{ "best_metric": null, "best_model_checkpoint": null, "epoch": 1.0, "eval_steps": 500, "global_step": 156, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.00641025641025641, "grad_norm": 3.8148568052575884, "learning_rate": 1.282051282051282e-07, "loss": 4.889, "step": 1 }, { "epoch": 0.01282051282051282, "grad_norm": 4.453444589892027, "learning_rate": 2.564102564102564e-07, "loss": 4.9097, "step": 2 }, { "epoch": 0.02564102564102564, "grad_norm": 4.896614258621833, "learning_rate": 5.128205128205128e-07, "loss": 4.9099, "step": 4 }, { "epoch": 0.038461538461538464, "grad_norm": 4.456576485464451, "learning_rate": 7.692307692307694e-07, "loss": 4.9102, "step": 6 }, { "epoch": 0.05128205128205128, "grad_norm": 4.193427815120892, "learning_rate": 1.0256410256410257e-06, "loss": 4.8924, "step": 8 }, { "epoch": 0.0641025641025641, "grad_norm": 3.6726747534666555, "learning_rate": 1.282051282051282e-06, "loss": 4.8372, "step": 10 }, { "epoch": 0.07692307692307693, "grad_norm": 3.337981680961211, "learning_rate": 1.5384615384615387e-06, "loss": 4.7794, "step": 12 }, { "epoch": 0.08974358974358974, "grad_norm": 2.675890453922504, "learning_rate": 1.794871794871795e-06, "loss": 4.6191, "step": 14 }, { "epoch": 0.10256410256410256, "grad_norm": 2.398848700299253, "learning_rate": 2.0512820512820513e-06, "loss": 4.5723, "step": 16 }, { "epoch": 0.11538461538461539, "grad_norm": 1.8159784961859098, "learning_rate": 2.307692307692308e-06, "loss": 4.3568, "step": 18 }, { "epoch": 0.1282051282051282, "grad_norm": 1.6094220673057946, "learning_rate": 2.564102564102564e-06, "loss": 4.2686, "step": 20 }, { "epoch": 0.14102564102564102, "grad_norm": 1.4349818434671497, "learning_rate": 2.8205128205128207e-06, "loss": 4.169, "step": 22 }, { "epoch": 0.15384615384615385, "grad_norm": 1.4412559958198408, "learning_rate": 3.0769230769230774e-06, "loss": 4.0415, "step": 24 }, { "epoch": 0.16666666666666666, "grad_norm": 1.3626982007755366, "learning_rate": 3.3333333333333333e-06, "loss": 3.8569, "step": 26 }, { "epoch": 0.1794871794871795, "grad_norm": 1.3679096739652512, "learning_rate": 3.58974358974359e-06, "loss": 3.7409, "step": 28 }, { "epoch": 0.19230769230769232, "grad_norm": 1.3396391976584703, "learning_rate": 3.846153846153847e-06, "loss": 3.6585, "step": 30 }, { "epoch": 0.20512820512820512, "grad_norm": 1.294876480457606, "learning_rate": 4.102564102564103e-06, "loss": 3.4961, "step": 32 }, { "epoch": 0.21794871794871795, "grad_norm": 1.103820056614455, "learning_rate": 4.358974358974359e-06, "loss": 3.3518, "step": 34 }, { "epoch": 0.23076923076923078, "grad_norm": 1.0522131115906572, "learning_rate": 4.615384615384616e-06, "loss": 3.1984, "step": 36 }, { "epoch": 0.24358974358974358, "grad_norm": 1.0081732884085817, "learning_rate": 4.871794871794872e-06, "loss": 3.054, "step": 38 }, { "epoch": 0.2564102564102564, "grad_norm": 0.9214039999549644, "learning_rate": 5.128205128205128e-06, "loss": 2.8628, "step": 40 }, { "epoch": 0.2692307692307692, "grad_norm": 0.8143994876297143, "learning_rate": 5.384615384615385e-06, "loss": 2.7475, "step": 42 }, { "epoch": 0.28205128205128205, "grad_norm": 0.700891765547207, "learning_rate": 5.641025641025641e-06, "loss": 2.5869, "step": 44 }, { "epoch": 0.2948717948717949, "grad_norm": 0.7510674065754775, "learning_rate": 5.897435897435898e-06, "loss": 2.4461, "step": 46 }, { "epoch": 0.3076923076923077, "grad_norm": 0.6794074940373539, "learning_rate": 6.153846153846155e-06, "loss": 2.3477, "step": 48 }, { "epoch": 0.32051282051282054, "grad_norm": 0.5162215042692575, "learning_rate": 6.410256410256412e-06, "loss": 2.2152, "step": 50 }, { "epoch": 0.3333333333333333, "grad_norm": 0.5146975027904754, "learning_rate": 6.666666666666667e-06, "loss": 2.1975, "step": 52 }, { "epoch": 0.34615384615384615, "grad_norm": 0.4474574545979082, "learning_rate": 6.923076923076923e-06, "loss": 2.0824, "step": 54 }, { "epoch": 0.358974358974359, "grad_norm": 0.40379510918119965, "learning_rate": 7.17948717948718e-06, "loss": 2.0388, "step": 56 }, { "epoch": 0.3717948717948718, "grad_norm": 0.4109144194248555, "learning_rate": 7.435897435897437e-06, "loss": 1.9699, "step": 58 }, { "epoch": 0.38461538461538464, "grad_norm": 0.36878556755849573, "learning_rate": 7.692307692307694e-06, "loss": 1.9252, "step": 60 }, { "epoch": 0.3974358974358974, "grad_norm": 0.33951214974325605, "learning_rate": 7.948717948717949e-06, "loss": 1.8773, "step": 62 }, { "epoch": 0.41025641025641024, "grad_norm": 0.31625266306424027, "learning_rate": 8.205128205128205e-06, "loss": 1.7966, "step": 64 }, { "epoch": 0.4230769230769231, "grad_norm": 0.7180890498799148, "learning_rate": 8.461538461538462e-06, "loss": 1.8108, "step": 66 }, { "epoch": 0.4358974358974359, "grad_norm": 0.33704662479371716, "learning_rate": 8.717948717948719e-06, "loss": 1.7498, "step": 68 }, { "epoch": 0.44871794871794873, "grad_norm": 0.2761824271642518, "learning_rate": 8.974358974358976e-06, "loss": 1.7124, "step": 70 }, { "epoch": 0.46153846153846156, "grad_norm": 0.24386286193528572, "learning_rate": 9.230769230769232e-06, "loss": 1.6382, "step": 72 }, { "epoch": 0.47435897435897434, "grad_norm": 0.25885451676676363, "learning_rate": 9.487179487179487e-06, "loss": 1.6588, "step": 74 }, { "epoch": 0.48717948717948717, "grad_norm": 0.3040030663690383, "learning_rate": 9.743589743589744e-06, "loss": 1.6209, "step": 76 }, { "epoch": 0.5, "grad_norm": 0.26598080566137733, "learning_rate": 1e-05, "loss": 1.6294, "step": 78 }, { "epoch": 0.5128205128205128, "grad_norm": 0.22696288673824674, "learning_rate": 9.99995506314361e-06, "loss": 1.58, "step": 80 }, { "epoch": 0.5256410256410257, "grad_norm": 0.21242259411358655, "learning_rate": 9.99982025338217e-06, "loss": 1.5439, "step": 82 }, { "epoch": 0.5384615384615384, "grad_norm": 0.20291826899403465, "learning_rate": 9.999595573138845e-06, "loss": 1.5274, "step": 84 }, { "epoch": 0.5512820512820513, "grad_norm": 0.1855444412322797, "learning_rate": 9.99928102645221e-06, "loss": 1.5161, "step": 86 }, { "epoch": 0.5641025641025641, "grad_norm": 0.17883874148398324, "learning_rate": 9.99887661897616e-06, "loss": 1.4916, "step": 88 }, { "epoch": 0.5769230769230769, "grad_norm": 0.17041478792908024, "learning_rate": 9.99838235797981e-06, "loss": 1.4679, "step": 90 }, { "epoch": 0.5897435897435898, "grad_norm": 0.1904762198987749, "learning_rate": 9.997798252347382e-06, "loss": 1.471, "step": 92 }, { "epoch": 0.6025641025641025, "grad_norm": 0.19077041355708335, "learning_rate": 9.99712431257802e-06, "loss": 1.4672, "step": 94 }, { "epoch": 0.6153846153846154, "grad_norm": 0.1702104328191874, "learning_rate": 9.996360550785619e-06, "loss": 1.4455, "step": 96 }, { "epoch": 0.6282051282051282, "grad_norm": 0.19039133859515542, "learning_rate": 9.9955069806986e-06, "loss": 1.4727, "step": 98 }, { "epoch": 0.6410256410256411, "grad_norm": 0.15448238517128507, "learning_rate": 9.994563617659665e-06, "loss": 1.4257, "step": 100 }, { "epoch": 0.6538461538461539, "grad_norm": 0.15202351051018634, "learning_rate": 9.993530478625524e-06, "loss": 1.4214, "step": 102 }, { "epoch": 0.6666666666666666, "grad_norm": 0.16296598133044526, "learning_rate": 9.992407582166582e-06, "loss": 1.4213, "step": 104 }, { "epoch": 0.6794871794871795, "grad_norm": 0.1462038294164801, "learning_rate": 9.991194948466615e-06, "loss": 1.3993, "step": 106 }, { "epoch": 0.6923076923076923, "grad_norm": 0.14470989191451086, "learning_rate": 9.989892599322404e-06, "loss": 1.4014, "step": 108 }, { "epoch": 0.7051282051282052, "grad_norm": 0.15440545758233384, "learning_rate": 9.988500558143337e-06, "loss": 1.3878, "step": 110 }, { "epoch": 0.717948717948718, "grad_norm": 0.1412948019214843, "learning_rate": 9.987018849950996e-06, "loss": 1.355, "step": 112 }, { "epoch": 0.7307692307692307, "grad_norm": 0.15156074653795895, "learning_rate": 9.985447501378706e-06, "loss": 1.3642, "step": 114 }, { "epoch": 0.7435897435897436, "grad_norm": 0.3875845143038168, "learning_rate": 9.983786540671052e-06, "loss": 1.3797, "step": 116 }, { "epoch": 0.7564102564102564, "grad_norm": 0.15788537547887518, "learning_rate": 9.982035997683372e-06, "loss": 1.3388, "step": 118 }, { "epoch": 0.7692307692307693, "grad_norm": 0.15056320914445512, "learning_rate": 9.980195903881231e-06, "loss": 1.343, "step": 120 }, { "epoch": 0.782051282051282, "grad_norm": 0.1555129283317706, "learning_rate": 9.978266292339838e-06, "loss": 1.328, "step": 122 }, { "epoch": 0.7948717948717948, "grad_norm": 0.14999182496915453, "learning_rate": 9.976247197743465e-06, "loss": 1.352, "step": 124 }, { "epoch": 0.8076923076923077, "grad_norm": 0.14124313426191026, "learning_rate": 9.974138656384815e-06, "loss": 1.3243, "step": 126 }, { "epoch": 0.8205128205128205, "grad_norm": 0.1378326204862212, "learning_rate": 9.97194070616438e-06, "loss": 1.3241, "step": 128 }, { "epoch": 0.8333333333333334, "grad_norm": 0.14227960534974604, "learning_rate": 9.969653386589749e-06, "loss": 1.3219, "step": 130 }, { "epoch": 0.8461538461538461, "grad_norm": 0.12713543749272155, "learning_rate": 9.967276738774897e-06, "loss": 1.3096, "step": 132 }, { "epoch": 0.8589743589743589, "grad_norm": 0.15061232362563903, "learning_rate": 9.964810805439464e-06, "loss": 1.3011, "step": 134 }, { "epoch": 0.8717948717948718, "grad_norm": 0.14361563348990292, "learning_rate": 9.962255630907964e-06, "loss": 1.2827, "step": 136 }, { "epoch": 0.8846153846153846, "grad_norm": 0.17754387209035652, "learning_rate": 9.959611261108999e-06, "loss": 1.3185, "step": 138 }, { "epoch": 0.8974358974358975, "grad_norm": 0.1458623897430443, "learning_rate": 9.956877743574437e-06, "loss": 1.3286, "step": 140 }, { "epoch": 0.9102564102564102, "grad_norm": 0.14084398418567437, "learning_rate": 9.954055127438554e-06, "loss": 1.3005, "step": 142 }, { "epoch": 0.9230769230769231, "grad_norm": 0.13580861113069753, "learning_rate": 9.951143463437145e-06, "loss": 1.3165, "step": 144 }, { "epoch": 0.9358974358974359, "grad_norm": 0.13622051889734035, "learning_rate": 9.948142803906623e-06, "loss": 1.2929, "step": 146 }, { "epoch": 0.9487179487179487, "grad_norm": 0.12679082371935066, "learning_rate": 9.94505320278307e-06, "loss": 1.2833, "step": 148 }, { "epoch": 0.9615384615384616, "grad_norm": 0.11939382079952243, "learning_rate": 9.94187471560127e-06, "loss": 1.2851, "step": 150 }, { "epoch": 0.9743589743589743, "grad_norm": 0.11752490134274678, "learning_rate": 9.938607399493714e-06, "loss": 1.2559, "step": 152 }, { "epoch": 0.9871794871794872, "grad_norm": 0.11807212671773365, "learning_rate": 9.935251313189564e-06, "loss": 1.285, "step": 154 }, { "epoch": 1.0, "grad_norm": 0.1120761333795772, "learning_rate": 9.931806517013612e-06, "loss": 1.2491, "step": 156 } ], "logging_steps": 2, "max_steps": 1560, "num_input_tokens_seen": 0, "num_train_epochs": 10, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 6.315670982665175e+18, "train_batch_size": 2, "trial_name": null, "trial_params": null }