| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 2361, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0021177467174925877, | |
| "grad_norm": 83.68173840087012, | |
| "learning_rate": 4.219409282700422e-07, | |
| "loss": 2.1661, | |
| "mean_token_accuracy": 0.5976044356822967, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004235493434985175, | |
| "grad_norm": 71.11062161153062, | |
| "learning_rate": 8.438818565400844e-07, | |
| "loss": 2.1622, | |
| "mean_token_accuracy": 0.5995522707700729, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0063532401524777635, | |
| "grad_norm": 34.572128830715705, | |
| "learning_rate": 1.2658227848101267e-06, | |
| "loss": 2.0632, | |
| "mean_token_accuracy": 0.5944636166095734, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00847098686997035, | |
| "grad_norm": 17.011229671312382, | |
| "learning_rate": 1.6877637130801689e-06, | |
| "loss": 1.7723, | |
| "mean_token_accuracy": 0.6232941240072251, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.010588733587462939, | |
| "grad_norm": 9.74778063232665, | |
| "learning_rate": 2.1097046413502114e-06, | |
| "loss": 1.5731, | |
| "mean_token_accuracy": 0.63005710542202, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.012706480304955527, | |
| "grad_norm": 7.914154804733739, | |
| "learning_rate": 2.5316455696202535e-06, | |
| "loss": 1.3488, | |
| "mean_token_accuracy": 0.6629315137863159, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.014824227022448115, | |
| "grad_norm": 7.497303646153751, | |
| "learning_rate": 2.9535864978902956e-06, | |
| "loss": 1.1306, | |
| "mean_token_accuracy": 0.6912301659584046, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0169419737399407, | |
| "grad_norm": 3.0571735289067807, | |
| "learning_rate": 3.3755274261603377e-06, | |
| "loss": 0.9338, | |
| "mean_token_accuracy": 0.7339568644762039, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.01905972045743329, | |
| "grad_norm": 3.7299236330227674, | |
| "learning_rate": 3.7974683544303802e-06, | |
| "loss": 0.8366, | |
| "mean_token_accuracy": 0.7472610950469971, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.021177467174925878, | |
| "grad_norm": 1.94550213470537, | |
| "learning_rate": 4.219409282700423e-06, | |
| "loss": 0.813, | |
| "mean_token_accuracy": 0.7466759532690048, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.023295213892418468, | |
| "grad_norm": 1.9631003842444021, | |
| "learning_rate": 4.641350210970465e-06, | |
| "loss": 0.7409, | |
| "mean_token_accuracy": 0.7591830432415009, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.025412960609911054, | |
| "grad_norm": 2.126411421817186, | |
| "learning_rate": 5.063291139240507e-06, | |
| "loss": 0.6999, | |
| "mean_token_accuracy": 0.7653463244438171, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.027530707327403644, | |
| "grad_norm": 2.431633067673993, | |
| "learning_rate": 5.485232067510548e-06, | |
| "loss": 0.6803, | |
| "mean_token_accuracy": 0.7705583959817887, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.02964845404489623, | |
| "grad_norm": 2.1470463103072706, | |
| "learning_rate": 5.907172995780591e-06, | |
| "loss": 0.6716, | |
| "mean_token_accuracy": 0.7747641324996948, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.03176620076238882, | |
| "grad_norm": 1.8134772555606546, | |
| "learning_rate": 6.329113924050634e-06, | |
| "loss": 0.6442, | |
| "mean_token_accuracy": 0.7782594561576843, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.0338839474798814, | |
| "grad_norm": 1.828059395701887, | |
| "learning_rate": 6.751054852320675e-06, | |
| "loss": 0.654, | |
| "mean_token_accuracy": 0.7730626821517944, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.03600169419737399, | |
| "grad_norm": 2.144653892020441, | |
| "learning_rate": 7.172995780590718e-06, | |
| "loss": 0.5866, | |
| "mean_token_accuracy": 0.7909977465867997, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.03811944091486658, | |
| "grad_norm": 1.8471427217270429, | |
| "learning_rate": 7.5949367088607605e-06, | |
| "loss": 0.6343, | |
| "mean_token_accuracy": 0.7756380766630173, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.04023718763235917, | |
| "grad_norm": 2.3290876362673916, | |
| "learning_rate": 8.016877637130802e-06, | |
| "loss": 0.6006, | |
| "mean_token_accuracy": 0.7818532437086105, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.042354934349851756, | |
| "grad_norm": 2.038115409634727, | |
| "learning_rate": 8.438818565400846e-06, | |
| "loss": 0.6123, | |
| "mean_token_accuracy": 0.7774519264698029, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.044472681067344345, | |
| "grad_norm": 1.8512017533544443, | |
| "learning_rate": 8.860759493670886e-06, | |
| "loss": 0.5782, | |
| "mean_token_accuracy": 0.787897452712059, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.046590427784836935, | |
| "grad_norm": 1.7617335354592987, | |
| "learning_rate": 9.28270042194093e-06, | |
| "loss": 0.5646, | |
| "mean_token_accuracy": 0.7916492879390716, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.04870817450232952, | |
| "grad_norm": 1.7594677346726018, | |
| "learning_rate": 9.704641350210972e-06, | |
| "loss": 0.5741, | |
| "mean_token_accuracy": 0.7923983573913574, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.05082592121982211, | |
| "grad_norm": 2.074930275455498, | |
| "learning_rate": 1.0126582278481014e-05, | |
| "loss": 0.5872, | |
| "mean_token_accuracy": 0.7833609640598297, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.0529436679373147, | |
| "grad_norm": 1.9672826514728756, | |
| "learning_rate": 1.0548523206751056e-05, | |
| "loss": 0.5525, | |
| "mean_token_accuracy": 0.7987953841686248, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.05506141465480729, | |
| "grad_norm": 1.8715882057544604, | |
| "learning_rate": 1.0970464135021096e-05, | |
| "loss": 0.5825, | |
| "mean_token_accuracy": 0.788796243071556, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.05717916137229987, | |
| "grad_norm": 2.055120934997949, | |
| "learning_rate": 1.139240506329114e-05, | |
| "loss": 0.5668, | |
| "mean_token_accuracy": 0.794330358505249, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.05929690808979246, | |
| "grad_norm": 2.1751457050987213, | |
| "learning_rate": 1.1814345991561182e-05, | |
| "loss": 0.5504, | |
| "mean_token_accuracy": 0.7986414194107055, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.06141465480728505, | |
| "grad_norm": 2.6530737679742735, | |
| "learning_rate": 1.2236286919831224e-05, | |
| "loss": 0.5825, | |
| "mean_token_accuracy": 0.787852120399475, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.06353240152477764, | |
| "grad_norm": 1.7772714746257652, | |
| "learning_rate": 1.2658227848101268e-05, | |
| "loss": 0.5321, | |
| "mean_token_accuracy": 0.7960227221250534, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.06565014824227022, | |
| "grad_norm": 2.007446829510951, | |
| "learning_rate": 1.3080168776371309e-05, | |
| "loss": 0.5652, | |
| "mean_token_accuracy": 0.7959463059902191, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.0677678949597628, | |
| "grad_norm": 1.5240825493431345, | |
| "learning_rate": 1.350210970464135e-05, | |
| "loss": 0.5471, | |
| "mean_token_accuracy": 0.7939142495393753, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.0698856416772554, | |
| "grad_norm": 2.1050082197685573, | |
| "learning_rate": 1.3924050632911395e-05, | |
| "loss": 0.5283, | |
| "mean_token_accuracy": 0.8012055605649948, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.07200338839474799, | |
| "grad_norm": 1.8465069166680506, | |
| "learning_rate": 1.4345991561181437e-05, | |
| "loss": 0.5525, | |
| "mean_token_accuracy": 0.8044249504804611, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.07412113511224058, | |
| "grad_norm": 1.6175686507972196, | |
| "learning_rate": 1.4767932489451477e-05, | |
| "loss": 0.5561, | |
| "mean_token_accuracy": 0.8003985285758972, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.07623888182973317, | |
| "grad_norm": 1.987593615824268, | |
| "learning_rate": 1.5189873417721521e-05, | |
| "loss": 0.5637, | |
| "mean_token_accuracy": 0.7922172099351883, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.07835662854722575, | |
| "grad_norm": 1.6436094243541917, | |
| "learning_rate": 1.5611814345991563e-05, | |
| "loss": 0.5662, | |
| "mean_token_accuracy": 0.7916066467761993, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.08047437526471835, | |
| "grad_norm": 1.6236359809975813, | |
| "learning_rate": 1.6033755274261603e-05, | |
| "loss": 0.5432, | |
| "mean_token_accuracy": 0.8009026974439621, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.08259212198221093, | |
| "grad_norm": 1.5274031981451834, | |
| "learning_rate": 1.6455696202531647e-05, | |
| "loss": 0.5484, | |
| "mean_token_accuracy": 0.7982567459344864, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.08470986869970351, | |
| "grad_norm": 2.03018219248001, | |
| "learning_rate": 1.687763713080169e-05, | |
| "loss": 0.5407, | |
| "mean_token_accuracy": 0.8011936664581298, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.08682761541719611, | |
| "grad_norm": 1.8014465384883518, | |
| "learning_rate": 1.729957805907173e-05, | |
| "loss": 0.5247, | |
| "mean_token_accuracy": 0.8084624141454697, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.08894536213468869, | |
| "grad_norm": 1.7271306151793162, | |
| "learning_rate": 1.7721518987341772e-05, | |
| "loss": 0.5708, | |
| "mean_token_accuracy": 0.7947988003492356, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.09106310885218127, | |
| "grad_norm": 1.9191596287336676, | |
| "learning_rate": 1.8143459915611816e-05, | |
| "loss": 0.5363, | |
| "mean_token_accuracy": 0.8047021597623825, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.09318085556967387, | |
| "grad_norm": 1.7320574921982606, | |
| "learning_rate": 1.856540084388186e-05, | |
| "loss": 0.5658, | |
| "mean_token_accuracy": 0.7928981482982635, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.09529860228716645, | |
| "grad_norm": 1.8013279459762328, | |
| "learning_rate": 1.89873417721519e-05, | |
| "loss": 0.5283, | |
| "mean_token_accuracy": 0.8064373075962067, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.09741634900465904, | |
| "grad_norm": 1.6963994963949376, | |
| "learning_rate": 1.9409282700421944e-05, | |
| "loss": 0.541, | |
| "mean_token_accuracy": 0.798399469256401, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.09953409572215163, | |
| "grad_norm": 1.8211709634602606, | |
| "learning_rate": 1.9831223628691984e-05, | |
| "loss": 0.5529, | |
| "mean_token_accuracy": 0.7973109990358352, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.10165184243964422, | |
| "grad_norm": 1.800221940229098, | |
| "learning_rate": 1.9999901552991966e-05, | |
| "loss": 0.5297, | |
| "mean_token_accuracy": 0.8061769932508469, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.10376958915713681, | |
| "grad_norm": 3.118430462846644, | |
| "learning_rate": 1.9999299939406875e-05, | |
| "loss": 0.567, | |
| "mean_token_accuracy": 0.7869770050048828, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.1058873358746294, | |
| "grad_norm": 6.373265842936888, | |
| "learning_rate": 1.9998151437882874e-05, | |
| "loss": 0.5194, | |
| "mean_token_accuracy": 0.8079254150390625, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.10800508259212198, | |
| "grad_norm": 1.7643542086224073, | |
| "learning_rate": 1.999645611123453e-05, | |
| "loss": 0.5476, | |
| "mean_token_accuracy": 0.8036489874124527, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.11012282930961458, | |
| "grad_norm": 1.7570808876197173, | |
| "learning_rate": 1.999421405218369e-05, | |
| "loss": 0.5183, | |
| "mean_token_accuracy": 0.8039919883012772, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.11224057602710716, | |
| "grad_norm": 1.4650600928842654, | |
| "learning_rate": 1.9991425383354462e-05, | |
| "loss": 0.5575, | |
| "mean_token_accuracy": 0.7989150047302246, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.11435832274459974, | |
| "grad_norm": 1.5715508311626518, | |
| "learning_rate": 1.9988090257266442e-05, | |
| "loss": 0.5276, | |
| "mean_token_accuracy": 0.8024184852838516, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.11647606946209234, | |
| "grad_norm": 1.5012575844730074, | |
| "learning_rate": 1.9984208856326433e-05, | |
| "loss": 0.511, | |
| "mean_token_accuracy": 0.810269170999527, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.11859381617958492, | |
| "grad_norm": 2.1674114266205553, | |
| "learning_rate": 1.9979781392818424e-05, | |
| "loss": 0.5069, | |
| "mean_token_accuracy": 0.8049084335565567, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.1207115628970775, | |
| "grad_norm": 1.597566985653751, | |
| "learning_rate": 1.9974808108892017e-05, | |
| "loss": 0.5097, | |
| "mean_token_accuracy": 0.810433080792427, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.1228293096145701, | |
| "grad_norm": 2.721798223377223, | |
| "learning_rate": 1.9969289276549144e-05, | |
| "loss": 0.526, | |
| "mean_token_accuracy": 0.8058519691228867, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.12494705633206268, | |
| "grad_norm": 1.526771766492988, | |
| "learning_rate": 1.9963225197629223e-05, | |
| "loss": 0.5172, | |
| "mean_token_accuracy": 0.8079220175743103, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.12706480304955528, | |
| "grad_norm": 1.3424112355487237, | |
| "learning_rate": 1.9956616203792636e-05, | |
| "loss": 0.5135, | |
| "mean_token_accuracy": 0.806724363565445, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.12918254976704785, | |
| "grad_norm": 1.5824773036593809, | |
| "learning_rate": 1.9949462656502588e-05, | |
| "loss": 0.5383, | |
| "mean_token_accuracy": 0.8001780599355698, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.13130029648454045, | |
| "grad_norm": 1.5157834737082827, | |
| "learning_rate": 1.994176494700534e-05, | |
| "loss": 0.5466, | |
| "mean_token_accuracy": 0.7970251202583313, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.13341804320203304, | |
| "grad_norm": 1.8369627378901519, | |
| "learning_rate": 1.993352349630882e-05, | |
| "loss": 0.5218, | |
| "mean_token_accuracy": 0.8072717070579529, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.1355357899195256, | |
| "grad_norm": 1.5676620169867563, | |
| "learning_rate": 1.9924738755159573e-05, | |
| "loss": 0.5116, | |
| "mean_token_accuracy": 0.8025958120822907, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.1376535366370182, | |
| "grad_norm": 1.5442271717658778, | |
| "learning_rate": 1.9915411204018137e-05, | |
| "loss": 0.495, | |
| "mean_token_accuracy": 0.8155842959880829, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.1397712833545108, | |
| "grad_norm": 1.9104862823035134, | |
| "learning_rate": 1.9905541353032744e-05, | |
| "loss": 0.4707, | |
| "mean_token_accuracy": 0.8196403324604035, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.14188903007200337, | |
| "grad_norm": 1.8843041038781683, | |
| "learning_rate": 1.9895129742011434e-05, | |
| "loss": 0.5359, | |
| "mean_token_accuracy": 0.8036209732294083, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.14400677678949597, | |
| "grad_norm": 1.2996290243783448, | |
| "learning_rate": 1.9884176940392522e-05, | |
| "loss": 0.5355, | |
| "mean_token_accuracy": 0.7970023989677429, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.14612452350698857, | |
| "grad_norm": 1.7409691547169837, | |
| "learning_rate": 1.9872683547213446e-05, | |
| "loss": 0.5222, | |
| "mean_token_accuracy": 0.8015773713588714, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.14824227022448117, | |
| "grad_norm": 1.3236145792783143, | |
| "learning_rate": 1.9860650191078033e-05, | |
| "loss": 0.5165, | |
| "mean_token_accuracy": 0.8045854181051254, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.15036001694197373, | |
| "grad_norm": 1.5674402609006048, | |
| "learning_rate": 1.9848077530122083e-05, | |
| "loss": 0.5141, | |
| "mean_token_accuracy": 0.8047444432973861, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.15247776365946633, | |
| "grad_norm": 1.4948547674340282, | |
| "learning_rate": 1.98349662519774e-05, | |
| "loss": 0.493, | |
| "mean_token_accuracy": 0.8128765910863877, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.15459551037695893, | |
| "grad_norm": 1.57285942684427, | |
| "learning_rate": 1.9821317073734173e-05, | |
| "loss": 0.5114, | |
| "mean_token_accuracy": 0.8024025142192841, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.1567132570944515, | |
| "grad_norm": 1.3725667498479879, | |
| "learning_rate": 1.9807130741901756e-05, | |
| "loss": 0.5552, | |
| "mean_token_accuracy": 0.7975639194250107, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.1588310038119441, | |
| "grad_norm": 1.6323326415858614, | |
| "learning_rate": 1.979240803236785e-05, | |
| "loss": 0.5101, | |
| "mean_token_accuracy": 0.8058428287506103, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.1609487505294367, | |
| "grad_norm": 1.293657741608038, | |
| "learning_rate": 1.9777149750356044e-05, | |
| "loss": 0.4931, | |
| "mean_token_accuracy": 0.8156037211418152, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.16306649724692926, | |
| "grad_norm": 1.584456213127757, | |
| "learning_rate": 1.9761356730381806e-05, | |
| "loss": 0.5066, | |
| "mean_token_accuracy": 0.8106210082769394, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.16518424396442186, | |
| "grad_norm": 1.3531024564685128, | |
| "learning_rate": 1.9745029836206813e-05, | |
| "loss": 0.4862, | |
| "mean_token_accuracy": 0.8180296182632446, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.16730199068191445, | |
| "grad_norm": 1.5992771952291873, | |
| "learning_rate": 1.9728169960791736e-05, | |
| "loss": 0.5158, | |
| "mean_token_accuracy": 0.8020082831382751, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 0.16941973739940702, | |
| "grad_norm": 1.3875752393035827, | |
| "learning_rate": 1.9710778026247367e-05, | |
| "loss": 0.5268, | |
| "mean_token_accuracy": 0.8021057844161987, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.17153748411689962, | |
| "grad_norm": 1.4892475787998831, | |
| "learning_rate": 1.9692854983784235e-05, | |
| "loss": 0.5031, | |
| "mean_token_accuracy": 0.8153967589139939, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 0.17365523083439222, | |
| "grad_norm": 1.3435721015179996, | |
| "learning_rate": 1.9674401813660532e-05, | |
| "loss": 0.5151, | |
| "mean_token_accuracy": 0.8066144526004791, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.17577297755188478, | |
| "grad_norm": 1.4757784795296558, | |
| "learning_rate": 1.9655419525128528e-05, | |
| "loss": 0.5197, | |
| "mean_token_accuracy": 0.8056324630975723, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 0.17789072426937738, | |
| "grad_norm": 1.8586890907074842, | |
| "learning_rate": 1.9635909156379373e-05, | |
| "loss": 0.4817, | |
| "mean_token_accuracy": 0.8227346748113632, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.18000847098686998, | |
| "grad_norm": 1.3338010634125226, | |
| "learning_rate": 1.9615871774486293e-05, | |
| "loss": 0.476, | |
| "mean_token_accuracy": 0.8171389639377594, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.18212621770436255, | |
| "grad_norm": 1.467996639944381, | |
| "learning_rate": 1.959530847534627e-05, | |
| "loss": 0.4857, | |
| "mean_token_accuracy": 0.8151497721672059, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.18424396442185514, | |
| "grad_norm": 1.482953746737999, | |
| "learning_rate": 1.9574220383620054e-05, | |
| "loss": 0.4922, | |
| "mean_token_accuracy": 0.8100210309028626, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 0.18636171113934774, | |
| "grad_norm": 5.208401516653082, | |
| "learning_rate": 1.95526086526707e-05, | |
| "loss": 0.5263, | |
| "mean_token_accuracy": 0.8080328673124313, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.1884794578568403, | |
| "grad_norm": 1.5834873689672437, | |
| "learning_rate": 1.9530474464500445e-05, | |
| "loss": 0.514, | |
| "mean_token_accuracy": 0.8094299465417862, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 0.1905972045743329, | |
| "grad_norm": 1.3405671636751928, | |
| "learning_rate": 1.9507819029686094e-05, | |
| "loss": 0.5119, | |
| "mean_token_accuracy": 0.8087350040674209, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.1927149512918255, | |
| "grad_norm": 1.3993020572279387, | |
| "learning_rate": 1.94846435873128e-05, | |
| "loss": 0.5153, | |
| "mean_token_accuracy": 0.8082747459411621, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 0.19483269800931807, | |
| "grad_norm": 1.3011551512989479, | |
| "learning_rate": 1.9460949404906285e-05, | |
| "loss": 0.5028, | |
| "mean_token_accuracy": 0.8120961904525756, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.19695044472681067, | |
| "grad_norm": 1.6479875272294309, | |
| "learning_rate": 1.9436737778363526e-05, | |
| "loss": 0.4787, | |
| "mean_token_accuracy": 0.8184203952550888, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 0.19906819144430327, | |
| "grad_norm": 1.2952323822215526, | |
| "learning_rate": 1.9412010031881884e-05, | |
| "loss": 0.4811, | |
| "mean_token_accuracy": 0.8196297824382782, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.20118593816179586, | |
| "grad_norm": 1.2434980503550659, | |
| "learning_rate": 1.9386767517886666e-05, | |
| "loss": 0.4992, | |
| "mean_token_accuracy": 0.8126247316598892, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.20330368487928843, | |
| "grad_norm": 1.2749730489780189, | |
| "learning_rate": 1.9361011616957165e-05, | |
| "loss": 0.5013, | |
| "mean_token_accuracy": 0.8094296991825104, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.20542143159678103, | |
| "grad_norm": 1.2801081991950354, | |
| "learning_rate": 1.933474373775115e-05, | |
| "loss": 0.4914, | |
| "mean_token_accuracy": 0.8103417336940766, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 0.20753917831427363, | |
| "grad_norm": 1.3841139586738282, | |
| "learning_rate": 1.930796531692783e-05, | |
| "loss": 0.503, | |
| "mean_token_accuracy": 0.8150111019611359, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.2096569250317662, | |
| "grad_norm": 1.2895819374549709, | |
| "learning_rate": 1.9280677819069273e-05, | |
| "loss": 0.4938, | |
| "mean_token_accuracy": 0.8058139503002166, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 0.2117746717492588, | |
| "grad_norm": 1.2705506609214867, | |
| "learning_rate": 1.9252882736600302e-05, | |
| "loss": 0.5041, | |
| "mean_token_accuracy": 0.8078715801239014, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.2138924184667514, | |
| "grad_norm": 1.3700128773821674, | |
| "learning_rate": 1.922458158970688e-05, | |
| "loss": 0.5122, | |
| "mean_token_accuracy": 0.805089196562767, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 0.21601016518424396, | |
| "grad_norm": 1.4292612681859336, | |
| "learning_rate": 1.9195775926252952e-05, | |
| "loss": 0.4799, | |
| "mean_token_accuracy": 0.8134547978639602, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.21812791190173655, | |
| "grad_norm": 2.589810653355124, | |
| "learning_rate": 1.91664673216958e-05, | |
| "loss": 0.4686, | |
| "mean_token_accuracy": 0.8232874065637589, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 0.22024565861922915, | |
| "grad_norm": 1.4425686621750156, | |
| "learning_rate": 1.913665737899988e-05, | |
| "loss": 0.4885, | |
| "mean_token_accuracy": 0.815599313378334, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.22236340533672172, | |
| "grad_norm": 1.4823410740282665, | |
| "learning_rate": 1.9106347728549134e-05, | |
| "loss": 0.4832, | |
| "mean_token_accuracy": 0.8109551817178726, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.22448115205421432, | |
| "grad_norm": 1.1459009249468546, | |
| "learning_rate": 1.9075540028057844e-05, | |
| "loss": 0.5156, | |
| "mean_token_accuracy": 0.8015700995922088, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.2265988987717069, | |
| "grad_norm": 1.273350806844229, | |
| "learning_rate": 1.9044235962479945e-05, | |
| "loss": 0.4901, | |
| "mean_token_accuracy": 0.8163118690252305, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 0.22871664548919948, | |
| "grad_norm": 1.2736969034780394, | |
| "learning_rate": 1.9012437243916895e-05, | |
| "loss": 0.475, | |
| "mean_token_accuracy": 0.8155727684497833, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.23083439220669208, | |
| "grad_norm": 1.1644155017049156, | |
| "learning_rate": 1.8980145611523996e-05, | |
| "loss": 0.5041, | |
| "mean_token_accuracy": 0.8130400031805038, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 0.23295213892418468, | |
| "grad_norm": 1.3543018612133357, | |
| "learning_rate": 1.8947362831415327e-05, | |
| "loss": 0.4668, | |
| "mean_token_accuracy": 0.8260669410228729, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.23506988564167725, | |
| "grad_norm": 1.2391111005758269, | |
| "learning_rate": 1.8914090696567104e-05, | |
| "loss": 0.4809, | |
| "mean_token_accuracy": 0.8127309769392014, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 0.23718763235916984, | |
| "grad_norm": 2.2015980143710583, | |
| "learning_rate": 1.888033102671965e-05, | |
| "loss": 0.4922, | |
| "mean_token_accuracy": 0.8155588954687119, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.23930537907666244, | |
| "grad_norm": 1.2198454979455773, | |
| "learning_rate": 1.884608566827785e-05, | |
| "loss": 0.5168, | |
| "mean_token_accuracy": 0.8062847316265106, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 0.241423125794155, | |
| "grad_norm": 1.184969374617232, | |
| "learning_rate": 1.8811356494210166e-05, | |
| "loss": 0.4805, | |
| "mean_token_accuracy": 0.8132707148790359, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.2435408725116476, | |
| "grad_norm": 1.187126766493632, | |
| "learning_rate": 1.8776145403946226e-05, | |
| "loss": 0.4955, | |
| "mean_token_accuracy": 0.8102918237447738, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.2456586192291402, | |
| "grad_norm": 1.3821096957818944, | |
| "learning_rate": 1.874045432327289e-05, | |
| "loss": 0.4985, | |
| "mean_token_accuracy": 0.8098550081253052, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.24777636594663277, | |
| "grad_norm": 1.214604218577671, | |
| "learning_rate": 1.8704285204228973e-05, | |
| "loss": 0.4627, | |
| "mean_token_accuracy": 0.8165160745382309, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 0.24989411266412537, | |
| "grad_norm": 1.4526314855211653, | |
| "learning_rate": 1.866764002499846e-05, | |
| "loss": 0.4909, | |
| "mean_token_accuracy": 0.8122711658477784, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.25201185938161796, | |
| "grad_norm": 1.1543877428891598, | |
| "learning_rate": 1.8630520789802308e-05, | |
| "loss": 0.4782, | |
| "mean_token_accuracy": 0.8182896554470063, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 0.25412960609911056, | |
| "grad_norm": 1.3086338857944744, | |
| "learning_rate": 1.8592929528788844e-05, | |
| "loss": 0.4753, | |
| "mean_token_accuracy": 0.8180733859539032, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.25624735281660316, | |
| "grad_norm": 1.3557276365311686, | |
| "learning_rate": 1.8554868297922728e-05, | |
| "loss": 0.4708, | |
| "mean_token_accuracy": 0.8193376958370209, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 0.2583650995340957, | |
| "grad_norm": 1.2996719117152657, | |
| "learning_rate": 1.8516339178872492e-05, | |
| "loss": 0.4518, | |
| "mean_token_accuracy": 0.8204487860202789, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.2604828462515883, | |
| "grad_norm": 1.3696724777806233, | |
| "learning_rate": 1.8477344278896708e-05, | |
| "loss": 0.5072, | |
| "mean_token_accuracy": 0.8076569020748139, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 0.2626005929690809, | |
| "grad_norm": 1.2308629288247015, | |
| "learning_rate": 1.8437885730728738e-05, | |
| "loss": 0.5113, | |
| "mean_token_accuracy": 0.8088377475738525, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.2647183396865735, | |
| "grad_norm": 1.2397238918015017, | |
| "learning_rate": 1.839796569246006e-05, | |
| "loss": 0.494, | |
| "mean_token_accuracy": 0.8118572622537613, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.2668360864040661, | |
| "grad_norm": 1.3479748389387212, | |
| "learning_rate": 1.8357586347422266e-05, | |
| "loss": 0.5081, | |
| "mean_token_accuracy": 0.8135558038949966, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.2689538331215587, | |
| "grad_norm": 1.1063564395200467, | |
| "learning_rate": 1.8316749904067637e-05, | |
| "loss": 0.4653, | |
| "mean_token_accuracy": 0.8218313783407212, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 0.2710715798390512, | |
| "grad_norm": 1.1492824512346658, | |
| "learning_rate": 1.8275458595848376e-05, | |
| "loss": 0.4817, | |
| "mean_token_accuracy": 0.8135390222072602, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.2731893265565438, | |
| "grad_norm": 1.4159749106872088, | |
| "learning_rate": 1.8233714681094405e-05, | |
| "loss": 0.4616, | |
| "mean_token_accuracy": 0.8250806093215942, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 0.2753070732740364, | |
| "grad_norm": 1.1611107224498594, | |
| "learning_rate": 1.819152044288992e-05, | |
| "loss": 0.488, | |
| "mean_token_accuracy": 0.8166846603155136, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.277424819991529, | |
| "grad_norm": 1.3205339840836507, | |
| "learning_rate": 1.814887818894846e-05, | |
| "loss": 0.5036, | |
| "mean_token_accuracy": 0.810426139831543, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 0.2795425667090216, | |
| "grad_norm": 1.2642547117014469, | |
| "learning_rate": 1.810579025148674e-05, | |
| "loss": 0.5063, | |
| "mean_token_accuracy": 0.8112012058496475, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.2816603134265142, | |
| "grad_norm": 5.33401159048522, | |
| "learning_rate": 1.8062258987097062e-05, | |
| "loss": 0.4478, | |
| "mean_token_accuracy": 0.8289118260145187, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 0.28377806014400675, | |
| "grad_norm": 1.3752087188227111, | |
| "learning_rate": 1.8018286776618446e-05, | |
| "loss": 0.4963, | |
| "mean_token_accuracy": 0.8137694984674454, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.28589580686149935, | |
| "grad_norm": 1.176266427707403, | |
| "learning_rate": 1.7973876025006407e-05, | |
| "loss": 0.4976, | |
| "mean_token_accuracy": 0.8188654541969299, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 0.28801355357899194, | |
| "grad_norm": 1.331341038204072, | |
| "learning_rate": 1.792902916120143e-05, | |
| "loss": 0.4939, | |
| "mean_token_accuracy": 0.8163222283124923, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.29013130029648454, | |
| "grad_norm": 1.1914829607255677, | |
| "learning_rate": 1.7883748637996113e-05, | |
| "loss": 0.4881, | |
| "mean_token_accuracy": 0.8130565702915191, | |
| "step": 685 | |
| }, | |
| { | |
| "epoch": 0.29224904701397714, | |
| "grad_norm": 1.2277506964948814, | |
| "learning_rate": 1.7838036931901033e-05, | |
| "loss": 0.4559, | |
| "mean_token_accuracy": 0.824514701962471, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.29436679373146973, | |
| "grad_norm": 1.0800320597549389, | |
| "learning_rate": 1.7791896543009282e-05, | |
| "loss": 0.4891, | |
| "mean_token_accuracy": 0.8174144089221954, | |
| "step": 695 | |
| }, | |
| { | |
| "epoch": 0.29648454044896233, | |
| "grad_norm": 1.5694294317697621, | |
| "learning_rate": 1.7745329994859746e-05, | |
| "loss": 0.4914, | |
| "mean_token_accuracy": 0.8185641199350357, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.29860228716645487, | |
| "grad_norm": 1.1923041867729132, | |
| "learning_rate": 1.7698339834299064e-05, | |
| "loss": 0.5008, | |
| "mean_token_accuracy": 0.8142161637544632, | |
| "step": 705 | |
| }, | |
| { | |
| "epoch": 0.30072003388394747, | |
| "grad_norm": 1.3729946102267174, | |
| "learning_rate": 1.7650928631342364e-05, | |
| "loss": 0.4845, | |
| "mean_token_accuracy": 0.8133604645729064, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.30283778060144007, | |
| "grad_norm": 1.174456646604131, | |
| "learning_rate": 1.7603098979032683e-05, | |
| "loss": 0.4777, | |
| "mean_token_accuracy": 0.813685166835785, | |
| "step": 715 | |
| }, | |
| { | |
| "epoch": 0.30495552731893266, | |
| "grad_norm": 1.158532302748484, | |
| "learning_rate": 1.7554853493299142e-05, | |
| "loss": 0.504, | |
| "mean_token_accuracy": 0.8088937163352966, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.30707327403642526, | |
| "grad_norm": 1.2620596837516858, | |
| "learning_rate": 1.7506194812813896e-05, | |
| "loss": 0.4817, | |
| "mean_token_accuracy": 0.8206409096717835, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 0.30919102075391786, | |
| "grad_norm": 1.148012521360775, | |
| "learning_rate": 1.74571255988478e-05, | |
| "loss": 0.4819, | |
| "mean_token_accuracy": 0.812398812174797, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.3113087674714104, | |
| "grad_norm": 1.2373133691587057, | |
| "learning_rate": 1.740764853512485e-05, | |
| "loss": 0.49, | |
| "mean_token_accuracy": 0.8143349289894104, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 0.313426514188903, | |
| "grad_norm": 2.100740115519466, | |
| "learning_rate": 1.7357766327675433e-05, | |
| "loss": 0.4651, | |
| "mean_token_accuracy": 0.8216336488723754, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.3155442609063956, | |
| "grad_norm": 1.4189894877798284, | |
| "learning_rate": 1.73074817046883e-05, | |
| "loss": 0.4801, | |
| "mean_token_accuracy": 0.8188165038824081, | |
| "step": 745 | |
| }, | |
| { | |
| "epoch": 0.3176620076238882, | |
| "grad_norm": 1.2994480429040771, | |
| "learning_rate": 1.725679741636136e-05, | |
| "loss": 0.4614, | |
| "mean_token_accuracy": 0.8237657248973846, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.3197797543413808, | |
| "grad_norm": 1.2308603791930401, | |
| "learning_rate": 1.720571623475128e-05, | |
| "loss": 0.492, | |
| "mean_token_accuracy": 0.8165101200342179, | |
| "step": 755 | |
| }, | |
| { | |
| "epoch": 0.3218975010588734, | |
| "grad_norm": 1.3843077010151197, | |
| "learning_rate": 1.7154240953621844e-05, | |
| "loss": 0.4564, | |
| "mean_token_accuracy": 0.825025874376297, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.3240152477763659, | |
| "grad_norm": 1.1848129565884666, | |
| "learning_rate": 1.7102374388291182e-05, | |
| "loss": 0.4575, | |
| "mean_token_accuracy": 0.8252220988273621, | |
| "step": 765 | |
| }, | |
| { | |
| "epoch": 0.3261329944938585, | |
| "grad_norm": 1.3217187216198285, | |
| "learning_rate": 1.705011937547779e-05, | |
| "loss": 0.4629, | |
| "mean_token_accuracy": 0.8198304086923599, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.3282507412113511, | |
| "grad_norm": 1.3851637896221318, | |
| "learning_rate": 1.6997478773145363e-05, | |
| "loss": 0.4337, | |
| "mean_token_accuracy": 0.8338131695985794, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 0.3303684879288437, | |
| "grad_norm": 1.423775789920787, | |
| "learning_rate": 1.6944455460346503e-05, | |
| "loss": 0.4807, | |
| "mean_token_accuracy": 0.8188902169466019, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.3324862346463363, | |
| "grad_norm": 1.3680154210297841, | |
| "learning_rate": 1.6891052337065256e-05, | |
| "loss": 0.4841, | |
| "mean_token_accuracy": 0.8188378721475601, | |
| "step": 785 | |
| }, | |
| { | |
| "epoch": 0.3346039813638289, | |
| "grad_norm": 1.1670007538420892, | |
| "learning_rate": 1.6837272324058487e-05, | |
| "loss": 0.4209, | |
| "mean_token_accuracy": 0.8359328061342239, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.33672172808132145, | |
| "grad_norm": 1.2238185684348435, | |
| "learning_rate": 1.6783118362696162e-05, | |
| "loss": 0.4687, | |
| "mean_token_accuracy": 0.8194981902837754, | |
| "step": 795 | |
| }, | |
| { | |
| "epoch": 0.33883947479881404, | |
| "grad_norm": 1.3104844364549155, | |
| "learning_rate": 1.672859341480046e-05, | |
| "loss": 0.4605, | |
| "mean_token_accuracy": 0.8169092148542404, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.34095722151630664, | |
| "grad_norm": 1.1074420443801423, | |
| "learning_rate": 1.6673700462483776e-05, | |
| "loss": 0.4424, | |
| "mean_token_accuracy": 0.8315922617912292, | |
| "step": 805 | |
| }, | |
| { | |
| "epoch": 0.34307496823379924, | |
| "grad_norm": 1.2002465546594834, | |
| "learning_rate": 1.661844250798565e-05, | |
| "loss": 0.4773, | |
| "mean_token_accuracy": 0.8234172344207764, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.34519271495129183, | |
| "grad_norm": 1.3643314568341807, | |
| "learning_rate": 1.6562822573508533e-05, | |
| "loss": 0.4803, | |
| "mean_token_accuracy": 0.8155502796173095, | |
| "step": 815 | |
| }, | |
| { | |
| "epoch": 0.34731046166878443, | |
| "grad_norm": 1.1653511889703811, | |
| "learning_rate": 1.650684370105252e-05, | |
| "loss": 0.4907, | |
| "mean_token_accuracy": 0.8095988690853119, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.34942820838627703, | |
| "grad_norm": 1.2052540958169133, | |
| "learning_rate": 1.6450508952248957e-05, | |
| "loss": 0.4664, | |
| "mean_token_accuracy": 0.8265933513641357, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 0.35154595510376957, | |
| "grad_norm": 1.5477552328113091, | |
| "learning_rate": 1.6393821408193007e-05, | |
| "loss": 0.4783, | |
| "mean_token_accuracy": 0.8169477820396424, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.35366370182126217, | |
| "grad_norm": 1.8070494772139423, | |
| "learning_rate": 1.6336784169275132e-05, | |
| "loss": 0.454, | |
| "mean_token_accuracy": 0.8248355984687805, | |
| "step": 835 | |
| }, | |
| { | |
| "epoch": 0.35578144853875476, | |
| "grad_norm": 1.2257376390653825, | |
| "learning_rate": 1.627940035501152e-05, | |
| "loss": 0.4506, | |
| "mean_token_accuracy": 0.8257219165563583, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.35789919525624736, | |
| "grad_norm": 1.3198794046839721, | |
| "learning_rate": 1.6221673103873474e-05, | |
| "loss": 0.4427, | |
| "mean_token_accuracy": 0.8296634495258332, | |
| "step": 845 | |
| }, | |
| { | |
| "epoch": 0.36001694197373996, | |
| "grad_norm": 2.109231295857473, | |
| "learning_rate": 1.616360557311575e-05, | |
| "loss": 0.489, | |
| "mean_token_accuracy": 0.8102859228849411, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.36213468869123255, | |
| "grad_norm": 1.1872292152679083, | |
| "learning_rate": 1.6105200938603917e-05, | |
| "loss": 0.4681, | |
| "mean_token_accuracy": 0.8261395335197449, | |
| "step": 855 | |
| }, | |
| { | |
| "epoch": 0.3642524354087251, | |
| "grad_norm": 1.214005452933459, | |
| "learning_rate": 1.60464623946406e-05, | |
| "loss": 0.4852, | |
| "mean_token_accuracy": 0.8179385870695114, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.3663701821262177, | |
| "grad_norm": 1.0907256335398452, | |
| "learning_rate": 1.5987393153790832e-05, | |
| "loss": 0.4623, | |
| "mean_token_accuracy": 0.8248693764209747, | |
| "step": 865 | |
| }, | |
| { | |
| "epoch": 0.3684879288437103, | |
| "grad_norm": 1.061691508146564, | |
| "learning_rate": 1.5927996446706308e-05, | |
| "loss": 0.4803, | |
| "mean_token_accuracy": 0.8169174045324326, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.3706056755612029, | |
| "grad_norm": 1.1759352091149649, | |
| "learning_rate": 1.5868275521948726e-05, | |
| "loss": 0.4563, | |
| "mean_token_accuracy": 0.8279780805110931, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 0.3727234222786955, | |
| "grad_norm": 1.2135030886876705, | |
| "learning_rate": 1.5808233645812087e-05, | |
| "loss": 0.4418, | |
| "mean_token_accuracy": 0.8301020473241806, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.3748411689961881, | |
| "grad_norm": 1.1266881444254488, | |
| "learning_rate": 1.5747874102144073e-05, | |
| "loss": 0.4626, | |
| "mean_token_accuracy": 0.8214969336986542, | |
| "step": 885 | |
| }, | |
| { | |
| "epoch": 0.3769589157136806, | |
| "grad_norm": 1.0911244736489776, | |
| "learning_rate": 1.5687200192166424e-05, | |
| "loss": 0.4635, | |
| "mean_token_accuracy": 0.8221491903066636, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.3790766624311732, | |
| "grad_norm": 1.0852849507203284, | |
| "learning_rate": 1.5626215234294416e-05, | |
| "loss": 0.451, | |
| "mean_token_accuracy": 0.8251518607139587, | |
| "step": 895 | |
| }, | |
| { | |
| "epoch": 0.3811944091486658, | |
| "grad_norm": 1.1215853338868707, | |
| "learning_rate": 1.5564922563955337e-05, | |
| "loss": 0.4608, | |
| "mean_token_accuracy": 0.8237892210483551, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.3833121558661584, | |
| "grad_norm": 0.9235255903522734, | |
| "learning_rate": 1.5503325533406076e-05, | |
| "loss": 0.4676, | |
| "mean_token_accuracy": 0.8222286731004715, | |
| "step": 905 | |
| }, | |
| { | |
| "epoch": 0.385429902583651, | |
| "grad_norm": 1.0494173037764836, | |
| "learning_rate": 1.5441427511549795e-05, | |
| "loss": 0.4652, | |
| "mean_token_accuracy": 0.8235789179801941, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.3875476493011436, | |
| "grad_norm": 1.2934333868332708, | |
| "learning_rate": 1.537923188375164e-05, | |
| "loss": 0.459, | |
| "mean_token_accuracy": 0.8253506690263748, | |
| "step": 915 | |
| }, | |
| { | |
| "epoch": 0.38966539601863615, | |
| "grad_norm": 1.045643086378396, | |
| "learning_rate": 1.5316742051653624e-05, | |
| "loss": 0.4487, | |
| "mean_token_accuracy": 0.8300421804189682, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.39178314273612874, | |
| "grad_norm": 1.0549731687620314, | |
| "learning_rate": 1.5253961432988548e-05, | |
| "loss": 0.4756, | |
| "mean_token_accuracy": 0.8141780078411103, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 0.39390088945362134, | |
| "grad_norm": 1.1263426428393677, | |
| "learning_rate": 1.5190893461393108e-05, | |
| "loss": 0.4698, | |
| "mean_token_accuracy": 0.8173887878656387, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.39601863617111394, | |
| "grad_norm": 1.1982411204873675, | |
| "learning_rate": 1.5127541586220077e-05, | |
| "loss": 0.4595, | |
| "mean_token_accuracy": 0.8246693462133408, | |
| "step": 935 | |
| }, | |
| { | |
| "epoch": 0.39813638288860653, | |
| "grad_norm": 1.331125977750805, | |
| "learning_rate": 1.5063909272349664e-05, | |
| "loss": 0.466, | |
| "mean_token_accuracy": 0.8266402333974838, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.40025412960609913, | |
| "grad_norm": 1.165754254305497, | |
| "learning_rate": 1.5000000000000002e-05, | |
| "loss": 0.435, | |
| "mean_token_accuracy": 0.8271202713251113, | |
| "step": 945 | |
| }, | |
| { | |
| "epoch": 0.4023718763235917, | |
| "grad_norm": 1.1585938088360928, | |
| "learning_rate": 1.4935817264536809e-05, | |
| "loss": 0.4386, | |
| "mean_token_accuracy": 0.8255492657423019, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.40448962304108427, | |
| "grad_norm": 1.1542702135186313, | |
| "learning_rate": 1.4871364576282223e-05, | |
| "loss": 0.4769, | |
| "mean_token_accuracy": 0.8163278847932816, | |
| "step": 955 | |
| }, | |
| { | |
| "epoch": 0.40660736975857686, | |
| "grad_norm": 1.1855267108232739, | |
| "learning_rate": 1.4806645460322804e-05, | |
| "loss": 0.4938, | |
| "mean_token_accuracy": 0.8140994518995285, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.40872511647606946, | |
| "grad_norm": 1.0583179034757253, | |
| "learning_rate": 1.4741663456316742e-05, | |
| "loss": 0.4694, | |
| "mean_token_accuracy": 0.8194496780633926, | |
| "step": 965 | |
| }, | |
| { | |
| "epoch": 0.41084286319356206, | |
| "grad_norm": 1.2166297794886325, | |
| "learning_rate": 1.4676422118300266e-05, | |
| "loss": 0.4583, | |
| "mean_token_accuracy": 0.8240072697401046, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.41296060991105465, | |
| "grad_norm": 1.2077033819076497, | |
| "learning_rate": 1.461092501449326e-05, | |
| "loss": 0.4683, | |
| "mean_token_accuracy": 0.8127462983131408, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 0.41507835662854725, | |
| "grad_norm": 1.2024839451726628, | |
| "learning_rate": 1.4545175727104113e-05, | |
| "loss": 0.4746, | |
| "mean_token_accuracy": 0.817327806353569, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.4171961033460398, | |
| "grad_norm": 43.895890122529586, | |
| "learning_rate": 1.4479177852133787e-05, | |
| "loss": 0.4339, | |
| "mean_token_accuracy": 0.83043053150177, | |
| "step": 985 | |
| }, | |
| { | |
| "epoch": 0.4193138500635324, | |
| "grad_norm": 1.3761452239892333, | |
| "learning_rate": 1.4412934999179169e-05, | |
| "loss": 0.4682, | |
| "mean_token_accuracy": 0.82216075360775, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.421431596781025, | |
| "grad_norm": 9.553572882081992, | |
| "learning_rate": 1.4346450791235611e-05, | |
| "loss": 0.425, | |
| "mean_token_accuracy": 0.8346862554550171, | |
| "step": 995 | |
| }, | |
| { | |
| "epoch": 0.4235493434985176, | |
| "grad_norm": 1.19535922636142, | |
| "learning_rate": 1.427972886449882e-05, | |
| "loss": 0.4916, | |
| "mean_token_accuracy": 0.8201052099466324, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.4256670902160102, | |
| "grad_norm": 1.487407000401354, | |
| "learning_rate": 1.4212772868165957e-05, | |
| "loss": 0.4759, | |
| "mean_token_accuracy": 0.8201690822839737, | |
| "step": 1005 | |
| }, | |
| { | |
| "epoch": 0.4277848369335028, | |
| "grad_norm": 1.2209557581398112, | |
| "learning_rate": 1.4145586464236074e-05, | |
| "loss": 0.4776, | |
| "mean_token_accuracy": 0.8144995361566544, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 0.4299025836509953, | |
| "grad_norm": 1.4175123984588354, | |
| "learning_rate": 1.4078173327309807e-05, | |
| "loss": 0.4697, | |
| "mean_token_accuracy": 0.820775744318962, | |
| "step": 1015 | |
| }, | |
| { | |
| "epoch": 0.4320203303684879, | |
| "grad_norm": 1.2129818965934513, | |
| "learning_rate": 1.4010537144388416e-05, | |
| "loss": 0.463, | |
| "mean_token_accuracy": 0.8259893089532853, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.4341380770859805, | |
| "grad_norm": 1.12010970838833, | |
| "learning_rate": 1.3942681614672144e-05, | |
| "loss": 0.4629, | |
| "mean_token_accuracy": 0.8218669801950454, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 0.4362558238034731, | |
| "grad_norm": 1.1464961804103622, | |
| "learning_rate": 1.3874610449357873e-05, | |
| "loss": 0.4238, | |
| "mean_token_accuracy": 0.8335713416337966, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 0.4383735705209657, | |
| "grad_norm": 1.1351310993680606, | |
| "learning_rate": 1.3806327371436159e-05, | |
| "loss": 0.4394, | |
| "mean_token_accuracy": 0.8307629436254501, | |
| "step": 1035 | |
| }, | |
| { | |
| "epoch": 0.4404913172384583, | |
| "grad_norm": 1.1188266853744508, | |
| "learning_rate": 1.3737836115487624e-05, | |
| "loss": 0.4663, | |
| "mean_token_accuracy": 0.8193978488445282, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.44260906395595084, | |
| "grad_norm": 1.1620199858915772, | |
| "learning_rate": 1.3669140427478693e-05, | |
| "loss": 0.4705, | |
| "mean_token_accuracy": 0.8229668527841568, | |
| "step": 1045 | |
| }, | |
| { | |
| "epoch": 0.44472681067344344, | |
| "grad_norm": 1.110101616240863, | |
| "learning_rate": 1.3600244064556702e-05, | |
| "loss": 0.4747, | |
| "mean_token_accuracy": 0.8179006308317185, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.44684455739093604, | |
| "grad_norm": 1.2783615446297392, | |
| "learning_rate": 1.353115079484444e-05, | |
| "loss": 0.4458, | |
| "mean_token_accuracy": 0.8308207571506501, | |
| "step": 1055 | |
| }, | |
| { | |
| "epoch": 0.44896230410842863, | |
| "grad_norm": 1.1007302332610067, | |
| "learning_rate": 1.3461864397234041e-05, | |
| "loss": 0.4598, | |
| "mean_token_accuracy": 0.8242943733930588, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.45108005082592123, | |
| "grad_norm": 1.2199483732995027, | |
| "learning_rate": 1.3392388661180303e-05, | |
| "loss": 0.445, | |
| "mean_token_accuracy": 0.824502220749855, | |
| "step": 1065 | |
| }, | |
| { | |
| "epoch": 0.4531977975434138, | |
| "grad_norm": 1.0010509955815885, | |
| "learning_rate": 1.332272738649345e-05, | |
| "loss": 0.4583, | |
| "mean_token_accuracy": 0.8303744524717331, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 0.45531554426090637, | |
| "grad_norm": 1.918284418636839, | |
| "learning_rate": 1.325288438313129e-05, | |
| "loss": 0.4269, | |
| "mean_token_accuracy": 0.8296439230442048, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 0.45743329097839897, | |
| "grad_norm": 1.1887902164021535, | |
| "learning_rate": 1.318286347099086e-05, | |
| "loss": 0.4625, | |
| "mean_token_accuracy": 0.8217881232500076, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.45955103769589156, | |
| "grad_norm": 1.1360766453253965, | |
| "learning_rate": 1.3112668479699486e-05, | |
| "loss": 0.4589, | |
| "mean_token_accuracy": 0.8269425123929978, | |
| "step": 1085 | |
| }, | |
| { | |
| "epoch": 0.46166878441338416, | |
| "grad_norm": 1.2399254503178083, | |
| "learning_rate": 1.3042303248405346e-05, | |
| "loss": 0.4555, | |
| "mean_token_accuracy": 0.8309968203306198, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 0.46378653113087676, | |
| "grad_norm": 1.0508779611719044, | |
| "learning_rate": 1.297177162556748e-05, | |
| "loss": 0.4545, | |
| "mean_token_accuracy": 0.824161484837532, | |
| "step": 1095 | |
| }, | |
| { | |
| "epoch": 0.46590427784836935, | |
| "grad_norm": 1.0822262810815348, | |
| "learning_rate": 1.2901077468745329e-05, | |
| "loss": 0.4571, | |
| "mean_token_accuracy": 0.8281063556671142, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.46802202456586195, | |
| "grad_norm": 1.0744745429140576, | |
| "learning_rate": 1.2830224644387742e-05, | |
| "loss": 0.471, | |
| "mean_token_accuracy": 0.8183866649866104, | |
| "step": 1105 | |
| }, | |
| { | |
| "epoch": 0.4701397712833545, | |
| "grad_norm": 1.2108459211634035, | |
| "learning_rate": 1.2759217027621507e-05, | |
| "loss": 0.4445, | |
| "mean_token_accuracy": 0.8313823521137238, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 0.4722575180008471, | |
| "grad_norm": 1.1385271166035913, | |
| "learning_rate": 1.2688058502039416e-05, | |
| "loss": 0.4724, | |
| "mean_token_accuracy": 0.8208224922418594, | |
| "step": 1115 | |
| }, | |
| { | |
| "epoch": 0.4743752647183397, | |
| "grad_norm": 1.1608922255857643, | |
| "learning_rate": 1.261675295948786e-05, | |
| "loss": 0.4402, | |
| "mean_token_accuracy": 0.8260656505823135, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.4764930114358323, | |
| "grad_norm": 1.2001870807148136, | |
| "learning_rate": 1.2545304299853977e-05, | |
| "loss": 0.4676, | |
| "mean_token_accuracy": 0.8217555999755859, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 0.4786107581533249, | |
| "grad_norm": 1.099496727008847, | |
| "learning_rate": 1.2473716430852353e-05, | |
| "loss": 0.436, | |
| "mean_token_accuracy": 0.8312188684940338, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 0.4807285048708175, | |
| "grad_norm": 2.032998570634967, | |
| "learning_rate": 1.2401993267811293e-05, | |
| "loss": 0.4317, | |
| "mean_token_accuracy": 0.8295620054006576, | |
| "step": 1135 | |
| }, | |
| { | |
| "epoch": 0.48284625158831, | |
| "grad_norm": 1.1812725212971202, | |
| "learning_rate": 1.2330138733458693e-05, | |
| "loss": 0.4156, | |
| "mean_token_accuracy": 0.8353513538837433, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.4849639983058026, | |
| "grad_norm": 1.138821301405385, | |
| "learning_rate": 1.2258156757707496e-05, | |
| "loss": 0.4506, | |
| "mean_token_accuracy": 0.8284595161676407, | |
| "step": 1145 | |
| }, | |
| { | |
| "epoch": 0.4870817450232952, | |
| "grad_norm": 1.039456646381961, | |
| "learning_rate": 1.2186051277440739e-05, | |
| "loss": 0.4281, | |
| "mean_token_accuracy": 0.8340547412633896, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.4891994917407878, | |
| "grad_norm": 1.0935441587184827, | |
| "learning_rate": 1.2113826236296245e-05, | |
| "loss": 0.4368, | |
| "mean_token_accuracy": 0.8294982463121414, | |
| "step": 1155 | |
| }, | |
| { | |
| "epoch": 0.4913172384582804, | |
| "grad_norm": 1.0601849025025707, | |
| "learning_rate": 1.2041485584450945e-05, | |
| "loss": 0.4496, | |
| "mean_token_accuracy": 0.8288684636354446, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.493434985175773, | |
| "grad_norm": 1.1432826242197904, | |
| "learning_rate": 1.1969033278404816e-05, | |
| "loss": 0.472, | |
| "mean_token_accuracy": 0.8184500396251678, | |
| "step": 1165 | |
| }, | |
| { | |
| "epoch": 0.49555273189326554, | |
| "grad_norm": 1.178255399480397, | |
| "learning_rate": 1.1896473280764498e-05, | |
| "loss": 0.453, | |
| "mean_token_accuracy": 0.82464899122715, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 0.49767047861075814, | |
| "grad_norm": 1.2123556499205794, | |
| "learning_rate": 1.1823809560026558e-05, | |
| "loss": 0.442, | |
| "mean_token_accuracy": 0.8262520909309388, | |
| "step": 1175 | |
| }, | |
| { | |
| "epoch": 0.49978822532825073, | |
| "grad_norm": 1.490671459887953, | |
| "learning_rate": 1.175104609036047e-05, | |
| "loss": 0.4493, | |
| "mean_token_accuracy": 0.8295370072126389, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.5019059720457433, | |
| "grad_norm": 3.5058816478434993, | |
| "learning_rate": 1.1678186851391218e-05, | |
| "loss": 0.4593, | |
| "mean_token_accuracy": 0.8269213020801545, | |
| "step": 1185 | |
| }, | |
| { | |
| "epoch": 0.5040237187632359, | |
| "grad_norm": 1.1384716073513477, | |
| "learning_rate": 1.1605235827981673e-05, | |
| "loss": 0.4463, | |
| "mean_token_accuracy": 0.8314786165952682, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 0.5061414654807285, | |
| "grad_norm": 1.1752572701433124, | |
| "learning_rate": 1.1532197010014636e-05, | |
| "loss": 0.4453, | |
| "mean_token_accuracy": 0.8288865953683853, | |
| "step": 1195 | |
| }, | |
| { | |
| "epoch": 0.5082592121982211, | |
| "grad_norm": 1.0006379736398943, | |
| "learning_rate": 1.1459074392174619e-05, | |
| "loss": 0.4293, | |
| "mean_token_accuracy": 0.8350226402282714, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.5103769589157137, | |
| "grad_norm": 1.1784455736187447, | |
| "learning_rate": 1.138587197372937e-05, | |
| "loss": 0.4612, | |
| "mean_token_accuracy": 0.8215854614973068, | |
| "step": 1205 | |
| }, | |
| { | |
| "epoch": 0.5124947056332063, | |
| "grad_norm": 1.1048766566547503, | |
| "learning_rate": 1.1312593758311143e-05, | |
| "loss": 0.4279, | |
| "mean_token_accuracy": 0.8407860666513443, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 0.5146124523506989, | |
| "grad_norm": 1.0718700385713946, | |
| "learning_rate": 1.1239243753697728e-05, | |
| "loss": 0.4288, | |
| "mean_token_accuracy": 0.8378984898328781, | |
| "step": 1215 | |
| }, | |
| { | |
| "epoch": 0.5167301990681914, | |
| "grad_norm": 1.558568433227081, | |
| "learning_rate": 1.1165825971593251e-05, | |
| "loss": 0.4678, | |
| "mean_token_accuracy": 0.825000548362732, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 0.518847945785684, | |
| "grad_norm": 1.082392246698731, | |
| "learning_rate": 1.1092344427408767e-05, | |
| "loss": 0.4276, | |
| "mean_token_accuracy": 0.8359992414712906, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 0.5209656925031766, | |
| "grad_norm": 1.256334909576375, | |
| "learning_rate": 1.1018803140042651e-05, | |
| "loss": 0.4633, | |
| "mean_token_accuracy": 0.8229638338088989, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 0.5230834392206692, | |
| "grad_norm": 1.303814596864245, | |
| "learning_rate": 1.0945206131660787e-05, | |
| "loss": 0.469, | |
| "mean_token_accuracy": 0.8193328499794006, | |
| "step": 1235 | |
| }, | |
| { | |
| "epoch": 0.5252011859381618, | |
| "grad_norm": 1.0507039996160834, | |
| "learning_rate": 1.0871557427476585e-05, | |
| "loss": 0.4414, | |
| "mean_token_accuracy": 0.8317544460296631, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.5273189326556544, | |
| "grad_norm": 1.015866344156703, | |
| "learning_rate": 1.0797861055530832e-05, | |
| "loss": 0.428, | |
| "mean_token_accuracy": 0.8305379122495651, | |
| "step": 1245 | |
| }, | |
| { | |
| "epoch": 0.529436679373147, | |
| "grad_norm": 1.1624992956977676, | |
| "learning_rate": 1.07241210464714e-05, | |
| "loss": 0.467, | |
| "mean_token_accuracy": 0.820591053366661, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.5315544260906395, | |
| "grad_norm": 1.2782647412686758, | |
| "learning_rate": 1.0650341433332778e-05, | |
| "loss": 0.4689, | |
| "mean_token_accuracy": 0.8219984292984008, | |
| "step": 1255 | |
| }, | |
| { | |
| "epoch": 0.5336721728081322, | |
| "grad_norm": 1.1784870838731618, | |
| "learning_rate": 1.0576526251315515e-05, | |
| "loss": 0.4596, | |
| "mean_token_accuracy": 0.8260756641626358, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.5357899195256247, | |
| "grad_norm": 1.1204805080469906, | |
| "learning_rate": 1.0502679537565507e-05, | |
| "loss": 0.442, | |
| "mean_token_accuracy": 0.8296466141939163, | |
| "step": 1265 | |
| }, | |
| { | |
| "epoch": 0.5379076662431174, | |
| "grad_norm": 1.0718296420595828, | |
| "learning_rate": 1.0428805330953209e-05, | |
| "loss": 0.4215, | |
| "mean_token_accuracy": 0.8308669030666351, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 0.5400254129606099, | |
| "grad_norm": 1.1125024136410944, | |
| "learning_rate": 1.0354907671852733e-05, | |
| "loss": 0.4363, | |
| "mean_token_accuracy": 0.8332655102014541, | |
| "step": 1275 | |
| }, | |
| { | |
| "epoch": 0.5421431596781024, | |
| "grad_norm": 1.090167844275342, | |
| "learning_rate": 1.0280990601920863e-05, | |
| "loss": 0.4435, | |
| "mean_token_accuracy": 0.8282716870307922, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 0.5442609063955951, | |
| "grad_norm": 1.0290238619990948, | |
| "learning_rate": 1.0207058163876021e-05, | |
| "loss": 0.4413, | |
| "mean_token_accuracy": 0.8311887979507446, | |
| "step": 1285 | |
| }, | |
| { | |
| "epoch": 0.5463786531130876, | |
| "grad_norm": 1.0778232888370207, | |
| "learning_rate": 1.013311440127714e-05, | |
| "loss": 0.4386, | |
| "mean_token_accuracy": 0.8266764581203461, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 0.5484963998305803, | |
| "grad_norm": 1.1219731141973122, | |
| "learning_rate": 1.0059163358302537e-05, | |
| "loss": 0.4103, | |
| "mean_token_accuracy": 0.8391000181436539, | |
| "step": 1295 | |
| }, | |
| { | |
| "epoch": 0.5506141465480728, | |
| "grad_norm": 1.1468466517999107, | |
| "learning_rate": 9.9852090795287e-06, | |
| "loss": 0.4391, | |
| "mean_token_accuracy": 0.8361193478107453, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.5527318932655655, | |
| "grad_norm": 1.0284132663014267, | |
| "learning_rate": 9.911255609709089e-06, | |
| "loss": 0.4409, | |
| "mean_token_accuracy": 0.8269284754991532, | |
| "step": 1305 | |
| }, | |
| { | |
| "epoch": 0.554849639983058, | |
| "grad_norm": 1.0310999165822667, | |
| "learning_rate": 9.83730699355294e-06, | |
| "loss": 0.4071, | |
| "mean_token_accuracy": 0.835135304927826, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 0.5569673867005506, | |
| "grad_norm": 1.2728900066425748, | |
| "learning_rate": 9.76336727550401e-06, | |
| "loss": 0.4601, | |
| "mean_token_accuracy": 0.8267913639545441, | |
| "step": 1315 | |
| }, | |
| { | |
| "epoch": 0.5590851334180432, | |
| "grad_norm": 1.2269899407592741, | |
| "learning_rate": 9.689440499519395e-06, | |
| "loss": 0.4322, | |
| "mean_token_accuracy": 0.8314703017473221, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 0.5612028801355358, | |
| "grad_norm": 1.1418757049837882, | |
| "learning_rate": 9.615530708848373e-06, | |
| "loss": 0.4231, | |
| "mean_token_accuracy": 0.8340400338172913, | |
| "step": 1325 | |
| }, | |
| { | |
| "epoch": 0.5633206268530284, | |
| "grad_norm": 1.1108149486798655, | |
| "learning_rate": 9.541641945811233e-06, | |
| "loss": 0.4492, | |
| "mean_token_accuracy": 0.8232677519321442, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 0.565438373570521, | |
| "grad_norm": 1.1088127297572268, | |
| "learning_rate": 9.467778251578217e-06, | |
| "loss": 0.4549, | |
| "mean_token_accuracy": 0.8236530691385269, | |
| "step": 1335 | |
| }, | |
| { | |
| "epoch": 0.5675561202880135, | |
| "grad_norm": 0.9179664771961787, | |
| "learning_rate": 9.393943665948478e-06, | |
| "loss": 0.4763, | |
| "mean_token_accuracy": 0.8244054973125458, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 0.5696738670055062, | |
| "grad_norm": 1.1777867866273308, | |
| "learning_rate": 9.320142227129158e-06, | |
| "loss": 0.4348, | |
| "mean_token_accuracy": 0.8331925332546234, | |
| "step": 1345 | |
| }, | |
| { | |
| "epoch": 0.5717916137229987, | |
| "grad_norm": 1.0020743360016087, | |
| "learning_rate": 9.246377971514504e-06, | |
| "loss": 0.4161, | |
| "mean_token_accuracy": 0.8360674440860748, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.5739093604404913, | |
| "grad_norm": 1.346066080223308, | |
| "learning_rate": 9.172654933465114e-06, | |
| "loss": 0.448, | |
| "mean_token_accuracy": 0.8250635206699372, | |
| "step": 1355 | |
| }, | |
| { | |
| "epoch": 0.5760271071579839, | |
| "grad_norm": 1.3221207747875352, | |
| "learning_rate": 9.0989771450873e-06, | |
| "loss": 0.4228, | |
| "mean_token_accuracy": 0.8357968628406525, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 0.5781448538754765, | |
| "grad_norm": 1.1501989319658534, | |
| "learning_rate": 9.025348636012537e-06, | |
| "loss": 0.4411, | |
| "mean_token_accuracy": 0.8290417343378067, | |
| "step": 1365 | |
| }, | |
| { | |
| "epoch": 0.5802626005929691, | |
| "grad_norm": 1.1694331116554113, | |
| "learning_rate": 8.951773433177095e-06, | |
| "loss": 0.4343, | |
| "mean_token_accuracy": 0.8303040146827698, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 0.5823803473104616, | |
| "grad_norm": 1.2089472872967426, | |
| "learning_rate": 8.878255560601781e-06, | |
| "loss": 0.4285, | |
| "mean_token_accuracy": 0.8339911371469497, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 0.5844980940279543, | |
| "grad_norm": 1.1555334960481487, | |
| "learning_rate": 8.804799039171863e-06, | |
| "loss": 0.4225, | |
| "mean_token_accuracy": 0.8346673488616944, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 0.5866158407454468, | |
| "grad_norm": 0.9976941601020334, | |
| "learning_rate": 8.731407886417155e-06, | |
| "loss": 0.4538, | |
| "mean_token_accuracy": 0.8272438108921051, | |
| "step": 1385 | |
| }, | |
| { | |
| "epoch": 0.5887335874629395, | |
| "grad_norm": 1.0977726966561636, | |
| "learning_rate": 8.658086116292283e-06, | |
| "loss": 0.4297, | |
| "mean_token_accuracy": 0.8334219962358475, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 0.590851334180432, | |
| "grad_norm": 2.0194878160007987, | |
| "learning_rate": 8.584837738957155e-06, | |
| "loss": 0.4413, | |
| "mean_token_accuracy": 0.8283408343791961, | |
| "step": 1395 | |
| }, | |
| { | |
| "epoch": 0.5929690808979247, | |
| "grad_norm": 1.2186719145281468, | |
| "learning_rate": 8.511666760557638e-06, | |
| "loss": 0.4693, | |
| "mean_token_accuracy": 0.8232256740331649, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.5950868276154172, | |
| "grad_norm": 1.1198588684752515, | |
| "learning_rate": 8.438577183006448e-06, | |
| "loss": 0.4221, | |
| "mean_token_accuracy": 0.8324928849935531, | |
| "step": 1405 | |
| }, | |
| { | |
| "epoch": 0.5972045743329097, | |
| "grad_norm": 1.1215071963961742, | |
| "learning_rate": 8.36557300376427e-06, | |
| "loss": 0.4392, | |
| "mean_token_accuracy": 0.8286356210708619, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 0.5993223210504024, | |
| "grad_norm": 1.107475266800191, | |
| "learning_rate": 8.292658215621139e-06, | |
| "loss": 0.4344, | |
| "mean_token_accuracy": 0.8313880443572998, | |
| "step": 1415 | |
| }, | |
| { | |
| "epoch": 0.6014400677678949, | |
| "grad_norm": 1.1686631557802003, | |
| "learning_rate": 8.219836806478049e-06, | |
| "loss": 0.4336, | |
| "mean_token_accuracy": 0.8312123149633408, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 0.6035578144853876, | |
| "grad_norm": 1.230978585871069, | |
| "learning_rate": 8.147112759128859e-06, | |
| "loss": 0.4647, | |
| "mean_token_accuracy": 0.8231993585824966, | |
| "step": 1425 | |
| }, | |
| { | |
| "epoch": 0.6056755612028801, | |
| "grad_norm": 1.0717890273842352, | |
| "learning_rate": 8.074490051042447e-06, | |
| "loss": 0.4353, | |
| "mean_token_accuracy": 0.8321529895067215, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 0.6077933079203727, | |
| "grad_norm": 1.085108371368418, | |
| "learning_rate": 8.001972654145194e-06, | |
| "loss": 0.4415, | |
| "mean_token_accuracy": 0.8277548223733902, | |
| "step": 1435 | |
| }, | |
| { | |
| "epoch": 0.6099110546378653, | |
| "grad_norm": 1.2119593900205077, | |
| "learning_rate": 7.929564534603722e-06, | |
| "loss": 0.4571, | |
| "mean_token_accuracy": 0.8255878984928131, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 0.6120288013553579, | |
| "grad_norm": 1.1055437345283827, | |
| "learning_rate": 7.857269652607995e-06, | |
| "loss": 0.4406, | |
| "mean_token_accuracy": 0.8275179982185363, | |
| "step": 1445 | |
| }, | |
| { | |
| "epoch": 0.6141465480728505, | |
| "grad_norm": 1.1275451956189597, | |
| "learning_rate": 7.78509196215472e-06, | |
| "loss": 0.4308, | |
| "mean_token_accuracy": 0.8301453530788422, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.6162642947903431, | |
| "grad_norm": 1.2886494426253579, | |
| "learning_rate": 7.713035410831086e-06, | |
| "loss": 0.4573, | |
| "mean_token_accuracy": 0.8251194447278977, | |
| "step": 1455 | |
| }, | |
| { | |
| "epoch": 0.6183820415078357, | |
| "grad_norm": 1.1109768793864798, | |
| "learning_rate": 7.64110393959887e-06, | |
| "loss": 0.4279, | |
| "mean_token_accuracy": 0.8380070447921752, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 0.6204997882253283, | |
| "grad_norm": 1.0182035864318235, | |
| "learning_rate": 7.569301482578885e-06, | |
| "loss": 0.4281, | |
| "mean_token_accuracy": 0.8316156834363937, | |
| "step": 1465 | |
| }, | |
| { | |
| "epoch": 0.6226175349428208, | |
| "grad_norm": 1.2074345207100396, | |
| "learning_rate": 7.497631966835828e-06, | |
| "loss": 0.4527, | |
| "mean_token_accuracy": 0.8231601238250732, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 0.6247352816603134, | |
| "grad_norm": 0.991329003303421, | |
| "learning_rate": 7.42609931216348e-06, | |
| "loss": 0.442, | |
| "mean_token_accuracy": 0.8327670186758042, | |
| "step": 1475 | |
| }, | |
| { | |
| "epoch": 0.626853028377806, | |
| "grad_norm": 1.38024365126256, | |
| "learning_rate": 7.354707430870332e-06, | |
| "loss": 0.4335, | |
| "mean_token_accuracy": 0.8324557185173035, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 0.6289707750952986, | |
| "grad_norm": 1.2263457500699402, | |
| "learning_rate": 7.283460227565614e-06, | |
| "loss": 0.4289, | |
| "mean_token_accuracy": 0.8289420217275619, | |
| "step": 1485 | |
| }, | |
| { | |
| "epoch": 0.6310885218127912, | |
| "grad_norm": 1.1601375730316865, | |
| "learning_rate": 7.2123615989457364e-06, | |
| "loss": 0.4465, | |
| "mean_token_accuracy": 0.832300814986229, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 0.6332062685302838, | |
| "grad_norm": 1.3029839142463893, | |
| "learning_rate": 7.141415433581169e-06, | |
| "loss": 0.4167, | |
| "mean_token_accuracy": 0.8393772184848786, | |
| "step": 1495 | |
| }, | |
| { | |
| "epoch": 0.6353240152477764, | |
| "grad_norm": 1.0421344337402514, | |
| "learning_rate": 7.070625611703762e-06, | |
| "loss": 0.4537, | |
| "mean_token_accuracy": 0.8257811456918717, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.6374417619652689, | |
| "grad_norm": 1.1352186472493642, | |
| "learning_rate": 6.9999960049945406e-06, | |
| "loss": 0.4227, | |
| "mean_token_accuracy": 0.8368300348520279, | |
| "step": 1505 | |
| }, | |
| { | |
| "epoch": 0.6395595086827616, | |
| "grad_norm": 0.9884985072070904, | |
| "learning_rate": 6.929530476371935e-06, | |
| "loss": 0.4189, | |
| "mean_token_accuracy": 0.8349219173192978, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 0.6416772554002541, | |
| "grad_norm": 1.7766008455284357, | |
| "learning_rate": 6.859232879780515e-06, | |
| "loss": 0.4288, | |
| "mean_token_accuracy": 0.8374936401844024, | |
| "step": 1515 | |
| }, | |
| { | |
| "epoch": 0.6437950021177468, | |
| "grad_norm": 1.012934970024209, | |
| "learning_rate": 6.7891070599802045e-06, | |
| "loss": 0.4549, | |
| "mean_token_accuracy": 0.8239244252443314, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 0.6459127488352393, | |
| "grad_norm": 0.9859441855867837, | |
| "learning_rate": 6.719156852336015e-06, | |
| "loss": 0.4293, | |
| "mean_token_accuracy": 0.8353272944688797, | |
| "step": 1525 | |
| }, | |
| { | |
| "epoch": 0.6480304955527318, | |
| "grad_norm": 1.261329902420831, | |
| "learning_rate": 6.649386082608256e-06, | |
| "loss": 0.428, | |
| "mean_token_accuracy": 0.8329044044017792, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 0.6501482422702245, | |
| "grad_norm": 1.2457535519058567, | |
| "learning_rate": 6.579798566743314e-06, | |
| "loss": 0.4324, | |
| "mean_token_accuracy": 0.8307075470685958, | |
| "step": 1535 | |
| }, | |
| { | |
| "epoch": 0.652265988987717, | |
| "grad_norm": 1.213114456712863, | |
| "learning_rate": 6.510398110664939e-06, | |
| "loss": 0.4223, | |
| "mean_token_accuracy": 0.8351607590913772, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 0.6543837357052097, | |
| "grad_norm": 1.155264435257233, | |
| "learning_rate": 6.441188510066092e-06, | |
| "loss": 0.4207, | |
| "mean_token_accuracy": 0.8374445289373398, | |
| "step": 1545 | |
| }, | |
| { | |
| "epoch": 0.6565014824227022, | |
| "grad_norm": 1.1756119576548756, | |
| "learning_rate": 6.372173550201346e-06, | |
| "loss": 0.4119, | |
| "mean_token_accuracy": 0.8390755444765091, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.6586192291401949, | |
| "grad_norm": 1.0243897900651528, | |
| "learning_rate": 6.303357005679858e-06, | |
| "loss": 0.4478, | |
| "mean_token_accuracy": 0.8277173846960068, | |
| "step": 1555 | |
| }, | |
| { | |
| "epoch": 0.6607369758576874, | |
| "grad_norm": 1.0868676429874986, | |
| "learning_rate": 6.234742640258938e-06, | |
| "loss": 0.4552, | |
| "mean_token_accuracy": 0.827509269118309, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 0.66285472257518, | |
| "grad_norm": 1.1792649536698685, | |
| "learning_rate": 6.166334206638186e-06, | |
| "loss": 0.4396, | |
| "mean_token_accuracy": 0.8288001954555512, | |
| "step": 1565 | |
| }, | |
| { | |
| "epoch": 0.6649724692926726, | |
| "grad_norm": 1.171894663481444, | |
| "learning_rate": 6.0981354462542456e-06, | |
| "loss": 0.4365, | |
| "mean_token_accuracy": 0.8315492898225785, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 0.6670902160101652, | |
| "grad_norm": 1.1333037764256397, | |
| "learning_rate": 6.030150089076199e-06, | |
| "loss": 0.4319, | |
| "mean_token_accuracy": 0.8316318243741989, | |
| "step": 1575 | |
| }, | |
| { | |
| "epoch": 0.6692079627276578, | |
| "grad_norm": 1.1892286300854609, | |
| "learning_rate": 5.9623818534015275e-06, | |
| "loss": 0.4275, | |
| "mean_token_accuracy": 0.8352140128612519, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 0.6713257094451504, | |
| "grad_norm": 4.250523219515856, | |
| "learning_rate": 5.894834445652777e-06, | |
| "loss": 0.411, | |
| "mean_token_accuracy": 0.8329778879880905, | |
| "step": 1585 | |
| }, | |
| { | |
| "epoch": 0.6734434561626429, | |
| "grad_norm": 1.157008090047474, | |
| "learning_rate": 5.827511560174835e-06, | |
| "loss": 0.4242, | |
| "mean_token_accuracy": 0.832972839474678, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 0.6755612028801355, | |
| "grad_norm": 1.1834078816860993, | |
| "learning_rate": 5.7604168790328774e-06, | |
| "loss": 0.3931, | |
| "mean_token_accuracy": 0.8443128287792205, | |
| "step": 1595 | |
| }, | |
| { | |
| "epoch": 0.6776789495976281, | |
| "grad_norm": 1.0766345733639675, | |
| "learning_rate": 5.693554071810987e-06, | |
| "loss": 0.4478, | |
| "mean_token_accuracy": 0.8282081812620163, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.6797966963151207, | |
| "grad_norm": 1.0314594529031804, | |
| "learning_rate": 5.626926795411447e-06, | |
| "loss": 0.4246, | |
| "mean_token_accuracy": 0.8321157455444336, | |
| "step": 1605 | |
| }, | |
| { | |
| "epoch": 0.6819144430326133, | |
| "grad_norm": 1.055274137880832, | |
| "learning_rate": 5.560538693854751e-06, | |
| "loss": 0.4193, | |
| "mean_token_accuracy": 0.8316533505916596, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 0.6840321897501059, | |
| "grad_norm": 1.1972782090907812, | |
| "learning_rate": 5.494393398080292e-06, | |
| "loss": 0.4313, | |
| "mean_token_accuracy": 0.834712353348732, | |
| "step": 1615 | |
| }, | |
| { | |
| "epoch": 0.6861499364675985, | |
| "grad_norm": 1.0962501568970522, | |
| "learning_rate": 5.428494525747769e-06, | |
| "loss": 0.4597, | |
| "mean_token_accuracy": 0.8248083680868149, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 0.688267683185091, | |
| "grad_norm": 1.0751444988160856, | |
| "learning_rate": 5.362845681039348e-06, | |
| "loss": 0.4321, | |
| "mean_token_accuracy": 0.8374727904796601, | |
| "step": 1625 | |
| }, | |
| { | |
| "epoch": 0.6903854299025837, | |
| "grad_norm": 1.1471090324016462, | |
| "learning_rate": 5.297450454462526e-06, | |
| "loss": 0.4328, | |
| "mean_token_accuracy": 0.8296476870775222, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 0.6925031766200762, | |
| "grad_norm": 0.962534660265453, | |
| "learning_rate": 5.23231242265375e-06, | |
| "loss": 0.4181, | |
| "mean_token_accuracy": 0.83418510556221, | |
| "step": 1635 | |
| }, | |
| { | |
| "epoch": 0.6946209233375689, | |
| "grad_norm": 1.1168651450432128, | |
| "learning_rate": 5.167435148182824e-06, | |
| "loss": 0.4176, | |
| "mean_token_accuracy": 0.8372534781694412, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 0.6967386700550614, | |
| "grad_norm": 1.2186341287706137, | |
| "learning_rate": 5.102822179358037e-06, | |
| "loss": 0.4075, | |
| "mean_token_accuracy": 0.8409687280654907, | |
| "step": 1645 | |
| }, | |
| { | |
| "epoch": 0.6988564167725541, | |
| "grad_norm": 0.9820636174800459, | |
| "learning_rate": 5.0384770500321175e-06, | |
| "loss": 0.4128, | |
| "mean_token_accuracy": 0.8384972155094147, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.7009741634900466, | |
| "grad_norm": 0.943830506781205, | |
| "learning_rate": 4.97440327940895e-06, | |
| "loss": 0.4027, | |
| "mean_token_accuracy": 0.8365049093961716, | |
| "step": 1655 | |
| }, | |
| { | |
| "epoch": 0.7030919102075391, | |
| "grad_norm": 1.0574783345670844, | |
| "learning_rate": 4.910604371851091e-06, | |
| "loss": 0.4308, | |
| "mean_token_accuracy": 0.8333552926778793, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 0.7052096569250318, | |
| "grad_norm": 1.103380699456734, | |
| "learning_rate": 4.847083816688123e-06, | |
| "loss": 0.412, | |
| "mean_token_accuracy": 0.8425119102001191, | |
| "step": 1665 | |
| }, | |
| { | |
| "epoch": 0.7073274036425243, | |
| "grad_norm": 1.117253769501395, | |
| "learning_rate": 4.783845088025807e-06, | |
| "loss": 0.4346, | |
| "mean_token_accuracy": 0.8330845534801483, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 0.709445150360017, | |
| "grad_norm": 1.4108563780024128, | |
| "learning_rate": 4.7208916445560625e-06, | |
| "loss": 0.414, | |
| "mean_token_accuracy": 0.8379091322422028, | |
| "step": 1675 | |
| }, | |
| { | |
| "epoch": 0.7115628970775095, | |
| "grad_norm": 1.031565575748758, | |
| "learning_rate": 4.658226929367826e-06, | |
| "loss": 0.4598, | |
| "mean_token_accuracy": 0.8240681082010269, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 0.7136806437950021, | |
| "grad_norm": 1.2248996065912452, | |
| "learning_rate": 4.595854369758727e-06, | |
| "loss": 0.4299, | |
| "mean_token_accuracy": 0.8363937050104141, | |
| "step": 1685 | |
| }, | |
| { | |
| "epoch": 0.7157983905124947, | |
| "grad_norm": 1.1049025661918381, | |
| "learning_rate": 4.5337773770476245e-06, | |
| "loss": 0.4273, | |
| "mean_token_accuracy": 0.8340339243412018, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 0.7179161372299873, | |
| "grad_norm": 1.1244170950870136, | |
| "learning_rate": 4.4719993463880695e-06, | |
| "loss": 0.4571, | |
| "mean_token_accuracy": 0.8225684702396393, | |
| "step": 1695 | |
| }, | |
| { | |
| "epoch": 0.7200338839474799, | |
| "grad_norm": 1.1969285633316296, | |
| "learning_rate": 4.410523656582576e-06, | |
| "loss": 0.4025, | |
| "mean_token_accuracy": 0.8440569192171097, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.7221516306649725, | |
| "grad_norm": 1.122866308313561, | |
| "learning_rate": 4.349353669897856e-06, | |
| "loss": 0.4208, | |
| "mean_token_accuracy": 0.837623131275177, | |
| "step": 1705 | |
| }, | |
| { | |
| "epoch": 0.7242693773824651, | |
| "grad_norm": 1.0173115464088704, | |
| "learning_rate": 4.288492731880917e-06, | |
| "loss": 0.4148, | |
| "mean_token_accuracy": 0.8388867497444152, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 0.7263871240999576, | |
| "grad_norm": 1.1018457774189827, | |
| "learning_rate": 4.227944171176072e-06, | |
| "loss": 0.4003, | |
| "mean_token_accuracy": 0.8392677456140518, | |
| "step": 1715 | |
| }, | |
| { | |
| "epoch": 0.7285048708174502, | |
| "grad_norm": 1.2471156860459571, | |
| "learning_rate": 4.167711299342909e-06, | |
| "loss": 0.4459, | |
| "mean_token_accuracy": 0.8256678134202957, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 0.7306226175349428, | |
| "grad_norm": 1.1273568017592417, | |
| "learning_rate": 4.107797410675166e-06, | |
| "loss": 0.4068, | |
| "mean_token_accuracy": 0.8386416286230087, | |
| "step": 1725 | |
| }, | |
| { | |
| "epoch": 0.7327403642524354, | |
| "grad_norm": 1.20918067568615, | |
| "learning_rate": 4.048205782020544e-06, | |
| "loss": 0.4539, | |
| "mean_token_accuracy": 0.8220532357692718, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 0.734858110969928, | |
| "grad_norm": 1.1573583276355073, | |
| "learning_rate": 3.988939672601509e-06, | |
| "loss": 0.395, | |
| "mean_token_accuracy": 0.844212406873703, | |
| "step": 1735 | |
| }, | |
| { | |
| "epoch": 0.7369758576874206, | |
| "grad_norm": 1.1516374922245958, | |
| "learning_rate": 3.930002323837026e-06, | |
| "loss": 0.4251, | |
| "mean_token_accuracy": 0.8371291518211365, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 0.7390936044049131, | |
| "grad_norm": 1.274643963255776, | |
| "learning_rate": 3.871396959165267e-06, | |
| "loss": 0.429, | |
| "mean_token_accuracy": 0.8348165363073349, | |
| "step": 1745 | |
| }, | |
| { | |
| "epoch": 0.7412113511224058, | |
| "grad_norm": 1.025583507042276, | |
| "learning_rate": 3.8131267838673336e-06, | |
| "loss": 0.4262, | |
| "mean_token_accuracy": 0.8343986541032791, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.7433290978398983, | |
| "grad_norm": 1.1299748085754966, | |
| "learning_rate": 3.755194984891943e-06, | |
| "loss": 0.4081, | |
| "mean_token_accuracy": 0.8430469453334808, | |
| "step": 1755 | |
| }, | |
| { | |
| "epoch": 0.745446844557391, | |
| "grad_norm": 1.0603027089656643, | |
| "learning_rate": 3.6976047306811115e-06, | |
| "loss": 0.4256, | |
| "mean_token_accuracy": 0.8382641762495041, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 0.7475645912748835, | |
| "grad_norm": 1.1281590494510496, | |
| "learning_rate": 3.6403591709968924e-06, | |
| "loss": 0.4357, | |
| "mean_token_accuracy": 0.8320927768945694, | |
| "step": 1765 | |
| }, | |
| { | |
| "epoch": 0.7496823379923762, | |
| "grad_norm": 1.0367839611389602, | |
| "learning_rate": 3.5834614367490706e-06, | |
| "loss": 0.4221, | |
| "mean_token_accuracy": 0.835366889834404, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 0.7518000847098687, | |
| "grad_norm": 1.0958827736818129, | |
| "learning_rate": 3.526914639823973e-06, | |
| "loss": 0.4381, | |
| "mean_token_accuracy": 0.8301591634750366, | |
| "step": 1775 | |
| }, | |
| { | |
| "epoch": 0.7539178314273612, | |
| "grad_norm": 1.0559223618431266, | |
| "learning_rate": 3.4707218729142224e-06, | |
| "loss": 0.4291, | |
| "mean_token_accuracy": 0.8316712707281113, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 0.7560355781448539, | |
| "grad_norm": 1.0792688197107765, | |
| "learning_rate": 3.414886209349615e-06, | |
| "loss": 0.4269, | |
| "mean_token_accuracy": 0.835688841342926, | |
| "step": 1785 | |
| }, | |
| { | |
| "epoch": 0.7581533248623464, | |
| "grad_norm": 1.1979681287726258, | |
| "learning_rate": 3.3594107029290347e-06, | |
| "loss": 0.4269, | |
| "mean_token_accuracy": 0.8371979027986527, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 0.7602710715798391, | |
| "grad_norm": 1.1468783022113433, | |
| "learning_rate": 3.304298387753426e-06, | |
| "loss": 0.4311, | |
| "mean_token_accuracy": 0.8341523915529251, | |
| "step": 1795 | |
| }, | |
| { | |
| "epoch": 0.7623888182973316, | |
| "grad_norm": 1.142335742385377, | |
| "learning_rate": 3.2495522780598442e-06, | |
| "loss": 0.4174, | |
| "mean_token_accuracy": 0.8298469454050064, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.7645065650148243, | |
| "grad_norm": 1.1968773332651736, | |
| "learning_rate": 3.1951753680566143e-06, | |
| "loss": 0.4383, | |
| "mean_token_accuracy": 0.8313175171613694, | |
| "step": 1805 | |
| }, | |
| { | |
| "epoch": 0.7666243117323168, | |
| "grad_norm": 1.0804618708583653, | |
| "learning_rate": 3.141170631759558e-06, | |
| "loss": 0.4086, | |
| "mean_token_accuracy": 0.8373444229364395, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 0.7687420584498094, | |
| "grad_norm": 1.0872538790077677, | |
| "learning_rate": 3.087541022829347e-06, | |
| "loss": 0.4221, | |
| "mean_token_accuracy": 0.8371105402708053, | |
| "step": 1815 | |
| }, | |
| { | |
| "epoch": 0.770859805167302, | |
| "grad_norm": 0.9905135006363225, | |
| "learning_rate": 3.034289474409943e-06, | |
| "loss": 0.4133, | |
| "mean_token_accuracy": 0.8365035742521286, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 0.7729775518847946, | |
| "grad_norm": 1.0890914888672922, | |
| "learning_rate": 2.981418898968186e-06, | |
| "loss": 0.4189, | |
| "mean_token_accuracy": 0.838862606883049, | |
| "step": 1825 | |
| }, | |
| { | |
| "epoch": 0.7750952986022872, | |
| "grad_norm": 1.1417209565486737, | |
| "learning_rate": 2.9289321881345257e-06, | |
| "loss": 0.4169, | |
| "mean_token_accuracy": 0.833648070693016, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 0.7772130453197797, | |
| "grad_norm": 1.1684616910176908, | |
| "learning_rate": 2.8768322125448265e-06, | |
| "loss": 0.4469, | |
| "mean_token_accuracy": 0.83056038916111, | |
| "step": 1835 | |
| }, | |
| { | |
| "epoch": 0.7793307920372723, | |
| "grad_norm": 1.1845681597767028, | |
| "learning_rate": 2.825121821683391e-06, | |
| "loss": 0.4223, | |
| "mean_token_accuracy": 0.8353413581848145, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 0.7814485387547649, | |
| "grad_norm": 1.1732126933903428, | |
| "learning_rate": 2.7738038437271288e-06, | |
| "loss": 0.4121, | |
| "mean_token_accuracy": 0.842677703499794, | |
| "step": 1845 | |
| }, | |
| { | |
| "epoch": 0.7835662854722575, | |
| "grad_norm": 1.0292583187860371, | |
| "learning_rate": 2.7228810853908406e-06, | |
| "loss": 0.3921, | |
| "mean_token_accuracy": 0.8447476714849472, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 0.7856840321897501, | |
| "grad_norm": 0.9892030702997285, | |
| "learning_rate": 2.67235633177373e-06, | |
| "loss": 0.4387, | |
| "mean_token_accuracy": 0.8288900941610337, | |
| "step": 1855 | |
| }, | |
| { | |
| "epoch": 0.7878017789072427, | |
| "grad_norm": 1.0050687986582967, | |
| "learning_rate": 2.6222323462070897e-06, | |
| "loss": 0.4356, | |
| "mean_token_accuracy": 0.828187745809555, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 0.7899195256247353, | |
| "grad_norm": 1.1304197153376732, | |
| "learning_rate": 2.572511870103149e-06, | |
| "loss": 0.4125, | |
| "mean_token_accuracy": 0.8425087302923202, | |
| "step": 1865 | |
| }, | |
| { | |
| "epoch": 0.7920372723422279, | |
| "grad_norm": 1.0444576639344187, | |
| "learning_rate": 2.5231976228051526e-06, | |
| "loss": 0.4318, | |
| "mean_token_accuracy": 0.8337043792009353, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 0.7941550190597204, | |
| "grad_norm": 1.0875080317220023, | |
| "learning_rate": 2.4742923014386154e-06, | |
| "loss": 0.4287, | |
| "mean_token_accuracy": 0.8368022799491882, | |
| "step": 1875 | |
| }, | |
| { | |
| "epoch": 0.7962727657772131, | |
| "grad_norm": 1.1517129093084153, | |
| "learning_rate": 2.4257985807638294e-06, | |
| "loss": 0.4284, | |
| "mean_token_accuracy": 0.8356128752231597, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 0.7983905124947056, | |
| "grad_norm": 1.2213468844119533, | |
| "learning_rate": 2.3777191130295673e-06, | |
| "loss": 0.411, | |
| "mean_token_accuracy": 0.8373890697956086, | |
| "step": 1885 | |
| }, | |
| { | |
| "epoch": 0.8005082592121983, | |
| "grad_norm": 1.1105462272187794, | |
| "learning_rate": 2.330056527828013e-06, | |
| "loss": 0.4549, | |
| "mean_token_accuracy": 0.8282926619052887, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 0.8026260059296908, | |
| "grad_norm": 1.1626653178571262, | |
| "learning_rate": 2.282813431950952e-06, | |
| "loss": 0.4295, | |
| "mean_token_accuracy": 0.8333282887935638, | |
| "step": 1895 | |
| }, | |
| { | |
| "epoch": 0.8047437526471835, | |
| "grad_norm": 1.1195581942328177, | |
| "learning_rate": 2.235992409247214e-06, | |
| "loss": 0.4338, | |
| "mean_token_accuracy": 0.8319763302803039, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.806861499364676, | |
| "grad_norm": 1.026868168904022, | |
| "learning_rate": 2.1895960204813194e-06, | |
| "loss": 0.4118, | |
| "mean_token_accuracy": 0.8370046824216842, | |
| "step": 1905 | |
| }, | |
| { | |
| "epoch": 0.8089792460821685, | |
| "grad_norm": 1.0639569641896143, | |
| "learning_rate": 2.1436268031934602e-06, | |
| "loss": 0.4411, | |
| "mean_token_accuracy": 0.8297486454248428, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 0.8110969927996612, | |
| "grad_norm": 1.0385740186847223, | |
| "learning_rate": 2.098087271560687e-06, | |
| "loss": 0.4152, | |
| "mean_token_accuracy": 0.8370089381933212, | |
| "step": 1915 | |
| }, | |
| { | |
| "epoch": 0.8132147395171537, | |
| "grad_norm": 1.1169845772777505, | |
| "learning_rate": 2.0529799162594242e-06, | |
| "loss": 0.4094, | |
| "mean_token_accuracy": 0.839673039317131, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 0.8153324862346464, | |
| "grad_norm": 1.0745546751170598, | |
| "learning_rate": 2.0083072043292406e-06, | |
| "loss": 0.417, | |
| "mean_token_accuracy": 0.8379459470510483, | |
| "step": 1925 | |
| }, | |
| { | |
| "epoch": 0.8174502329521389, | |
| "grad_norm": 1.206429363415916, | |
| "learning_rate": 1.9640715790379084e-06, | |
| "loss": 0.4133, | |
| "mean_token_accuracy": 0.8345289677381516, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 0.8195679796696315, | |
| "grad_norm": 1.0452292636568519, | |
| "learning_rate": 1.920275459747796e-06, | |
| "loss": 0.4123, | |
| "mean_token_accuracy": 0.8368586808443069, | |
| "step": 1935 | |
| }, | |
| { | |
| "epoch": 0.8216857263871241, | |
| "grad_norm": 1.0706189800647066, | |
| "learning_rate": 1.8769212417835314e-06, | |
| "loss": 0.3773, | |
| "mean_token_accuracy": 0.8513321369886399, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 0.8238034731046167, | |
| "grad_norm": 1.0974535637452612, | |
| "learning_rate": 1.8340112963009993e-06, | |
| "loss": 0.4353, | |
| "mean_token_accuracy": 0.8337271898984909, | |
| "step": 1945 | |
| }, | |
| { | |
| "epoch": 0.8259212198221093, | |
| "grad_norm": 1.0867209847341632, | |
| "learning_rate": 1.7915479701576577e-06, | |
| "loss": 0.4489, | |
| "mean_token_accuracy": 0.8291646331548691, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 0.8280389665396019, | |
| "grad_norm": 1.1993569416921062, | |
| "learning_rate": 1.7495335857841855e-06, | |
| "loss": 0.4138, | |
| "mean_token_accuracy": 0.8385995358228684, | |
| "step": 1955 | |
| }, | |
| { | |
| "epoch": 0.8301567132570945, | |
| "grad_norm": 1.1414883228473476, | |
| "learning_rate": 1.7079704410574505e-06, | |
| "loss": 0.3859, | |
| "mean_token_accuracy": 0.8459228605031968, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 0.832274459974587, | |
| "grad_norm": 1.048311577922366, | |
| "learning_rate": 1.6668608091748495e-06, | |
| "loss": 0.426, | |
| "mean_token_accuracy": 0.8357879251241684, | |
| "step": 1965 | |
| }, | |
| { | |
| "epoch": 0.8343922066920796, | |
| "grad_norm": 1.0617438922962255, | |
| "learning_rate": 1.6262069385299694e-06, | |
| "loss": 0.4334, | |
| "mean_token_accuracy": 0.8343731433153152, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 0.8365099534095722, | |
| "grad_norm": 1.1279209328755353, | |
| "learning_rate": 1.5860110525896143e-06, | |
| "loss": 0.4197, | |
| "mean_token_accuracy": 0.835442116856575, | |
| "step": 1975 | |
| }, | |
| { | |
| "epoch": 0.8386277001270648, | |
| "grad_norm": 0.9640338154076892, | |
| "learning_rate": 1.5462753497722139e-06, | |
| "loss": 0.4228, | |
| "mean_token_accuracy": 0.8363285154104233, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 0.8407454468445574, | |
| "grad_norm": 1.065476222817932, | |
| "learning_rate": 1.5070020033275655e-06, | |
| "loss": 0.3954, | |
| "mean_token_accuracy": 0.8427035689353943, | |
| "step": 1985 | |
| }, | |
| { | |
| "epoch": 0.84286319356205, | |
| "grad_norm": 1.055480105683973, | |
| "learning_rate": 1.4681931612179901e-06, | |
| "loss": 0.4289, | |
| "mean_token_accuracy": 0.8340502351522445, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 0.8449809402795425, | |
| "grad_norm": 1.0690985831761302, | |
| "learning_rate": 1.4298509460008491e-06, | |
| "loss": 0.4072, | |
| "mean_token_accuracy": 0.8402904689311981, | |
| "step": 1995 | |
| }, | |
| { | |
| "epoch": 0.8470986869970352, | |
| "grad_norm": 1.0063164183000968, | |
| "learning_rate": 1.39197745471245e-06, | |
| "loss": 0.4231, | |
| "mean_token_accuracy": 0.8361636906862259, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.8492164337145277, | |
| "grad_norm": 1.0247616494577987, | |
| "learning_rate": 1.354574758753363e-06, | |
| "loss": 0.4189, | |
| "mean_token_accuracy": 0.8310322672128677, | |
| "step": 2005 | |
| }, | |
| { | |
| "epoch": 0.8513341804320204, | |
| "grad_norm": 1.044860588344852, | |
| "learning_rate": 1.3176449037751294e-06, | |
| "loss": 0.4404, | |
| "mean_token_accuracy": 0.8303707420825959, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 0.8534519271495129, | |
| "grad_norm": 2.4537559889629694, | |
| "learning_rate": 1.28118990956837e-06, | |
| "loss": 0.4104, | |
| "mean_token_accuracy": 0.835821408033371, | |
| "step": 2015 | |
| }, | |
| { | |
| "epoch": 0.8555696738670056, | |
| "grad_norm": 1.0972489520800874, | |
| "learning_rate": 1.2452117699523303e-06, | |
| "loss": 0.4027, | |
| "mean_token_accuracy": 0.8460766285657882, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 0.8576874205844981, | |
| "grad_norm": 1.2309045137234433, | |
| "learning_rate": 1.2097124526658277e-06, | |
| "loss": 0.419, | |
| "mean_token_accuracy": 0.8366678208112717, | |
| "step": 2025 | |
| }, | |
| { | |
| "epoch": 0.8598051673019906, | |
| "grad_norm": 1.0849048269411365, | |
| "learning_rate": 1.1746938992596257e-06, | |
| "loss": 0.4174, | |
| "mean_token_accuracy": 0.8296289384365082, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 0.8619229140194833, | |
| "grad_norm": 0.989974221522167, | |
| "learning_rate": 1.1401580249902566e-06, | |
| "loss": 0.4153, | |
| "mean_token_accuracy": 0.8379861056804657, | |
| "step": 2035 | |
| }, | |
| { | |
| "epoch": 0.8640406607369758, | |
| "grad_norm": 1.0066596115748891, | |
| "learning_rate": 1.1061067187152584e-06, | |
| "loss": 0.4041, | |
| "mean_token_accuracy": 0.8417060792446136, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 0.8661584074544685, | |
| "grad_norm": 1.0526259070425423, | |
| "learning_rate": 1.0725418427898792e-06, | |
| "loss": 0.4099, | |
| "mean_token_accuracy": 0.8398545056581497, | |
| "step": 2045 | |
| }, | |
| { | |
| "epoch": 0.868276154171961, | |
| "grad_norm": 1.134470581551777, | |
| "learning_rate": 1.0394652329652165e-06, | |
| "loss": 0.4146, | |
| "mean_token_accuracy": 0.8354752600193024, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 0.8703939008894537, | |
| "grad_norm": 1.130864865166622, | |
| "learning_rate": 1.0068786982878087e-06, | |
| "loss": 0.418, | |
| "mean_token_accuracy": 0.8398678600788116, | |
| "step": 2055 | |
| }, | |
| { | |
| "epoch": 0.8725116476069462, | |
| "grad_norm": 1.1500087879964977, | |
| "learning_rate": 9.747840210007021e-07, | |
| "loss": 0.4157, | |
| "mean_token_accuracy": 0.8322781622409821, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 0.8746293943244388, | |
| "grad_norm": 0.9770307768209092, | |
| "learning_rate": 9.43182956445976e-07, | |
| "loss": 0.3977, | |
| "mean_token_accuracy": 0.8416966944932938, | |
| "step": 2065 | |
| }, | |
| { | |
| "epoch": 0.8767471410419314, | |
| "grad_norm": 1.2583818143393242, | |
| "learning_rate": 9.120772329687278e-07, | |
| "loss": 0.4251, | |
| "mean_token_accuracy": 0.8354076951742172, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 0.878864887759424, | |
| "grad_norm": 1.0618576291439479, | |
| "learning_rate": 8.814685518225552e-07, | |
| "loss": 0.4291, | |
| "mean_token_accuracy": 0.8308704495429993, | |
| "step": 2075 | |
| }, | |
| { | |
| "epoch": 0.8809826344769166, | |
| "grad_norm": 1.1180367611245425, | |
| "learning_rate": 8.513585870765118e-07, | |
| "loss": 0.3907, | |
| "mean_token_accuracy": 0.8452890306711197, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 0.8831003811944091, | |
| "grad_norm": 1.230123212504081, | |
| "learning_rate": 8.217489855235338e-07, | |
| "loss": 0.4144, | |
| "mean_token_accuracy": 0.8392110764980316, | |
| "step": 2085 | |
| }, | |
| { | |
| "epoch": 0.8852181279119017, | |
| "grad_norm": 1.1108948475484288, | |
| "learning_rate": 7.926413665903931e-07, | |
| "loss": 0.4151, | |
| "mean_token_accuracy": 0.8380868971347809, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 0.8873358746293943, | |
| "grad_norm": 1.098761542271965, | |
| "learning_rate": 7.640373222491038e-07, | |
| "loss": 0.4196, | |
| "mean_token_accuracy": 0.8407029449939728, | |
| "step": 2095 | |
| }, | |
| { | |
| "epoch": 0.8894536213468869, | |
| "grad_norm": 1.0940803341605705, | |
| "learning_rate": 7.359384169298744e-07, | |
| "loss": 0.4097, | |
| "mean_token_accuracy": 0.8401619613170623, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.8915713680643795, | |
| "grad_norm": 0.9066347453646844, | |
| "learning_rate": 7.083461874355335e-07, | |
| "loss": 0.4257, | |
| "mean_token_accuracy": 0.8362819194793701, | |
| "step": 2105 | |
| }, | |
| { | |
| "epoch": 0.8936891147818721, | |
| "grad_norm": 1.0448023766882066, | |
| "learning_rate": 6.81262142857475e-07, | |
| "loss": 0.3898, | |
| "mean_token_accuracy": 0.8459620922803879, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 0.8958068614993647, | |
| "grad_norm": 1.0611643496346475, | |
| "learning_rate": 6.546877644931315e-07, | |
| "loss": 0.4208, | |
| "mean_token_accuracy": 0.8312031596899032, | |
| "step": 2115 | |
| }, | |
| { | |
| "epoch": 0.8979246082168573, | |
| "grad_norm": 1.1224663985096108, | |
| "learning_rate": 6.286245057649542e-07, | |
| "loss": 0.3994, | |
| "mean_token_accuracy": 0.8465497404336929, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 0.9000423549343498, | |
| "grad_norm": 1.0832056476567533, | |
| "learning_rate": 6.030737921409169e-07, | |
| "loss": 0.3867, | |
| "mean_token_accuracy": 0.8440623044967651, | |
| "step": 2125 | |
| }, | |
| { | |
| "epoch": 0.9021601016518425, | |
| "grad_norm": 1.0523110523954844, | |
| "learning_rate": 5.7803702105656e-07, | |
| "loss": 0.4127, | |
| "mean_token_accuracy": 0.8366563141345977, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 0.904277848369335, | |
| "grad_norm": 1.0105232913792406, | |
| "learning_rate": 5.535155618385612e-07, | |
| "loss": 0.4195, | |
| "mean_token_accuracy": 0.8335390537977219, | |
| "step": 2135 | |
| }, | |
| { | |
| "epoch": 0.9063955950868277, | |
| "grad_norm": 1.1129917485868344, | |
| "learning_rate": 5.295107556298329e-07, | |
| "loss": 0.3928, | |
| "mean_token_accuracy": 0.8431670844554902, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 0.9085133418043202, | |
| "grad_norm": 1.145719574659648, | |
| "learning_rate": 5.060239153161872e-07, | |
| "loss": 0.4019, | |
| "mean_token_accuracy": 0.8419764310121536, | |
| "step": 2145 | |
| }, | |
| { | |
| "epoch": 0.9106310885218127, | |
| "grad_norm": 1.443628282269306, | |
| "learning_rate": 4.830563254545207e-07, | |
| "loss": 0.4233, | |
| "mean_token_accuracy": 0.8361739784479141, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 0.9127488352393054, | |
| "grad_norm": 1.1691030241329559, | |
| "learning_rate": 4.6060924220255654e-07, | |
| "loss": 0.4257, | |
| "mean_token_accuracy": 0.8305665761232376, | |
| "step": 2155 | |
| }, | |
| { | |
| "epoch": 0.9148665819567979, | |
| "grad_norm": 1.2424085660240223, | |
| "learning_rate": 4.386838932501547e-07, | |
| "loss": 0.4303, | |
| "mean_token_accuracy": 0.8358988225460052, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 0.9169843286742906, | |
| "grad_norm": 1.0258262640063769, | |
| "learning_rate": 4.172814777521483e-07, | |
| "loss": 0.4298, | |
| "mean_token_accuracy": 0.8366893321275711, | |
| "step": 2165 | |
| }, | |
| { | |
| "epoch": 0.9191020753917831, | |
| "grad_norm": 1.0932401792673323, | |
| "learning_rate": 3.9640316626277654e-07, | |
| "loss": 0.4172, | |
| "mean_token_accuracy": 0.836585283279419, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 0.9212198221092758, | |
| "grad_norm": 1.0881178279493329, | |
| "learning_rate": 3.7605010067165216e-07, | |
| "loss": 0.42, | |
| "mean_token_accuracy": 0.8352493315935134, | |
| "step": 2175 | |
| }, | |
| { | |
| "epoch": 0.9233375688267683, | |
| "grad_norm": 1.057750886441079, | |
| "learning_rate": 3.562233941413096e-07, | |
| "loss": 0.3975, | |
| "mean_token_accuracy": 0.8412194460630417, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 0.9254553155442609, | |
| "grad_norm": 1.1056774030421723, | |
| "learning_rate": 3.3692413104633226e-07, | |
| "loss": 0.3976, | |
| "mean_token_accuracy": 0.840697067975998, | |
| "step": 2185 | |
| }, | |
| { | |
| "epoch": 0.9275730622617535, | |
| "grad_norm": 1.163101779598673, | |
| "learning_rate": 3.1815336691403464e-07, | |
| "loss": 0.3751, | |
| "mean_token_accuracy": 0.8496327966451644, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 0.929690808979246, | |
| "grad_norm": 0.9755793569303719, | |
| "learning_rate": 2.999121283667339e-07, | |
| "loss": 0.4079, | |
| "mean_token_accuracy": 0.8418219208717346, | |
| "step": 2195 | |
| }, | |
| { | |
| "epoch": 0.9318085556967387, | |
| "grad_norm": 1.021358583461123, | |
| "learning_rate": 2.8220141306561034e-07, | |
| "loss": 0.4186, | |
| "mean_token_accuracy": 0.8352805793285369, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.9339263024142312, | |
| "grad_norm": 1.0396837778560488, | |
| "learning_rate": 2.6502218965613335e-07, | |
| "loss": 0.4225, | |
| "mean_token_accuracy": 0.8338442891836166, | |
| "step": 2205 | |
| }, | |
| { | |
| "epoch": 0.9360440491317239, | |
| "grad_norm": 1.1742052357618658, | |
| "learning_rate": 2.483753977150882e-07, | |
| "loss": 0.4067, | |
| "mean_token_accuracy": 0.8387827515602112, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 0.9381617958492164, | |
| "grad_norm": 1.0739901995137444, | |
| "learning_rate": 2.3226194769918497e-07, | |
| "loss": 0.4041, | |
| "mean_token_accuracy": 0.837730023264885, | |
| "step": 2215 | |
| }, | |
| { | |
| "epoch": 0.940279542566709, | |
| "grad_norm": 1.0246012489566791, | |
| "learning_rate": 2.1668272089526377e-07, | |
| "loss": 0.4161, | |
| "mean_token_accuracy": 0.8399739652872086, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 0.9423972892842016, | |
| "grad_norm": 1.0463273467785923, | |
| "learning_rate": 2.0163856937210236e-07, | |
| "loss": 0.4245, | |
| "mean_token_accuracy": 0.8379955619573594, | |
| "step": 2225 | |
| }, | |
| { | |
| "epoch": 0.9445150360016942, | |
| "grad_norm": 1.13493837929642, | |
| "learning_rate": 1.8713031593380116e-07, | |
| "loss": 0.405, | |
| "mean_token_accuracy": 0.8368137925863266, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 0.9466327827191868, | |
| "grad_norm": 1.1326422720007092, | |
| "learning_rate": 1.731587540747903e-07, | |
| "loss": 0.4164, | |
| "mean_token_accuracy": 0.839913833141327, | |
| "step": 2235 | |
| }, | |
| { | |
| "epoch": 0.9487505294366794, | |
| "grad_norm": 1.1288581153860058, | |
| "learning_rate": 1.597246479364345e-07, | |
| "loss": 0.4345, | |
| "mean_token_accuracy": 0.8263521671295166, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 0.9508682761541719, | |
| "grad_norm": 1.0618048867408285, | |
| "learning_rate": 1.4682873226523064e-07, | |
| "loss": 0.4116, | |
| "mean_token_accuracy": 0.8380947977304458, | |
| "step": 2245 | |
| }, | |
| { | |
| "epoch": 0.9529860228716646, | |
| "grad_norm": 1.0089748524009554, | |
| "learning_rate": 1.3447171237262912e-07, | |
| "loss": 0.4281, | |
| "mean_token_accuracy": 0.8311914891004563, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 0.9551037695891571, | |
| "grad_norm": 1.1718653607363838, | |
| "learning_rate": 1.2265426409645676e-07, | |
| "loss": 0.4205, | |
| "mean_token_accuracy": 0.8367854833602906, | |
| "step": 2255 | |
| }, | |
| { | |
| "epoch": 0.9572215163066498, | |
| "grad_norm": 1.009709808393184, | |
| "learning_rate": 1.1137703376395304e-07, | |
| "loss": 0.4307, | |
| "mean_token_accuracy": 0.8332184463739395, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 0.9593392630241423, | |
| "grad_norm": 1.0456672123180084, | |
| "learning_rate": 1.0064063815642178e-07, | |
| "loss": 0.4143, | |
| "mean_token_accuracy": 0.8407183200120926, | |
| "step": 2265 | |
| }, | |
| { | |
| "epoch": 0.961457009741635, | |
| "grad_norm": 1.4564232381895734, | |
| "learning_rate": 9.044566447549697e-08, | |
| "loss": 0.3935, | |
| "mean_token_accuracy": 0.843877837061882, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 0.9635747564591275, | |
| "grad_norm": 1.006395133879737, | |
| "learning_rate": 8.079267031102844e-08, | |
| "loss": 0.4379, | |
| "mean_token_accuracy": 0.8322035163640976, | |
| "step": 2275 | |
| }, | |
| { | |
| "epoch": 0.96569250317662, | |
| "grad_norm": 1.0451381392295622, | |
| "learning_rate": 7.16821836105841e-08, | |
| "loss": 0.3998, | |
| "mean_token_accuracy": 0.8473025262355804, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 0.9678102498941127, | |
| "grad_norm": 1.0472971428422386, | |
| "learning_rate": 6.311470265057518e-08, | |
| "loss": 0.423, | |
| "mean_token_accuracy": 0.8354467749595642, | |
| "step": 2285 | |
| }, | |
| { | |
| "epoch": 0.9699279966116052, | |
| "grad_norm": 1.1605199240395647, | |
| "learning_rate": 5.5090696009004744e-08, | |
| "loss": 0.4257, | |
| "mean_token_accuracy": 0.8360013753175736, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 0.9720457433290979, | |
| "grad_norm": 0.9898182837486158, | |
| "learning_rate": 4.761060253984151e-08, | |
| "loss": 0.4204, | |
| "mean_token_accuracy": 0.8367842882871628, | |
| "step": 2295 | |
| }, | |
| { | |
| "epoch": 0.9741634900465904, | |
| "grad_norm": 1.088987157568079, | |
| "learning_rate": 4.067483134901573e-08, | |
| "loss": 0.4134, | |
| "mean_token_accuracy": 0.83856400847435, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.976281236764083, | |
| "grad_norm": 1.0295706774122013, | |
| "learning_rate": 3.4283761772042623e-08, | |
| "loss": 0.4224, | |
| "mean_token_accuracy": 0.8354990780353546, | |
| "step": 2305 | |
| }, | |
| { | |
| "epoch": 0.9783989834815756, | |
| "grad_norm": 1.0694735478921555, | |
| "learning_rate": 2.84377433532812e-08, | |
| "loss": 0.4305, | |
| "mean_token_accuracy": 0.8316824287176132, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 0.9805167301990682, | |
| "grad_norm": 1.0827744380795652, | |
| "learning_rate": 2.3137095826809564e-08, | |
| "loss": 0.402, | |
| "mean_token_accuracy": 0.8404913783073426, | |
| "step": 2315 | |
| }, | |
| { | |
| "epoch": 0.9826344769165608, | |
| "grad_norm": 1.0960538876783272, | |
| "learning_rate": 1.8382109098944444e-08, | |
| "loss": 0.4352, | |
| "mean_token_accuracy": 0.8338410943746567, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 0.9847522236340533, | |
| "grad_norm": 1.1206569874331853, | |
| "learning_rate": 1.4173043232380557e-08, | |
| "loss": 0.4076, | |
| "mean_token_accuracy": 0.8435803085565567, | |
| "step": 2325 | |
| }, | |
| { | |
| "epoch": 0.986869970351546, | |
| "grad_norm": 1.0708342349134583, | |
| "learning_rate": 1.0510128431968635e-08, | |
| "loss": 0.4041, | |
| "mean_token_accuracy": 0.8435177773237228, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 0.9889877170690385, | |
| "grad_norm": 1.0195754299190762, | |
| "learning_rate": 7.3935650321255156e-09, | |
| "loss": 0.4017, | |
| "mean_token_accuracy": 0.8434190511703491, | |
| "step": 2335 | |
| }, | |
| { | |
| "epoch": 0.9911054637865311, | |
| "grad_norm": 1.043562362927536, | |
| "learning_rate": 4.823523485879556e-09, | |
| "loss": 0.4441, | |
| "mean_token_accuracy": 0.8331767469644547, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 0.9932232105040237, | |
| "grad_norm": 0.9692528305370003, | |
| "learning_rate": 2.800144355540324e-09, | |
| "loss": 0.4112, | |
| "mean_token_accuracy": 0.836205193400383, | |
| "step": 2345 | |
| }, | |
| { | |
| "epoch": 0.9953409572215163, | |
| "grad_norm": 0.9767634882260735, | |
| "learning_rate": 1.32353830502141e-09, | |
| "loss": 0.4233, | |
| "mean_token_accuracy": 0.8327444672584534, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 0.9974587039390089, | |
| "grad_norm": 1.1074445733229596, | |
| "learning_rate": 3.9378609377971335e-10, | |
| "loss": 0.3959, | |
| "mean_token_accuracy": 0.8446923106908798, | |
| "step": 2355 | |
| }, | |
| { | |
| "epoch": 0.9995764506565015, | |
| "grad_norm": 1.0245959330198788, | |
| "learning_rate": 1.0938572402308111e-11, | |
| "loss": 0.4106, | |
| "mean_token_accuracy": 0.8339618355035782, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "mean_token_accuracy": 0.890313521027565, | |
| "step": 2361, | |
| "total_flos": 451385831948288.0, | |
| "train_loss": 0.48239256052181206, | |
| "train_runtime": 37146.7848, | |
| "train_samples_per_second": 1.017, | |
| "train_steps_per_second": 0.064 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 2361, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": false, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 451385831948288.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |