|
{ |
|
"best_metric": 0.1894965022802353, |
|
"best_model_checkpoint": "autotrain-8s6z2-1g2hg/checkpoint-32895", |
|
"epoch": 3.0, |
|
"eval_steps": 500, |
|
"global_step": 32895, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.05, |
|
"grad_norm": 3.4229037761688232, |
|
"learning_rate": 8.282674772036476e-06, |
|
"loss": 0.655, |
|
"step": 548 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"grad_norm": 2.956129789352417, |
|
"learning_rate": 1.661094224924012e-05, |
|
"loss": 0.5579, |
|
"step": 1096 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"grad_norm": 7.492773056030273, |
|
"learning_rate": 2.493920972644377e-05, |
|
"loss": 0.4886, |
|
"step": 1644 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"grad_norm": 9.447515487670898, |
|
"learning_rate": 3.326747720364742e-05, |
|
"loss": 0.4206, |
|
"step": 2192 |
|
}, |
|
{ |
|
"epoch": 0.25, |
|
"grad_norm": 10.904797554016113, |
|
"learning_rate": 4.158054711246201e-05, |
|
"loss": 0.4038, |
|
"step": 2740 |
|
}, |
|
{ |
|
"epoch": 0.3, |
|
"grad_norm": 8.469663619995117, |
|
"learning_rate": 4.9908814589665656e-05, |
|
"loss": 0.3769, |
|
"step": 3288 |
|
}, |
|
{ |
|
"epoch": 0.35, |
|
"grad_norm": 6.261867046356201, |
|
"learning_rate": 4.9086302989359904e-05, |
|
"loss": 0.3841, |
|
"step": 3836 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"grad_norm": 4.032571792602539, |
|
"learning_rate": 4.8160783651410236e-05, |
|
"loss": 0.3391, |
|
"step": 4384 |
|
}, |
|
{ |
|
"epoch": 0.45, |
|
"grad_norm": 48.33228302001953, |
|
"learning_rate": 4.723526431346057e-05, |
|
"loss": 0.3192, |
|
"step": 4932 |
|
}, |
|
{ |
|
"epoch": 0.5, |
|
"grad_norm": 4.632198810577393, |
|
"learning_rate": 4.630974497551089e-05, |
|
"loss": 0.3239, |
|
"step": 5480 |
|
}, |
|
{ |
|
"epoch": 0.55, |
|
"grad_norm": 2.5730295181274414, |
|
"learning_rate": 4.5384225637561225e-05, |
|
"loss": 0.3143, |
|
"step": 6028 |
|
}, |
|
{ |
|
"epoch": 0.6, |
|
"grad_norm": 3.378683090209961, |
|
"learning_rate": 4.446208410741429e-05, |
|
"loss": 0.3059, |
|
"step": 6576 |
|
}, |
|
{ |
|
"epoch": 0.65, |
|
"grad_norm": 10.585208892822266, |
|
"learning_rate": 4.353656476946462e-05, |
|
"loss": 0.2987, |
|
"step": 7124 |
|
}, |
|
{ |
|
"epoch": 0.7, |
|
"grad_norm": 16.021188735961914, |
|
"learning_rate": 4.261104543151495e-05, |
|
"loss": 0.2935, |
|
"step": 7672 |
|
}, |
|
{ |
|
"epoch": 0.75, |
|
"grad_norm": 2.585524797439575, |
|
"learning_rate": 4.168552609356528e-05, |
|
"loss": 0.292, |
|
"step": 8220 |
|
}, |
|
{ |
|
"epoch": 0.8, |
|
"grad_norm": 0.8300177454948425, |
|
"learning_rate": 4.0761695659516976e-05, |
|
"loss": 0.2746, |
|
"step": 8768 |
|
}, |
|
{ |
|
"epoch": 0.85, |
|
"grad_norm": 1.8167496919631958, |
|
"learning_rate": 3.9837865225468676e-05, |
|
"loss": 0.288, |
|
"step": 9316 |
|
}, |
|
{ |
|
"epoch": 0.9, |
|
"grad_norm": 14.431105613708496, |
|
"learning_rate": 3.8912345887519e-05, |
|
"loss": 0.3442, |
|
"step": 9864 |
|
}, |
|
{ |
|
"epoch": 0.95, |
|
"grad_norm": 4.341527462005615, |
|
"learning_rate": 3.798682654956933e-05, |
|
"loss": 0.2964, |
|
"step": 10412 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"grad_norm": 0.9708638191223145, |
|
"learning_rate": 3.706130721161966e-05, |
|
"loss": 0.2836, |
|
"step": 10960 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"eval_accuracy": 0.9091862559565882, |
|
"eval_auc": 0.9327717478336053, |
|
"eval_f1": 0.9394671651544857, |
|
"eval_loss": 0.26499995589256287, |
|
"eval_precision": 0.9356703902158447, |
|
"eval_recall": 0.9432948788378197, |
|
"eval_runtime": 90.2174, |
|
"eval_samples_per_second": 486.148, |
|
"eval_steps_per_second": 15.197, |
|
"step": 10965 |
|
}, |
|
{ |
|
"epoch": 1.05, |
|
"grad_norm": 10.155410766601562, |
|
"learning_rate": 3.613578787366999e-05, |
|
"loss": 0.2915, |
|
"step": 11508 |
|
}, |
|
{ |
|
"epoch": 1.1, |
|
"grad_norm": 13.481185913085938, |
|
"learning_rate": 3.521026853572032e-05, |
|
"loss": 0.2706, |
|
"step": 12056 |
|
}, |
|
{ |
|
"epoch": 1.15, |
|
"grad_norm": 11.898757934570312, |
|
"learning_rate": 3.428474919777065e-05, |
|
"loss": 0.2577, |
|
"step": 12604 |
|
}, |
|
{ |
|
"epoch": 1.2, |
|
"grad_norm": 102.29252624511719, |
|
"learning_rate": 3.336091876372234e-05, |
|
"loss": 0.2867, |
|
"step": 13152 |
|
}, |
|
{ |
|
"epoch": 1.25, |
|
"grad_norm": 0.8772763609886169, |
|
"learning_rate": 3.243539942577267e-05, |
|
"loss": 0.2543, |
|
"step": 13700 |
|
}, |
|
{ |
|
"epoch": 1.3, |
|
"grad_norm": 3.079983711242676, |
|
"learning_rate": 3.1509880087823005e-05, |
|
"loss": 0.2747, |
|
"step": 14248 |
|
}, |
|
{ |
|
"epoch": 1.35, |
|
"grad_norm": 2.654982805252075, |
|
"learning_rate": 3.058436074987334e-05, |
|
"loss": 0.2637, |
|
"step": 14796 |
|
}, |
|
{ |
|
"epoch": 1.4, |
|
"grad_norm": 8.28964900970459, |
|
"learning_rate": 2.9658841411923666e-05, |
|
"loss": 0.2433, |
|
"step": 15344 |
|
}, |
|
{ |
|
"epoch": 1.45, |
|
"grad_norm": 0.606247067451477, |
|
"learning_rate": 2.873669988177673e-05, |
|
"loss": 0.2496, |
|
"step": 15892 |
|
}, |
|
{ |
|
"epoch": 1.5, |
|
"grad_norm": 4.818925857543945, |
|
"learning_rate": 2.781118054382706e-05, |
|
"loss": 0.2344, |
|
"step": 16440 |
|
}, |
|
{ |
|
"epoch": 1.55, |
|
"grad_norm": 9.206971168518066, |
|
"learning_rate": 2.6885661205877388e-05, |
|
"loss": 0.224, |
|
"step": 16988 |
|
}, |
|
{ |
|
"epoch": 1.6, |
|
"grad_norm": 1.9517682790756226, |
|
"learning_rate": 2.5960141867927716e-05, |
|
"loss": 0.2115, |
|
"step": 17536 |
|
}, |
|
{ |
|
"epoch": 1.65, |
|
"grad_norm": 10.609549522399902, |
|
"learning_rate": 2.503462252997805e-05, |
|
"loss": 0.2102, |
|
"step": 18084 |
|
}, |
|
{ |
|
"epoch": 1.7, |
|
"grad_norm": 20.039274215698242, |
|
"learning_rate": 2.4109103192028377e-05, |
|
"loss": 0.2027, |
|
"step": 18632 |
|
}, |
|
{ |
|
"epoch": 1.75, |
|
"grad_norm": 2.285228729248047, |
|
"learning_rate": 2.3183583854078706e-05, |
|
"loss": 0.1995, |
|
"step": 19180 |
|
}, |
|
{ |
|
"epoch": 1.8, |
|
"grad_norm": 9.45280647277832, |
|
"learning_rate": 2.2258064516129034e-05, |
|
"loss": 0.2076, |
|
"step": 19728 |
|
}, |
|
{ |
|
"epoch": 1.85, |
|
"grad_norm": 8.692055702209473, |
|
"learning_rate": 2.1332545178179363e-05, |
|
"loss": 0.2075, |
|
"step": 20276 |
|
}, |
|
{ |
|
"epoch": 1.9, |
|
"grad_norm": 8.51143741607666, |
|
"learning_rate": 2.040871474413106e-05, |
|
"loss": 0.2097, |
|
"step": 20824 |
|
}, |
|
{ |
|
"epoch": 1.95, |
|
"grad_norm": 4.226066589355469, |
|
"learning_rate": 1.948319540618139e-05, |
|
"loss": 0.2153, |
|
"step": 21372 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"grad_norm": 3.73645281791687, |
|
"learning_rate": 1.855767606823172e-05, |
|
"loss": 0.2082, |
|
"step": 21920 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_accuracy": 0.9314621856403474, |
|
"eval_auc": 0.96886043230506, |
|
"eval_f1": 0.953925385487876, |
|
"eval_loss": 0.2151412069797516, |
|
"eval_precision": 0.9581845054809706, |
|
"eval_recall": 0.9497039614234267, |
|
"eval_runtime": 90.5052, |
|
"eval_samples_per_second": 484.602, |
|
"eval_steps_per_second": 15.148, |
|
"step": 21930 |
|
}, |
|
{ |
|
"epoch": 2.05, |
|
"grad_norm": 2.4432873725891113, |
|
"learning_rate": 1.763215673028205e-05, |
|
"loss": 0.1786, |
|
"step": 22468 |
|
}, |
|
{ |
|
"epoch": 2.1, |
|
"grad_norm": 0.6836100816726685, |
|
"learning_rate": 1.6708326296233746e-05, |
|
"loss": 0.1842, |
|
"step": 23016 |
|
}, |
|
{ |
|
"epoch": 2.15, |
|
"grad_norm": 2.6022326946258545, |
|
"learning_rate": 1.5784495862185442e-05, |
|
"loss": 0.1801, |
|
"step": 23564 |
|
}, |
|
{ |
|
"epoch": 2.2, |
|
"grad_norm": 1.9158451557159424, |
|
"learning_rate": 1.4858976524235771e-05, |
|
"loss": 0.1731, |
|
"step": 24112 |
|
}, |
|
{ |
|
"epoch": 2.25, |
|
"grad_norm": 7.503026485443115, |
|
"learning_rate": 1.39334571862861e-05, |
|
"loss": 0.1726, |
|
"step": 24660 |
|
}, |
|
{ |
|
"epoch": 2.3, |
|
"grad_norm": 3.1770987510681152, |
|
"learning_rate": 1.300793784833643e-05, |
|
"loss": 0.1771, |
|
"step": 25208 |
|
}, |
|
{ |
|
"epoch": 2.35, |
|
"grad_norm": 4.539430141448975, |
|
"learning_rate": 1.208241851038676e-05, |
|
"loss": 0.1551, |
|
"step": 25756 |
|
}, |
|
{ |
|
"epoch": 2.4, |
|
"grad_norm": 1.772599458694458, |
|
"learning_rate": 1.1156899172437089e-05, |
|
"loss": 0.1735, |
|
"step": 26304 |
|
}, |
|
{ |
|
"epoch": 2.45, |
|
"grad_norm": 3.809593439102173, |
|
"learning_rate": 1.023137983448742e-05, |
|
"loss": 0.1683, |
|
"step": 26852 |
|
}, |
|
{ |
|
"epoch": 2.5, |
|
"grad_norm": 10.1038179397583, |
|
"learning_rate": 9.307549400439116e-06, |
|
"loss": 0.1617, |
|
"step": 27400 |
|
}, |
|
{ |
|
"epoch": 2.55, |
|
"grad_norm": 18.696857452392578, |
|
"learning_rate": 8.382030062489445e-06, |
|
"loss": 0.1589, |
|
"step": 27948 |
|
}, |
|
{ |
|
"epoch": 2.6, |
|
"grad_norm": 15.82597827911377, |
|
"learning_rate": 7.4565107245397735e-06, |
|
"loss": 0.1636, |
|
"step": 28496 |
|
}, |
|
{ |
|
"epoch": 2.65, |
|
"grad_norm": 1.0566959381103516, |
|
"learning_rate": 6.530991386590103e-06, |
|
"loss": 0.1553, |
|
"step": 29044 |
|
}, |
|
{ |
|
"epoch": 2.7, |
|
"grad_norm": 13.043928146362305, |
|
"learning_rate": 5.6054720486404325e-06, |
|
"loss": 0.1532, |
|
"step": 29592 |
|
}, |
|
{ |
|
"epoch": 2.75, |
|
"grad_norm": 19.499807357788086, |
|
"learning_rate": 4.679952710690762e-06, |
|
"loss": 0.1426, |
|
"step": 30140 |
|
}, |
|
{ |
|
"epoch": 2.8, |
|
"grad_norm": 24.73866081237793, |
|
"learning_rate": 3.756122276642459e-06, |
|
"loss": 0.1514, |
|
"step": 30688 |
|
}, |
|
{ |
|
"epoch": 2.85, |
|
"grad_norm": 6.256073474884033, |
|
"learning_rate": 2.8306029386927886e-06, |
|
"loss": 0.1554, |
|
"step": 31236 |
|
}, |
|
{ |
|
"epoch": 2.9, |
|
"grad_norm": 0.34589943289756775, |
|
"learning_rate": 1.9050836007431179e-06, |
|
"loss": 0.1459, |
|
"step": 31784 |
|
}, |
|
{ |
|
"epoch": 2.95, |
|
"grad_norm": 2.303668737411499, |
|
"learning_rate": 9.795642627934472e-07, |
|
"loss": 0.1584, |
|
"step": 32332 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"grad_norm": 4.459900379180908, |
|
"learning_rate": 5.404492484377639e-08, |
|
"loss": 0.152, |
|
"step": 32880 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"eval_accuracy": 0.945028386420119, |
|
"eval_auc": 0.9812675754686511, |
|
"eval_f1": 0.9633213150168105, |
|
"eval_loss": 0.1894965022802353, |
|
"eval_precision": 0.9603846270512937, |
|
"eval_recall": 0.9662760178233535, |
|
"eval_runtime": 90.4032, |
|
"eval_samples_per_second": 485.149, |
|
"eval_steps_per_second": 15.165, |
|
"step": 32895 |
|
} |
|
], |
|
"logging_steps": 548, |
|
"max_steps": 32895, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 3, |
|
"save_steps": 500, |
|
"total_flos": 3.46191659978112e+16, |
|
"train_batch_size": 16, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|