0.825162947177887, | |
| "learning_rate": 2.3333333333333336e-05, | |
| "loss": 0.316, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "eval_accuracy": 0.8367346938775511, | |
| "eval_loss": 0.3773196041584015, | |
| "eval_runtime": 1.1893, | |
| "eval_samples_per_second": 82.399, | |
| "eval_steps_per_second": 0.841, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 81.0, | |
| "eval_accuracy": 0.8469387755102041, | |
| "eval_loss": 0.33054399490356445, | |
| "eval_runtime": 1.1987, | |
| "eval_samples_per_second": 81.752, | |
| "eval_steps_per_second": 0.834, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 82.0, | |
| "eval_accuracy": 0.8571428571428571, | |
| "eval_loss": 0.3614092171192169, | |
| "eval_runtime": 1.1892, | |
| "eval_samples_per_second": 82.41, | |
| "eval_steps_per_second": 0.841, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 83.0, | |
| "eval_accuracy": 0.826530612244898, | |
| "eval_loss": 0.3490673005580902, | |
| "eval_runtime": 1.2082, | |
| "eval_samples_per_second": 81.111, | |
| "eval_steps_per_second": 0.828, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 84.0, | |
| "eval_accuracy": 0.8571428571428571, | |
| "eval_loss": 0.34793397784233093, | |
| "eval_runtime": 1.1918, | |
| "eval_samples_per_second": 82.229, | |
| "eval_steps_per_second": 0.839, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 85.0, | |
| "eval_accuracy": 0.8367346938775511, | |
| "eval_loss": 0.36838239431381226, | |
| "eval_runtime": 1.1842, | |
| "eval_samples_per_second": 82.758, | |
| "eval_steps_per_second": 0.844, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 86.0, | |
| "eval_accuracy": 0.8571428571428571, | |
| "eval_loss": 0.35111716389656067, | |
| "eval_runtime": 1.1928, | |
| "eval_samples_per_second": 82.162, | |
| "eval_steps_per_second": 0.838, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 87.0, | |
| "eval_accuracy": 0.826530612244898, | |
| "eval_loss": 0.36582064628601074, | |
| "eval_runtime": 1.2026, | |
| "eval_samples_per_second": 81.493, | |
| "eval_steps_per_second": 0.832, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 88.0, | |
| "eval_accuracy": 0.8367346938775511, | |
| "eval_loss": 0.3332655727863312, | |
| "eval_runtime": 1.1993, | |
| "eval_samples_per_second": 81.713, | |
| "eval_steps_per_second": 0.834, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 89.0, | |
| "eval_accuracy": 0.8775510204081632, | |
| "eval_loss": 0.3584078550338745, | |
| "eval_runtime": 1.1944, | |
| "eval_samples_per_second": 82.048, | |
| "eval_steps_per_second": 0.837, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 90.0, | |
| "grad_norm": 0.8733311295509338, | |
| "learning_rate": 1.2222222222222222e-05, | |
| "loss": 0.3089, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 90.0, | |
| "eval_accuracy": 0.8571428571428571, | |
| "eval_loss": 0.3277149498462677, | |
| "eval_runtime": 1.1993, | |
| "eval_samples_per_second": 81.712, | |
| "eval_steps_per_second": 0.834, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 91.0, | |
| "eval_accuracy": 0.8367346938775511, | |
| "eval_loss": 0.3874940276145935, | |
| "eval_runtime": 1.236, | |
| "eval_samples_per_second": 79.287, | |
| "eval_steps_per_second": 0.809, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 92.0, | |
| "eval_accuracy": 0.8367346938775511, | |
| "eval_loss": 0.3757161796092987, | |
| "eval_runtime": 1.2043, | |
| "eval_samples_per_second": 81.378, | |
| "eval_steps_per_second": 0.83, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 93.0, | |
| "eval_accuracy": 0.8367346938775511, | |
| "eval_loss": 0.34884124994277954, | |
| "eval_runtime": 1.1848, | |
| "eval_samples_per_second": 82.716, | |
| "eval_steps_per_second": 0.844, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 94.0, | |
| "eval_accuracy": 0.8571428571428571, | |
| "eval_loss": 0.32820624113082886, | |
| "eval_runtime": 1.1771, | |
| "eval_samples_per_second": 83.253, | |
| "eval_steps_per_second": 0.85, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 95.0, | |
| "eval_accuracy": 0.8571428571428571, | |
| "eval_loss": 0.36127328872680664, | |
| "eval_runtime": 1.1851, | |
| "eval_samples_per_second": 82.69, | |
| "eval_steps_per_second": 0.844, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 96.0, | |
| "eval_accuracy": 0.8469387755102041, | |
| "eval_loss": 0.3753064274787903, | |
| "eval_runtime": 1.1883, | |
| "eval_samples_per_second": 82.468, | |
| "eval_steps_per_second": 0.842, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 97.0, | |
| "eval_accuracy": 0.8469387755102041, | |
| "eval_loss": 0.3625222146511078, | |
| "eval_runtime": 1.1837, | |
| "eval_samples_per_second": 82.79, | |
| "eval_steps_per_second": 0.845, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 98.0, | |
| "eval_accuracy": 0.826530612244898, | |
| "eval_loss": 0.39299532771110535, | |
| "eval_runtime": 1.1901, | |
| "eval_samples_per_second": 82.345, | |
| "eval_steps_per_second": 0.84, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 99.0, | |
| "eval_accuracy": 0.8469387755102041, | |
| "eval_loss": 0.33383709192276, | |
| "eval_runtime": 1.2031, | |
| "eval_samples_per_second": 81.453, | |
| "eval_steps_per_second": 0.831, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "grad_norm": 0.7086212038993835, | |
| "learning_rate": 1.1111111111111112e-06, | |
| "loss": 0.3131, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "eval_accuracy": 0.8367346938775511, | |
| "eval_loss": 0.3329985439777374, | |
| "eval_runtime": 1.1868, | |
| "eval_samples_per_second": 82.575, | |
| "eval_steps_per_second": 0.843, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "step": 100, | |
| "total_flos": 2.86484619552768e+17, | |
| "train_loss": 0.35724998712539674, | |
| "train_runtime": 1042.9816, | |
| "train_samples_per_second": 75.84, | |
| "train_steps_per_second": 0.096 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 100, | |
| "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": 2.86484619552768e+17, | |
| "train_batch_size": 256, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |