| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 9.0368, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.888888888888889e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011111111111111112, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013333333333333334, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015555555555555556, | |
| "loss": 0.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017777777777777779, | |
| "loss": 0.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019999417253661235, | |
| "loss": 0.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019997669082563597, | |
| "loss": 0.0, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019994755690455152, | |
| "loss": 0.0, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019990677416889608, | |
| "loss": 0.0, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001998543473718677, | |
| "loss": 0.0, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019979028262377118, | |
| "loss": 0.0, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019971458739130598, | |
| "loss": 0.0, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000199627270496696, | |
| "loss": 0.0, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001995283421166614, | |
| "loss": 0.0, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019941781378123244, | |
| "loss": 0.0, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019929569837240564, | |
| "loss": 0.0, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019916201012264254, | |
| "loss": 0.0, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019901676461321066, | |
| "loss": 0.0, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019885997877236788, | |
| "loss": 0.0, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019869167087338907, | |
| "loss": 0.0, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019851186053243666, | |
| "loss": 0.0, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019832056870627417, | |
| "loss": 0.0, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001981178176898239, | |
| "loss": 0.0, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019790363111356837, | |
| "loss": 0.0, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019767803394079615, | |
| "loss": 0.0, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019744105246469263, | |
| "loss": 0.0, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001971927143052752, | |
| "loss": 0.0, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019693304840617457, | |
| "loss": 0.0, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019666208503126112, | |
| "loss": 0.0, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019637985576111778, | |
| "loss": 0.0, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001960863934893594, | |
| "loss": 0.0, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019578173241879872, | |
| "loss": 0.0, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019546590805746052, | |
| "loss": 0.0, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019513895721444286, | |
| "loss": 0.0, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019480091799562704, | |
| "loss": 0.0, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019445182979923654, | |
| "loss": 0.0, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000194091733311245, | |
| "loss": 0.0, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019372067050063438, | |
| "loss": 0.0, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001933386846145036, | |
| "loss": 0.0, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019294582017302797, | |
| "loss": 0.0, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019254212296427044, | |
| "loss": 0.0, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001921276400388451, | |
| "loss": 0.0, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019170241970443343, | |
| "loss": 0.0, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019126651152015403, | |
| "loss": 0.0, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019081996629078657, | |
| "loss": 0.0, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019036283606085053, | |
| "loss": 0.0, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018989517410853955, | |
| "loss": 0.0, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018941703493951164, | |
| "loss": 0.0, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018892847428053693, | |
| "loss": 0.0, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018842954907300236, | |
| "loss": 0.0, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018792031746627563, | |
| "loss": 0.0, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001874008388109276, | |
| "loss": 0.0, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018687117365181512, | |
| "loss": 0.0, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018633138372102468, | |
| "loss": 0.0, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018578153193067745, | |
| "loss": 0.0, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018522168236559695, | |
| "loss": 0.0, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018465190027584005, | |
| "loss": 0.0, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018407225206909208, | |
| "loss": 0.0, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018348280530292713, | |
| "loss": 0.0, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018288362867693414, | |
| "loss": 0.0, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018227479202471015, | |
| "loss": 0.0, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001816563663057211, | |
| "loss": 0.0, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018102842359703176, | |
| "loss": 0.0, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018039103708490499, | |
| "loss": 0.0, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017974428105627208, | |
| "loss": 0.0, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017908823089007457, | |
| "loss": 0.0, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017842296304847893, | |
| "loss": 0.0, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017774855506796496, | |
| "loss": 0.0, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017706508555028893, | |
| "loss": 0.0, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001763726341533227, | |
| "loss": 0.0, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017567128158176953, | |
| "loss": 0.0, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001749611095777581, | |
| "loss": 0.0, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017424220091131535, | |
| "loss": 0.0, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017351463937072004, | |
| "loss": 0.0, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017277850975273696, | |
| "loss": 0.0, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000172033897852734, | |
| "loss": 0.0, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017128089045468294, | |
| "loss": 0.0, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001705195753210446, | |
| "loss": 0.0, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001697500411825403, | |
| "loss": 0.0, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016897237772781044, | |
| "loss": 0.0, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001681866755929612, | |
| "loss": 0.0, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016739302635100108, | |
| "loss": 0.0, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016659152250116812, | |
| "loss": 0.0, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016578225745814907, | |
| "loss": 0.0, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016496532554119214, | |
| "loss": 0.0, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000164140821963114, | |
| "loss": 0.0, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000163308842819203, | |
| "loss": 0.0, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016246948507601914, | |
| "loss": 0.0, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016162284656009274, | |
| "loss": 0.0, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001607690259465229, | |
| "loss": 0.0, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015990812274747692, | |
| "loss": 0.0, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015904023730059228, | |
| "loss": 0.0, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015816547075728226, | |
| "loss": 0.0, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000157283925070947, | |
| "loss": 0.0, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015639570298509064, | |
| "loss": 0.0, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000155500908021347, | |
| "loss": 0.0, | |
| "step": 1000 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 3000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 1000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.5321212387328e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |