| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9959579628132579, | |
| "eval_steps": 500, | |
| "global_step": 154, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.019401778496362168, | |
| "grad_norm": 139.02731323242188, | |
| "learning_rate": 1.9610389610389612e-05, | |
| "loss": 1.8718, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.038803556992724336, | |
| "grad_norm": 31.607357025146484, | |
| "learning_rate": 1.9220779220779222e-05, | |
| "loss": 1.6642, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0582053354890865, | |
| "grad_norm": 118.545166015625, | |
| "learning_rate": 1.8831168831168833e-05, | |
| "loss": 1.5334, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.07760711398544867, | |
| "grad_norm": 180.7499542236328, | |
| "learning_rate": 1.8441558441558443e-05, | |
| "loss": 1.396, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.09700889248181083, | |
| "grad_norm": 199.1714324951172, | |
| "learning_rate": 1.8051948051948053e-05, | |
| "loss": 1.3652, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.116410670978173, | |
| "grad_norm": 136.60414123535156, | |
| "learning_rate": 1.7662337662337664e-05, | |
| "loss": 1.3432, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.13581244947453516, | |
| "grad_norm": 82.5650634765625, | |
| "learning_rate": 1.7272727272727274e-05, | |
| "loss": 1.2614, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.15521422797089734, | |
| "grad_norm": 18.96686553955078, | |
| "learning_rate": 1.6883116883116884e-05, | |
| "loss": 1.2303, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.1746160064672595, | |
| "grad_norm": 7.933801174163818, | |
| "learning_rate": 1.6493506493506495e-05, | |
| "loss": 1.1984, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.19401778496362165, | |
| "grad_norm": 2.686699390411377, | |
| "learning_rate": 1.6103896103896105e-05, | |
| "loss": 1.1016, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.21341956345998384, | |
| "grad_norm": 1.455581545829773, | |
| "learning_rate": 1.5714285714285715e-05, | |
| "loss": 1.0671, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.232821341956346, | |
| "grad_norm": 0.5924062132835388, | |
| "learning_rate": 1.5324675324675326e-05, | |
| "loss": 1.012, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.25222312045270817, | |
| "grad_norm": 0.3087107837200165, | |
| "learning_rate": 1.4935064935064936e-05, | |
| "loss": 0.9758, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.2716248989490703, | |
| "grad_norm": 0.2992459535598755, | |
| "learning_rate": 1.4545454545454546e-05, | |
| "loss": 0.9262, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.2910266774454325, | |
| "grad_norm": 0.2895904779434204, | |
| "learning_rate": 1.4155844155844157e-05, | |
| "loss": 0.8271, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.3104284559417947, | |
| "grad_norm": 0.2948096692562103, | |
| "learning_rate": 1.3766233766233767e-05, | |
| "loss": 0.7895, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.32983023443815684, | |
| "grad_norm": 0.31464704871177673, | |
| "learning_rate": 1.3376623376623377e-05, | |
| "loss": 0.7299, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.349232012934519, | |
| "grad_norm": 0.3038002550601959, | |
| "learning_rate": 1.2987012987012988e-05, | |
| "loss": 0.6857, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.36863379143088115, | |
| "grad_norm": 0.33729803562164307, | |
| "learning_rate": 1.25974025974026e-05, | |
| "loss": 0.5946, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.3880355699272433, | |
| "grad_norm": 0.39213827252388, | |
| "learning_rate": 1.2207792207792208e-05, | |
| "loss": 0.5636, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.4074373484236055, | |
| "grad_norm": 0.3482286334037781, | |
| "learning_rate": 1.181818181818182e-05, | |
| "loss": 0.5094, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.42683912691996767, | |
| "grad_norm": 0.3112964630126953, | |
| "learning_rate": 1.1428571428571429e-05, | |
| "loss": 0.4541, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.4462409054163298, | |
| "grad_norm": 0.26819908618927, | |
| "learning_rate": 1.1038961038961041e-05, | |
| "loss": 0.4181, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.465642683912692, | |
| "grad_norm": 0.28413137793540955, | |
| "learning_rate": 1.064935064935065e-05, | |
| "loss": 0.4095, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.4850444624090542, | |
| "grad_norm": 0.3022381365299225, | |
| "learning_rate": 1.025974025974026e-05, | |
| "loss": 0.3623, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.5044462409054163, | |
| "grad_norm": 0.29346349835395813, | |
| "learning_rate": 9.87012987012987e-06, | |
| "loss": 0.3334, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.5238480194017785, | |
| "grad_norm": 0.2659854292869568, | |
| "learning_rate": 9.48051948051948e-06, | |
| "loss": 0.3115, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.5432497978981407, | |
| "grad_norm": 0.23122940957546234, | |
| "learning_rate": 9.090909090909091e-06, | |
| "loss": 0.2817, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.5626515763945028, | |
| "grad_norm": 0.2369256317615509, | |
| "learning_rate": 8.701298701298701e-06, | |
| "loss": 0.2809, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.582053354890865, | |
| "grad_norm": 0.2082873433828354, | |
| "learning_rate": 8.311688311688313e-06, | |
| "loss": 0.2455, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.6014551333872271, | |
| "grad_norm": 0.21645894646644592, | |
| "learning_rate": 7.922077922077924e-06, | |
| "loss": 0.2503, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.6208569118835894, | |
| "grad_norm": 0.19337739050388336, | |
| "learning_rate": 7.532467532467533e-06, | |
| "loss": 0.2286, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.6402586903799515, | |
| "grad_norm": 0.1808944046497345, | |
| "learning_rate": 7.1428571428571436e-06, | |
| "loss": 0.2401, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.6596604688763137, | |
| "grad_norm": 0.1630856841802597, | |
| "learning_rate": 6.753246753246754e-06, | |
| "loss": 0.2251, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.6790622473726758, | |
| "grad_norm": 0.16326990723609924, | |
| "learning_rate": 6.363636363636364e-06, | |
| "loss": 0.2291, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.698464025869038, | |
| "grad_norm": 0.16061735153198242, | |
| "learning_rate": 5.9740259740259746e-06, | |
| "loss": 0.2331, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.7178658043654002, | |
| "grad_norm": 0.17352429032325745, | |
| "learning_rate": 5.584415584415585e-06, | |
| "loss": 0.2149, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.7372675828617623, | |
| "grad_norm": 0.17043530941009521, | |
| "learning_rate": 5.194805194805194e-06, | |
| "loss": 0.2187, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.7566693613581245, | |
| "grad_norm": 0.16479559242725372, | |
| "learning_rate": 4.805194805194806e-06, | |
| "loss": 0.2218, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.7760711398544866, | |
| "grad_norm": 0.17882439494132996, | |
| "learning_rate": 4.415584415584416e-06, | |
| "loss": 0.205, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.7954729183508489, | |
| "grad_norm": 0.1911778748035431, | |
| "learning_rate": 4.025974025974026e-06, | |
| "loss": 0.2172, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.814874696847211, | |
| "grad_norm": 0.17751498520374298, | |
| "learning_rate": 3.6363636363636366e-06, | |
| "loss": 0.2096, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.8342764753435732, | |
| "grad_norm": 0.1702156662940979, | |
| "learning_rate": 3.246753246753247e-06, | |
| "loss": 0.1911, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.8536782538399353, | |
| "grad_norm": 0.1764981597661972, | |
| "learning_rate": 2.8571428571428573e-06, | |
| "loss": 0.2103, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.8730800323362975, | |
| "grad_norm": 0.1592799872159958, | |
| "learning_rate": 2.4675324675324676e-06, | |
| "loss": 0.2053, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.8924818108326596, | |
| "grad_norm": 0.21512138843536377, | |
| "learning_rate": 2.0779220779220784e-06, | |
| "loss": 0.2197, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.9118835893290218, | |
| "grad_norm": 0.17707495391368866, | |
| "learning_rate": 1.6883116883116885e-06, | |
| "loss": 0.2051, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.931285367825384, | |
| "grad_norm": 0.1585138887166977, | |
| "learning_rate": 1.2987012987012986e-06, | |
| "loss": 0.1984, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.9506871463217461, | |
| "grad_norm": 0.15231232345104218, | |
| "learning_rate": 9.090909090909091e-07, | |
| "loss": 0.1774, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.9700889248181084, | |
| "grad_norm": 0.15338800847530365, | |
| "learning_rate": 5.194805194805196e-07, | |
| "loss": 0.2046, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.9894907033144705, | |
| "grad_norm": 0.16579587757587433, | |
| "learning_rate": 1.298701298701299e-07, | |
| "loss": 0.1871, | |
| "step": 153 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 154, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.5705942959542764e+18, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |