| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 20.0, | |
| "global_step": 620, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.0009993582535855264, | |
| "loss": 0.7008, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.0009974346616959476, | |
| "loss": 0.4261, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 0.0009942341621640557, | |
| "loss": 0.3999, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 0.0009897649706262473, | |
| "loss": 0.403, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 0.000984038559433102, | |
| "loss": 0.3025, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 0.0009770696282000244, | |
| "loss": 0.3243, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 0.0009688760660735403, | |
| "loss": 0.1971, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 0.0009594789058101153, | |
| "loss": 0.3054, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 0.0009489022697853709, | |
| "loss": 0.3146, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "learning_rate": 0.0009371733080722911, | |
| "loss": 0.1914, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.55, | |
| "learning_rate": 0.0009243221287473755, | |
| "loss": 0.2848, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 3.87, | |
| "learning_rate": 0.0009103817206036382, | |
| "loss": 0.1316, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "learning_rate": 0.0008953878684688492, | |
| "loss": 0.3139, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 4.52, | |
| "learning_rate": 0.0008793790613463954, | |
| "loss": 0.1033, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 4.84, | |
| "learning_rate": 0.00086239639361456, | |
| "loss": 0.1794, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 5.16, | |
| "learning_rate": 0.0008444834595378434, | |
| "loss": 0.1794, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 5.48, | |
| "learning_rate": 0.0008256862413611113, | |
| "loss": 0.1136, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 5.81, | |
| "learning_rate": 0.0008060529912738315, | |
| "loss": 0.1584, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 6.13, | |
| "learning_rate": 0.0007856341075473961, | |
| "loss": 0.1127, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 6.45, | |
| "learning_rate": 0.0007644820051634812, | |
| "loss": 0.1422, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 6.77, | |
| "learning_rate": 0.0007426509812655407, | |
| "loss": 0.1001, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 7.1, | |
| "learning_rate": 0.0007201970757788173, | |
| "loss": 0.0521, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 7.42, | |
| "learning_rate": 0.0006971779275566593, | |
| "loss": 0.0499, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 7.74, | |
| "learning_rate": 0.0006736526264224101, | |
| "loss": 0.1083, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 8.06, | |
| "learning_rate": 0.0006496815614866791, | |
| "loss": 0.0762, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 8.39, | |
| "learning_rate": 0.0006253262661293602, | |
| "loss": 0.0363, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 8.71, | |
| "learning_rate": 0.0006006492600443301, | |
| "loss": 0.0455, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 9.03, | |
| "learning_rate": 0.0005757138887522884, | |
| "loss": 0.0614, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 9.35, | |
| "learning_rate": 0.0005505841609937161, | |
| "loss": 0.0279, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 9.68, | |
| "learning_rate": 0.0005253245844193564, | |
| "loss": 0.0383, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 0.0005, | |
| "loss": 0.0219, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 10.32, | |
| "learning_rate": 0.0004746754155806437, | |
| "loss": 0.0069, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 10.65, | |
| "learning_rate": 0.000449415839006284, | |
| "loss": 0.0399, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 10.97, | |
| "learning_rate": 0.00042428611124771184, | |
| "loss": 0.0208, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 11.29, | |
| "learning_rate": 0.0003993507399556699, | |
| "loss": 0.0109, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 11.61, | |
| "learning_rate": 0.00037467373387063967, | |
| "loss": 0.0249, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 11.94, | |
| "learning_rate": 0.000350318438513321, | |
| "loss": 0.0041, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 12.26, | |
| "learning_rate": 0.0003263473735775899, | |
| "loss": 0.009, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 12.58, | |
| "learning_rate": 0.00030282207244334083, | |
| "loss": 0.007, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 12.9, | |
| "learning_rate": 0.0002798029242211828, | |
| "loss": 0.0089, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 13.23, | |
| "learning_rate": 0.0002573490187344596, | |
| "loss": 0.0103, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 13.55, | |
| "learning_rate": 0.0002355179948365189, | |
| "loss": 0.0054, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 13.87, | |
| "learning_rate": 0.00021436589245260373, | |
| "loss": 0.0037, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 14.19, | |
| "learning_rate": 0.00019394700872616856, | |
| "loss": 0.0047, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 14.52, | |
| "learning_rate": 0.00017431375863888898, | |
| "loss": 0.0061, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 14.84, | |
| "learning_rate": 0.00015551654046215668, | |
| "loss": 0.0043, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 15.16, | |
| "learning_rate": 0.00013760360638544013, | |
| "loss": 0.0058, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 15.48, | |
| "learning_rate": 0.00012062093865360457, | |
| "loss": 0.0029, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 15.81, | |
| "learning_rate": 0.00010461213153115079, | |
| "loss": 0.0037, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 16.13, | |
| "learning_rate": 8.961827939636197e-05, | |
| "loss": 0.004, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 16.45, | |
| "learning_rate": 7.567787125262449e-05, | |
| "loss": 0.0048, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 16.77, | |
| "learning_rate": 6.282669192770896e-05, | |
| "loss": 0.0036, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 17.1, | |
| "learning_rate": 5.109773021462921e-05, | |
| "loss": 0.0018, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 17.42, | |
| "learning_rate": 4.05210941898847e-05, | |
| "loss": 0.0039, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 17.74, | |
| "learning_rate": 3.112393392645985e-05, | |
| "loss": 0.004, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 18.06, | |
| "learning_rate": 2.2930371799975592e-05, | |
| "loss": 0.0038, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 18.39, | |
| "learning_rate": 1.596144056689791e-05, | |
| "loss": 0.0027, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 18.71, | |
| "learning_rate": 1.0235029373752758e-05, | |
| "loss": 0.0043, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 19.03, | |
| "learning_rate": 5.76583783594431e-06, | |
| "loss": 0.0034, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 19.35, | |
| "learning_rate": 2.5653383040524227e-06, | |
| "loss": 0.0034, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 19.68, | |
| "learning_rate": 6.417464144736207e-07, | |
| "loss": 0.0037, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.0038, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "step": 620, | |
| "total_flos": 7.220647174835405e+16, | |
| "train_loss": 0.09885127827404969, | |
| "train_runtime": 1180.114, | |
| "train_samples_per_second": 2.085, | |
| "train_steps_per_second": 0.525 | |
| } | |
| ], | |
| "max_steps": 620, | |
| "num_train_epochs": 20, | |
| "total_flos": 7.220647174835405e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |