| { | |
| "best_metric": 0.12031927704811096, | |
| "best_model_checkpoint": "Joseph-large-2024_09_16-batch-size32_epochs150_freeze/checkpoint-22113", | |
| "epoch": 91.0, | |
| "eval_steps": 500, | |
| "global_step": 24843, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.21656271656271656, | |
| "eval_f1_macro": 0.5384503258991854, | |
| "eval_f1_micro": 0.7477812526413659, | |
| "eval_loss": 0.17758780717849731, | |
| "eval_roc_auc": 0.8364480125638629, | |
| "eval_runtime": 594.1704, | |
| "eval_samples_per_second": 4.857, | |
| "eval_steps_per_second": 0.153, | |
| "learning_rate": 0.001, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 1.8315018315018317, | |
| "grad_norm": 0.2863590717315674, | |
| "learning_rate": 0.001, | |
| "loss": 0.2726, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.24532224532224534, | |
| "eval_f1_macro": 0.5760774961516321, | |
| "eval_f1_micro": 0.7697450182129848, | |
| "eval_loss": 0.153945192694664, | |
| "eval_roc_auc": 0.8447603712499155, | |
| "eval_runtime": 583.9253, | |
| "eval_samples_per_second": 4.942, | |
| "eval_steps_per_second": 0.156, | |
| "learning_rate": 0.001, | |
| "step": 546 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.2515592515592516, | |
| "eval_f1_macro": 0.6098114408992151, | |
| "eval_f1_micro": 0.7744839226208509, | |
| "eval_loss": 0.14735348522663116, | |
| "eval_roc_auc": 0.8447204921454395, | |
| "eval_runtime": 592.1092, | |
| "eval_samples_per_second": 4.874, | |
| "eval_steps_per_second": 0.154, | |
| "learning_rate": 0.001, | |
| "step": 819 | |
| }, | |
| { | |
| "epoch": 3.663003663003663, | |
| "grad_norm": 0.24709707498550415, | |
| "learning_rate": 0.001, | |
| "loss": 0.1701, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.25363825363825365, | |
| "eval_f1_macro": 0.6213514572326843, | |
| "eval_f1_micro": 0.7738915615654661, | |
| "eval_loss": 0.14645476639270782, | |
| "eval_roc_auc": 0.8440185501551167, | |
| "eval_runtime": 589.7047, | |
| "eval_samples_per_second": 4.894, | |
| "eval_steps_per_second": 0.154, | |
| "learning_rate": 0.001, | |
| "step": 1092 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.25017325017325015, | |
| "eval_f1_macro": 0.6353051230272125, | |
| "eval_f1_micro": 0.78146492434663, | |
| "eval_loss": 0.14515458047389984, | |
| "eval_roc_auc": 0.850253359073442, | |
| "eval_runtime": 596.3244, | |
| "eval_samples_per_second": 4.84, | |
| "eval_steps_per_second": 0.153, | |
| "learning_rate": 0.001, | |
| "step": 1365 | |
| }, | |
| { | |
| "epoch": 5.4945054945054945, | |
| "grad_norm": 0.24183644354343414, | |
| "learning_rate": 0.001, | |
| "loss": 0.1622, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.2577962577962578, | |
| "eval_f1_macro": 0.6141782571643486, | |
| "eval_f1_micro": 0.781259480778399, | |
| "eval_loss": 0.1445809006690979, | |
| "eval_roc_auc": 0.8479418733548026, | |
| "eval_runtime": 590.8762, | |
| "eval_samples_per_second": 4.884, | |
| "eval_steps_per_second": 0.154, | |
| "learning_rate": 0.001, | |
| "step": 1638 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.26195426195426197, | |
| "eval_f1_macro": 0.6232727577909734, | |
| "eval_f1_micro": 0.7800943800943801, | |
| "eval_loss": 0.14445114135742188, | |
| "eval_roc_auc": 0.8500464116049401, | |
| "eval_runtime": 601.2858, | |
| "eval_samples_per_second": 4.8, | |
| "eval_steps_per_second": 0.151, | |
| "learning_rate": 0.001, | |
| "step": 1911 | |
| }, | |
| { | |
| "epoch": 7.326007326007326, | |
| "grad_norm": 0.2069859653711319, | |
| "learning_rate": 0.001, | |
| "loss": 0.159, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.25848925848925847, | |
| "eval_f1_macro": 0.6339480584029394, | |
| "eval_f1_micro": 0.7879197465681098, | |
| "eval_loss": 0.14366209506988525, | |
| "eval_roc_auc": 0.8585186757078976, | |
| "eval_runtime": 584.2361, | |
| "eval_samples_per_second": 4.94, | |
| "eval_steps_per_second": 0.156, | |
| "learning_rate": 0.001, | |
| "step": 2184 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.2577962577962578, | |
| "eval_f1_macro": 0.6442804243684905, | |
| "eval_f1_micro": 0.785476860138072, | |
| "eval_loss": 0.1447097659111023, | |
| "eval_roc_auc": 0.8547549628224266, | |
| "eval_runtime": 597.754, | |
| "eval_samples_per_second": 4.828, | |
| "eval_steps_per_second": 0.152, | |
| "learning_rate": 0.001, | |
| "step": 2457 | |
| }, | |
| { | |
| "epoch": 9.157509157509157, | |
| "grad_norm": 0.2012098729610443, | |
| "learning_rate": 0.001, | |
| "loss": 0.1563, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.2442827442827443, | |
| "eval_f1_macro": 0.6149084687726756, | |
| "eval_f1_micro": 0.7683399403144626, | |
| "eval_loss": 0.1538563072681427, | |
| "eval_roc_auc": 0.8340795854397406, | |
| "eval_runtime": 582.8083, | |
| "eval_samples_per_second": 4.952, | |
| "eval_steps_per_second": 0.156, | |
| "learning_rate": 0.001, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 10.989010989010989, | |
| "grad_norm": 0.1713365614414215, | |
| "learning_rate": 0.001, | |
| "loss": 0.1558, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.26334026334026334, | |
| "eval_f1_macro": 0.6334773464226039, | |
| "eval_f1_micro": 0.7896514859952961, | |
| "eval_loss": 0.1389196366071701, | |
| "eval_roc_auc": 0.8560665869710553, | |
| "eval_runtime": 581.0367, | |
| "eval_samples_per_second": 4.967, | |
| "eval_steps_per_second": 0.157, | |
| "learning_rate": 0.001, | |
| "step": 3003 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.26403326403326405, | |
| "eval_f1_macro": 0.6406158966836866, | |
| "eval_f1_micro": 0.7908438442264407, | |
| "eval_loss": 0.1395249217748642, | |
| "eval_roc_auc": 0.8586128939486779, | |
| "eval_runtime": 577.8577, | |
| "eval_samples_per_second": 4.994, | |
| "eval_steps_per_second": 0.157, | |
| "learning_rate": 0.001, | |
| "step": 3276 | |
| }, | |
| { | |
| "epoch": 12.820512820512821, | |
| "grad_norm": 0.1511967033147812, | |
| "learning_rate": 0.001, | |
| "loss": 0.155, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.26507276507276506, | |
| "eval_f1_macro": 0.6557265830014797, | |
| "eval_f1_micro": 0.7893533497260687, | |
| "eval_loss": 0.1390257179737091, | |
| "eval_roc_auc": 0.8535165777960444, | |
| "eval_runtime": 583.6052, | |
| "eval_samples_per_second": 4.945, | |
| "eval_steps_per_second": 0.156, | |
| "learning_rate": 0.001, | |
| "step": 3549 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.2623007623007623, | |
| "eval_f1_macro": 0.640540413256037, | |
| "eval_f1_micro": 0.787792943600309, | |
| "eval_loss": 0.13910652697086334, | |
| "eval_roc_auc": 0.8540478028799876, | |
| "eval_runtime": 575.9469, | |
| "eval_samples_per_second": 5.011, | |
| "eval_steps_per_second": 0.158, | |
| "learning_rate": 0.001, | |
| "step": 3822 | |
| }, | |
| { | |
| "epoch": 14.652014652014651, | |
| "grad_norm": 0.17730183899402618, | |
| "learning_rate": 0.001, | |
| "loss": 0.154, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.253984753984754, | |
| "eval_f1_macro": 0.6406412255611948, | |
| "eval_f1_micro": 0.7885381419454319, | |
| "eval_loss": 0.13990363478660583, | |
| "eval_roc_auc": 0.8550214137243141, | |
| "eval_runtime": 589.3337, | |
| "eval_samples_per_second": 4.897, | |
| "eval_steps_per_second": 0.154, | |
| "learning_rate": 0.001, | |
| "step": 4095 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.2668052668052668, | |
| "eval_f1_macro": 0.6374513053376879, | |
| "eval_f1_micro": 0.7847859161051945, | |
| "eval_loss": 0.13938209414482117, | |
| "eval_roc_auc": 0.8490304535245456, | |
| "eval_runtime": 577.6041, | |
| "eval_samples_per_second": 4.997, | |
| "eval_steps_per_second": 0.158, | |
| "learning_rate": 0.001, | |
| "step": 4368 | |
| }, | |
| { | |
| "epoch": 16.483516483516482, | |
| "grad_norm": 0.16627363860607147, | |
| "learning_rate": 0.001, | |
| "loss": 0.1527, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.24185724185724186, | |
| "eval_f1_macro": 0.6424904129432089, | |
| "eval_f1_micro": 0.7857319587628866, | |
| "eval_loss": 0.15936270356178284, | |
| "eval_roc_auc": 0.8640092624686252, | |
| "eval_runtime": 582.0471, | |
| "eval_samples_per_second": 4.958, | |
| "eval_steps_per_second": 0.156, | |
| "learning_rate": 0.001, | |
| "step": 4641 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.27546777546777546, | |
| "eval_f1_macro": 0.6768028620378452, | |
| "eval_f1_micro": 0.8036556603773585, | |
| "eval_loss": 0.13188092410564423, | |
| "eval_roc_auc": 0.8679473273890709, | |
| "eval_runtime": 578.2193, | |
| "eval_samples_per_second": 4.991, | |
| "eval_steps_per_second": 0.157, | |
| "learning_rate": 0.0001, | |
| "step": 4914 | |
| }, | |
| { | |
| "epoch": 18.315018315018314, | |
| "grad_norm": 0.17489519715309143, | |
| "learning_rate": 0.0001, | |
| "loss": 0.149, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.27893277893277896, | |
| "eval_f1_macro": 0.6715138701269487, | |
| "eval_f1_micro": 0.8038422649140546, | |
| "eval_loss": 0.13244545459747314, | |
| "eval_roc_auc": 0.8679532160291196, | |
| "eval_runtime": 573.231, | |
| "eval_samples_per_second": 5.035, | |
| "eval_steps_per_second": 0.159, | |
| "learning_rate": 0.0001, | |
| "step": 5187 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.27893277893277896, | |
| "eval_f1_macro": 0.6733647561041333, | |
| "eval_f1_micro": 0.8066104665720725, | |
| "eval_loss": 0.1306440383195877, | |
| "eval_roc_auc": 0.8722063701403293, | |
| "eval_runtime": 585.8615, | |
| "eval_samples_per_second": 4.926, | |
| "eval_steps_per_second": 0.155, | |
| "learning_rate": 0.0001, | |
| "step": 5460 | |
| }, | |
| { | |
| "epoch": 20.146520146520146, | |
| "grad_norm": 0.15949666500091553, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1412, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.2817047817047817, | |
| "eval_f1_macro": 0.6728395801753237, | |
| "eval_f1_micro": 0.8037271837637748, | |
| "eval_loss": 0.1302667111158371, | |
| "eval_roc_auc": 0.8650841471907833, | |
| "eval_runtime": 573.2529, | |
| "eval_samples_per_second": 5.034, | |
| "eval_steps_per_second": 0.159, | |
| "learning_rate": 0.0001, | |
| "step": 5733 | |
| }, | |
| { | |
| "epoch": 21.978021978021978, | |
| "grad_norm": 0.1902228742837906, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1385, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.2841302841302841, | |
| "eval_f1_macro": 0.6735047356746011, | |
| "eval_f1_micro": 0.8074214632089395, | |
| "eval_loss": 0.12870918214321136, | |
| "eval_roc_auc": 0.869659164440877, | |
| "eval_runtime": 581.2149, | |
| "eval_samples_per_second": 4.965, | |
| "eval_steps_per_second": 0.157, | |
| "learning_rate": 0.0001, | |
| "step": 6006 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.2841302841302841, | |
| "eval_f1_macro": 0.678520497542563, | |
| "eval_f1_micro": 0.8058198574902932, | |
| "eval_loss": 0.1287251114845276, | |
| "eval_roc_auc": 0.8654212081182214, | |
| "eval_runtime": 576.7801, | |
| "eval_samples_per_second": 5.004, | |
| "eval_steps_per_second": 0.158, | |
| "learning_rate": 0.0001, | |
| "step": 6279 | |
| }, | |
| { | |
| "epoch": 23.80952380952381, | |
| "grad_norm": 0.20738890767097473, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1377, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.2869022869022869, | |
| "eval_f1_macro": 0.6840871439155845, | |
| "eval_f1_micro": 0.8057504997660669, | |
| "eval_loss": 0.1279863715171814, | |
| "eval_roc_auc": 0.8662783338824032, | |
| "eval_runtime": 580.6409, | |
| "eval_samples_per_second": 4.97, | |
| "eval_steps_per_second": 0.157, | |
| "learning_rate": 0.0001, | |
| "step": 6552 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.28586278586278585, | |
| "eval_f1_macro": 0.6787317976982782, | |
| "eval_f1_micro": 0.8074392712550608, | |
| "eval_loss": 0.127402663230896, | |
| "eval_roc_auc": 0.8696325247161917, | |
| "eval_runtime": 571.2341, | |
| "eval_samples_per_second": 5.052, | |
| "eval_steps_per_second": 0.159, | |
| "learning_rate": 0.0001, | |
| "step": 6825 | |
| }, | |
| { | |
| "epoch": 25.641025641025642, | |
| "grad_norm": 0.18043966591358185, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1361, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.28586278586278585, | |
| "eval_f1_macro": 0.6740298841901063, | |
| "eval_f1_micro": 0.8063818050664064, | |
| "eval_loss": 0.12828372418880463, | |
| "eval_roc_auc": 0.8672987185031534, | |
| "eval_runtime": 580.3575, | |
| "eval_samples_per_second": 4.973, | |
| "eval_steps_per_second": 0.157, | |
| "learning_rate": 0.0001, | |
| "step": 7098 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.2882882882882883, | |
| "eval_f1_macro": 0.68897744745899, | |
| "eval_f1_micro": 0.8110456615281781, | |
| "eval_loss": 0.12681305408477783, | |
| "eval_roc_auc": 0.8743537519356053, | |
| "eval_runtime": 580.6984, | |
| "eval_samples_per_second": 4.97, | |
| "eval_steps_per_second": 0.157, | |
| "learning_rate": 0.0001, | |
| "step": 7371 | |
| }, | |
| { | |
| "epoch": 27.47252747252747, | |
| "grad_norm": 0.17303021252155304, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1354, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.28932778932778935, | |
| "eval_f1_macro": 0.6812786729949134, | |
| "eval_f1_micro": 0.8099940913311386, | |
| "eval_loss": 0.12666279077529907, | |
| "eval_roc_auc": 0.8708112319303257, | |
| "eval_runtime": 576.4341, | |
| "eval_samples_per_second": 5.007, | |
| "eval_steps_per_second": 0.158, | |
| "learning_rate": 0.0001, | |
| "step": 7644 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.29175329175329173, | |
| "eval_f1_macro": 0.6881122302734826, | |
| "eval_f1_micro": 0.8081058020477816, | |
| "eval_loss": 0.12675043940544128, | |
| "eval_roc_auc": 0.8666940799181009, | |
| "eval_runtime": 578.6537, | |
| "eval_samples_per_second": 4.987, | |
| "eval_steps_per_second": 0.157, | |
| "learning_rate": 0.0001, | |
| "step": 7917 | |
| }, | |
| { | |
| "epoch": 29.304029304029303, | |
| "grad_norm": 0.17676015198230743, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1339, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.2927927927927928, | |
| "eval_f1_macro": 0.6872571297964245, | |
| "eval_f1_micro": 0.8108657880239013, | |
| "eval_loss": 0.12635387480258942, | |
| "eval_roc_auc": 0.8701037366439205, | |
| "eval_runtime": 582.8932, | |
| "eval_samples_per_second": 4.951, | |
| "eval_steps_per_second": 0.156, | |
| "learning_rate": 0.0001, | |
| "step": 8190 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_accuracy": 0.29140679140679143, | |
| "eval_f1_macro": 0.6823767206574823, | |
| "eval_f1_micro": 0.8089332139965051, | |
| "eval_loss": 0.1258317530155182, | |
| "eval_roc_auc": 0.867421427567313, | |
| "eval_runtime": 578.6563, | |
| "eval_samples_per_second": 4.987, | |
| "eval_steps_per_second": 0.157, | |
| "learning_rate": 0.0001, | |
| "step": 8463 | |
| }, | |
| { | |
| "epoch": 31.135531135531135, | |
| "grad_norm": 0.19538064301013947, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1332, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.29313929313929316, | |
| "eval_f1_macro": 0.6924178674344362, | |
| "eval_f1_micro": 0.8112645318336341, | |
| "eval_loss": 0.1260402798652649, | |
| "eval_roc_auc": 0.8731307927316745, | |
| "eval_runtime": 588.1542, | |
| "eval_samples_per_second": 4.907, | |
| "eval_steps_per_second": 0.155, | |
| "learning_rate": 0.0001, | |
| "step": 8736 | |
| }, | |
| { | |
| "epoch": 32.967032967032964, | |
| "grad_norm": 0.20809406042099, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1321, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_accuracy": 0.2910602910602911, | |
| "eval_f1_macro": 0.6959916792345996, | |
| "eval_f1_micro": 0.8133097762073027, | |
| "eval_loss": 0.1250443458557129, | |
| "eval_roc_auc": 0.8735809182308003, | |
| "eval_runtime": 593.1758, | |
| "eval_samples_per_second": 4.865, | |
| "eval_steps_per_second": 0.153, | |
| "learning_rate": 0.0001, | |
| "step": 9009 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.29417879417879417, | |
| "eval_f1_macro": 0.6891130310994343, | |
| "eval_f1_micro": 0.8116187492060803, | |
| "eval_loss": 0.12511762976646423, | |
| "eval_roc_auc": 0.8707582878249215, | |
| "eval_runtime": 596.9449, | |
| "eval_samples_per_second": 4.835, | |
| "eval_steps_per_second": 0.152, | |
| "learning_rate": 0.0001, | |
| "step": 9282 | |
| }, | |
| { | |
| "epoch": 34.798534798534796, | |
| "grad_norm": 0.23537498712539673, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1309, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_accuracy": 0.2955647955647956, | |
| "eval_f1_macro": 0.6945448365895581, | |
| "eval_f1_micro": 0.8124288545048274, | |
| "eval_loss": 0.12488266825675964, | |
| "eval_roc_auc": 0.8724487031041583, | |
| "eval_runtime": 587.4735, | |
| "eval_samples_per_second": 4.913, | |
| "eval_steps_per_second": 0.155, | |
| "learning_rate": 0.0001, | |
| "step": 9555 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.29417879417879417, | |
| "eval_f1_macro": 0.6971439978031583, | |
| "eval_f1_micro": 0.8115410842141152, | |
| "eval_loss": 0.1252983808517456, | |
| "eval_roc_auc": 0.8688457809436633, | |
| "eval_runtime": 588.3939, | |
| "eval_samples_per_second": 4.905, | |
| "eval_steps_per_second": 0.155, | |
| "learning_rate": 0.0001, | |
| "step": 9828 | |
| }, | |
| { | |
| "epoch": 36.63003663003663, | |
| "grad_norm": 0.2208484709262848, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1305, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_accuracy": 0.29521829521829523, | |
| "eval_f1_macro": 0.6961006786941204, | |
| "eval_f1_micro": 0.8116249469664828, | |
| "eval_loss": 0.12479764968156815, | |
| "eval_roc_auc": 0.870187076326433, | |
| "eval_runtime": 588.2172, | |
| "eval_samples_per_second": 4.906, | |
| "eval_steps_per_second": 0.155, | |
| "learning_rate": 0.0001, | |
| "step": 10101 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.3004158004158004, | |
| "eval_f1_macro": 0.6991177533793484, | |
| "eval_f1_micro": 0.8129930394431555, | |
| "eval_loss": 0.12497606873512268, | |
| "eval_roc_auc": 0.8725859392689393, | |
| "eval_runtime": 593.6086, | |
| "eval_samples_per_second": 4.862, | |
| "eval_steps_per_second": 0.153, | |
| "learning_rate": 0.0001, | |
| "step": 10374 | |
| }, | |
| { | |
| "epoch": 38.46153846153846, | |
| "grad_norm": 0.27702799439430237, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1285, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_accuracy": 0.29521829521829523, | |
| "eval_f1_macro": 0.6970545191351545, | |
| "eval_f1_micro": 0.8141541282874172, | |
| "eval_loss": 0.1252022236585617, | |
| "eval_roc_auc": 0.8767588388621269, | |
| "eval_runtime": 586.6264, | |
| "eval_samples_per_second": 4.92, | |
| "eval_steps_per_second": 0.155, | |
| "learning_rate": 0.0001, | |
| "step": 10647 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.2955647955647956, | |
| "eval_f1_macro": 0.7070171403235663, | |
| "eval_f1_micro": 0.816655585106383, | |
| "eval_loss": 0.12485132366418839, | |
| "eval_roc_auc": 0.8790201839509206, | |
| "eval_runtime": 586.1423, | |
| "eval_samples_per_second": 4.924, | |
| "eval_steps_per_second": 0.155, | |
| "learning_rate": 0.0001, | |
| "step": 10920 | |
| }, | |
| { | |
| "epoch": 40.29304029304029, | |
| "grad_norm": 0.24468237161636353, | |
| "learning_rate": 0.0001, | |
| "loss": 0.129, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_accuracy": 0.28967428967428965, | |
| "eval_f1_macro": 0.6961881266838973, | |
| "eval_f1_micro": 0.8103573101656658, | |
| "eval_loss": 0.12500154972076416, | |
| "eval_roc_auc": 0.8684120872988876, | |
| "eval_runtime": 589.4017, | |
| "eval_samples_per_second": 4.896, | |
| "eval_steps_per_second": 0.154, | |
| "learning_rate": 0.0001, | |
| "step": 11193 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.3038808038808039, | |
| "eval_f1_macro": 0.7064304960359926, | |
| "eval_f1_micro": 0.816535301022975, | |
| "eval_loss": 0.12350151687860489, | |
| "eval_roc_auc": 0.8763375931853813, | |
| "eval_runtime": 591.1388, | |
| "eval_samples_per_second": 4.882, | |
| "eval_steps_per_second": 0.154, | |
| "learning_rate": 0.0001, | |
| "step": 11466 | |
| }, | |
| { | |
| "epoch": 42.124542124542124, | |
| "grad_norm": 0.29772019386291504, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1277, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_accuracy": 0.2955647955647956, | |
| "eval_f1_macro": 0.7047254887418923, | |
| "eval_f1_micro": 0.8150093808630394, | |
| "eval_loss": 0.12367021292448044, | |
| "eval_roc_auc": 0.8771339814503815, | |
| "eval_runtime": 597.1526, | |
| "eval_samples_per_second": 4.833, | |
| "eval_steps_per_second": 0.152, | |
| "learning_rate": 0.0001, | |
| "step": 11739 | |
| }, | |
| { | |
| "epoch": 43.956043956043956, | |
| "grad_norm": 0.32455483078956604, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1279, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.30076230076230076, | |
| "eval_f1_macro": 0.705396366545505, | |
| "eval_f1_micro": 0.8170209225905745, | |
| "eval_loss": 0.12371324002742767, | |
| "eval_roc_auc": 0.8789390307110687, | |
| "eval_runtime": 618.592, | |
| "eval_samples_per_second": 4.665, | |
| "eval_steps_per_second": 0.147, | |
| "learning_rate": 0.0001, | |
| "step": 12012 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_accuracy": 0.30145530145530147, | |
| "eval_f1_macro": 0.7058009223379548, | |
| "eval_f1_micro": 0.8163231034048448, | |
| "eval_loss": 0.12333343178033829, | |
| "eval_roc_auc": 0.8758137724962146, | |
| "eval_runtime": 593.5671, | |
| "eval_samples_per_second": 4.862, | |
| "eval_steps_per_second": 0.153, | |
| "learning_rate": 0.0001, | |
| "step": 12285 | |
| }, | |
| { | |
| "epoch": 45.78754578754579, | |
| "grad_norm": 0.2913854718208313, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1264, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 0.30076230076230076, | |
| "eval_f1_macro": 0.6992655670184796, | |
| "eval_f1_micro": 0.8158692722371967, | |
| "eval_loss": 0.12297776341438293, | |
| "eval_roc_auc": 0.8746400552002995, | |
| "eval_runtime": 597.9766, | |
| "eval_samples_per_second": 4.826, | |
| "eval_steps_per_second": 0.152, | |
| "learning_rate": 0.0001, | |
| "step": 12558 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_accuracy": 0.29902979902979904, | |
| "eval_f1_macro": 0.7026416067016249, | |
| "eval_f1_micro": 0.8135392426486143, | |
| "eval_loss": 0.12366960942745209, | |
| "eval_roc_auc": 0.8720258880176504, | |
| "eval_runtime": 608.7312, | |
| "eval_samples_per_second": 4.741, | |
| "eval_steps_per_second": 0.149, | |
| "learning_rate": 0.0001, | |
| "step": 12831 | |
| }, | |
| { | |
| "epoch": 47.61904761904762, | |
| "grad_norm": 0.2678842842578888, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1267, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.30180180180180183, | |
| "eval_f1_macro": 0.7044430417074125, | |
| "eval_f1_micro": 0.8169049621530698, | |
| "eval_loss": 0.12326876819133759, | |
| "eval_roc_auc": 0.8756520830494087, | |
| "eval_runtime": 581.2988, | |
| "eval_samples_per_second": 4.965, | |
| "eval_steps_per_second": 0.157, | |
| "learning_rate": 0.0001, | |
| "step": 13104 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_accuracy": 0.30214830214830213, | |
| "eval_f1_macro": 0.705026725915288, | |
| "eval_f1_micro": 0.8161126713333613, | |
| "eval_loss": 0.12315386533737183, | |
| "eval_roc_auc": 0.8761665945900701, | |
| "eval_runtime": 586.6485, | |
| "eval_samples_per_second": 4.919, | |
| "eval_steps_per_second": 0.155, | |
| "learning_rate": 0.0001, | |
| "step": 13377 | |
| }, | |
| { | |
| "epoch": 49.45054945054945, | |
| "grad_norm": 0.31903648376464844, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1249, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 0.30145530145530147, | |
| "eval_f1_macro": 0.7085649491291086, | |
| "eval_f1_micro": 0.8179686845851126, | |
| "eval_loss": 0.12265044450759888, | |
| "eval_roc_auc": 0.877547259354487, | |
| "eval_runtime": 581.1034, | |
| "eval_samples_per_second": 4.966, | |
| "eval_steps_per_second": 0.157, | |
| "learning_rate": 0.0001, | |
| "step": 13650 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_accuracy": 0.30214830214830213, | |
| "eval_f1_macro": 0.710831288086539, | |
| "eval_f1_micro": 0.8190420609445996, | |
| "eval_loss": 0.12310674786567688, | |
| "eval_roc_auc": 0.87941579593488, | |
| "eval_runtime": 606.1273, | |
| "eval_samples_per_second": 4.761, | |
| "eval_steps_per_second": 0.15, | |
| "learning_rate": 0.0001, | |
| "step": 13923 | |
| }, | |
| { | |
| "epoch": 51.282051282051285, | |
| "grad_norm": 0.26118701696395874, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1243, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.30214830214830213, | |
| "eval_f1_macro": 0.704117146056294, | |
| "eval_f1_micro": 0.816390260370511, | |
| "eval_loss": 0.12280686944723129, | |
| "eval_roc_auc": 0.8743457841629654, | |
| "eval_runtime": 611.1334, | |
| "eval_samples_per_second": 4.722, | |
| "eval_steps_per_second": 0.149, | |
| "learning_rate": 0.0001, | |
| "step": 14196 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_accuracy": 0.3038808038808039, | |
| "eval_f1_macro": 0.7080185810697228, | |
| "eval_f1_micro": 0.8189015751312609, | |
| "eval_loss": 0.1225290596485138, | |
| "eval_roc_auc": 0.8794495583654101, | |
| "eval_runtime": 586.3165, | |
| "eval_samples_per_second": 4.922, | |
| "eval_steps_per_second": 0.155, | |
| "learning_rate": 0.0001, | |
| "step": 14469 | |
| }, | |
| { | |
| "epoch": 53.11355311355312, | |
| "grad_norm": 0.24176084995269775, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1248, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_accuracy": 0.30180180180180183, | |
| "eval_f1_macro": 0.7053875588266636, | |
| "eval_f1_micro": 0.8162527837304089, | |
| "eval_loss": 0.12376156449317932, | |
| "eval_roc_auc": 0.8755284752634194, | |
| "eval_runtime": 590.1707, | |
| "eval_samples_per_second": 4.89, | |
| "eval_steps_per_second": 0.154, | |
| "learning_rate": 0.0001, | |
| "step": 14742 | |
| }, | |
| { | |
| "epoch": 54.94505494505494, | |
| "grad_norm": 0.3652552366256714, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1233, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "eval_accuracy": 0.30284130284130284, | |
| "eval_f1_macro": 0.7092508494713976, | |
| "eval_f1_micro": 0.818075117370892, | |
| "eval_loss": 0.12211860716342926, | |
| "eval_roc_auc": 0.8772347053641084, | |
| "eval_runtime": 591.2857, | |
| "eval_samples_per_second": 4.881, | |
| "eval_steps_per_second": 0.154, | |
| "learning_rate": 0.0001, | |
| "step": 15015 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.3049203049203049, | |
| "eval_f1_macro": 0.7091508009521661, | |
| "eval_f1_micro": 0.818769689935334, | |
| "eval_loss": 0.12255053967237473, | |
| "eval_roc_auc": 0.8809376807503978, | |
| "eval_runtime": 619.809, | |
| "eval_samples_per_second": 4.656, | |
| "eval_steps_per_second": 0.147, | |
| "learning_rate": 0.0001, | |
| "step": 15288 | |
| }, | |
| { | |
| "epoch": 56.776556776556774, | |
| "grad_norm": 0.2984638214111328, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1237, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "eval_accuracy": 0.3052668052668053, | |
| "eval_f1_macro": 0.7056269081565454, | |
| "eval_f1_micro": 0.8183564389510606, | |
| "eval_loss": 0.12233822792768478, | |
| "eval_roc_auc": 0.8785286099375562, | |
| "eval_runtime": 613.5916, | |
| "eval_samples_per_second": 4.703, | |
| "eval_steps_per_second": 0.148, | |
| "learning_rate": 0.0001, | |
| "step": 15561 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_accuracy": 0.30284130284130284, | |
| "eval_f1_macro": 0.7093876090831799, | |
| "eval_f1_micro": 0.8179678964618875, | |
| "eval_loss": 0.12230789661407471, | |
| "eval_roc_auc": 0.8764581158068805, | |
| "eval_runtime": 607.5944, | |
| "eval_samples_per_second": 4.75, | |
| "eval_steps_per_second": 0.15, | |
| "learning_rate": 0.0001, | |
| "step": 15834 | |
| }, | |
| { | |
| "epoch": 58.608058608058606, | |
| "grad_norm": 0.2825208604335785, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1234, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "eval_accuracy": 0.30734580734580735, | |
| "eval_f1_macro": 0.7102428483836337, | |
| "eval_f1_micro": 0.8198051269184126, | |
| "eval_loss": 0.12226579338312149, | |
| "eval_roc_auc": 0.8788947787212716, | |
| "eval_runtime": 579.6776, | |
| "eval_samples_per_second": 4.979, | |
| "eval_steps_per_second": 0.157, | |
| "learning_rate": 0.0001, | |
| "step": 16107 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_accuracy": 0.29799029799029797, | |
| "eval_f1_macro": 0.7068409531794828, | |
| "eval_f1_micro": 0.8173416232565955, | |
| "eval_loss": 0.1236739531159401, | |
| "eval_roc_auc": 0.8761882980515712, | |
| "eval_runtime": 577.7976, | |
| "eval_samples_per_second": 4.995, | |
| "eval_steps_per_second": 0.157, | |
| "learning_rate": 0.0001, | |
| "step": 16380 | |
| }, | |
| { | |
| "epoch": 60.43956043956044, | |
| "grad_norm": 0.313997745513916, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1232, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 61.0, | |
| "eval_accuracy": 0.305959805959806, | |
| "eval_f1_macro": 0.7139384635953806, | |
| "eval_f1_micro": 0.8201011747982775, | |
| "eval_loss": 0.12236195057630539, | |
| "eval_roc_auc": 0.8791326851447451, | |
| "eval_runtime": 576.7269, | |
| "eval_samples_per_second": 5.004, | |
| "eval_steps_per_second": 0.158, | |
| "learning_rate": 0.0001, | |
| "step": 16653 | |
| }, | |
| { | |
| "epoch": 62.0, | |
| "eval_accuracy": 0.30284130284130284, | |
| "eval_f1_macro": 0.7188990083298508, | |
| "eval_f1_micro": 0.8209334277030684, | |
| "eval_loss": 0.12215279042720795, | |
| "eval_roc_auc": 0.8808361117698756, | |
| "eval_runtime": 585.2414, | |
| "eval_samples_per_second": 4.931, | |
| "eval_steps_per_second": 0.155, | |
| "learning_rate": 1e-05, | |
| "step": 16926 | |
| }, | |
| { | |
| "epoch": 62.27106227106227, | |
| "grad_norm": 0.322051465511322, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1204, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 63.0, | |
| "eval_accuracy": 0.3097713097713098, | |
| "eval_f1_macro": 0.7190866276619315, | |
| "eval_f1_micro": 0.820752746564184, | |
| "eval_loss": 0.12084941565990448, | |
| "eval_roc_auc": 0.8797410795822204, | |
| "eval_runtime": 586.6749, | |
| "eval_samples_per_second": 4.919, | |
| "eval_steps_per_second": 0.155, | |
| "learning_rate": 1e-05, | |
| "step": 17199 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "eval_accuracy": 0.3108108108108108, | |
| "eval_f1_macro": 0.7187730185556146, | |
| "eval_f1_micro": 0.8218151540383014, | |
| "eval_loss": 0.12093428522348404, | |
| "eval_roc_auc": 0.8813373302757117, | |
| "eval_runtime": 589.1584, | |
| "eval_samples_per_second": 4.899, | |
| "eval_steps_per_second": 0.154, | |
| "learning_rate": 1e-05, | |
| "step": 17472 | |
| }, | |
| { | |
| "epoch": 64.1025641025641, | |
| "grad_norm": 0.32896944880485535, | |
| "learning_rate": 1e-05, | |
| "loss": 0.12, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 65.0, | |
| "eval_accuracy": 0.30803880803880807, | |
| "eval_f1_macro": 0.7186584702198188, | |
| "eval_f1_micro": 0.8209837715435904, | |
| "eval_loss": 0.12085793167352676, | |
| "eval_roc_auc": 0.8787241154699269, | |
| "eval_runtime": 587.8337, | |
| "eval_samples_per_second": 4.91, | |
| "eval_steps_per_second": 0.155, | |
| "learning_rate": 1e-05, | |
| "step": 17745 | |
| }, | |
| { | |
| "epoch": 65.93406593406593, | |
| "grad_norm": 0.3432726263999939, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1187, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 66.0, | |
| "eval_accuracy": 0.3135828135828136, | |
| "eval_f1_macro": 0.7185770967712465, | |
| "eval_f1_micro": 0.8215507887488523, | |
| "eval_loss": 0.12076118588447571, | |
| "eval_roc_auc": 0.8804684272314324, | |
| "eval_runtime": 588.6607, | |
| "eval_samples_per_second": 4.903, | |
| "eval_steps_per_second": 0.155, | |
| "learning_rate": 1e-05, | |
| "step": 18018 | |
| }, | |
| { | |
| "epoch": 67.0, | |
| "eval_accuracy": 0.31115731115731116, | |
| "eval_f1_macro": 0.7239469969506999, | |
| "eval_f1_micro": 0.8232429532417151, | |
| "eval_loss": 0.1210499182343483, | |
| "eval_roc_auc": 0.8847649346106092, | |
| "eval_runtime": 591.9527, | |
| "eval_samples_per_second": 4.875, | |
| "eval_steps_per_second": 0.154, | |
| "learning_rate": 1e-05, | |
| "step": 18291 | |
| }, | |
| { | |
| "epoch": 67.76556776556777, | |
| "grad_norm": 0.3457956612110138, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1179, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "eval_accuracy": 0.3125433125433125, | |
| "eval_f1_macro": 0.720063006101889, | |
| "eval_f1_micro": 0.8211584808443447, | |
| "eval_loss": 0.1208076998591423, | |
| "eval_roc_auc": 0.8815457934989414, | |
| "eval_runtime": 585.5944, | |
| "eval_samples_per_second": 4.928, | |
| "eval_steps_per_second": 0.155, | |
| "learning_rate": 1e-05, | |
| "step": 18564 | |
| }, | |
| { | |
| "epoch": 69.0, | |
| "eval_accuracy": 0.31011781011781014, | |
| "eval_f1_macro": 0.7197984794848579, | |
| "eval_f1_micro": 0.821014765549839, | |
| "eval_loss": 0.12105683237314224, | |
| "eval_roc_auc": 0.8794876936812611, | |
| "eval_runtime": 586.2959, | |
| "eval_samples_per_second": 4.922, | |
| "eval_steps_per_second": 0.155, | |
| "learning_rate": 1e-05, | |
| "step": 18837 | |
| }, | |
| { | |
| "epoch": 69.59706959706959, | |
| "grad_norm": 0.2593284845352173, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1177, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "eval_accuracy": 0.31115731115731116, | |
| "eval_f1_macro": 0.719699492247552, | |
| "eval_f1_micro": 0.821309285237141, | |
| "eval_loss": 0.12111356854438782, | |
| "eval_roc_auc": 0.8802103867562204, | |
| "eval_runtime": 592.4319, | |
| "eval_samples_per_second": 4.871, | |
| "eval_steps_per_second": 0.154, | |
| "learning_rate": 1e-05, | |
| "step": 19110 | |
| }, | |
| { | |
| "epoch": 71.0, | |
| "eval_accuracy": 0.31115731115731116, | |
| "eval_f1_macro": 0.7163966165871272, | |
| "eval_f1_micro": 0.8206033106461642, | |
| "eval_loss": 0.12063230574131012, | |
| "eval_roc_auc": 0.8779552656514418, | |
| "eval_runtime": 588.5502, | |
| "eval_samples_per_second": 4.904, | |
| "eval_steps_per_second": 0.155, | |
| "learning_rate": 1e-05, | |
| "step": 19383 | |
| }, | |
| { | |
| "epoch": 71.42857142857143, | |
| "grad_norm": 0.3827510476112366, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1179, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "eval_accuracy": 0.3128898128898129, | |
| "eval_f1_macro": 0.7171818163524962, | |
| "eval_f1_micro": 0.8206118081490495, | |
| "eval_loss": 0.12075439840555191, | |
| "eval_roc_auc": 0.8783204820582929, | |
| "eval_runtime": 584.4453, | |
| "eval_samples_per_second": 4.938, | |
| "eval_steps_per_second": 0.156, | |
| "learning_rate": 1e-05, | |
| "step": 19656 | |
| }, | |
| { | |
| "epoch": 73.0, | |
| "eval_accuracy": 0.31323631323631324, | |
| "eval_f1_macro": 0.7214307826544399, | |
| "eval_f1_micro": 0.8217462106977327, | |
| "eval_loss": 0.12078637629747391, | |
| "eval_roc_auc": 0.8804145307491638, | |
| "eval_runtime": 588.6768, | |
| "eval_samples_per_second": 4.903, | |
| "eval_steps_per_second": 0.155, | |
| "learning_rate": 1e-05, | |
| "step": 19929 | |
| }, | |
| { | |
| "epoch": 73.26007326007326, | |
| "grad_norm": 0.29221299290657043, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1177, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 74.0, | |
| "eval_accuracy": 0.3108108108108108, | |
| "eval_f1_macro": 0.715483654869702, | |
| "eval_f1_micro": 0.8200794388574326, | |
| "eval_loss": 0.12086880952119827, | |
| "eval_roc_auc": 0.8759783190736136, | |
| "eval_runtime": 595.2281, | |
| "eval_samples_per_second": 4.849, | |
| "eval_steps_per_second": 0.153, | |
| "learning_rate": 1e-05, | |
| "step": 20202 | |
| }, | |
| { | |
| "epoch": 75.0, | |
| "eval_accuracy": 0.3153153153153153, | |
| "eval_f1_macro": 0.7151281975948514, | |
| "eval_f1_micro": 0.8207404925448148, | |
| "eval_loss": 0.12054955214262009, | |
| "eval_roc_auc": 0.8789508616462007, | |
| "eval_runtime": 588.2243, | |
| "eval_samples_per_second": 4.906, | |
| "eval_steps_per_second": 0.155, | |
| "learning_rate": 1e-05, | |
| "step": 20475 | |
| }, | |
| { | |
| "epoch": 75.0915750915751, | |
| "grad_norm": 0.3488374352455139, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1171, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 76.0, | |
| "eval_accuracy": 0.31566181566181567, | |
| "eval_f1_macro": 0.722403613960237, | |
| "eval_f1_micro": 0.8221261740503699, | |
| "eval_loss": 0.12033110857009888, | |
| "eval_roc_auc": 0.8820333836259857, | |
| "eval_runtime": 591.3419, | |
| "eval_samples_per_second": 4.88, | |
| "eval_steps_per_second": 0.154, | |
| "learning_rate": 1e-05, | |
| "step": 20748 | |
| }, | |
| { | |
| "epoch": 76.92307692307692, | |
| "grad_norm": 0.37617847323417664, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1171, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 77.0, | |
| "eval_accuracy": 0.3135828135828136, | |
| "eval_f1_macro": 0.7234417953998725, | |
| "eval_f1_micro": 0.8231996372480317, | |
| "eval_loss": 0.12079885601997375, | |
| "eval_roc_auc": 0.8850904999468814, | |
| "eval_runtime": 598.1869, | |
| "eval_samples_per_second": 4.825, | |
| "eval_steps_per_second": 0.152, | |
| "learning_rate": 1e-05, | |
| "step": 21021 | |
| }, | |
| { | |
| "epoch": 78.0, | |
| "eval_accuracy": 0.3115038115038115, | |
| "eval_f1_macro": 0.7233107692667189, | |
| "eval_f1_micro": 0.8230326613403982, | |
| "eval_loss": 0.12099317461252213, | |
| "eval_roc_auc": 0.8837231818723246, | |
| "eval_runtime": 585.8629, | |
| "eval_samples_per_second": 4.926, | |
| "eval_steps_per_second": 0.155, | |
| "learning_rate": 1e-05, | |
| "step": 21294 | |
| }, | |
| { | |
| "epoch": 78.75457875457876, | |
| "grad_norm": 0.36047452688217163, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1168, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 79.0, | |
| "eval_accuracy": 0.31011781011781014, | |
| "eval_f1_macro": 0.7172980311198172, | |
| "eval_f1_micro": 0.8202369947054374, | |
| "eval_loss": 0.12051720172166824, | |
| "eval_roc_auc": 0.8777043478820749, | |
| "eval_runtime": 595.4358, | |
| "eval_samples_per_second": 4.847, | |
| "eval_steps_per_second": 0.153, | |
| "learning_rate": 1e-05, | |
| "step": 21567 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "eval_accuracy": 0.31185031185031187, | |
| "eval_f1_macro": 0.7248558336823359, | |
| "eval_f1_micro": 0.8231793006530544, | |
| "eval_loss": 0.12073608487844467, | |
| "eval_roc_auc": 0.8842671366132298, | |
| "eval_runtime": 604.2206, | |
| "eval_samples_per_second": 4.776, | |
| "eval_steps_per_second": 0.151, | |
| "learning_rate": 1e-05, | |
| "step": 21840 | |
| }, | |
| { | |
| "epoch": 80.58608058608058, | |
| "grad_norm": 0.35180962085723877, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1171, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 81.0, | |
| "eval_accuracy": 0.3128898128898129, | |
| "eval_f1_macro": 0.7212996450160633, | |
| "eval_f1_micro": 0.822080253872813, | |
| "eval_loss": 0.12031927704811096, | |
| "eval_roc_auc": 0.8805991577232666, | |
| "eval_runtime": 597.4583, | |
| "eval_samples_per_second": 4.83, | |
| "eval_steps_per_second": 0.152, | |
| "learning_rate": 1e-05, | |
| "step": 22113 | |
| }, | |
| { | |
| "epoch": 82.0, | |
| "eval_accuracy": 0.3142758142758143, | |
| "eval_f1_macro": 0.7178066335813648, | |
| "eval_f1_micro": 0.8215302193202746, | |
| "eval_loss": 0.1204884946346283, | |
| "eval_roc_auc": 0.8795852787754633, | |
| "eval_runtime": 583.2227, | |
| "eval_samples_per_second": 4.948, | |
| "eval_steps_per_second": 0.156, | |
| "learning_rate": 1e-05, | |
| "step": 22386 | |
| }, | |
| { | |
| "epoch": 82.41758241758242, | |
| "grad_norm": 0.3334418535232544, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 0.1157, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 83.0, | |
| "eval_accuracy": 0.31115731115731116, | |
| "eval_f1_macro": 0.7113142483409282, | |
| "eval_f1_micro": 0.8179971218149497, | |
| "eval_loss": 0.12136666476726532, | |
| "eval_roc_auc": 0.8743461195069316, | |
| "eval_runtime": 580.12, | |
| "eval_samples_per_second": 4.975, | |
| "eval_steps_per_second": 0.157, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "step": 22659 | |
| }, | |
| { | |
| "epoch": 84.0, | |
| "eval_accuracy": 0.3115038115038115, | |
| "eval_f1_macro": 0.7250649377579587, | |
| "eval_f1_micro": 0.8234267187629895, | |
| "eval_loss": 0.12041348963975906, | |
| "eval_roc_auc": 0.8827056007271329, | |
| "eval_runtime": 581.6672, | |
| "eval_samples_per_second": 4.962, | |
| "eval_steps_per_second": 0.156, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "step": 22932 | |
| }, | |
| { | |
| "epoch": 84.24908424908425, | |
| "grad_norm": 0.3593423068523407, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 0.1169, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 85.0, | |
| "eval_accuracy": 0.31323631323631324, | |
| "eval_f1_macro": 0.7213085414821642, | |
| "eval_f1_micro": 0.8229879338226147, | |
| "eval_loss": 0.12035409361124039, | |
| "eval_roc_auc": 0.8831987441502598, | |
| "eval_runtime": 579.5593, | |
| "eval_samples_per_second": 4.98, | |
| "eval_steps_per_second": 0.157, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "step": 23205 | |
| }, | |
| { | |
| "epoch": 86.0, | |
| "eval_accuracy": 0.3076923076923077, | |
| "eval_f1_macro": 0.7218120076279698, | |
| "eval_f1_micro": 0.8196243388446962, | |
| "eval_loss": 0.12250283360481262, | |
| "eval_roc_auc": 0.8800111790264615, | |
| "eval_runtime": 583.2647, | |
| "eval_samples_per_second": 4.948, | |
| "eval_steps_per_second": 0.156, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "step": 23478 | |
| }, | |
| { | |
| "epoch": 86.08058608058609, | |
| "grad_norm": 0.3458651602268219, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 0.1157, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 87.0, | |
| "eval_accuracy": 0.3090783090783091, | |
| "eval_f1_macro": 0.7151954083158903, | |
| "eval_f1_micro": 0.8203968852047224, | |
| "eval_loss": 0.12075748294591904, | |
| "eval_roc_auc": 0.8788858049167326, | |
| "eval_runtime": 580.273, | |
| "eval_samples_per_second": 4.974, | |
| "eval_steps_per_second": 0.157, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "step": 23751 | |
| }, | |
| { | |
| "epoch": 87.91208791208791, | |
| "grad_norm": 0.2947898507118225, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 0.1156, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 88.0, | |
| "eval_accuracy": 0.30838530838530837, | |
| "eval_f1_macro": 0.7168335672232342, | |
| "eval_f1_micro": 0.8215440749647566, | |
| "eval_loss": 0.12086642533540726, | |
| "eval_roc_auc": 0.8824075738373759, | |
| "eval_runtime": 581.7056, | |
| "eval_samples_per_second": 4.961, | |
| "eval_steps_per_second": 0.156, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "step": 24024 | |
| }, | |
| { | |
| "epoch": 89.0, | |
| "eval_accuracy": 0.3163548163548164, | |
| "eval_f1_macro": 0.733984551040518, | |
| "eval_f1_micro": 0.8244650323850127, | |
| "eval_loss": 0.12105640023946762, | |
| "eval_roc_auc": 0.8874893628893881, | |
| "eval_runtime": 592.213, | |
| "eval_samples_per_second": 4.873, | |
| "eval_steps_per_second": 0.154, | |
| "learning_rate": 1.0000000000000002e-07, | |
| "step": 24297 | |
| }, | |
| { | |
| "epoch": 89.74358974358974, | |
| "grad_norm": 0.27441146969795227, | |
| "learning_rate": 1.0000000000000002e-07, | |
| "loss": 0.1157, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 90.0, | |
| "eval_accuracy": 0.31185031185031187, | |
| "eval_f1_macro": 0.7245620055819162, | |
| "eval_f1_micro": 0.8232248520710059, | |
| "eval_loss": 0.12090421468019485, | |
| "eval_roc_auc": 0.8860665789228, | |
| "eval_runtime": 602.5705, | |
| "eval_samples_per_second": 4.789, | |
| "eval_steps_per_second": 0.151, | |
| "learning_rate": 1.0000000000000002e-07, | |
| "step": 24570 | |
| }, | |
| { | |
| "epoch": 91.0, | |
| "eval_accuracy": 0.3115038115038115, | |
| "eval_f1_macro": 0.7163143946337084, | |
| "eval_f1_micro": 0.8200938495056143, | |
| "eval_loss": 0.12043782323598862, | |
| "eval_roc_auc": 0.8784951828509925, | |
| "eval_runtime": 602.4626, | |
| "eval_samples_per_second": 4.79, | |
| "eval_steps_per_second": 0.151, | |
| "learning_rate": 1.0000000000000002e-07, | |
| "step": 24843 | |
| }, | |
| { | |
| "epoch": 91.0, | |
| "learning_rate": 1.0000000000000002e-07, | |
| "step": 24843, | |
| "total_flos": 1.1760993126572918e+21, | |
| "train_loss": 0.13338198287712655, | |
| "train_runtime": 215448.2605, | |
| "train_samples_per_second": 6.068, | |
| "train_steps_per_second": 0.19 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 40950, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 150, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 10, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.1760993126572918e+21, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |