| { | |
| "best_metric": 0.8737166324435318, | |
| "best_model_checkpoint": "vc-bantai-vit-withoutAMBI-adunest-v1/checkpoint-1800", | |
| "epoch": 12.048192771084338, | |
| "global_step": 3000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.4, | |
| "eval_accuracy": 0.40811088295687886, | |
| "eval_loss": 1.2037091255187988, | |
| "eval_runtime": 11.1902, | |
| "eval_samples_per_second": 174.08, | |
| "eval_steps_per_second": 5.451, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_accuracy": 0.44096509240246407, | |
| "eval_loss": 0.9935279488563538, | |
| "eval_runtime": 11.2125, | |
| "eval_samples_per_second": 173.734, | |
| "eval_steps_per_second": 5.44, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "eval_accuracy": 0.6914784394250514, | |
| "eval_loss": 0.6460596323013306, | |
| "eval_runtime": 11.4894, | |
| "eval_samples_per_second": 169.547, | |
| "eval_steps_per_second": 5.309, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "eval_accuracy": 0.7705338809034907, | |
| "eval_loss": 0.49376896023750305, | |
| "eval_runtime": 11.1511, | |
| "eval_samples_per_second": 174.691, | |
| "eval_steps_per_second": 5.47, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 0.0004949799196787149, | |
| "loss": 0.357, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "eval_accuracy": 0.784394250513347, | |
| "eval_loss": 0.4601840376853943, | |
| "eval_runtime": 11.4476, | |
| "eval_samples_per_second": 170.167, | |
| "eval_steps_per_second": 5.329, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "eval_accuracy": 0.7294661190965093, | |
| "eval_loss": 0.5220066905021667, | |
| "eval_runtime": 11.1921, | |
| "eval_samples_per_second": 174.052, | |
| "eval_steps_per_second": 5.45, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "eval_accuracy": 0.7782340862422998, | |
| "eval_loss": 0.46649423241615295, | |
| "eval_runtime": 11.2377, | |
| "eval_samples_per_second": 173.346, | |
| "eval_steps_per_second": 5.428, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "eval_accuracy": 0.830082135523614, | |
| "eval_loss": 0.44400569796562195, | |
| "eval_runtime": 11.2183, | |
| "eval_samples_per_second": 173.645, | |
| "eval_steps_per_second": 5.438, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "eval_accuracy": 0.7176591375770021, | |
| "eval_loss": 0.5121513605117798, | |
| "eval_runtime": 11.196, | |
| "eval_samples_per_second": 173.991, | |
| "eval_steps_per_second": 5.448, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "learning_rate": 0.0004899598393574297, | |
| "loss": 0.2437, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "eval_accuracy": 0.7320328542094456, | |
| "eval_loss": 0.6155115962028503, | |
| "eval_runtime": 11.2061, | |
| "eval_samples_per_second": 173.833, | |
| "eval_steps_per_second": 5.443, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.42, | |
| "eval_accuracy": 0.7684804928131417, | |
| "eval_loss": 0.5802133679389954, | |
| "eval_runtime": 11.2176, | |
| "eval_samples_per_second": 173.655, | |
| "eval_steps_per_second": 5.438, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 4.82, | |
| "eval_accuracy": 0.8028747433264887, | |
| "eval_loss": 0.47085943818092346, | |
| "eval_runtime": 11.2201, | |
| "eval_samples_per_second": 173.617, | |
| "eval_steps_per_second": 5.437, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 5.22, | |
| "eval_accuracy": 0.8352156057494866, | |
| "eval_loss": 0.4694225490093231, | |
| "eval_runtime": 11.2031, | |
| "eval_samples_per_second": 173.881, | |
| "eval_steps_per_second": 5.445, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 5.62, | |
| "eval_accuracy": 0.8203285420944558, | |
| "eval_loss": 0.46516597270965576, | |
| "eval_runtime": 11.1655, | |
| "eval_samples_per_second": 174.467, | |
| "eval_steps_per_second": 5.463, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 6.02, | |
| "learning_rate": 0.0004849397590361446, | |
| "loss": 0.1841, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 6.02, | |
| "eval_accuracy": 0.7648870636550308, | |
| "eval_loss": 0.5424289107322693, | |
| "eval_runtime": 11.2414, | |
| "eval_samples_per_second": 173.288, | |
| "eval_steps_per_second": 5.426, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 6.43, | |
| "eval_accuracy": 0.8059548254620124, | |
| "eval_loss": 0.46159353852272034, | |
| "eval_runtime": 11.1678, | |
| "eval_samples_per_second": 174.43, | |
| "eval_steps_per_second": 5.462, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 6.83, | |
| "eval_accuracy": 0.8547227926078029, | |
| "eval_loss": 0.35685229301452637, | |
| "eval_runtime": 11.2186, | |
| "eval_samples_per_second": 173.64, | |
| "eval_steps_per_second": 5.437, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 7.23, | |
| "eval_accuracy": 0.8737166324435318, | |
| "eval_loss": 0.36519739031791687, | |
| "eval_runtime": 11.1645, | |
| "eval_samples_per_second": 174.481, | |
| "eval_steps_per_second": 5.464, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 7.63, | |
| "eval_accuracy": 0.7438398357289527, | |
| "eval_loss": 0.7777961492538452, | |
| "eval_runtime": 11.2328, | |
| "eval_samples_per_second": 173.421, | |
| "eval_steps_per_second": 5.431, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 8.03, | |
| "learning_rate": 0.0004799196787148594, | |
| "loss": 0.1328, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 8.03, | |
| "eval_accuracy": 0.8162217659137577, | |
| "eval_loss": 0.546014666557312, | |
| "eval_runtime": 11.2154, | |
| "eval_samples_per_second": 173.689, | |
| "eval_steps_per_second": 5.439, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 8.43, | |
| "eval_accuracy": 0.776694045174538, | |
| "eval_loss": 0.8070306777954102, | |
| "eval_runtime": 11.1916, | |
| "eval_samples_per_second": 174.06, | |
| "eval_steps_per_second": 5.451, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 8.84, | |
| "eval_accuracy": 0.7797741273100616, | |
| "eval_loss": 0.6872759461402893, | |
| "eval_runtime": 11.206, | |
| "eval_samples_per_second": 173.835, | |
| "eval_steps_per_second": 5.444, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 9.24, | |
| "eval_accuracy": 0.7782340862422998, | |
| "eval_loss": 0.8942956328392029, | |
| "eval_runtime": 11.1451, | |
| "eval_samples_per_second": 174.785, | |
| "eval_steps_per_second": 5.473, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 9.64, | |
| "eval_accuracy": 0.8552361396303901, | |
| "eval_loss": 0.5378373265266418, | |
| "eval_runtime": 11.1452, | |
| "eval_samples_per_second": 174.784, | |
| "eval_steps_per_second": 5.473, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 10.04, | |
| "learning_rate": 0.0004748995983935743, | |
| "loss": 0.1059, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 10.04, | |
| "eval_accuracy": 0.8069815195071869, | |
| "eval_loss": 0.7080937623977661, | |
| "eval_runtime": 11.2065, | |
| "eval_samples_per_second": 173.828, | |
| "eval_steps_per_second": 5.443, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 10.44, | |
| "eval_accuracy": 0.7012320328542094, | |
| "eval_loss": 0.994149923324585, | |
| "eval_runtime": 11.1681, | |
| "eval_samples_per_second": 174.426, | |
| "eval_steps_per_second": 5.462, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 10.84, | |
| "eval_accuracy": 0.7900410677618069, | |
| "eval_loss": 0.9151853919029236, | |
| "eval_runtime": 11.2106, | |
| "eval_samples_per_second": 173.764, | |
| "eval_steps_per_second": 5.441, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 11.24, | |
| "eval_accuracy": 0.7736139630390144, | |
| "eval_loss": 0.7493842244148254, | |
| "eval_runtime": 11.1841, | |
| "eval_samples_per_second": 174.175, | |
| "eval_steps_per_second": 5.454, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 11.65, | |
| "eval_accuracy": 0.7869609856262834, | |
| "eval_loss": 0.7680638432502747, | |
| "eval_runtime": 11.2188, | |
| "eval_samples_per_second": 173.636, | |
| "eval_steps_per_second": 5.437, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 12.05, | |
| "learning_rate": 0.0004698795180722892, | |
| "loss": 0.081, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 12.05, | |
| "eval_accuracy": 0.8039014373716632, | |
| "eval_loss": 0.7735891342163086, | |
| "eval_runtime": 11.4086, | |
| "eval_samples_per_second": 170.748, | |
| "eval_steps_per_second": 5.347, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 12.05, | |
| "step": 3000, | |
| "total_flos": 7.416049873230029e+18, | |
| "train_loss": 0.18408180872599283, | |
| "train_runtime": 1888.403, | |
| "train_samples_per_second": 841.24, | |
| "train_steps_per_second": 26.371 | |
| } | |
| ], | |
| "max_steps": 49800, | |
| "num_train_epochs": 200, | |
| "total_flos": 7.416049873230029e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |