classification_right_false_data
/
swin-tiny-patch4-window7-224-finetuned-kiru
/checkpoint-300
/trainer_state.json
| { | |
| "best_metric": 0.9393939393939394, | |
| "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-kiru\\checkpoint-63", | |
| "epoch": 100.0, | |
| "eval_steps": 500, | |
| "global_step": 300, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.2, | |
| "eval_loss": 0.9137158989906311, | |
| "eval_runtime": 2.4017, | |
| "eval_samples_per_second": 68.703, | |
| "eval_steps_per_second": 2.498, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.41818181818181815, | |
| "eval_loss": 0.7433991432189941, | |
| "eval_runtime": 2.3854, | |
| "eval_samples_per_second": 69.171, | |
| "eval_steps_per_second": 2.515, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.7757575757575758, | |
| "eval_loss": 0.558496356010437, | |
| "eval_runtime": 2.91, | |
| "eval_samples_per_second": 56.702, | |
| "eval_steps_per_second": 2.062, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.7757575757575758, | |
| "eval_loss": 0.4807980954647064, | |
| "eval_runtime": 2.7225, | |
| "eval_samples_per_second": 60.606, | |
| "eval_steps_per_second": 2.204, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.7757575757575758, | |
| "eval_loss": 0.44610753655433655, | |
| "eval_runtime": 2.8794, | |
| "eval_samples_per_second": 57.303, | |
| "eval_steps_per_second": 2.084, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.8, | |
| "eval_loss": 0.41230690479278564, | |
| "eval_runtime": 2.7147, | |
| "eval_samples_per_second": 60.781, | |
| "eval_steps_per_second": 2.21, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.8545454545454545, | |
| "eval_loss": 0.4499864876270294, | |
| "eval_runtime": 2.9708, | |
| "eval_samples_per_second": 55.54, | |
| "eval_steps_per_second": 2.02, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.7636363636363637, | |
| "eval_loss": 0.4703312814235687, | |
| "eval_runtime": 2.7665, | |
| "eval_samples_per_second": 59.642, | |
| "eval_steps_per_second": 2.169, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.8, | |
| "eval_loss": 0.41265082359313965, | |
| "eval_runtime": 2.7687, | |
| "eval_samples_per_second": 59.595, | |
| "eval_steps_per_second": 2.167, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 5e-05, | |
| "loss": 0.5353, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.8787878787878788, | |
| "eval_loss": 0.3097422420978546, | |
| "eval_runtime": 2.932, | |
| "eval_samples_per_second": 56.276, | |
| "eval_steps_per_second": 2.046, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.7696969696969697, | |
| "eval_loss": 0.45016413927078247, | |
| "eval_runtime": 2.8763, | |
| "eval_samples_per_second": 57.366, | |
| "eval_steps_per_second": 2.086, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.8121212121212121, | |
| "eval_loss": 0.3948935270309448, | |
| "eval_runtime": 2.4262, | |
| "eval_samples_per_second": 68.008, | |
| "eval_steps_per_second": 2.473, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.8727272727272727, | |
| "eval_loss": 0.2976933419704437, | |
| "eval_runtime": 2.9565, | |
| "eval_samples_per_second": 55.809, | |
| "eval_steps_per_second": 2.029, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.8121212121212121, | |
| "eval_loss": 0.37680599093437195, | |
| "eval_runtime": 2.6485, | |
| "eval_samples_per_second": 62.3, | |
| "eval_steps_per_second": 2.265, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.8424242424242424, | |
| "eval_loss": 0.36290910840034485, | |
| "eval_runtime": 3.3518, | |
| "eval_samples_per_second": 49.227, | |
| "eval_steps_per_second": 1.79, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.8545454545454545, | |
| "eval_loss": 0.31888607144355774, | |
| "eval_runtime": 3.4102, | |
| "eval_samples_per_second": 48.385, | |
| "eval_steps_per_second": 1.759, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.8484848484848485, | |
| "eval_loss": 0.27646660804748535, | |
| "eval_runtime": 3.2469, | |
| "eval_samples_per_second": 50.818, | |
| "eval_steps_per_second": 1.848, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.9030303030303031, | |
| "eval_loss": 0.22981072962284088, | |
| "eval_runtime": 3.3886, | |
| "eval_samples_per_second": 48.692, | |
| "eval_steps_per_second": 1.771, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.8242424242424242, | |
| "eval_loss": 0.4056190848350525, | |
| "eval_runtime": 3.359, | |
| "eval_samples_per_second": 49.122, | |
| "eval_steps_per_second": 1.786, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.2047, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.8848484848484849, | |
| "eval_loss": 0.2524569034576416, | |
| "eval_runtime": 3.3911, | |
| "eval_samples_per_second": 48.657, | |
| "eval_steps_per_second": 1.769, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.9393939393939394, | |
| "eval_loss": 0.179116889834404, | |
| "eval_runtime": 3.4087, | |
| "eval_samples_per_second": 48.406, | |
| "eval_steps_per_second": 1.76, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.8606060606060606, | |
| "eval_loss": 0.34358078241348267, | |
| "eval_runtime": 3.4132, | |
| "eval_samples_per_second": 48.342, | |
| "eval_steps_per_second": 1.758, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.8545454545454545, | |
| "eval_loss": 0.37361884117126465, | |
| "eval_runtime": 2.5007, | |
| "eval_samples_per_second": 65.981, | |
| "eval_steps_per_second": 2.399, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.9272727272727272, | |
| "eval_loss": 0.20224401354789734, | |
| "eval_runtime": 3.4453, | |
| "eval_samples_per_second": 47.891, | |
| "eval_steps_per_second": 1.741, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.896969696969697, | |
| "eval_loss": 0.2309740036725998, | |
| "eval_runtime": 3.4325, | |
| "eval_samples_per_second": 48.07, | |
| "eval_steps_per_second": 1.748, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.8484848484848485, | |
| "eval_loss": 0.4356694221496582, | |
| "eval_runtime": 3.4524, | |
| "eval_samples_per_second": 47.792, | |
| "eval_steps_per_second": 1.738, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.8909090909090909, | |
| "eval_loss": 0.23648156225681305, | |
| "eval_runtime": 3.3817, | |
| "eval_samples_per_second": 48.792, | |
| "eval_steps_per_second": 1.774, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.896969696969697, | |
| "eval_loss": 0.2242034673690796, | |
| "eval_runtime": 3.5408, | |
| "eval_samples_per_second": 46.6, | |
| "eval_steps_per_second": 1.695, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.8787878787878788, | |
| "eval_loss": 0.3519549071788788, | |
| "eval_runtime": 3.5339, | |
| "eval_samples_per_second": 46.69, | |
| "eval_steps_per_second": 1.698, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 0.1214, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.8666666666666667, | |
| "eval_loss": 0.3405221700668335, | |
| "eval_runtime": 3.3876, | |
| "eval_samples_per_second": 48.707, | |
| "eval_steps_per_second": 1.771, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_accuracy": 0.8848484848484849, | |
| "eval_loss": 0.26643767952919006, | |
| "eval_runtime": 3.5147, | |
| "eval_samples_per_second": 46.946, | |
| "eval_steps_per_second": 1.707, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.896969696969697, | |
| "eval_loss": 0.30635523796081543, | |
| "eval_runtime": 3.4904, | |
| "eval_samples_per_second": 47.273, | |
| "eval_steps_per_second": 1.719, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_accuracy": 0.8909090909090909, | |
| "eval_loss": 0.28046053647994995, | |
| "eval_runtime": 3.4457, | |
| "eval_samples_per_second": 47.886, | |
| "eval_steps_per_second": 1.741, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.9090909090909091, | |
| "eval_loss": 0.2581537067890167, | |
| "eval_runtime": 3.3583, | |
| "eval_samples_per_second": 49.131, | |
| "eval_steps_per_second": 1.787, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_accuracy": 0.896969696969697, | |
| "eval_loss": 0.3365895748138428, | |
| "eval_runtime": 3.5154, | |
| "eval_samples_per_second": 46.936, | |
| "eval_steps_per_second": 1.707, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.8242424242424242, | |
| "eval_loss": 0.4986293315887451, | |
| "eval_runtime": 3.4596, | |
| "eval_samples_per_second": 47.693, | |
| "eval_steps_per_second": 1.734, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_accuracy": 0.896969696969697, | |
| "eval_loss": 0.33538326621055603, | |
| "eval_runtime": 3.4043, | |
| "eval_samples_per_second": 48.468, | |
| "eval_steps_per_second": 1.762, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.9151515151515152, | |
| "eval_loss": 0.28124478459358215, | |
| "eval_runtime": 3.3948, | |
| "eval_samples_per_second": 48.604, | |
| "eval_steps_per_second": 1.767, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_accuracy": 0.9151515151515152, | |
| "eval_loss": 0.28065553307533264, | |
| "eval_runtime": 2.327, | |
| "eval_samples_per_second": 70.907, | |
| "eval_steps_per_second": 2.578, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.0667, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.8787878787878788, | |
| "eval_loss": 0.33923324942588806, | |
| "eval_runtime": 2.2919, | |
| "eval_samples_per_second": 71.992, | |
| "eval_steps_per_second": 2.618, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_accuracy": 0.9212121212121213, | |
| "eval_loss": 0.2863142192363739, | |
| "eval_runtime": 2.4128, | |
| "eval_samples_per_second": 68.385, | |
| "eval_steps_per_second": 2.487, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.9090909090909091, | |
| "eval_loss": 0.29716795682907104, | |
| "eval_runtime": 2.3275, | |
| "eval_samples_per_second": 70.891, | |
| "eval_steps_per_second": 2.578, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_accuracy": 0.9090909090909091, | |
| "eval_loss": 0.3144596815109253, | |
| "eval_runtime": 2.3029, | |
| "eval_samples_per_second": 71.647, | |
| "eval_steps_per_second": 2.605, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.896969696969697, | |
| "eval_loss": 0.3420035243034363, | |
| "eval_runtime": 2.3671, | |
| "eval_samples_per_second": 69.706, | |
| "eval_steps_per_second": 2.535, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_accuracy": 0.9030303030303031, | |
| "eval_loss": 0.2978503704071045, | |
| "eval_runtime": 2.3504, | |
| "eval_samples_per_second": 70.202, | |
| "eval_steps_per_second": 2.553, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 0.9090909090909091, | |
| "eval_loss": 0.305865615606308, | |
| "eval_runtime": 2.328, | |
| "eval_samples_per_second": 70.877, | |
| "eval_steps_per_second": 2.577, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_accuracy": 0.9090909090909091, | |
| "eval_loss": 0.33988600969314575, | |
| "eval_runtime": 2.3424, | |
| "eval_samples_per_second": 70.44, | |
| "eval_steps_per_second": 2.561, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.896969696969697, | |
| "eval_loss": 0.3573344945907593, | |
| "eval_runtime": 2.3771, | |
| "eval_samples_per_second": 69.411, | |
| "eval_steps_per_second": 2.524, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_accuracy": 0.9090909090909091, | |
| "eval_loss": 0.3080121874809265, | |
| "eval_runtime": 2.3669, | |
| "eval_samples_per_second": 69.711, | |
| "eval_steps_per_second": 2.535, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.0489, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 0.9090909090909091, | |
| "eval_loss": 0.3075540363788605, | |
| "eval_runtime": 2.3013, | |
| "eval_samples_per_second": 71.698, | |
| "eval_steps_per_second": 2.607, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_accuracy": 0.896969696969697, | |
| "eval_loss": 0.36510610580444336, | |
| "eval_runtime": 2.3178, | |
| "eval_samples_per_second": 71.189, | |
| "eval_steps_per_second": 2.589, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.9030303030303031, | |
| "eval_loss": 0.31200146675109863, | |
| "eval_runtime": 2.3395, | |
| "eval_samples_per_second": 70.528, | |
| "eval_steps_per_second": 2.565, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_accuracy": 0.9151515151515152, | |
| "eval_loss": 0.3011230528354645, | |
| "eval_runtime": 2.349, | |
| "eval_samples_per_second": 70.244, | |
| "eval_steps_per_second": 2.554, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_accuracy": 0.896969696969697, | |
| "eval_loss": 0.33502820134162903, | |
| "eval_runtime": 2.3148, | |
| "eval_samples_per_second": 71.282, | |
| "eval_steps_per_second": 2.592, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "eval_accuracy": 0.8727272727272727, | |
| "eval_loss": 0.42433637380599976, | |
| "eval_runtime": 2.3813, | |
| "eval_samples_per_second": 69.288, | |
| "eval_steps_per_second": 2.52, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.896969696969697, | |
| "eval_loss": 0.39749395847320557, | |
| "eval_runtime": 2.3457, | |
| "eval_samples_per_second": 70.341, | |
| "eval_steps_per_second": 2.558, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "eval_accuracy": 0.8848484848484849, | |
| "eval_loss": 0.3484455943107605, | |
| "eval_runtime": 2.3486, | |
| "eval_samples_per_second": 70.254, | |
| "eval_steps_per_second": 2.555, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_accuracy": 0.8727272727272727, | |
| "eval_loss": 0.4501076340675354, | |
| "eval_runtime": 2.3305, | |
| "eval_samples_per_second": 70.8, | |
| "eval_steps_per_second": 2.575, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "eval_accuracy": 0.8303030303030303, | |
| "eval_loss": 0.550175130367279, | |
| "eval_runtime": 2.33, | |
| "eval_samples_per_second": 70.814, | |
| "eval_steps_per_second": 2.575, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.0497, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_accuracy": 0.8727272727272727, | |
| "eval_loss": 0.4404814839363098, | |
| "eval_runtime": 2.3704, | |
| "eval_samples_per_second": 69.608, | |
| "eval_steps_per_second": 2.531, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 61.0, | |
| "eval_accuracy": 0.8909090909090909, | |
| "eval_loss": 0.36748144030570984, | |
| "eval_runtime": 2.3087, | |
| "eval_samples_per_second": 71.47, | |
| "eval_steps_per_second": 2.599, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 62.0, | |
| "eval_accuracy": 0.8909090909090909, | |
| "eval_loss": 0.3592420518398285, | |
| "eval_runtime": 2.6613, | |
| "eval_samples_per_second": 61.999, | |
| "eval_steps_per_second": 2.255, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 63.0, | |
| "eval_accuracy": 0.9090909090909091, | |
| "eval_loss": 0.3651820421218872, | |
| "eval_runtime": 2.4228, | |
| "eval_samples_per_second": 68.102, | |
| "eval_steps_per_second": 2.476, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "eval_accuracy": 0.8848484848484849, | |
| "eval_loss": 0.42894408106803894, | |
| "eval_runtime": 2.4722, | |
| "eval_samples_per_second": 66.741, | |
| "eval_steps_per_second": 2.427, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 65.0, | |
| "eval_accuracy": 0.896969696969697, | |
| "eval_loss": 0.3802632987499237, | |
| "eval_runtime": 2.4846, | |
| "eval_samples_per_second": 66.408, | |
| "eval_steps_per_second": 2.415, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 66.0, | |
| "eval_accuracy": 0.9030303030303031, | |
| "eval_loss": 0.35655370354652405, | |
| "eval_runtime": 2.3659, | |
| "eval_samples_per_second": 69.74, | |
| "eval_steps_per_second": 2.536, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 67.0, | |
| "eval_accuracy": 0.9030303030303031, | |
| "eval_loss": 0.3601439297199249, | |
| "eval_runtime": 2.4242, | |
| "eval_samples_per_second": 68.063, | |
| "eval_steps_per_second": 2.475, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "eval_accuracy": 0.8787878787878788, | |
| "eval_loss": 0.38698670268058777, | |
| "eval_runtime": 2.4852, | |
| "eval_samples_per_second": 66.394, | |
| "eval_steps_per_second": 2.414, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 69.0, | |
| "eval_accuracy": 0.8363636363636363, | |
| "eval_loss": 0.5403356552124023, | |
| "eval_runtime": 2.7549, | |
| "eval_samples_per_second": 59.894, | |
| "eval_steps_per_second": 2.178, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.0335, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "eval_accuracy": 0.8121212121212121, | |
| "eval_loss": 0.5928748846054077, | |
| "eval_runtime": 2.456, | |
| "eval_samples_per_second": 67.181, | |
| "eval_steps_per_second": 2.443, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 71.0, | |
| "eval_accuracy": 0.8606060606060606, | |
| "eval_loss": 0.4446137547492981, | |
| "eval_runtime": 3.4376, | |
| "eval_samples_per_second": 47.998, | |
| "eval_steps_per_second": 1.745, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "eval_accuracy": 0.9030303030303031, | |
| "eval_loss": 0.3456382155418396, | |
| "eval_runtime": 3.4289, | |
| "eval_samples_per_second": 48.12, | |
| "eval_steps_per_second": 1.75, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 73.0, | |
| "eval_accuracy": 0.9030303030303031, | |
| "eval_loss": 0.3497260808944702, | |
| "eval_runtime": 3.448, | |
| "eval_samples_per_second": 47.854, | |
| "eval_steps_per_second": 1.74, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 74.0, | |
| "eval_accuracy": 0.8909090909090909, | |
| "eval_loss": 0.3460451066493988, | |
| "eval_runtime": 3.5723, | |
| "eval_samples_per_second": 46.189, | |
| "eval_steps_per_second": 1.68, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 75.0, | |
| "eval_accuracy": 0.9030303030303031, | |
| "eval_loss": 0.35541394352912903, | |
| "eval_runtime": 3.3617, | |
| "eval_samples_per_second": 49.082, | |
| "eval_steps_per_second": 1.785, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 76.0, | |
| "eval_accuracy": 0.9151515151515152, | |
| "eval_loss": 0.37109458446502686, | |
| "eval_runtime": 3.3954, | |
| "eval_samples_per_second": 48.596, | |
| "eval_steps_per_second": 1.767, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 77.0, | |
| "eval_accuracy": 0.8909090909090909, | |
| "eval_loss": 0.3966122567653656, | |
| "eval_runtime": 3.39, | |
| "eval_samples_per_second": 48.673, | |
| "eval_steps_per_second": 1.77, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 78.0, | |
| "eval_accuracy": 0.896969696969697, | |
| "eval_loss": 0.37558913230895996, | |
| "eval_runtime": 2.4777, | |
| "eval_samples_per_second": 66.594, | |
| "eval_steps_per_second": 2.422, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 79.0, | |
| "eval_accuracy": 0.8848484848484849, | |
| "eval_loss": 0.3648350238800049, | |
| "eval_runtime": 2.4024, | |
| "eval_samples_per_second": 68.681, | |
| "eval_steps_per_second": 2.497, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.0354, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "eval_accuracy": 0.8848484848484849, | |
| "eval_loss": 0.364296555519104, | |
| "eval_runtime": 2.4061, | |
| "eval_samples_per_second": 68.576, | |
| "eval_steps_per_second": 2.494, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 81.0, | |
| "eval_accuracy": 0.8787878787878788, | |
| "eval_loss": 0.37478142976760864, | |
| "eval_runtime": 2.4973, | |
| "eval_samples_per_second": 66.07, | |
| "eval_steps_per_second": 2.403, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 82.0, | |
| "eval_accuracy": 0.8848484848484849, | |
| "eval_loss": 0.38661420345306396, | |
| "eval_runtime": 3.4194, | |
| "eval_samples_per_second": 48.254, | |
| "eval_steps_per_second": 1.755, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 83.0, | |
| "eval_accuracy": 0.8787878787878788, | |
| "eval_loss": 0.3912670314311981, | |
| "eval_runtime": 3.4156, | |
| "eval_samples_per_second": 48.308, | |
| "eval_steps_per_second": 1.757, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 84.0, | |
| "eval_accuracy": 0.896969696969697, | |
| "eval_loss": 0.39883953332901, | |
| "eval_runtime": 3.3424, | |
| "eval_samples_per_second": 49.366, | |
| "eval_steps_per_second": 1.795, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 85.0, | |
| "eval_accuracy": 0.896969696969697, | |
| "eval_loss": 0.3957526981830597, | |
| "eval_runtime": 3.493, | |
| "eval_samples_per_second": 47.238, | |
| "eval_steps_per_second": 1.718, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 86.0, | |
| "eval_accuracy": 0.8909090909090909, | |
| "eval_loss": 0.3850858211517334, | |
| "eval_runtime": 3.5272, | |
| "eval_samples_per_second": 46.779, | |
| "eval_steps_per_second": 1.701, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 87.0, | |
| "eval_accuracy": 0.9030303030303031, | |
| "eval_loss": 0.3711934983730316, | |
| "eval_runtime": 3.5137, | |
| "eval_samples_per_second": 46.958, | |
| "eval_steps_per_second": 1.708, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 88.0, | |
| "eval_accuracy": 0.9090909090909091, | |
| "eval_loss": 0.36674121022224426, | |
| "eval_runtime": 3.4451, | |
| "eval_samples_per_second": 47.895, | |
| "eval_steps_per_second": 1.742, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 89.0, | |
| "eval_accuracy": 0.9090909090909091, | |
| "eval_loss": 0.3646032214164734, | |
| "eval_runtime": 3.4393, | |
| "eval_samples_per_second": 47.975, | |
| "eval_steps_per_second": 1.745, | |
| "step": 267 | |
| }, | |
| { | |
| "epoch": 90.0, | |
| "learning_rate": 5.555555555555556e-06, | |
| "loss": 0.0221, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 90.0, | |
| "eval_accuracy": 0.896969696969697, | |
| "eval_loss": 0.3635583221912384, | |
| "eval_runtime": 3.3452, | |
| "eval_samples_per_second": 49.324, | |
| "eval_steps_per_second": 1.794, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 91.0, | |
| "eval_accuracy": 0.896969696969697, | |
| "eval_loss": 0.36410683393478394, | |
| "eval_runtime": 2.9568, | |
| "eval_samples_per_second": 55.804, | |
| "eval_steps_per_second": 2.029, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 92.0, | |
| "eval_accuracy": 0.9090909090909091, | |
| "eval_loss": 0.36949315667152405, | |
| "eval_runtime": 2.4369, | |
| "eval_samples_per_second": 67.709, | |
| "eval_steps_per_second": 2.462, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 93.0, | |
| "eval_accuracy": 0.9090909090909091, | |
| "eval_loss": 0.3717237412929535, | |
| "eval_runtime": 2.381, | |
| "eval_samples_per_second": 69.298, | |
| "eval_steps_per_second": 2.52, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 94.0, | |
| "eval_accuracy": 0.9090909090909091, | |
| "eval_loss": 0.3703281879425049, | |
| "eval_runtime": 3.4459, | |
| "eval_samples_per_second": 47.883, | |
| "eval_steps_per_second": 1.741, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 95.0, | |
| "eval_accuracy": 0.9090909090909091, | |
| "eval_loss": 0.3681131899356842, | |
| "eval_runtime": 3.3629, | |
| "eval_samples_per_second": 49.064, | |
| "eval_steps_per_second": 1.784, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 96.0, | |
| "eval_accuracy": 0.9151515151515152, | |
| "eval_loss": 0.36634162068367004, | |
| "eval_runtime": 2.3736, | |
| "eval_samples_per_second": 69.515, | |
| "eval_steps_per_second": 2.528, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 97.0, | |
| "eval_accuracy": 0.9090909090909091, | |
| "eval_loss": 0.3671952784061432, | |
| "eval_runtime": 2.5265, | |
| "eval_samples_per_second": 65.309, | |
| "eval_steps_per_second": 2.375, | |
| "step": 291 | |
| }, | |
| { | |
| "epoch": 98.0, | |
| "eval_accuracy": 0.9090909090909091, | |
| "eval_loss": 0.3688179850578308, | |
| "eval_runtime": 2.477, | |
| "eval_samples_per_second": 66.614, | |
| "eval_steps_per_second": 2.422, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 99.0, | |
| "eval_accuracy": 0.9090909090909091, | |
| "eval_loss": 0.3698950707912445, | |
| "eval_runtime": 2.8966, | |
| "eval_samples_per_second": 56.963, | |
| "eval_steps_per_second": 2.071, | |
| "step": 297 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.0225, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "eval_accuracy": 0.9090909090909091, | |
| "eval_loss": 0.3700920343399048, | |
| "eval_runtime": 2.4031, | |
| "eval_samples_per_second": 68.662, | |
| "eval_steps_per_second": 2.497, | |
| "step": 300 | |
| } | |
| ], | |
| "logging_steps": 30, | |
| "max_steps": 300, | |
| "num_train_epochs": 100, | |
| "save_steps": 500, | |
| "total_flos": 9.494987792596992e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |