| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 7.7947882736156355, | |
| "eval_steps": 200, | |
| "global_step": 600, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.13029315960912052, | |
| "grad_norm": 8.268109321594238, | |
| "learning_rate": 1.1249999999999999e-05, | |
| "loss": 8.118, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.26058631921824105, | |
| "grad_norm": 1.9696224927902222, | |
| "learning_rate": 2.3749999999999998e-05, | |
| "loss": 6.7018, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.39087947882736157, | |
| "grad_norm": 1.5390442609786987, | |
| "learning_rate": 3.625e-05, | |
| "loss": 5.7973, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5211726384364821, | |
| "grad_norm": 1.8240673542022705, | |
| "learning_rate": 4.875e-05, | |
| "loss": 4.3519, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.6514657980456026, | |
| "grad_norm": 1.5940146446228027, | |
| "learning_rate": 6.125e-05, | |
| "loss": 2.7139, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.7817589576547231, | |
| "grad_norm": 1.8101792335510254, | |
| "learning_rate": 7.374999999999999e-05, | |
| "loss": 1.319, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.9120521172638436, | |
| "grad_norm": 1.423922061920166, | |
| "learning_rate": 7.49486075532965e-05, | |
| "loss": 0.8324, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.0390879478827362, | |
| "grad_norm": 1.1624470949172974, | |
| "learning_rate": 7.477113549054449e-05, | |
| "loss": 0.6864, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.1693811074918568, | |
| "grad_norm": 0.8140671253204346, | |
| "learning_rate": 7.446754970319223e-05, | |
| "loss": 0.6267, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.2996742671009773, | |
| "grad_norm": 0.9221881628036499, | |
| "learning_rate": 7.403887742944632e-05, | |
| "loss": 0.4194, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.4299674267100977, | |
| "grad_norm": 0.6408695578575134, | |
| "learning_rate": 7.348656916058809e-05, | |
| "loss": 0.3262, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.5602605863192183, | |
| "grad_norm": 0.5344031453132629, | |
| "learning_rate": 7.281249373297033e-05, | |
| "loss": 0.3679, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.6905537459283386, | |
| "grad_norm": 0.6845048666000366, | |
| "learning_rate": 7.201893200446651e-05, | |
| "loss": 0.3101, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.8208469055374592, | |
| "grad_norm": 0.5909339189529419, | |
| "learning_rate": 7.110856913676987e-05, | |
| "loss": 0.2775, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.9511400651465798, | |
| "grad_norm": 0.4650987684726715, | |
| "learning_rate": 7.008448550965612e-05, | |
| "loss": 0.275, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.0781758957654723, | |
| "grad_norm": 0.444742351770401, | |
| "learning_rate": 6.89501462979534e-05, | |
| "loss": 0.2893, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.208469055374593, | |
| "grad_norm": 0.42899981141090393, | |
| "learning_rate": 6.770938974648747e-05, | |
| "loss": 0.213, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.3387622149837135, | |
| "grad_norm": 0.4496869444847107, | |
| "learning_rate": 6.636641418267628e-05, | |
| "loss": 0.3031, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.469055374592834, | |
| "grad_norm": 0.5703123807907104, | |
| "learning_rate": 6.492576381071889e-05, | |
| "loss": 0.2808, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 2.5993485342019547, | |
| "grad_norm": 0.43668872117996216, | |
| "learning_rate": 6.339231333544685e-05, | |
| "loss": 0.3289, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.729641693811075, | |
| "grad_norm": 0.3623226583003998, | |
| "learning_rate": 6.177125146786621e-05, | |
| "loss": 0.2122, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 2.8599348534201954, | |
| "grad_norm": 0.35421496629714966, | |
| "learning_rate": 6.0068063368201814e-05, | |
| "loss": 0.2559, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.990228013029316, | |
| "grad_norm": 0.38672634959220886, | |
| "learning_rate": 5.828851208585143e-05, | |
| "loss": 0.2479, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 3.1172638436482085, | |
| "grad_norm": 0.2925184369087219, | |
| "learning_rate": 5.643861905905087e-05, | |
| "loss": 0.2245, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 3.247557003257329, | |
| "grad_norm": 0.3759796619415283, | |
| "learning_rate": 5.4524643740232996e-05, | |
| "loss": 0.184, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 3.3778501628664497, | |
| "grad_norm": 0.6650795340538025, | |
| "learning_rate": 5.255306241602209e-05, | |
| "loss": 0.1786, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 3.5081433224755703, | |
| "grad_norm": 0.31284600496292114, | |
| "learning_rate": 5.053054629352992e-05, | |
| "loss": 0.2012, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 3.6384364820846904, | |
| "grad_norm": 0.48433321714401245, | |
| "learning_rate": 4.8463938927102625e-05, | |
| "loss": 0.1715, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 3.768729641693811, | |
| "grad_norm": 0.41222795844078064, | |
| "learning_rate": 4.6360233061899054e-05, | |
| "loss": 0.17, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 3.8990228013029316, | |
| "grad_norm": 0.34344053268432617, | |
| "learning_rate": 4.422654697265465e-05, | |
| "loss": 0.1903, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 4.026058631921824, | |
| "grad_norm": 0.25037407875061035, | |
| "learning_rate": 4.2070100377693023e-05, | |
| "loss": 0.2105, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 4.156351791530945, | |
| "grad_norm": 0.402792364358902, | |
| "learning_rate": 3.9898190009684456e-05, | |
| "loss": 0.1178, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 4.286644951140065, | |
| "grad_norm": 0.5768423080444336, | |
| "learning_rate": 3.7718164925812265e-05, | |
| "loss": 0.1553, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 4.416938110749186, | |
| "grad_norm": 0.3002632260322571, | |
| "learning_rate": 3.55374016408896e-05, | |
| "loss": 0.1381, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 4.547231270358306, | |
| "grad_norm": 0.45716574788093567, | |
| "learning_rate": 3.3363279167568306e-05, | |
| "loss": 0.1134, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 4.677524429967427, | |
| "grad_norm": 0.47437748312950134, | |
| "learning_rate": 3.120315404809586e-05, | |
| "loss": 0.1067, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 4.807817589576548, | |
| "grad_norm": 0.680506706237793, | |
| "learning_rate": 2.9064335462105067e-05, | |
| "loss": 0.1564, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 4.938110749185668, | |
| "grad_norm": 0.41097283363342285, | |
| "learning_rate": 2.6954060494663847e-05, | |
| "loss": 0.108, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 5.06514657980456, | |
| "grad_norm": 0.48278936743736267, | |
| "learning_rate": 2.4879469648270256e-05, | |
| "loss": 0.123, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 5.195439739413681, | |
| "grad_norm": 0.7354271411895752, | |
| "learning_rate": 2.2847582681652236e-05, | |
| "loss": 0.0881, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 5.3257328990228014, | |
| "grad_norm": 0.40792593359947205, | |
| "learning_rate": 2.0865274857126165e-05, | |
| "loss": 0.0718, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 5.456026058631922, | |
| "grad_norm": 0.44886234402656555, | |
| "learning_rate": 1.8939253676885473e-05, | |
| "loss": 0.0942, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 5.586319218241043, | |
| "grad_norm": 0.432784765958786, | |
| "learning_rate": 1.7076036186936484e-05, | |
| "loss": 0.0876, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 5.716612377850163, | |
| "grad_norm": 0.20283620059490204, | |
| "learning_rate": 1.52819269254776e-05, | |
| "loss": 0.0416, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 5.846905537459284, | |
| "grad_norm": 0.47396963834762573, | |
| "learning_rate": 1.3562996590337701e-05, | |
| "loss": 0.0797, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 5.977198697068404, | |
| "grad_norm": 0.3657645285129547, | |
| "learning_rate": 1.192506149765631e-05, | |
| "loss": 0.0981, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 6.1042345276872965, | |
| "grad_norm": 0.34181857109069824, | |
| "learning_rate": 1.0373663901310948e-05, | |
| "loss": 0.044, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 6.234527687296417, | |
| "grad_norm": 0.484397828578949, | |
| "learning_rate": 8.91405323968433e-06, | |
| "loss": 0.0605, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 6.364820846905538, | |
| "grad_norm": 0.3345278799533844, | |
| "learning_rate": 7.551168373226526e-06, | |
| "loss": 0.0381, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 6.495114006514658, | |
| "grad_norm": 0.2914145290851593, | |
| "learning_rate": 6.289620872914588e-06, | |
| "loss": 0.0447, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 6.625407166123779, | |
| "grad_norm": 0.4786616563796997, | |
| "learning_rate": 5.133679416156135e-06, | |
| "loss": 0.0375, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 6.755700325732899, | |
| "grad_norm": 0.2902482748031616, | |
| "learning_rate": 4.0872553429362075e-06, | |
| "loss": 0.0727, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 6.88599348534202, | |
| "grad_norm": 0.28187865018844604, | |
| "learning_rate": 3.153889421080841e-06, | |
| "loss": 0.0685, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 7.013029315960912, | |
| "grad_norm": 0.24184636771678925, | |
| "learning_rate": 2.3367398654195707e-06, | |
| "loss": 0.055, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 7.143322475570033, | |
| "grad_norm": 0.364844411611557, | |
| "learning_rate": 1.638571651386171e-06, | |
| "loss": 0.0447, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 7.273615635179153, | |
| "grad_norm": 0.24921606481075287, | |
| "learning_rate": 1.061747159216994e-06, | |
| "loss": 0.0323, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 7.403908794788274, | |
| "grad_norm": 0.3031994700431824, | |
| "learning_rate": 6.082181804040465e-07, | |
| "loss": 0.0491, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 7.534201954397394, | |
| "grad_norm": 0.21111436188220978, | |
| "learning_rate": 2.795193134504256e-07, | |
| "loss": 0.0327, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 7.664495114006515, | |
| "grad_norm": 0.37282687425613403, | |
| "learning_rate": 7.67627712747243e-08, | |
| "loss": 0.049, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 7.7947882736156355, | |
| "grad_norm": 0.3026382029056549, | |
| "learning_rate": 6.346178345911779e-10, | |
| "loss": 0.0405, | |
| "step": 600 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 600, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 8, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.804936549180113e+18, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |