{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.09328720799160416, "eval_steps": 500, "global_step": 300, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0, "grad_norm": 0.47774845361709595, "learning_rate": 4.999970160815579e-05, "loss": 2.0765, "step": 5 }, { "epoch": 0.0, "grad_norm": 0.6051416397094727, "learning_rate": 4.999880643974619e-05, "loss": 2.2297, "step": 10 }, { "epoch": 0.0, "grad_norm": 0.6161717772483826, "learning_rate": 4.9997314516140056e-05, "loss": 2.1103, "step": 15 }, { "epoch": 0.01, "grad_norm": 0.4686434268951416, "learning_rate": 4.999522587295162e-05, "loss": 2.0057, "step": 20 }, { "epoch": 0.01, "grad_norm": 0.8412289023399353, "learning_rate": 4.999254056003963e-05, "loss": 2.1778, "step": 25 }, { "epoch": 0.01, "grad_norm": 0.5333625078201294, "learning_rate": 4.99892586415061e-05, "loss": 2.2399, "step": 30 }, { "epoch": 0.01, "grad_norm": 0.821148157119751, "learning_rate": 4.9985380195694856e-05, "loss": 2.3215, "step": 35 }, { "epoch": 0.01, "grad_norm": 0.8403909206390381, "learning_rate": 4.998090531518962e-05, "loss": 1.8295, "step": 40 }, { "epoch": 0.01, "grad_norm": 0.6633398532867432, "learning_rate": 4.9975834106811834e-05, "loss": 2.0195, "step": 45 }, { "epoch": 0.02, "grad_norm": 0.6386868357658386, "learning_rate": 4.997016669161806e-05, "loss": 2.1257, "step": 50 }, { "epoch": 0.02, "grad_norm": 0.7762248516082764, "learning_rate": 4.996390320489715e-05, "loss": 2.057, "step": 55 }, { "epoch": 0.02, "grad_norm": 1.3192856311798096, "learning_rate": 4.9957043796166966e-05, "loss": 2.0753, "step": 60 }, { "epoch": 0.02, "grad_norm": 0.9797518849372864, "learning_rate": 4.994958862917083e-05, "loss": 1.9736, "step": 65 }, { "epoch": 0.02, "grad_norm": 1.000693440437317, "learning_rate": 4.994153788187363e-05, "loss": 2.1572, "step": 70 }, { "epoch": 0.02, "grad_norm": 0.6852813959121704, "learning_rate": 4.993289174645757e-05, "loss": 2.1491, "step": 75 }, { "epoch": 0.02, "grad_norm": 1.0075691938400269, "learning_rate": 4.992365042931752e-05, "loss": 1.945, "step": 80 }, { "epoch": 0.03, "grad_norm": 1.1973133087158203, "learning_rate": 4.991381415105619e-05, "loss": 2.0811, "step": 85 }, { "epoch": 0.03, "grad_norm": 0.9927239418029785, "learning_rate": 4.990338314647881e-05, "loss": 1.961, "step": 90 }, { "epoch": 0.03, "grad_norm": 0.9499759674072266, "learning_rate": 4.98923576645875e-05, "loss": 2.0653, "step": 95 }, { "epoch": 0.03, "grad_norm": 0.7233040928840637, "learning_rate": 4.9880737968575365e-05, "loss": 1.9999, "step": 100 }, { "epoch": 0.03, "grad_norm": 1.55235755443573, "learning_rate": 4.986852433582022e-05, "loss": 2.2258, "step": 105 }, { "epoch": 0.03, "grad_norm": 0.9007890820503235, "learning_rate": 4.985571705787793e-05, "loss": 2.1034, "step": 110 }, { "epoch": 0.04, "grad_norm": 0.6774860620498657, "learning_rate": 4.9842316440475475e-05, "loss": 2.1753, "step": 115 }, { "epoch": 0.04, "grad_norm": 0.7676737308502197, "learning_rate": 4.9828322803503665e-05, "loss": 2.1384, "step": 120 }, { "epoch": 0.04, "grad_norm": 0.9624544978141785, "learning_rate": 4.981373648100946e-05, "loss": 2.0521, "step": 125 }, { "epoch": 0.04, "grad_norm": 0.9315722584724426, "learning_rate": 4.979855782118802e-05, "loss": 1.9256, "step": 130 }, { "epoch": 0.04, "grad_norm": 0.9035864472389221, "learning_rate": 4.978278718637443e-05, "loss": 2.0882, "step": 135 }, { "epoch": 0.04, "grad_norm": 0.7997236251831055, "learning_rate": 4.9766424953035e-05, "loss": 2.0724, "step": 140 }, { "epoch": 0.05, "grad_norm": 1.0692921876907349, "learning_rate": 4.974947151175826e-05, "loss": 2.1329, "step": 145 }, { "epoch": 0.05, "grad_norm": 0.9506180286407471, "learning_rate": 4.973192726724572e-05, "loss": 2.082, "step": 150 }, { "epoch": 0.05, "grad_norm": 0.8647387027740479, "learning_rate": 4.9713792638302145e-05, "loss": 2.0366, "step": 155 }, { "epoch": 0.05, "grad_norm": 1.105302095413208, "learning_rate": 4.969506805782555e-05, "loss": 2.1481, "step": 160 }, { "epoch": 0.05, "grad_norm": 0.7593303918838501, "learning_rate": 4.967575397279689e-05, "loss": 2.032, "step": 165 }, { "epoch": 0.05, "grad_norm": 0.7521979808807373, "learning_rate": 4.965585084426943e-05, "loss": 2.0379, "step": 170 }, { "epoch": 0.05, "grad_norm": 0.947120726108551, "learning_rate": 4.9635359147357655e-05, "loss": 2.1444, "step": 175 }, { "epoch": 0.06, "grad_norm": 1.2184454202651978, "learning_rate": 4.961427937122598e-05, "loss": 1.9164, "step": 180 }, { "epoch": 0.06, "grad_norm": 1.221663475036621, "learning_rate": 4.959261201907707e-05, "loss": 2.0084, "step": 185 }, { "epoch": 0.06, "grad_norm": 1.0457361936569214, "learning_rate": 4.957035760813982e-05, "loss": 2.2032, "step": 190 }, { "epoch": 0.06, "grad_norm": 0.8834909200668335, "learning_rate": 4.954751666965701e-05, "loss": 2.2101, "step": 195 }, { "epoch": 0.06, "grad_norm": 0.791902482509613, "learning_rate": 4.9524089748872615e-05, "loss": 2.0472, "step": 200 }, { "epoch": 0.06, "grad_norm": 1.2905739545822144, "learning_rate": 4.9500077405018807e-05, "loss": 2.0987, "step": 205 }, { "epoch": 0.07, "grad_norm": 0.8612006306648254, "learning_rate": 4.9475480211302583e-05, "loss": 2.1765, "step": 210 }, { "epoch": 0.07, "grad_norm": 1.3128459453582764, "learning_rate": 4.945029875489212e-05, "loss": 1.9926, "step": 215 }, { "epoch": 0.07, "grad_norm": 0.9610918164253235, "learning_rate": 4.94245336369027e-05, "loss": 2.0124, "step": 220 }, { "epoch": 0.07, "grad_norm": 0.873160183429718, "learning_rate": 4.939818547238241e-05, "loss": 2.2229, "step": 225 }, { "epoch": 0.07, "grad_norm": 1.5535285472869873, "learning_rate": 4.9371254890297446e-05, "loss": 2.2013, "step": 230 }, { "epoch": 0.07, "grad_norm": 1.1951836347579956, "learning_rate": 4.93437425335171e-05, "loss": 2.014, "step": 235 }, { "epoch": 0.07, "grad_norm": 0.7874170541763306, "learning_rate": 4.9315649058798384e-05, "loss": 2.1701, "step": 240 }, { "epoch": 0.08, "grad_norm": 1.3503323793411255, "learning_rate": 4.928697513677042e-05, "loss": 2.1681, "step": 245 }, { "epoch": 0.08, "grad_norm": 1.3091179132461548, "learning_rate": 4.925772145191834e-05, "loss": 2.1224, "step": 250 }, { "epoch": 0.08, "grad_norm": 1.4428555965423584, "learning_rate": 4.9227888702567044e-05, "loss": 2.0512, "step": 255 }, { "epoch": 0.08, "grad_norm": 0.8234395980834961, "learning_rate": 4.9197477600864446e-05, "loss": 2.1067, "step": 260 }, { "epoch": 0.08, "grad_norm": 1.9094969034194946, "learning_rate": 4.9166488872764526e-05, "loss": 1.8884, "step": 265 }, { "epoch": 0.08, "grad_norm": 1.0074087381362915, "learning_rate": 4.913492325800999e-05, "loss": 1.9345, "step": 270 }, { "epoch": 0.09, "grad_norm": 1.0867297649383545, "learning_rate": 4.910278151011458e-05, "loss": 2.1928, "step": 275 }, { "epoch": 0.09, "grad_norm": 0.6842357516288757, "learning_rate": 4.907006439634516e-05, "loss": 2.0407, "step": 280 }, { "epoch": 0.09, "grad_norm": 0.8409023284912109, "learning_rate": 4.903677269770329e-05, "loss": 2.2344, "step": 285 }, { "epoch": 0.09, "grad_norm": 0.8119503259658813, "learning_rate": 4.900290720890671e-05, "loss": 2.1296, "step": 290 }, { "epoch": 0.09, "grad_norm": 0.9938147068023682, "learning_rate": 4.8968468738370244e-05, "loss": 2.152, "step": 295 }, { "epoch": 0.09, "grad_norm": 0.9865244030952454, "learning_rate": 4.8933458108186606e-05, "loss": 1.9623, "step": 300 } ], "logging_steps": 5, "max_steps": 3215, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 100, "total_flos": 4027137608908800.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }