| { | |
| "best_metric": 0.2235843539237976, | |
| "best_model_checkpoint": "nsfw-images-2/checkpoint-1868", | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 1868, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.013383297644539615, | |
| "grad_norm": 18.170637130737305, | |
| "learning_rate": 1.2312633832976446e-05, | |
| "loss": 0.7179, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.02676659528907923, | |
| "grad_norm": 3.0997555255889893, | |
| "learning_rate": 2.569593147751606e-05, | |
| "loss": 0.3338, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04014989293361884, | |
| "grad_norm": 31.291412353515625, | |
| "learning_rate": 3.9079229122055675e-05, | |
| "loss": 0.3848, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.05353319057815846, | |
| "grad_norm": 0.03622590750455856, | |
| "learning_rate": 5.246252676659529e-05, | |
| "loss": 0.0596, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.06691648822269808, | |
| "grad_norm": 26.821062088012695, | |
| "learning_rate": 6.58458244111349e-05, | |
| "loss": 0.3471, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.08029978586723768, | |
| "grad_norm": 0.011622205376625061, | |
| "learning_rate": 7.922912205567452e-05, | |
| "loss": 0.1036, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.0936830835117773, | |
| "grad_norm": 0.07030396908521652, | |
| "learning_rate": 9.261241970021414e-05, | |
| "loss": 0.0683, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.10706638115631692, | |
| "grad_norm": 0.1393502801656723, | |
| "learning_rate": 0.00010599571734475374, | |
| "loss": 0.3868, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.12044967880085652, | |
| "grad_norm": 0.019323009997606277, | |
| "learning_rate": 0.00011937901498929336, | |
| "loss": 0.5266, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.13383297644539616, | |
| "grad_norm": 0.02416042983531952, | |
| "learning_rate": 0.000132762312633833, | |
| "loss": 0.2695, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.14721627408993576, | |
| "grad_norm": 2.2118706703186035, | |
| "learning_rate": 0.0001461456102783726, | |
| "loss": 0.4989, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.16059957173447537, | |
| "grad_norm": 11.72065258026123, | |
| "learning_rate": 0.0001595289079229122, | |
| "loss": 0.3731, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.173982869379015, | |
| "grad_norm": 0.0027222177013754845, | |
| "learning_rate": 0.00017291220556745181, | |
| "loss": 0.1109, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.1873661670235546, | |
| "grad_norm": 0.0008230574312619865, | |
| "learning_rate": 0.00018629550321199142, | |
| "loss": 0.2094, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.2007494646680942, | |
| "grad_norm": 0.036911237984895706, | |
| "learning_rate": 0.00019967880085653106, | |
| "loss": 0.6709, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.21413276231263384, | |
| "grad_norm": 20.274892807006836, | |
| "learning_rate": 0.00021306209850107066, | |
| "loss": 0.5297, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.22751605995717344, | |
| "grad_norm": 0.04864942654967308, | |
| "learning_rate": 0.00022644539614561027, | |
| "loss": 0.1467, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.24089935760171305, | |
| "grad_norm": 0.12074282765388489, | |
| "learning_rate": 0.0002398286937901499, | |
| "loss": 0.6298, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.25428265524625265, | |
| "grad_norm": 0.11845938861370087, | |
| "learning_rate": 0.00025321199143468954, | |
| "loss": 0.257, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.2676659528907923, | |
| "grad_norm": 0.09819821268320084, | |
| "learning_rate": 0.00026659528907922915, | |
| "loss": 0.8714, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.2810492505353319, | |
| "grad_norm": 0.09790199995040894, | |
| "learning_rate": 0.00027997858672376875, | |
| "loss": 0.2357, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.2944325481798715, | |
| "grad_norm": 0.5837295055389404, | |
| "learning_rate": 0.00029336188436830836, | |
| "loss": 0.7943, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.3078158458244111, | |
| "grad_norm": 0.14801590144634247, | |
| "learning_rate": 0.00030674518201284797, | |
| "loss": 0.4615, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.32119914346895073, | |
| "grad_norm": 0.05935389921069145, | |
| "learning_rate": 0.0003201284796573876, | |
| "loss": 0.2401, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.33458244111349034, | |
| "grad_norm": 12.694086074829102, | |
| "learning_rate": 0.00033297644539614566, | |
| "loss": 0.6572, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.34796573875803, | |
| "grad_norm": 0.05311077833175659, | |
| "learning_rate": 0.00034635974304068526, | |
| "loss": 0.3569, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.3613490364025696, | |
| "grad_norm": 0.03182295709848404, | |
| "learning_rate": 0.0003597430406852248, | |
| "loss": 0.1498, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 0.3747323340471092, | |
| "grad_norm": 0.33807849884033203, | |
| "learning_rate": 0.0003731263383297644, | |
| "loss": 0.3766, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.3881156316916488, | |
| "grad_norm": 0.08421733975410461, | |
| "learning_rate": 0.00038650963597430403, | |
| "loss": 0.2979, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 0.4014989293361884, | |
| "grad_norm": 0.01755744405090809, | |
| "learning_rate": 0.0003998929336188437, | |
| "loss": 0.0031, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.4148822269807281, | |
| "grad_norm": 0.21543407440185547, | |
| "learning_rate": 0.0004132762312633833, | |
| "loss": 0.4799, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 0.4282655246252677, | |
| "grad_norm": 0.18580827116966248, | |
| "learning_rate": 0.0004266595289079229, | |
| "loss": 0.3885, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.4416488222698073, | |
| "grad_norm": 11.58962631225586, | |
| "learning_rate": 0.0004400428265524625, | |
| "loss": 0.3268, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 0.4550321199143469, | |
| "grad_norm": 0.0360148549079895, | |
| "learning_rate": 0.0004534261241970021, | |
| "loss": 0.3201, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.4684154175588865, | |
| "grad_norm": 0.09959446638822556, | |
| "learning_rate": 0.0004668094218415418, | |
| "loss": 0.2712, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 0.4817987152034261, | |
| "grad_norm": 0.25127506256103516, | |
| "learning_rate": 0.0004801927194860814, | |
| "loss": 0.3106, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.49518201284796576, | |
| "grad_norm": 11.287735939025879, | |
| "learning_rate": 0.000493576017130621, | |
| "loss": 0.2296, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 0.5085653104925053, | |
| "grad_norm": 10.859394073486328, | |
| "learning_rate": 0.0004992267428027599, | |
| "loss": 0.3712, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.521948608137045, | |
| "grad_norm": 0.18585732579231262, | |
| "learning_rate": 0.0004977397097311444, | |
| "loss": 0.3561, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 0.5353319057815846, | |
| "grad_norm": 14.576325416564941, | |
| "learning_rate": 0.000496252676659529, | |
| "loss": 0.3283, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.5487152034261242, | |
| "grad_norm": 0.00898987427353859, | |
| "learning_rate": 0.0004947656435879134, | |
| "loss": 0.0033, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 0.5620985010706638, | |
| "grad_norm": 0.27176257967948914, | |
| "learning_rate": 0.0004932786105162979, | |
| "loss": 0.5933, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.5754817987152034, | |
| "grad_norm": 0.012289056554436684, | |
| "learning_rate": 0.0004917915774446823, | |
| "loss": 0.1723, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 0.588865096359743, | |
| "grad_norm": 0.050152458250522614, | |
| "learning_rate": 0.0004903045443730669, | |
| "loss": 0.5719, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.6022483940042827, | |
| "grad_norm": 0.6666317582130432, | |
| "learning_rate": 0.0004888175113014514, | |
| "loss": 0.7938, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 0.6156316916488223, | |
| "grad_norm": 0.35938775539398193, | |
| "learning_rate": 0.00048733047822983584, | |
| "loss": 0.4964, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.6290149892933619, | |
| "grad_norm": 0.08501864224672318, | |
| "learning_rate": 0.0004858434451582203, | |
| "loss": 0.2737, | |
| "step": 1175 | |
| }, | |
| { | |
| "epoch": 0.6423982869379015, | |
| "grad_norm": 0.02361874282360077, | |
| "learning_rate": 0.0004843564120866048, | |
| "loss": 0.15, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.6557815845824411, | |
| "grad_norm": 0.05745585262775421, | |
| "learning_rate": 0.0004828693790149893, | |
| "loss": 0.2676, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 0.6691648822269807, | |
| "grad_norm": 0.15592187643051147, | |
| "learning_rate": 0.00048138234594337375, | |
| "loss": 0.3195, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.6825481798715204, | |
| "grad_norm": 0.01977529190480709, | |
| "learning_rate": 0.0004798953128717583, | |
| "loss": 0.1439, | |
| "step": 1275 | |
| }, | |
| { | |
| "epoch": 0.69593147751606, | |
| "grad_norm": 11.418144226074219, | |
| "learning_rate": 0.0004784082798001428, | |
| "loss": 0.2578, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.7093147751605996, | |
| "grad_norm": 0.12220004945993423, | |
| "learning_rate": 0.00047692124672852725, | |
| "loss": 0.2181, | |
| "step": 1325 | |
| }, | |
| { | |
| "epoch": 0.7226980728051392, | |
| "grad_norm": 0.2515058219432831, | |
| "learning_rate": 0.00047543421365691177, | |
| "loss": 0.4207, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.7360813704496788, | |
| "grad_norm": 10.930126190185547, | |
| "learning_rate": 0.00047394718058529624, | |
| "loss": 0.3217, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 0.7494646680942184, | |
| "grad_norm": 0.1796221137046814, | |
| "learning_rate": 0.0004724601475136807, | |
| "loss": 0.4147, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.762847965738758, | |
| "grad_norm": 0.12057535350322723, | |
| "learning_rate": 0.0004709731144420652, | |
| "loss": 0.2845, | |
| "step": 1425 | |
| }, | |
| { | |
| "epoch": 0.7762312633832976, | |
| "grad_norm": 0.6278265714645386, | |
| "learning_rate": 0.0004694860813704497, | |
| "loss": 0.6357, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.7896145610278372, | |
| "grad_norm": 0.08220059424638748, | |
| "learning_rate": 0.00046799904829883415, | |
| "loss": 0.4283, | |
| "step": 1475 | |
| }, | |
| { | |
| "epoch": 0.8029978586723768, | |
| "grad_norm": 10.042654991149902, | |
| "learning_rate": 0.00046651201522721866, | |
| "loss": 0.3957, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.8163811563169164, | |
| "grad_norm": 0.20416533946990967, | |
| "learning_rate": 0.00046502498215560313, | |
| "loss": 0.4242, | |
| "step": 1525 | |
| }, | |
| { | |
| "epoch": 0.8297644539614561, | |
| "grad_norm": 0.12127134948968887, | |
| "learning_rate": 0.00046353794908398765, | |
| "loss": 0.1901, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.8431477516059958, | |
| "grad_norm": 0.07789531350135803, | |
| "learning_rate": 0.00046205091601237216, | |
| "loss": 0.2266, | |
| "step": 1575 | |
| }, | |
| { | |
| "epoch": 0.8565310492505354, | |
| "grad_norm": 0.03442813456058502, | |
| "learning_rate": 0.00046056388294075663, | |
| "loss": 0.2767, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.869914346895075, | |
| "grad_norm": 0.2261192798614502, | |
| "learning_rate": 0.0004590768498691411, | |
| "loss": 0.3227, | |
| "step": 1625 | |
| }, | |
| { | |
| "epoch": 0.8832976445396146, | |
| "grad_norm": 0.05203871801495552, | |
| "learning_rate": 0.0004575898167975256, | |
| "loss": 0.1059, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.8966809421841542, | |
| "grad_norm": 0.17587050795555115, | |
| "learning_rate": 0.0004561027837259101, | |
| "loss": 0.4627, | |
| "step": 1675 | |
| }, | |
| { | |
| "epoch": 0.9100642398286938, | |
| "grad_norm": 0.04208080843091011, | |
| "learning_rate": 0.00045461575065429454, | |
| "loss": 0.1095, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.9234475374732334, | |
| "grad_norm": 0.07704867422580719, | |
| "learning_rate": 0.00045312871758267906, | |
| "loss": 0.2484, | |
| "step": 1725 | |
| }, | |
| { | |
| "epoch": 0.936830835117773, | |
| "grad_norm": 9.084434509277344, | |
| "learning_rate": 0.0004516416845110635, | |
| "loss": 0.4368, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.9502141327623126, | |
| "grad_norm": 0.09450817853212357, | |
| "learning_rate": 0.000450154651439448, | |
| "loss": 0.2326, | |
| "step": 1775 | |
| }, | |
| { | |
| "epoch": 0.9635974304068522, | |
| "grad_norm": 0.27564939856529236, | |
| "learning_rate": 0.0004486676183678325, | |
| "loss": 0.5406, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.9769807280513919, | |
| "grad_norm": 0.1096988320350647, | |
| "learning_rate": 0.000447180585296217, | |
| "loss": 0.2194, | |
| "step": 1825 | |
| }, | |
| { | |
| "epoch": 0.9903640256959315, | |
| "grad_norm": 0.06793688237667084, | |
| "learning_rate": 0.0004456935522246015, | |
| "loss": 0.3206, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9325481798715204, | |
| "eval_auc": 0.8326772729757805, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.2235843539237976, | |
| "eval_precision": 0.0, | |
| "eval_recall": 0.0, | |
| "eval_runtime": 12.9282, | |
| "eval_samples_per_second": 72.245, | |
| "eval_steps_per_second": 18.1, | |
| "step": 1868 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 9340, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.01 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.894325812105011e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |