| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 10.0, | |
| "eval_steps": 500, | |
| "global_step": 3800, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02631578947368421, | |
| "grad_norm": 9.638947486877441, | |
| "learning_rate": 5.263157894736842e-06, | |
| "loss": 1.4471, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05263157894736842, | |
| "grad_norm": 9.498916625976562, | |
| "learning_rate": 1.0526315789473684e-05, | |
| "loss": 1.2214, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07894736842105263, | |
| "grad_norm": 2.470106601715088, | |
| "learning_rate": 1.5789473684210526e-05, | |
| "loss": 0.6744, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.10526315789473684, | |
| "grad_norm": 2.844433546066284, | |
| "learning_rate": 2.105263157894737e-05, | |
| "loss": 0.4362, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.13157894736842105, | |
| "grad_norm": 1.874556303024292, | |
| "learning_rate": 2.6315789473684212e-05, | |
| "loss": 0.3136, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.15789473684210525, | |
| "grad_norm": 1.6943750381469727, | |
| "learning_rate": 3.157894736842105e-05, | |
| "loss": 0.2589, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.18421052631578946, | |
| "grad_norm": 2.1084232330322266, | |
| "learning_rate": 3.6842105263157895e-05, | |
| "loss": 0.2282, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.21052631578947367, | |
| "grad_norm": 1.509325623512268, | |
| "learning_rate": 4.210526315789474e-05, | |
| "loss": 0.1952, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.23684210526315788, | |
| "grad_norm": 2.0447444915771484, | |
| "learning_rate": 4.736842105263158e-05, | |
| "loss": 0.1842, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.2631578947368421, | |
| "grad_norm": 1.149940013885498, | |
| "learning_rate": 5.2631578947368424e-05, | |
| "loss": 0.1915, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.2894736842105263, | |
| "grad_norm": 1.1014671325683594, | |
| "learning_rate": 5.789473684210527e-05, | |
| "loss": 0.1688, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.3157894736842105, | |
| "grad_norm": 1.9964191913604736, | |
| "learning_rate": 6.31578947368421e-05, | |
| "loss": 0.1494, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.34210526315789475, | |
| "grad_norm": 0.7053777575492859, | |
| "learning_rate": 6.842105263157895e-05, | |
| "loss": 0.1418, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.3684210526315789, | |
| "grad_norm": 1.077986240386963, | |
| "learning_rate": 7.368421052631579e-05, | |
| "loss": 0.1442, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.39473684210526316, | |
| "grad_norm": 1.095324993133545, | |
| "learning_rate": 7.894736842105263e-05, | |
| "loss": 0.1332, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.42105263157894735, | |
| "grad_norm": 0.9210699200630188, | |
| "learning_rate": 8.421052631578948e-05, | |
| "loss": 0.1322, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.4473684210526316, | |
| "grad_norm": 1.3079745769500732, | |
| "learning_rate": 8.947368421052632e-05, | |
| "loss": 0.1204, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.47368421052631576, | |
| "grad_norm": 1.196655035018921, | |
| "learning_rate": 9.473684210526316e-05, | |
| "loss": 0.1227, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 0.8218312859535217, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1215, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.5263157894736842, | |
| "grad_norm": 0.9372950196266174, | |
| "learning_rate": 9.999810668616086e-05, | |
| "loss": 0.114, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.5526315789473685, | |
| "grad_norm": 1.0510334968566895, | |
| "learning_rate": 9.999242688802886e-05, | |
| "loss": 0.1101, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.5789473684210527, | |
| "grad_norm": 0.7145567536354065, | |
| "learning_rate": 9.998296103574967e-05, | |
| "loss": 0.0964, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.6052631578947368, | |
| "grad_norm": 0.7895988821983337, | |
| "learning_rate": 9.996970984619641e-05, | |
| "loss": 0.0948, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.631578947368421, | |
| "grad_norm": 0.8074854612350464, | |
| "learning_rate": 9.995267432291555e-05, | |
| "loss": 0.1025, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.6578947368421053, | |
| "grad_norm": 0.9896809458732605, | |
| "learning_rate": 9.993185575605073e-05, | |
| "loss": 0.0954, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.6842105263157895, | |
| "grad_norm": 1.2382564544677734, | |
| "learning_rate": 9.990725572224521e-05, | |
| "loss": 0.0965, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.7105263157894737, | |
| "grad_norm": 0.6677968502044678, | |
| "learning_rate": 9.987887608452235e-05, | |
| "loss": 0.104, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.7368421052631579, | |
| "grad_norm": 0.8802872896194458, | |
| "learning_rate": 9.984671899214457e-05, | |
| "loss": 0.0936, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.7631578947368421, | |
| "grad_norm": 0.5323192477226257, | |
| "learning_rate": 9.981078688045062e-05, | |
| "loss": 0.0937, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.7894736842105263, | |
| "grad_norm": 0.43582749366760254, | |
| "learning_rate": 9.977108247067108e-05, | |
| "loss": 0.0913, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.8157894736842105, | |
| "grad_norm": 0.5718427896499634, | |
| "learning_rate": 9.972760876972226e-05, | |
| "loss": 0.0913, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.8421052631578947, | |
| "grad_norm": 0.5905811190605164, | |
| "learning_rate": 9.968036906997855e-05, | |
| "loss": 0.091, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.868421052631579, | |
| "grad_norm": 0.5551950931549072, | |
| "learning_rate": 9.962936694902307e-05, | |
| "loss": 0.0827, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.8947368421052632, | |
| "grad_norm": 0.37185293436050415, | |
| "learning_rate": 9.957460626937664e-05, | |
| "loss": 0.0768, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.9210526315789473, | |
| "grad_norm": 0.7125674486160278, | |
| "learning_rate": 9.951609117820538e-05, | |
| "loss": 0.0878, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.9473684210526315, | |
| "grad_norm": 0.518326461315155, | |
| "learning_rate": 9.945382610700657e-05, | |
| "loss": 0.0841, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.9736842105263158, | |
| "grad_norm": 0.40797701478004456, | |
| "learning_rate": 9.938781577127306e-05, | |
| "loss": 0.0899, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.8398942351341248, | |
| "learning_rate": 9.931806517013612e-05, | |
| "loss": 0.082, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.0263157894736843, | |
| "grad_norm": 0.5522546768188477, | |
| "learning_rate": 9.92445795859869e-05, | |
| "loss": 0.0833, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.0526315789473684, | |
| "grad_norm": 0.7629371285438538, | |
| "learning_rate": 9.916736458407632e-05, | |
| "loss": 0.0782, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.0789473684210527, | |
| "grad_norm": 0.6491877436637878, | |
| "learning_rate": 9.908642601209366e-05, | |
| "loss": 0.0795, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.1052631578947367, | |
| "grad_norm": 0.5657724142074585, | |
| "learning_rate": 9.900176999972366e-05, | |
| "loss": 0.0763, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.131578947368421, | |
| "grad_norm": 0.9348977208137512, | |
| "learning_rate": 9.89134029581823e-05, | |
| "loss": 0.0789, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.1578947368421053, | |
| "grad_norm": 0.9060670733451843, | |
| "learning_rate": 9.88213315797313e-05, | |
| "loss": 0.0897, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.1842105263157894, | |
| "grad_norm": 0.5024181008338928, | |
| "learning_rate": 9.872556283717125e-05, | |
| "loss": 0.0781, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.2105263157894737, | |
| "grad_norm": 0.6639284491539001, | |
| "learning_rate": 9.86261039833136e-05, | |
| "loss": 0.0871, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.236842105263158, | |
| "grad_norm": 0.572541356086731, | |
| "learning_rate": 9.852296255043129e-05, | |
| "loss": 0.0741, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.263157894736842, | |
| "grad_norm": 0.8119587898254395, | |
| "learning_rate": 9.841614634968843e-05, | |
| "loss": 0.0732, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.2894736842105263, | |
| "grad_norm": 0.45451977849006653, | |
| "learning_rate": 9.830566347054868e-05, | |
| "loss": 0.0734, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.3157894736842106, | |
| "grad_norm": 0.48096764087677, | |
| "learning_rate": 9.819152228016257e-05, | |
| "loss": 0.0729, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.3421052631578947, | |
| "grad_norm": 0.4565185606479645, | |
| "learning_rate": 9.807373142273395e-05, | |
| "loss": 0.0673, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.368421052631579, | |
| "grad_norm": 0.7846236824989319, | |
| "learning_rate": 9.795229981886521e-05, | |
| "loss": 0.0687, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.3947368421052633, | |
| "grad_norm": 0.46232283115386963, | |
| "learning_rate": 9.782723666488181e-05, | |
| "loss": 0.0718, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.4210526315789473, | |
| "grad_norm": 0.5114668607711792, | |
| "learning_rate": 9.769855143213575e-05, | |
| "loss": 0.0739, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.4473684210526316, | |
| "grad_norm": 0.7048826217651367, | |
| "learning_rate": 9.756625386628832e-05, | |
| "loss": 0.066, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.4736842105263157, | |
| "grad_norm": 0.609493613243103, | |
| "learning_rate": 9.743035398657201e-05, | |
| "loss": 0.0744, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 0.6096906065940857, | |
| "learning_rate": 9.729086208503174e-05, | |
| "loss": 0.0678, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.526315789473684, | |
| "grad_norm": 0.8587449193000793, | |
| "learning_rate": 9.714778872574541e-05, | |
| "loss": 0.0656, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.5526315789473686, | |
| "grad_norm": 0.576169490814209, | |
| "learning_rate": 9.700114474402387e-05, | |
| "loss": 0.0715, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.5789473684210527, | |
| "grad_norm": 0.6562088131904602, | |
| "learning_rate": 9.685094124559034e-05, | |
| "loss": 0.0694, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.6052631578947367, | |
| "grad_norm": 0.3795994818210602, | |
| "learning_rate": 9.669718960573927e-05, | |
| "loss": 0.0643, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.631578947368421, | |
| "grad_norm": 0.5144829154014587, | |
| "learning_rate": 9.653990146847499e-05, | |
| "loss": 0.0713, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.6578947368421053, | |
| "grad_norm": 0.34501057863235474, | |
| "learning_rate": 9.637908874562978e-05, | |
| "loss": 0.0655, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.6842105263157894, | |
| "grad_norm": 0.3585371673107147, | |
| "learning_rate": 9.621476361596177e-05, | |
| "loss": 0.0634, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.7105263157894737, | |
| "grad_norm": 0.4583841562271118, | |
| "learning_rate": 9.604693852423268e-05, | |
| "loss": 0.0603, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.736842105263158, | |
| "grad_norm": 0.372306764125824, | |
| "learning_rate": 9.58756261802652e-05, | |
| "loss": 0.0606, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.763157894736842, | |
| "grad_norm": 0.49868544936180115, | |
| "learning_rate": 9.570083955798065e-05, | |
| "loss": 0.0651, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.7894736842105263, | |
| "grad_norm": 0.531895101070404, | |
| "learning_rate": 9.552259189441626e-05, | |
| "loss": 0.0708, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.8157894736842106, | |
| "grad_norm": 0.5189070701599121, | |
| "learning_rate": 9.534089668872274e-05, | |
| "loss": 0.0688, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.8421052631578947, | |
| "grad_norm": 0.36183297634124756, | |
| "learning_rate": 9.515576770114199e-05, | |
| "loss": 0.0684, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.868421052631579, | |
| "grad_norm": 0.2646963894367218, | |
| "learning_rate": 9.496721895196497e-05, | |
| "loss": 0.0604, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.8947368421052633, | |
| "grad_norm": 0.4395381510257721, | |
| "learning_rate": 9.477526472046995e-05, | |
| "loss": 0.0523, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.9210526315789473, | |
| "grad_norm": 0.5579097867012024, | |
| "learning_rate": 9.457991954384105e-05, | |
| "loss": 0.0612, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 1.9473684210526314, | |
| "grad_norm": 0.4455315172672272, | |
| "learning_rate": 9.438119821606727e-05, | |
| "loss": 0.0625, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.973684210526316, | |
| "grad_norm": 0.5463271737098694, | |
| "learning_rate": 9.417911578682229e-05, | |
| "loss": 0.0605, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.7862467765808105, | |
| "learning_rate": 9.397368756032445e-05, | |
| "loss": 0.0606, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 2.026315789473684, | |
| "grad_norm": 0.48962733149528503, | |
| "learning_rate": 9.376492909417795e-05, | |
| "loss": 0.0565, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 2.0526315789473686, | |
| "grad_norm": 0.37852731347084045, | |
| "learning_rate": 9.35528561981945e-05, | |
| "loss": 0.0622, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 2.0789473684210527, | |
| "grad_norm": 0.37320488691329956, | |
| "learning_rate": 9.333748493319603e-05, | |
| "loss": 0.0602, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 2.1052631578947367, | |
| "grad_norm": 0.5312328338623047, | |
| "learning_rate": 9.311883160979844e-05, | |
| "loss": 0.0522, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.1315789473684212, | |
| "grad_norm": 0.5505270957946777, | |
| "learning_rate": 9.289691278717623e-05, | |
| "loss": 0.0544, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 2.1578947368421053, | |
| "grad_norm": 0.6213037371635437, | |
| "learning_rate": 9.267174527180853e-05, | |
| "loss": 0.0647, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 2.1842105263157894, | |
| "grad_norm": 0.5001884698867798, | |
| "learning_rate": 9.244334611620629e-05, | |
| "loss": 0.0573, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 2.2105263157894735, | |
| "grad_norm": 0.41479626297950745, | |
| "learning_rate": 9.221173261762073e-05, | |
| "loss": 0.0576, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 2.236842105263158, | |
| "grad_norm": 0.4636107385158539, | |
| "learning_rate": 9.197692231673361e-05, | |
| "loss": 0.0607, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 2.263157894736842, | |
| "grad_norm": 0.4859972298145294, | |
| "learning_rate": 9.173893299632856e-05, | |
| "loss": 0.0561, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 2.2894736842105265, | |
| "grad_norm": 0.3786041736602783, | |
| "learning_rate": 9.149778267994457e-05, | |
| "loss": 0.0594, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 2.3157894736842106, | |
| "grad_norm": 0.5478907823562622, | |
| "learning_rate": 9.12534896305109e-05, | |
| "loss": 0.0547, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 2.3421052631578947, | |
| "grad_norm": 0.3971192240715027, | |
| "learning_rate": 9.100607234896397e-05, | |
| "loss": 0.058, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 2.3684210526315788, | |
| "grad_norm": 0.4420956075191498, | |
| "learning_rate": 9.075554957284633e-05, | |
| "loss": 0.0576, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.3947368421052633, | |
| "grad_norm": 0.5636497139930725, | |
| "learning_rate": 9.050194027488754e-05, | |
| "loss": 0.0513, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 2.4210526315789473, | |
| "grad_norm": 0.6197888255119324, | |
| "learning_rate": 9.024526366156732e-05, | |
| "loss": 0.0547, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 2.4473684210526314, | |
| "grad_norm": 0.5714887976646423, | |
| "learning_rate": 8.998553917166108e-05, | |
| "loss": 0.0605, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 2.473684210526316, | |
| "grad_norm": 0.3763100206851959, | |
| "learning_rate": 8.972278647476764e-05, | |
| "loss": 0.053, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "grad_norm": 0.4168098270893097, | |
| "learning_rate": 8.945702546981969e-05, | |
| "loss": 0.0587, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 2.526315789473684, | |
| "grad_norm": 0.3482176959514618, | |
| "learning_rate": 8.918827628357677e-05, | |
| "loss": 0.053, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 2.5526315789473686, | |
| "grad_norm": 0.4938332736492157, | |
| "learning_rate": 8.891655926910103e-05, | |
| "loss": 0.06, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 2.5789473684210527, | |
| "grad_norm": 0.3451533317565918, | |
| "learning_rate": 8.864189500421582e-05, | |
| "loss": 0.0612, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 2.6052631578947367, | |
| "grad_norm": 0.4287240505218506, | |
| "learning_rate": 8.836430428994732e-05, | |
| "loss": 0.054, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 2.6315789473684212, | |
| "grad_norm": 0.6272952556610107, | |
| "learning_rate": 8.808380814894912e-05, | |
| "loss": 0.0555, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.6578947368421053, | |
| "grad_norm": 0.46518048644065857, | |
| "learning_rate": 8.780042782391028e-05, | |
| "loss": 0.0608, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 2.6842105263157894, | |
| "grad_norm": 0.7546030282974243, | |
| "learning_rate": 8.751418477594645e-05, | |
| "loss": 0.0566, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 2.7105263157894735, | |
| "grad_norm": 0.6570419073104858, | |
| "learning_rate": 8.722510068297454e-05, | |
| "loss": 0.0565, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 2.736842105263158, | |
| "grad_norm": 0.5381316542625427, | |
| "learning_rate": 8.693319743807116e-05, | |
| "loss": 0.0534, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 2.763157894736842, | |
| "grad_norm": 0.566612958908081, | |
| "learning_rate": 8.663849714781442e-05, | |
| "loss": 0.05, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 2.7894736842105265, | |
| "grad_norm": 0.49792104959487915, | |
| "learning_rate": 8.634102213060984e-05, | |
| "loss": 0.0501, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 2.8157894736842106, | |
| "grad_norm": 0.39989131689071655, | |
| "learning_rate": 8.60407949150001e-05, | |
| "loss": 0.0541, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 2.8421052631578947, | |
| "grad_norm": 0.3729485273361206, | |
| "learning_rate": 8.573783823795889e-05, | |
| "loss": 0.0568, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 2.8684210526315788, | |
| "grad_norm": 0.3304407000541687, | |
| "learning_rate": 8.543217504316896e-05, | |
| "loss": 0.0508, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 2.8947368421052633, | |
| "grad_norm": 0.3478791415691376, | |
| "learning_rate": 8.512382847928461e-05, | |
| "loss": 0.0544, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.9210526315789473, | |
| "grad_norm": 0.35698530077934265, | |
| "learning_rate": 8.48128218981785e-05, | |
| "loss": 0.0522, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 2.9473684210526314, | |
| "grad_norm": 0.37133410573005676, | |
| "learning_rate": 8.44991788531732e-05, | |
| "loss": 0.0488, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 2.973684210526316, | |
| "grad_norm": 0.31634142994880676, | |
| "learning_rate": 8.418292309725738e-05, | |
| "loss": 0.0551, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 0.5727193355560303, | |
| "learning_rate": 8.386407858128706e-05, | |
| "loss": 0.0497, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 3.026315789473684, | |
| "grad_norm": 0.3365287482738495, | |
| "learning_rate": 8.35426694521716e-05, | |
| "loss": 0.048, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 3.0526315789473686, | |
| "grad_norm": 0.26241013407707214, | |
| "learning_rate": 8.321872005104509e-05, | |
| "loss": 0.0517, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 3.0789473684210527, | |
| "grad_norm": 0.39349165558815, | |
| "learning_rate": 8.289225491142292e-05, | |
| "loss": 0.0559, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 3.1052631578947367, | |
| "grad_norm": 0.4374188482761383, | |
| "learning_rate": 8.256329875734375e-05, | |
| "loss": 0.0544, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 3.1315789473684212, | |
| "grad_norm": 0.3512132465839386, | |
| "learning_rate": 8.223187650149712e-05, | |
| "loss": 0.0477, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 3.1578947368421053, | |
| "grad_norm": 0.3832947313785553, | |
| "learning_rate": 8.189801324333681e-05, | |
| "loss": 0.0453, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 3.1842105263157894, | |
| "grad_norm": 0.27593138813972473, | |
| "learning_rate": 8.156173426717988e-05, | |
| "loss": 0.0529, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 3.2105263157894735, | |
| "grad_norm": 0.3951173424720764, | |
| "learning_rate": 8.122306504029194e-05, | |
| "loss": 0.0524, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 3.236842105263158, | |
| "grad_norm": 0.3123633563518524, | |
| "learning_rate": 8.08820312109583e-05, | |
| "loss": 0.0477, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 3.263157894736842, | |
| "grad_norm": 0.4703565835952759, | |
| "learning_rate": 8.053865860654175e-05, | |
| "loss": 0.0473, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 3.2894736842105265, | |
| "grad_norm": 0.3525274991989136, | |
| "learning_rate": 8.019297323152642e-05, | |
| "loss": 0.057, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 3.3157894736842106, | |
| "grad_norm": 0.352622926235199, | |
| "learning_rate": 7.984500126554853e-05, | |
| "loss": 0.0487, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 3.3421052631578947, | |
| "grad_norm": 0.5331799387931824, | |
| "learning_rate": 7.94947690614136e-05, | |
| "loss": 0.0519, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 3.3684210526315788, | |
| "grad_norm": 0.5408539772033691, | |
| "learning_rate": 7.914230314310079e-05, | |
| "loss": 0.0467, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 3.3947368421052633, | |
| "grad_norm": 0.42730775475502014, | |
| "learning_rate": 7.878763020375415e-05, | |
| "loss": 0.0486, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 3.4210526315789473, | |
| "grad_norm": 0.3785395920276642, | |
| "learning_rate": 7.843077710366105e-05, | |
| "loss": 0.0518, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 3.4473684210526314, | |
| "grad_norm": 0.3049032986164093, | |
| "learning_rate": 7.807177086821802e-05, | |
| "loss": 0.0433, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 3.473684210526316, | |
| "grad_norm": 0.3494362533092499, | |
| "learning_rate": 7.771063868588399e-05, | |
| "loss": 0.0453, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "grad_norm": 0.4008173942565918, | |
| "learning_rate": 7.734740790612136e-05, | |
| "loss": 0.0544, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 3.526315789473684, | |
| "grad_norm": 0.5177074074745178, | |
| "learning_rate": 7.698210603732454e-05, | |
| "loss": 0.0433, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 3.5526315789473686, | |
| "grad_norm": 0.42569538950920105, | |
| "learning_rate": 7.661476074473695e-05, | |
| "loss": 0.0428, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 3.5789473684210527, | |
| "grad_norm": 0.36168932914733887, | |
| "learning_rate": 7.624539984835557e-05, | |
| "loss": 0.0466, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 3.6052631578947367, | |
| "grad_norm": 0.4134399890899658, | |
| "learning_rate": 7.587405132082433e-05, | |
| "loss": 0.0468, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 3.6315789473684212, | |
| "grad_norm": 0.2959583103656769, | |
| "learning_rate": 7.550074328531545e-05, | |
| "loss": 0.0477, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 3.6578947368421053, | |
| "grad_norm": 0.4948980510234833, | |
| "learning_rate": 7.512550401339971e-05, | |
| "loss": 0.0453, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 3.6842105263157894, | |
| "grad_norm": 0.5422468185424805, | |
| "learning_rate": 7.47483619229054e-05, | |
| "loss": 0.049, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 3.7105263157894735, | |
| "grad_norm": 0.4651060402393341, | |
| "learning_rate": 7.436934557576612e-05, | |
| "loss": 0.0486, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 3.736842105263158, | |
| "grad_norm": 0.37345531582832336, | |
| "learning_rate": 7.39884836758576e-05, | |
| "loss": 0.0428, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 3.763157894736842, | |
| "grad_norm": 0.4845902621746063, | |
| "learning_rate": 7.360580506682414e-05, | |
| "loss": 0.0435, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 3.7894736842105265, | |
| "grad_norm": 0.38114190101623535, | |
| "learning_rate": 7.322133872989398e-05, | |
| "loss": 0.0384, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 3.8157894736842106, | |
| "grad_norm": 0.4120785892009735, | |
| "learning_rate": 7.283511378168458e-05, | |
| "loss": 0.0422, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 3.8421052631578947, | |
| "grad_norm": 0.4169304370880127, | |
| "learning_rate": 7.244715947199749e-05, | |
| "loss": 0.0413, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 3.8684210526315788, | |
| "grad_norm": 0.3038704991340637, | |
| "learning_rate": 7.20575051816033e-05, | |
| "loss": 0.0445, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 3.8947368421052633, | |
| "grad_norm": 0.3277107775211334, | |
| "learning_rate": 7.16661804200164e-05, | |
| "loss": 0.0443, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 3.9210526315789473, | |
| "grad_norm": 0.3675183057785034, | |
| "learning_rate": 7.127321482326026e-05, | |
| "loss": 0.046, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 3.9473684210526314, | |
| "grad_norm": 0.3455309569835663, | |
| "learning_rate": 7.087863815162298e-05, | |
| "loss": 0.0424, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 3.973684210526316, | |
| "grad_norm": 0.49531644582748413, | |
| "learning_rate": 7.04824802874035e-05, | |
| "loss": 0.0457, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 0.6025938391685486, | |
| "learning_rate": 7.008477123264848e-05, | |
| "loss": 0.0497, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 4.026315789473684, | |
| "grad_norm": 0.2605507969856262, | |
| "learning_rate": 6.96855411068802e-05, | |
| "loss": 0.047, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 4.052631578947368, | |
| "grad_norm": 0.3557581603527069, | |
| "learning_rate": 6.928482014481558e-05, | |
| "loss": 0.0434, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 4.078947368421052, | |
| "grad_norm": 0.6790323257446289, | |
| "learning_rate": 6.888263869407631e-05, | |
| "loss": 0.0431, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 4.105263157894737, | |
| "grad_norm": 0.5850968360900879, | |
| "learning_rate": 6.847902721289068e-05, | |
| "loss": 0.0444, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 4.131578947368421, | |
| "grad_norm": 0.22265614569187164, | |
| "learning_rate": 6.807401626778679e-05, | |
| "loss": 0.0463, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 4.157894736842105, | |
| "grad_norm": 0.3996434509754181, | |
| "learning_rate": 6.766763653127773e-05, | |
| "loss": 0.0391, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 4.184210526315789, | |
| "grad_norm": 0.4038737118244171, | |
| "learning_rate": 6.725991877953868e-05, | |
| "loss": 0.0432, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 4.2105263157894735, | |
| "grad_norm": 0.5624067187309265, | |
| "learning_rate": 6.685089389007612e-05, | |
| "loss": 0.0437, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 4.2368421052631575, | |
| "grad_norm": 0.32445138692855835, | |
| "learning_rate": 6.644059283938938e-05, | |
| "loss": 0.0439, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 4.2631578947368425, | |
| "grad_norm": 0.385633647441864, | |
| "learning_rate": 6.602904670062476e-05, | |
| "loss": 0.0362, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 4.2894736842105265, | |
| "grad_norm": 0.4192872643470764, | |
| "learning_rate": 6.561628664122226e-05, | |
| "loss": 0.0439, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 4.315789473684211, | |
| "grad_norm": 0.46780234575271606, | |
| "learning_rate": 6.520234392055522e-05, | |
| "loss": 0.0447, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 4.342105263157895, | |
| "grad_norm": 0.30417683720588684, | |
| "learning_rate": 6.478724988756285e-05, | |
| "loss": 0.0413, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 4.368421052631579, | |
| "grad_norm": 0.3585522472858429, | |
| "learning_rate": 6.437103597837631e-05, | |
| "loss": 0.0451, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 4.394736842105263, | |
| "grad_norm": 0.2543241083621979, | |
| "learning_rate": 6.39537337139377e-05, | |
| "loss": 0.0454, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 4.421052631578947, | |
| "grad_norm": 0.41101086139678955, | |
| "learning_rate": 6.353537469761315e-05, | |
| "loss": 0.0468, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 4.447368421052632, | |
| "grad_norm": 0.2859801650047302, | |
| "learning_rate": 6.311599061279932e-05, | |
| "loss": 0.0462, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 4.473684210526316, | |
| "grad_norm": 0.2935991585254669, | |
| "learning_rate": 6.269561322052378e-05, | |
| "loss": 0.0457, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 4.5, | |
| "grad_norm": 0.311879426240921, | |
| "learning_rate": 6.227427435703997e-05, | |
| "loss": 0.0419, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 4.526315789473684, | |
| "grad_norm": 0.4428638517856598, | |
| "learning_rate": 6.185200593141593e-05, | |
| "loss": 0.0412, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 4.552631578947368, | |
| "grad_norm": 0.44332432746887207, | |
| "learning_rate": 6.142883992311781e-05, | |
| "loss": 0.0391, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 4.578947368421053, | |
| "grad_norm": 0.31303486227989197, | |
| "learning_rate": 6.100480837958802e-05, | |
| "loss": 0.0478, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 4.605263157894737, | |
| "grad_norm": 0.4248807430267334, | |
| "learning_rate": 6.057994341381813e-05, | |
| "loss": 0.0419, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 4.631578947368421, | |
| "grad_norm": 0.38378843665122986, | |
| "learning_rate": 6.015427720191693e-05, | |
| "loss": 0.0388, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 4.657894736842105, | |
| "grad_norm": 0.232202410697937, | |
| "learning_rate": 5.9727841980673604e-05, | |
| "loss": 0.0491, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 4.684210526315789, | |
| "grad_norm": 0.3846134841442108, | |
| "learning_rate": 5.93006700451164e-05, | |
| "loss": 0.0442, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 4.7105263157894735, | |
| "grad_norm": 0.24118691682815552, | |
| "learning_rate": 5.887279374606679e-05, | |
| "loss": 0.0379, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 4.7368421052631575, | |
| "grad_norm": 0.3538924753665924, | |
| "learning_rate": 5.844424548768952e-05, | |
| "loss": 0.0371, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 4.7631578947368425, | |
| "grad_norm": 0.2391858547925949, | |
| "learning_rate": 5.8015057725038534e-05, | |
| "loss": 0.0393, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 4.7894736842105265, | |
| "grad_norm": 0.43974366784095764, | |
| "learning_rate": 5.7585262961599054e-05, | |
| "loss": 0.0408, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 4.815789473684211, | |
| "grad_norm": 0.3488527834415436, | |
| "learning_rate": 5.7154893746826014e-05, | |
| "loss": 0.0419, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 4.842105263157895, | |
| "grad_norm": 0.5002457499504089, | |
| "learning_rate": 5.672398267367902e-05, | |
| "loss": 0.0403, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 4.868421052631579, | |
| "grad_norm": 0.31320708990097046, | |
| "learning_rate": 5.6292562376154037e-05, | |
| "loss": 0.0423, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 4.894736842105263, | |
| "grad_norm": 0.26685863733291626, | |
| "learning_rate": 5.586066552681179e-05, | |
| "loss": 0.0377, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 4.921052631578947, | |
| "grad_norm": 0.3947713077068329, | |
| "learning_rate": 5.542832483430363e-05, | |
| "loss": 0.0401, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 4.947368421052632, | |
| "grad_norm": 0.20824529230594635, | |
| "learning_rate": 5.499557304089419e-05, | |
| "loss": 0.0382, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 4.973684210526316, | |
| "grad_norm": 0.25169357657432556, | |
| "learning_rate": 5.4562442919981816e-05, | |
| "loss": 0.0339, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 0.4444282054901123, | |
| "learning_rate": 5.4128967273616625e-05, | |
| "loss": 0.0443, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 5.026315789473684, | |
| "grad_norm": 0.4260099530220032, | |
| "learning_rate": 5.3695178930016196e-05, | |
| "loss": 0.0364, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 5.052631578947368, | |
| "grad_norm": 0.33936482667922974, | |
| "learning_rate": 5.3261110741079525e-05, | |
| "loss": 0.0367, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 5.078947368421052, | |
| "grad_norm": 0.5758324861526489, | |
| "learning_rate": 5.2826795579898956e-05, | |
| "loss": 0.0383, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 5.105263157894737, | |
| "grad_norm": 0.4980020821094513, | |
| "learning_rate": 5.2392266338270736e-05, | |
| "loss": 0.0422, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 5.131578947368421, | |
| "grad_norm": 0.4701398015022278, | |
| "learning_rate": 5.195755592420387e-05, | |
| "loss": 0.0372, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 5.157894736842105, | |
| "grad_norm": 0.3783451020717621, | |
| "learning_rate": 5.1522697259428146e-05, | |
| "loss": 0.0371, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 5.184210526315789, | |
| "grad_norm": 0.41548261046409607, | |
| "learning_rate": 5.1087723276900646e-05, | |
| "loss": 0.0415, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 5.2105263157894735, | |
| "grad_norm": 0.3551521897315979, | |
| "learning_rate": 5.065266691831181e-05, | |
| "loss": 0.0344, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 5.2368421052631575, | |
| "grad_norm": 0.5270403623580933, | |
| "learning_rate": 5.021756113159062e-05, | |
| "loss": 0.0355, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 5.2631578947368425, | |
| "grad_norm": 0.29675352573394775, | |
| "learning_rate": 4.978243886840939e-05, | |
| "loss": 0.0424, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 5.2894736842105265, | |
| "grad_norm": 0.3667472302913666, | |
| "learning_rate": 4.934733308168821e-05, | |
| "loss": 0.0449, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 5.315789473684211, | |
| "grad_norm": 0.34768638014793396, | |
| "learning_rate": 4.891227672309935e-05, | |
| "loss": 0.041, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 5.342105263157895, | |
| "grad_norm": 0.38154706358909607, | |
| "learning_rate": 4.8477302740571866e-05, | |
| "loss": 0.0382, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 5.368421052631579, | |
| "grad_norm": 0.16855105757713318, | |
| "learning_rate": 4.804244407579613e-05, | |
| "loss": 0.0376, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 5.394736842105263, | |
| "grad_norm": 0.3421989679336548, | |
| "learning_rate": 4.760773366172929e-05, | |
| "loss": 0.0381, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 5.421052631578947, | |
| "grad_norm": 0.3012019991874695, | |
| "learning_rate": 4.717320442010105e-05, | |
| "loss": 0.0353, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 5.447368421052632, | |
| "grad_norm": 0.2907329797744751, | |
| "learning_rate": 4.673888925892048e-05, | |
| "loss": 0.0372, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 5.473684210526316, | |
| "grad_norm": 0.3655814826488495, | |
| "learning_rate": 4.630482106998381e-05, | |
| "loss": 0.0354, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 5.5, | |
| "grad_norm": 0.3697777986526489, | |
| "learning_rate": 4.5871032726383386e-05, | |
| "loss": 0.0426, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 5.526315789473684, | |
| "grad_norm": 0.22509945929050446, | |
| "learning_rate": 4.5437557080018175e-05, | |
| "loss": 0.0358, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 5.552631578947368, | |
| "grad_norm": 0.30516788363456726, | |
| "learning_rate": 4.500442695910582e-05, | |
| "loss": 0.0411, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 5.578947368421053, | |
| "grad_norm": 0.3428977429866791, | |
| "learning_rate": 4.457167516569637e-05, | |
| "loss": 0.032, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 5.605263157894737, | |
| "grad_norm": 0.2875311076641083, | |
| "learning_rate": 4.413933447318821e-05, | |
| "loss": 0.0339, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 5.631578947368421, | |
| "grad_norm": 0.3058890700340271, | |
| "learning_rate": 4.3707437623845995e-05, | |
| "loss": 0.035, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 5.657894736842105, | |
| "grad_norm": 0.317531019449234, | |
| "learning_rate": 4.3276017326320985e-05, | |
| "loss": 0.0324, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 5.684210526315789, | |
| "grad_norm": 0.3118530809879303, | |
| "learning_rate": 4.2845106253174e-05, | |
| "loss": 0.0345, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 5.7105263157894735, | |
| "grad_norm": 0.2496698647737503, | |
| "learning_rate": 4.2414737038400964e-05, | |
| "loss": 0.0373, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 5.7368421052631575, | |
| "grad_norm": 0.26971638202667236, | |
| "learning_rate": 4.198494227496148e-05, | |
| "loss": 0.0368, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 5.7631578947368425, | |
| "grad_norm": 0.43503808975219727, | |
| "learning_rate": 4.155575451231048e-05, | |
| "loss": 0.0348, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 5.7894736842105265, | |
| "grad_norm": 0.26233163475990295, | |
| "learning_rate": 4.112720625393322e-05, | |
| "loss": 0.0354, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 5.815789473684211, | |
| "grad_norm": 0.40549346804618835, | |
| "learning_rate": 4.069932995488361e-05, | |
| "loss": 0.0385, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 5.842105263157895, | |
| "grad_norm": 0.3487369120121002, | |
| "learning_rate": 4.0272158019326414e-05, | |
| "loss": 0.0365, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 5.868421052631579, | |
| "grad_norm": 0.35258445143699646, | |
| "learning_rate": 3.9845722798083066e-05, | |
| "loss": 0.035, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 5.894736842105263, | |
| "grad_norm": 0.3888448476791382, | |
| "learning_rate": 3.942005658618188e-05, | |
| "loss": 0.0357, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 5.921052631578947, | |
| "grad_norm": 0.41619524359703064, | |
| "learning_rate": 3.8995191620412e-05, | |
| "loss": 0.0352, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 5.947368421052632, | |
| "grad_norm": 0.5103023052215576, | |
| "learning_rate": 3.8571160076882204e-05, | |
| "loss": 0.0331, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 5.973684210526316, | |
| "grad_norm": 0.458965927362442, | |
| "learning_rate": 3.8147994068584087e-05, | |
| "loss": 0.0301, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 0.32402315735816956, | |
| "learning_rate": 3.772572564296005e-05, | |
| "loss": 0.0351, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 6.026315789473684, | |
| "grad_norm": 0.2968176603317261, | |
| "learning_rate": 3.730438677947624e-05, | |
| "loss": 0.0413, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 6.052631578947368, | |
| "grad_norm": 0.3646889626979828, | |
| "learning_rate": 3.6884009387200714e-05, | |
| "loss": 0.0357, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 6.078947368421052, | |
| "grad_norm": 0.26003819704055786, | |
| "learning_rate": 3.646462530238684e-05, | |
| "loss": 0.0334, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 6.105263157894737, | |
| "grad_norm": 0.28209343552589417, | |
| "learning_rate": 3.60462662860623e-05, | |
| "loss": 0.0317, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 6.131578947368421, | |
| "grad_norm": 0.4188937544822693, | |
| "learning_rate": 3.56289640216237e-05, | |
| "loss": 0.0354, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 6.157894736842105, | |
| "grad_norm": 0.44584834575653076, | |
| "learning_rate": 3.521275011243715e-05, | |
| "loss": 0.0395, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 6.184210526315789, | |
| "grad_norm": 0.44341957569122314, | |
| "learning_rate": 3.4797656079444806e-05, | |
| "loss": 0.033, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 6.2105263157894735, | |
| "grad_norm": 0.3678707182407379, | |
| "learning_rate": 3.4383713358777735e-05, | |
| "loss": 0.0344, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 6.2368421052631575, | |
| "grad_norm": 0.30562394857406616, | |
| "learning_rate": 3.397095329937526e-05, | |
| "loss": 0.0339, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 6.2631578947368425, | |
| "grad_norm": 0.4624996781349182, | |
| "learning_rate": 3.355940716061064e-05, | |
| "loss": 0.0341, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 6.2894736842105265, | |
| "grad_norm": 0.20757588744163513, | |
| "learning_rate": 3.31491061099239e-05, | |
| "loss": 0.0296, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 6.315789473684211, | |
| "grad_norm": 0.31677284836769104, | |
| "learning_rate": 3.274008122046132e-05, | |
| "loss": 0.0338, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 6.342105263157895, | |
| "grad_norm": 0.24551235139369965, | |
| "learning_rate": 3.233236346872227e-05, | |
| "loss": 0.0381, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 6.368421052631579, | |
| "grad_norm": 0.250813364982605, | |
| "learning_rate": 3.192598373221322e-05, | |
| "loss": 0.0333, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 6.394736842105263, | |
| "grad_norm": 0.5114396810531616, | |
| "learning_rate": 3.152097278710933e-05, | |
| "loss": 0.0396, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 6.421052631578947, | |
| "grad_norm": 0.4336398243904114, | |
| "learning_rate": 3.1117361305923684e-05, | |
| "loss": 0.0361, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 6.447368421052632, | |
| "grad_norm": 0.3308594226837158, | |
| "learning_rate": 3.071517985518442e-05, | |
| "loss": 0.0314, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 6.473684210526316, | |
| "grad_norm": 0.4118829667568207, | |
| "learning_rate": 3.0314458893119808e-05, | |
| "loss": 0.0337, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 6.5, | |
| "grad_norm": 0.19590795040130615, | |
| "learning_rate": 2.991522876735154e-05, | |
| "loss": 0.0359, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 6.526315789473684, | |
| "grad_norm": 0.39492878317832947, | |
| "learning_rate": 2.9517519712596498e-05, | |
| "loss": 0.0304, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 6.552631578947368, | |
| "grad_norm": 0.2706056833267212, | |
| "learning_rate": 2.9121361848377014e-05, | |
| "loss": 0.0301, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 6.578947368421053, | |
| "grad_norm": 0.2509630024433136, | |
| "learning_rate": 2.872678517673975e-05, | |
| "loss": 0.0313, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 6.605263157894737, | |
| "grad_norm": 0.37828516960144043, | |
| "learning_rate": 2.8333819579983623e-05, | |
| "loss": 0.0323, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 6.631578947368421, | |
| "grad_norm": 0.3628530204296112, | |
| "learning_rate": 2.794249481839669e-05, | |
| "loss": 0.0292, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 6.657894736842105, | |
| "grad_norm": 0.35174816846847534, | |
| "learning_rate": 2.7552840528002498e-05, | |
| "loss": 0.0326, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 6.684210526315789, | |
| "grad_norm": 0.3942660391330719, | |
| "learning_rate": 2.7164886218315444e-05, | |
| "loss": 0.0314, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 6.7105263157894735, | |
| "grad_norm": 0.2891586124897003, | |
| "learning_rate": 2.6778661270106025e-05, | |
| "loss": 0.0346, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 6.7368421052631575, | |
| "grad_norm": 0.3602871000766754, | |
| "learning_rate": 2.6394194933175875e-05, | |
| "loss": 0.0338, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 6.7631578947368425, | |
| "grad_norm": 0.3285452127456665, | |
| "learning_rate": 2.601151632414241e-05, | |
| "loss": 0.0301, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 6.7894736842105265, | |
| "grad_norm": 0.3526369035243988, | |
| "learning_rate": 2.5630654424233903e-05, | |
| "loss": 0.0331, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 6.815789473684211, | |
| "grad_norm": 0.2297569215297699, | |
| "learning_rate": 2.5251638077094602e-05, | |
| "loss": 0.0311, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 6.842105263157895, | |
| "grad_norm": 0.24023893475532532, | |
| "learning_rate": 2.4874495986600294e-05, | |
| "loss": 0.0299, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 6.868421052631579, | |
| "grad_norm": 0.3183501660823822, | |
| "learning_rate": 2.4499256714684565e-05, | |
| "loss": 0.0329, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 6.894736842105263, | |
| "grad_norm": 0.335347056388855, | |
| "learning_rate": 2.4125948679175686e-05, | |
| "loss": 0.0302, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 6.921052631578947, | |
| "grad_norm": 0.31279057264328003, | |
| "learning_rate": 2.3754600151644445e-05, | |
| "loss": 0.0317, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 6.947368421052632, | |
| "grad_norm": 0.25722017884254456, | |
| "learning_rate": 2.3385239255263077e-05, | |
| "loss": 0.034, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 6.973684210526316, | |
| "grad_norm": 0.4903739392757416, | |
| "learning_rate": 2.3017893962675458e-05, | |
| "loss": 0.0272, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "grad_norm": 0.31394830346107483, | |
| "learning_rate": 2.2652592093878666e-05, | |
| "loss": 0.0343, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 7.026315789473684, | |
| "grad_norm": 0.24519610404968262, | |
| "learning_rate": 2.228936131411601e-05, | |
| "loss": 0.0283, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 7.052631578947368, | |
| "grad_norm": 0.3303487002849579, | |
| "learning_rate": 2.1928229131782007e-05, | |
| "loss": 0.0311, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 7.078947368421052, | |
| "grad_norm": 0.18910463154315948, | |
| "learning_rate": 2.1569222896338966e-05, | |
| "loss": 0.0272, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 7.105263157894737, | |
| "grad_norm": 0.2918621003627777, | |
| "learning_rate": 2.1212369796245864e-05, | |
| "loss": 0.0298, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 7.131578947368421, | |
| "grad_norm": 0.42113614082336426, | |
| "learning_rate": 2.0857696856899232e-05, | |
| "loss": 0.0295, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 7.157894736842105, | |
| "grad_norm": 0.3034079670906067, | |
| "learning_rate": 2.0505230938586418e-05, | |
| "loss": 0.0235, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 7.184210526315789, | |
| "grad_norm": 0.4173114001750946, | |
| "learning_rate": 2.0154998734451474e-05, | |
| "loss": 0.0302, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 7.2105263157894735, | |
| "grad_norm": 0.3530351519584656, | |
| "learning_rate": 1.980702676847358e-05, | |
| "loss": 0.0322, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 7.2368421052631575, | |
| "grad_norm": 0.29570046067237854, | |
| "learning_rate": 1.9461341393458254e-05, | |
| "loss": 0.0272, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 7.2631578947368425, | |
| "grad_norm": 0.2424498051404953, | |
| "learning_rate": 1.9117968789041712e-05, | |
| "loss": 0.028, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 7.2894736842105265, | |
| "grad_norm": 0.3934868574142456, | |
| "learning_rate": 1.877693495970809e-05, | |
| "loss": 0.0272, | |
| "step": 2770 | |
| }, | |
| { | |
| "epoch": 7.315789473684211, | |
| "grad_norm": 0.21242979168891907, | |
| "learning_rate": 1.8438265732820126e-05, | |
| "loss": 0.0327, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 7.342105263157895, | |
| "grad_norm": 0.37688693404197693, | |
| "learning_rate": 1.8101986756663197e-05, | |
| "loss": 0.0351, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 7.368421052631579, | |
| "grad_norm": 0.22811609506607056, | |
| "learning_rate": 1.776812349850289e-05, | |
| "loss": 0.0276, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 7.394736842105263, | |
| "grad_norm": 0.22656874358654022, | |
| "learning_rate": 1.7436701242656272e-05, | |
| "loss": 0.0287, | |
| "step": 2810 | |
| }, | |
| { | |
| "epoch": 7.421052631578947, | |
| "grad_norm": 0.35913366079330444, | |
| "learning_rate": 1.7107745088577087e-05, | |
| "loss": 0.0309, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 7.447368421052632, | |
| "grad_norm": 0.23046566545963287, | |
| "learning_rate": 1.678127994895492e-05, | |
| "loss": 0.0242, | |
| "step": 2830 | |
| }, | |
| { | |
| "epoch": 7.473684210526316, | |
| "grad_norm": 0.5616809725761414, | |
| "learning_rate": 1.6457330547828402e-05, | |
| "loss": 0.0292, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 7.5, | |
| "grad_norm": 0.25659796595573425, | |
| "learning_rate": 1.6135921418712956e-05, | |
| "loss": 0.0265, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 7.526315789473684, | |
| "grad_norm": 0.32121288776397705, | |
| "learning_rate": 1.5817076902742622e-05, | |
| "loss": 0.0283, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 7.552631578947368, | |
| "grad_norm": 0.4093388319015503, | |
| "learning_rate": 1.5500821146826805e-05, | |
| "loss": 0.0338, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 7.578947368421053, | |
| "grad_norm": 0.4066798686981201, | |
| "learning_rate": 1.5187178101821503e-05, | |
| "loss": 0.0354, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 7.605263157894737, | |
| "grad_norm": 0.2548167109489441, | |
| "learning_rate": 1.4876171520715399e-05, | |
| "loss": 0.0289, | |
| "step": 2890 | |
| }, | |
| { | |
| "epoch": 7.631578947368421, | |
| "grad_norm": 0.375201940536499, | |
| "learning_rate": 1.4567824956831043e-05, | |
| "loss": 0.0308, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 7.657894736842105, | |
| "grad_norm": 0.2906716763973236, | |
| "learning_rate": 1.4262161762041121e-05, | |
| "loss": 0.03, | |
| "step": 2910 | |
| }, | |
| { | |
| "epoch": 7.684210526315789, | |
| "grad_norm": 0.25092822313308716, | |
| "learning_rate": 1.3959205084999911e-05, | |
| "loss": 0.0262, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 7.7105263157894735, | |
| "grad_norm": 0.27973148226737976, | |
| "learning_rate": 1.3658977869390166e-05, | |
| "loss": 0.0259, | |
| "step": 2930 | |
| }, | |
| { | |
| "epoch": 7.7368421052631575, | |
| "grad_norm": 0.24641232192516327, | |
| "learning_rate": 1.336150285218558e-05, | |
| "loss": 0.0288, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 7.7631578947368425, | |
| "grad_norm": 0.17812731862068176, | |
| "learning_rate": 1.3066802561928854e-05, | |
| "loss": 0.0302, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 7.7894736842105265, | |
| "grad_norm": 0.2735963761806488, | |
| "learning_rate": 1.2774899317025468e-05, | |
| "loss": 0.0281, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 7.815789473684211, | |
| "grad_norm": 0.2304324209690094, | |
| "learning_rate": 1.2485815224053582e-05, | |
| "loss": 0.0286, | |
| "step": 2970 | |
| }, | |
| { | |
| "epoch": 7.842105263157895, | |
| "grad_norm": 0.28357961773872375, | |
| "learning_rate": 1.2199572176089741e-05, | |
| "loss": 0.0228, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 7.868421052631579, | |
| "grad_norm": 0.20956674218177795, | |
| "learning_rate": 1.1916191851050873e-05, | |
| "loss": 0.0276, | |
| "step": 2990 | |
| }, | |
| { | |
| "epoch": 7.894736842105263, | |
| "grad_norm": 0.25499334931373596, | |
| "learning_rate": 1.163569571005269e-05, | |
| "loss": 0.0263, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 7.921052631578947, | |
| "grad_norm": 0.406367689371109, | |
| "learning_rate": 1.1358104995784186e-05, | |
| "loss": 0.03, | |
| "step": 3010 | |
| }, | |
| { | |
| "epoch": 7.947368421052632, | |
| "grad_norm": 0.49673014879226685, | |
| "learning_rate": 1.1083440730898974e-05, | |
| "loss": 0.029, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 7.973684210526316, | |
| "grad_norm": 0.21329355239868164, | |
| "learning_rate": 1.0811723716423233e-05, | |
| "loss": 0.0254, | |
| "step": 3030 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 0.38303622603416443, | |
| "learning_rate": 1.0542974530180327e-05, | |
| "loss": 0.031, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 8.026315789473685, | |
| "grad_norm": 0.30326029658317566, | |
| "learning_rate": 1.027721352523237e-05, | |
| "loss": 0.031, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 8.052631578947368, | |
| "grad_norm": 0.18923179805278778, | |
| "learning_rate": 1.0014460828338928e-05, | |
| "loss": 0.0239, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 8.078947368421053, | |
| "grad_norm": 0.2916359603404999, | |
| "learning_rate": 9.75473633843268e-06, | |
| "loss": 0.0288, | |
| "step": 3070 | |
| }, | |
| { | |
| "epoch": 8.105263157894736, | |
| "grad_norm": 0.39194855093955994, | |
| "learning_rate": 9.498059725112467e-06, | |
| "loss": 0.0255, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 8.131578947368421, | |
| "grad_norm": 0.23311467468738556, | |
| "learning_rate": 9.244450427153683e-06, | |
| "loss": 0.0271, | |
| "step": 3090 | |
| }, | |
| { | |
| "epoch": 8.157894736842104, | |
| "grad_norm": 0.25806355476379395, | |
| "learning_rate": 8.99392765103605e-06, | |
| "loss": 0.0253, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 8.18421052631579, | |
| "grad_norm": 0.19991613924503326, | |
| "learning_rate": 8.746510369489103e-06, | |
| "loss": 0.0306, | |
| "step": 3110 | |
| }, | |
| { | |
| "epoch": 8.210526315789474, | |
| "grad_norm": 0.26584678888320923, | |
| "learning_rate": 8.502217320055427e-06, | |
| "loss": 0.0295, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 8.236842105263158, | |
| "grad_norm": 0.28366735577583313, | |
| "learning_rate": 8.261067003671447e-06, | |
| "loss": 0.0267, | |
| "step": 3130 | |
| }, | |
| { | |
| "epoch": 8.263157894736842, | |
| "grad_norm": 0.2124335616827011, | |
| "learning_rate": 8.0230776832664e-06, | |
| "loss": 0.027, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 8.289473684210526, | |
| "grad_norm": 0.6940687894821167, | |
| "learning_rate": 7.78826738237926e-06, | |
| "loss": 0.0239, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 8.31578947368421, | |
| "grad_norm": 0.3029802739620209, | |
| "learning_rate": 7.556653883793724e-06, | |
| "loss": 0.0293, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 8.342105263157896, | |
| "grad_norm": 0.33494675159454346, | |
| "learning_rate": 7.328254728191464e-06, | |
| "loss": 0.0322, | |
| "step": 3170 | |
| }, | |
| { | |
| "epoch": 8.368421052631579, | |
| "grad_norm": 0.5959463715553284, | |
| "learning_rate": 7.103087212823778e-06, | |
| "loss": 0.0282, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 8.394736842105264, | |
| "grad_norm": 0.3299950957298279, | |
| "learning_rate": 6.881168390201581e-06, | |
| "loss": 0.0289, | |
| "step": 3190 | |
| }, | |
| { | |
| "epoch": 8.421052631578947, | |
| "grad_norm": 0.28407934308052063, | |
| "learning_rate": 6.66251506680397e-06, | |
| "loss": 0.0277, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 8.447368421052632, | |
| "grad_norm": 0.24567903578281403, | |
| "learning_rate": 6.447143801805516e-06, | |
| "loss": 0.0293, | |
| "step": 3210 | |
| }, | |
| { | |
| "epoch": 8.473684210526315, | |
| "grad_norm": 0.20823001861572266, | |
| "learning_rate": 6.23507090582206e-06, | |
| "loss": 0.0257, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 8.5, | |
| "grad_norm": 0.29089733958244324, | |
| "learning_rate": 6.026312439675552e-06, | |
| "loss": 0.0268, | |
| "step": 3230 | |
| }, | |
| { | |
| "epoch": 8.526315789473685, | |
| "grad_norm": 0.3374447524547577, | |
| "learning_rate": 5.820884213177713e-06, | |
| "loss": 0.0276, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 8.552631578947368, | |
| "grad_norm": 0.32109740376472473, | |
| "learning_rate": 5.618801783932725e-06, | |
| "loss": 0.0302, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 8.578947368421053, | |
| "grad_norm": 0.25355905294418335, | |
| "learning_rate": 5.420080456158971e-06, | |
| "loss": 0.0263, | |
| "step": 3260 | |
| }, | |
| { | |
| "epoch": 8.605263157894736, | |
| "grad_norm": 0.6211085319519043, | |
| "learning_rate": 5.224735279530063e-06, | |
| "loss": 0.0284, | |
| "step": 3270 | |
| }, | |
| { | |
| "epoch": 8.631578947368421, | |
| "grad_norm": 0.23430858552455902, | |
| "learning_rate": 5.032781048035034e-06, | |
| "loss": 0.0264, | |
| "step": 3280 | |
| }, | |
| { | |
| "epoch": 8.657894736842106, | |
| "grad_norm": 0.24149766564369202, | |
| "learning_rate": 4.84423229885802e-06, | |
| "loss": 0.027, | |
| "step": 3290 | |
| }, | |
| { | |
| "epoch": 8.68421052631579, | |
| "grad_norm": 0.3725610077381134, | |
| "learning_rate": 4.659103311277274e-06, | |
| "loss": 0.0253, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 8.710526315789474, | |
| "grad_norm": 0.2504403293132782, | |
| "learning_rate": 4.477408105583741e-06, | |
| "loss": 0.0276, | |
| "step": 3310 | |
| }, | |
| { | |
| "epoch": 8.736842105263158, | |
| "grad_norm": 0.21490493416786194, | |
| "learning_rate": 4.29916044201934e-06, | |
| "loss": 0.0272, | |
| "step": 3320 | |
| }, | |
| { | |
| "epoch": 8.763157894736842, | |
| "grad_norm": 0.30955877900123596, | |
| "learning_rate": 4.124373819734795e-06, | |
| "loss": 0.0308, | |
| "step": 3330 | |
| }, | |
| { | |
| "epoch": 8.789473684210526, | |
| "grad_norm": 0.210093155503273, | |
| "learning_rate": 3.953061475767339e-06, | |
| "loss": 0.0264, | |
| "step": 3340 | |
| }, | |
| { | |
| "epoch": 8.81578947368421, | |
| "grad_norm": 0.29672837257385254, | |
| "learning_rate": 3.785236384038232e-06, | |
| "loss": 0.0295, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 8.842105263157894, | |
| "grad_norm": 0.5261228680610657, | |
| "learning_rate": 3.620911254370224e-06, | |
| "loss": 0.0249, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 8.868421052631579, | |
| "grad_norm": 0.22544153034687042, | |
| "learning_rate": 3.460098531525019e-06, | |
| "loss": 0.028, | |
| "step": 3370 | |
| }, | |
| { | |
| "epoch": 8.894736842105264, | |
| "grad_norm": 0.24784667789936066, | |
| "learning_rate": 3.302810394260736e-06, | |
| "loss": 0.0252, | |
| "step": 3380 | |
| }, | |
| { | |
| "epoch": 8.921052631578947, | |
| "grad_norm": 0.21960538625717163, | |
| "learning_rate": 3.1490587544096782e-06, | |
| "loss": 0.0255, | |
| "step": 3390 | |
| }, | |
| { | |
| "epoch": 8.947368421052632, | |
| "grad_norm": 0.4938012361526489, | |
| "learning_rate": 2.9988552559761294e-06, | |
| "loss": 0.0261, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 8.973684210526315, | |
| "grad_norm": 0.2430790662765503, | |
| "learning_rate": 2.85221127425459e-06, | |
| "loss": 0.0283, | |
| "step": 3410 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "grad_norm": 0.3423117995262146, | |
| "learning_rate": 2.7091379149682685e-06, | |
| "loss": 0.0262, | |
| "step": 3420 | |
| }, | |
| { | |
| "epoch": 9.026315789473685, | |
| "grad_norm": 0.1678830087184906, | |
| "learning_rate": 2.5696460134279955e-06, | |
| "loss": 0.0226, | |
| "step": 3430 | |
| }, | |
| { | |
| "epoch": 9.052631578947368, | |
| "grad_norm": 0.1864800751209259, | |
| "learning_rate": 2.4337461337116894e-06, | |
| "loss": 0.028, | |
| "step": 3440 | |
| }, | |
| { | |
| "epoch": 9.078947368421053, | |
| "grad_norm": 0.3498280942440033, | |
| "learning_rate": 2.3014485678642563e-06, | |
| "loss": 0.0251, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 9.105263157894736, | |
| "grad_norm": 0.2959420680999756, | |
| "learning_rate": 2.1727633351182e-06, | |
| "loss": 0.0267, | |
| "step": 3460 | |
| }, | |
| { | |
| "epoch": 9.131578947368421, | |
| "grad_norm": 0.46708524227142334, | |
| "learning_rate": 2.0477001811347985e-06, | |
| "loss": 0.0271, | |
| "step": 3470 | |
| }, | |
| { | |
| "epoch": 9.157894736842104, | |
| "grad_norm": 0.21950027346611023, | |
| "learning_rate": 1.9262685772660606e-06, | |
| "loss": 0.0241, | |
| "step": 3480 | |
| }, | |
| { | |
| "epoch": 9.18421052631579, | |
| "grad_norm": 0.19924266636371613, | |
| "learning_rate": 1.8084777198374315e-06, | |
| "loss": 0.0276, | |
| "step": 3490 | |
| }, | |
| { | |
| "epoch": 9.210526315789474, | |
| "grad_norm": 0.29325613379478455, | |
| "learning_rate": 1.6943365294513236e-06, | |
| "loss": 0.0278, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 9.236842105263158, | |
| "grad_norm": 0.19263319671154022, | |
| "learning_rate": 1.5838536503115675e-06, | |
| "loss": 0.0275, | |
| "step": 3510 | |
| }, | |
| { | |
| "epoch": 9.263157894736842, | |
| "grad_norm": 0.3293076753616333, | |
| "learning_rate": 1.4770374495687134e-06, | |
| "loss": 0.0232, | |
| "step": 3520 | |
| }, | |
| { | |
| "epoch": 9.289473684210526, | |
| "grad_norm": 0.23276633024215698, | |
| "learning_rate": 1.3738960166864101e-06, | |
| "loss": 0.0245, | |
| "step": 3530 | |
| }, | |
| { | |
| "epoch": 9.31578947368421, | |
| "grad_norm": 0.3246747553348541, | |
| "learning_rate": 1.274437162828751e-06, | |
| "loss": 0.0258, | |
| "step": 3540 | |
| }, | |
| { | |
| "epoch": 9.342105263157896, | |
| "grad_norm": 0.3524140417575836, | |
| "learning_rate": 1.1786684202687026e-06, | |
| "loss": 0.023, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 9.368421052631579, | |
| "grad_norm": 0.27717113494873047, | |
| "learning_rate": 1.0865970418177051e-06, | |
| "loss": 0.0292, | |
| "step": 3560 | |
| }, | |
| { | |
| "epoch": 9.394736842105264, | |
| "grad_norm": 0.29303857684135437, | |
| "learning_rate": 9.98230000276351e-07, | |
| "loss": 0.0239, | |
| "step": 3570 | |
| }, | |
| { | |
| "epoch": 9.421052631578947, | |
| "grad_norm": 0.5621191263198853, | |
| "learning_rate": 9.135739879063465e-07, | |
| "loss": 0.0242, | |
| "step": 3580 | |
| }, | |
| { | |
| "epoch": 9.447368421052632, | |
| "grad_norm": 0.41081079840660095, | |
| "learning_rate": 8.326354159236882e-07, | |
| "loss": 0.0232, | |
| "step": 3590 | |
| }, | |
| { | |
| "epoch": 9.473684210526315, | |
| "grad_norm": 0.48332345485687256, | |
| "learning_rate": 7.554204140131138e-07, | |
| "loss": 0.026, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 9.5, | |
| "grad_norm": 0.36336687207221985, | |
| "learning_rate": 6.819348298638839e-07, | |
| "loss": 0.0226, | |
| "step": 3610 | |
| }, | |
| { | |
| "epoch": 9.526315789473685, | |
| "grad_norm": 0.4939121901988983, | |
| "learning_rate": 6.121842287269419e-07, | |
| "loss": 0.0274, | |
| "step": 3620 | |
| }, | |
| { | |
| "epoch": 9.552631578947368, | |
| "grad_norm": 0.60195392370224, | |
| "learning_rate": 5.46173892993429e-07, | |
| "loss": 0.0229, | |
| "step": 3630 | |
| }, | |
| { | |
| "epoch": 9.578947368421053, | |
| "grad_norm": 0.3372774124145508, | |
| "learning_rate": 4.839088217946208e-07, | |
| "loss": 0.0236, | |
| "step": 3640 | |
| }, | |
| { | |
| "epoch": 9.605263157894736, | |
| "grad_norm": 0.2751666307449341, | |
| "learning_rate": 4.253937306233691e-07, | |
| "loss": 0.0267, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 9.631578947368421, | |
| "grad_norm": 0.2811025381088257, | |
| "learning_rate": 3.706330509769429e-07, | |
| "loss": 0.0269, | |
| "step": 3660 | |
| }, | |
| { | |
| "epoch": 9.657894736842106, | |
| "grad_norm": 0.27488309144973755, | |
| "learning_rate": 3.1963093002145285e-07, | |
| "loss": 0.0294, | |
| "step": 3670 | |
| }, | |
| { | |
| "epoch": 9.68421052631579, | |
| "grad_norm": 0.29794642329216003, | |
| "learning_rate": 2.7239123027775204e-07, | |
| "loss": 0.0226, | |
| "step": 3680 | |
| }, | |
| { | |
| "epoch": 9.710526315789474, | |
| "grad_norm": 0.49477118253707886, | |
| "learning_rate": 2.289175293289314e-07, | |
| "loss": 0.0263, | |
| "step": 3690 | |
| }, | |
| { | |
| "epoch": 9.736842105263158, | |
| "grad_norm": 0.44544729590415955, | |
| "learning_rate": 1.8921311954937516e-07, | |
| "loss": 0.024, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 9.763157894736842, | |
| "grad_norm": 0.380344033241272, | |
| "learning_rate": 1.5328100785542697e-07, | |
| "loss": 0.0243, | |
| "step": 3710 | |
| }, | |
| { | |
| "epoch": 9.789473684210526, | |
| "grad_norm": 0.2532555162906647, | |
| "learning_rate": 1.211239154776611e-07, | |
| "loss": 0.0256, | |
| "step": 3720 | |
| }, | |
| { | |
| "epoch": 9.81578947368421, | |
| "grad_norm": 0.3260039985179901, | |
| "learning_rate": 9.27442777547971e-08, | |
| "loss": 0.0253, | |
| "step": 3730 | |
| }, | |
| { | |
| "epoch": 9.842105263157894, | |
| "grad_norm": 0.2649020254611969, | |
| "learning_rate": 6.814424394926966e-08, | |
| "loss": 0.0298, | |
| "step": 3740 | |
| }, | |
| { | |
| "epoch": 9.868421052631579, | |
| "grad_norm": 0.257893443107605, | |
| "learning_rate": 4.732567708445878e-08, | |
| "loss": 0.0223, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 9.894736842105264, | |
| "grad_norm": 0.20920208096504211, | |
| "learning_rate": 3.029015380359157e-08, | |
| "loss": 0.0249, | |
| "step": 3760 | |
| }, | |
| { | |
| "epoch": 9.921052631578947, | |
| "grad_norm": 0.19053097069263458, | |
| "learning_rate": 1.7038964250343238e-08, | |
| "loss": 0.029, | |
| "step": 3770 | |
| }, | |
| { | |
| "epoch": 9.947368421052632, | |
| "grad_norm": 0.3256742060184479, | |
| "learning_rate": 7.573111971148627e-09, | |
| "loss": 0.0254, | |
| "step": 3780 | |
| }, | |
| { | |
| "epoch": 9.973684210526315, | |
| "grad_norm": 0.3680499792098999, | |
| "learning_rate": 1.8933138391574732e-09, | |
| "loss": 0.025, | |
| "step": 3790 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 0.5628379583358765, | |
| "learning_rate": 0.0, | |
| "loss": 0.0263, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 3800, | |
| "total_flos": 4.0064924863782144e+17, | |
| "train_loss": 0.05822706136264299, | |
| "train_runtime": 3981.0494, | |
| "train_samples_per_second": 46.716, | |
| "train_steps_per_second": 0.955 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 3800, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 10000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.0064924863782144e+17, | |
| "train_batch_size": 49, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |