| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.052209097435228086, | |
| "eval_steps": 500, | |
| "global_step": 800, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006526137179403511, | |
| "grad_norm": 17.690582114691438, | |
| "learning_rate": 1.948051948051948e-06, | |
| "loss": 1.3559, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0013052274358807021, | |
| "grad_norm": 7.768088366444893, | |
| "learning_rate": 3.896103896103896e-06, | |
| "loss": 1.2706, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.001957841153821053, | |
| "grad_norm": 7.705313536090087, | |
| "learning_rate": 5.844155844155845e-06, | |
| "loss": 1.3781, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0026104548717614043, | |
| "grad_norm": 34.39078827766783, | |
| "learning_rate": 7.792207792207792e-06, | |
| "loss": 1.2749, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0032630685897017554, | |
| "grad_norm": 68.28824334896528, | |
| "learning_rate": 9.74025974025974e-06, | |
| "loss": 1.2955, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.003915682307642106, | |
| "grad_norm": 14.220322607917241, | |
| "learning_rate": 1.168831168831169e-05, | |
| "loss": 1.2315, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.0045682960255824575, | |
| "grad_norm": 12.611848231734811, | |
| "learning_rate": 1.3636363636363637e-05, | |
| "loss": 1.0953, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.0052209097435228086, | |
| "grad_norm": 6.055664298727015, | |
| "learning_rate": 1.5584415584415583e-05, | |
| "loss": 1.105, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.00587352346146316, | |
| "grad_norm": 3.52269227801977, | |
| "learning_rate": 1.753246753246753e-05, | |
| "loss": 0.9563, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.006526137179403511, | |
| "grad_norm": 10.771884023354394, | |
| "learning_rate": 1.948051948051948e-05, | |
| "loss": 0.9523, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.007178750897343862, | |
| "grad_norm": 33.41476483216757, | |
| "learning_rate": 2.1428571428571428e-05, | |
| "loss": 0.832, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.007831364615284213, | |
| "grad_norm": 31.120240364617406, | |
| "learning_rate": 2.337662337662338e-05, | |
| "loss": 0.8376, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.008483978333224564, | |
| "grad_norm": 5.517231564060886, | |
| "learning_rate": 2.5324675324675325e-05, | |
| "loss": 0.8293, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.009136592051164915, | |
| "grad_norm": 4.311605388342058, | |
| "learning_rate": 2.7272727272727273e-05, | |
| "loss": 0.8295, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.009789205769105266, | |
| "grad_norm": 6.997724163121519, | |
| "learning_rate": 2.922077922077922e-05, | |
| "loss": 0.7662, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.010441819487045617, | |
| "grad_norm": 6.517836234400708, | |
| "learning_rate": 2.999998841890695e-05, | |
| "loss": 0.8158, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.011094433204985968, | |
| "grad_norm": 4.186989141019666, | |
| "learning_rate": 2.99999176456253e-05, | |
| "loss": 0.8037, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.01174704692292632, | |
| "grad_norm": 5.181546943355458, | |
| "learning_rate": 2.9999782533305785e-05, | |
| "loss": 0.7274, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.01239966064086667, | |
| "grad_norm": 3.767076521211455, | |
| "learning_rate": 2.9999583082527935e-05, | |
| "loss": 0.7474, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.013052274358807021, | |
| "grad_norm": 18.84416377940188, | |
| "learning_rate": 2.999931929414726e-05, | |
| "loss": 0.7708, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.013704888076747372, | |
| "grad_norm": 3.169160630444992, | |
| "learning_rate": 2.999899116929522e-05, | |
| "loss": 0.8279, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.014357501794687724, | |
| "grad_norm": 1.912782077307437, | |
| "learning_rate": 2.999859870937924e-05, | |
| "loss": 0.7407, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.015010115512628075, | |
| "grad_norm": 3.3906505952914974, | |
| "learning_rate": 2.9998141916082696e-05, | |
| "loss": 0.7732, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.015662729230568426, | |
| "grad_norm": 2.7144492322383584, | |
| "learning_rate": 2.999762079136491e-05, | |
| "loss": 0.7272, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.01631534294850878, | |
| "grad_norm": 7.109330196029837, | |
| "learning_rate": 2.9997035337461135e-05, | |
| "loss": 0.7748, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.016967956666449128, | |
| "grad_norm": 1.6054280593801813, | |
| "learning_rate": 2.9996385556882555e-05, | |
| "loss": 0.7676, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.01762057038438948, | |
| "grad_norm": 10.883212441614672, | |
| "learning_rate": 2.9995671452416274e-05, | |
| "loss": 0.735, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.01827318410232983, | |
| "grad_norm": 3.511064886507805, | |
| "learning_rate": 2.999489302712529e-05, | |
| "loss": 0.7741, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.018925797820270183, | |
| "grad_norm": 3.618603818375307, | |
| "learning_rate": 2.9994050284348497e-05, | |
| "loss": 0.749, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.019578411538210532, | |
| "grad_norm": 6.012944880342178, | |
| "learning_rate": 2.9993143227700668e-05, | |
| "loss": 0.7411, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.020231025256150885, | |
| "grad_norm": 2.348670372295822, | |
| "learning_rate": 2.9992171861072428e-05, | |
| "loss": 0.7394, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.020883638974091234, | |
| "grad_norm": 4.728309497649916, | |
| "learning_rate": 2.9991136188630263e-05, | |
| "loss": 0.8077, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.021536252692031587, | |
| "grad_norm": 15.611917863290122, | |
| "learning_rate": 2.9990036214816467e-05, | |
| "loss": 0.7209, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.022188866409971936, | |
| "grad_norm": 3.7315277354070817, | |
| "learning_rate": 2.998887194434916e-05, | |
| "loss": 0.7101, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.02284148012791229, | |
| "grad_norm": 6.618759094750745, | |
| "learning_rate": 2.998764338222222e-05, | |
| "loss": 0.7759, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.02349409384585264, | |
| "grad_norm": 6.770044306239603, | |
| "learning_rate": 2.998635053370533e-05, | |
| "loss": 0.7398, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.02414670756379299, | |
| "grad_norm": 12.471224202357552, | |
| "learning_rate": 2.998499340434389e-05, | |
| "loss": 0.7046, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.02479932128173334, | |
| "grad_norm": 4.147359416986547, | |
| "learning_rate": 2.9983571999959013e-05, | |
| "loss": 0.761, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.025451934999673693, | |
| "grad_norm": 34.84722866603778, | |
| "learning_rate": 2.9982086326647533e-05, | |
| "loss": 0.757, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.026104548717614043, | |
| "grad_norm": 5.245498180313093, | |
| "learning_rate": 2.998053639078193e-05, | |
| "loss": 0.7536, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.026757162435554396, | |
| "grad_norm": 36.55990241841121, | |
| "learning_rate": 2.997892219901034e-05, | |
| "loss": 0.7395, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.027409776153494745, | |
| "grad_norm": 5.03198653806696, | |
| "learning_rate": 2.9977243758256494e-05, | |
| "loss": 0.7208, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.028062389871435098, | |
| "grad_norm": 11.376914733036081, | |
| "learning_rate": 2.997550107571972e-05, | |
| "loss": 0.719, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.028715003589375447, | |
| "grad_norm": 2.958119684662306, | |
| "learning_rate": 2.9973694158874898e-05, | |
| "loss": 0.7271, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.0293676173073158, | |
| "grad_norm": 6.037096737490817, | |
| "learning_rate": 2.9971823015472418e-05, | |
| "loss": 0.7356, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.03002023102525615, | |
| "grad_norm": 5.3042973640363575, | |
| "learning_rate": 2.9969887653538164e-05, | |
| "loss": 0.7207, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.030672844743196502, | |
| "grad_norm": 2.4985603001745624, | |
| "learning_rate": 2.996788808137347e-05, | |
| "loss": 0.7769, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.03132545846113685, | |
| "grad_norm": 7.607065841315647, | |
| "learning_rate": 2.9965824307555084e-05, | |
| "loss": 0.7091, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.03197807217907721, | |
| "grad_norm": 4.322533035107957, | |
| "learning_rate": 2.9963696340935144e-05, | |
| "loss": 0.7114, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.03263068589701756, | |
| "grad_norm": 5.878565903250334, | |
| "learning_rate": 2.9961504190641108e-05, | |
| "loss": 0.7284, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.033283299614957906, | |
| "grad_norm": 5.0026507027119855, | |
| "learning_rate": 2.9959247866075764e-05, | |
| "loss": 0.6992, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.033935913332898256, | |
| "grad_norm": 7.12632150273901, | |
| "learning_rate": 2.9956927376917137e-05, | |
| "loss": 0.7285, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.03458852705083861, | |
| "grad_norm": 5.211123255860348, | |
| "learning_rate": 2.9954542733118496e-05, | |
| "loss": 0.7511, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.03524114076877896, | |
| "grad_norm": 9.925273547498618, | |
| "learning_rate": 2.995209394490827e-05, | |
| "loss": 0.7699, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.03589375448671931, | |
| "grad_norm": 7.418381681996765, | |
| "learning_rate": 2.9949581022790025e-05, | |
| "loss": 0.759, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.03654636820465966, | |
| "grad_norm": 4.352380973507467, | |
| "learning_rate": 2.9947003977542423e-05, | |
| "loss": 0.7537, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.037198981922600016, | |
| "grad_norm": 9.712842120769198, | |
| "learning_rate": 2.9944362820219167e-05, | |
| "loss": 0.7063, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.037851595640540366, | |
| "grad_norm": 5.757600819230482, | |
| "learning_rate": 2.994165756214895e-05, | |
| "loss": 0.7893, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.038504209358480715, | |
| "grad_norm": 5.529209601152462, | |
| "learning_rate": 2.9938888214935426e-05, | |
| "loss": 0.6771, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.039156823076421064, | |
| "grad_norm": 10.550479346499758, | |
| "learning_rate": 2.9936054790457127e-05, | |
| "loss": 0.737, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.03980943679436142, | |
| "grad_norm": 8.284279553451016, | |
| "learning_rate": 2.9933157300867437e-05, | |
| "loss": 0.7182, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.04046205051230177, | |
| "grad_norm": 8.18511648646326, | |
| "learning_rate": 2.9930195758594542e-05, | |
| "loss": 0.6901, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.04111466423024212, | |
| "grad_norm": 14.569754827631956, | |
| "learning_rate": 2.9927170176341365e-05, | |
| "loss": 0.7008, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.04176727794818247, | |
| "grad_norm": 4.214581273685441, | |
| "learning_rate": 2.992408056708551e-05, | |
| "loss": 0.7489, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.042419891666122825, | |
| "grad_norm": 10.038596627079452, | |
| "learning_rate": 2.9920926944079224e-05, | |
| "loss": 0.7649, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.043072505384063174, | |
| "grad_norm": 2.386544029221306, | |
| "learning_rate": 2.9917709320849305e-05, | |
| "loss": 0.7223, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.043725119102003523, | |
| "grad_norm": 8.286359254511249, | |
| "learning_rate": 2.9914427711197096e-05, | |
| "loss": 0.7089, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.04437773281994387, | |
| "grad_norm": 4.235819327444911, | |
| "learning_rate": 2.9911082129198372e-05, | |
| "loss": 0.7138, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.04503034653788423, | |
| "grad_norm": 5.187338033698449, | |
| "learning_rate": 2.9907672589203316e-05, | |
| "loss": 0.7192, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.04568296025582458, | |
| "grad_norm": 6.360475337181379, | |
| "learning_rate": 2.9904199105836443e-05, | |
| "loss": 0.7094, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.04633557397376493, | |
| "grad_norm": 4.906400836156689, | |
| "learning_rate": 2.990066169399654e-05, | |
| "loss": 0.654, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.04698818769170528, | |
| "grad_norm": 17.600495314130633, | |
| "learning_rate": 2.9897060368856603e-05, | |
| "loss": 0.7299, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.04764080140964563, | |
| "grad_norm": 7.765935941492389, | |
| "learning_rate": 2.989339514586377e-05, | |
| "loss": 0.7486, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.04829341512758598, | |
| "grad_norm": 7.30026395137639, | |
| "learning_rate": 2.9889666040739252e-05, | |
| "loss": 0.6941, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.04894602884552633, | |
| "grad_norm": 4.676985481218465, | |
| "learning_rate": 2.9885873069478275e-05, | |
| "loss": 0.7701, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.04959864256346668, | |
| "grad_norm": 42.50656974727186, | |
| "learning_rate": 2.9882016248350006e-05, | |
| "loss": 0.7428, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.05025125628140704, | |
| "grad_norm": 3.9893667031114766, | |
| "learning_rate": 2.9878095593897474e-05, | |
| "loss": 0.7204, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.05090386999934739, | |
| "grad_norm": 8.909028486553332, | |
| "learning_rate": 2.9874111122937518e-05, | |
| "loss": 0.7336, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.051556483717287736, | |
| "grad_norm": 5.256925284136456, | |
| "learning_rate": 2.9870062852560698e-05, | |
| "loss": 0.7674, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.052209097435228086, | |
| "grad_norm": 5.835535487534073, | |
| "learning_rate": 2.986595080013123e-05, | |
| "loss": 0.7547, | |
| "step": 800 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 15323, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 400, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.1868564721958912e+18, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |