| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.9941672067401166, | |
| "eval_steps": 50, | |
| "global_step": 1155, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.012961762799740765, | |
| "grad_norm": 17.21252896134672, | |
| "learning_rate": 5e-07, | |
| "loss": 1.6823, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02592352559948153, | |
| "grad_norm": 12.008964700255303, | |
| "learning_rate": 1e-06, | |
| "loss": 1.566, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03888528839922229, | |
| "grad_norm": 7.9698215919555055, | |
| "learning_rate": 9.99952949745378e-07, | |
| "loss": 1.2721, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.05184705119896306, | |
| "grad_norm": 4.447326184155441, | |
| "learning_rate": 9.998118078364185e-07, | |
| "loss": 1.1461, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06480881399870382, | |
| "grad_norm": 3.9602084655818675, | |
| "learning_rate": 9.995766008361718e-07, | |
| "loss": 1.0509, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.07777057679844458, | |
| "grad_norm": 3.524237361034851, | |
| "learning_rate": 9.992473730108354e-07, | |
| "loss": 0.9982, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.09073233959818536, | |
| "grad_norm": 3.633387524272681, | |
| "learning_rate": 9.98824186321421e-07, | |
| "loss": 0.9804, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.10369410239792612, | |
| "grad_norm": 3.4822921075242577, | |
| "learning_rate": 9.98307120412095e-07, | |
| "loss": 0.954, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.11665586519766688, | |
| "grad_norm": 3.519195574393169, | |
| "learning_rate": 9.976962725951878e-07, | |
| "loss": 0.928, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.12961762799740764, | |
| "grad_norm": 3.3308237206179423, | |
| "learning_rate": 9.969917578328807e-07, | |
| "loss": 0.9184, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.12961762799740764, | |
| "eval_loss": 0.92087721824646, | |
| "eval_runtime": 190.61, | |
| "eval_samples_per_second": 57.547, | |
| "eval_steps_per_second": 0.902, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1425793907971484, | |
| "grad_norm": 3.343853179925445, | |
| "learning_rate": 9.961937087155695e-07, | |
| "loss": 0.9194, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.15554115359688916, | |
| "grad_norm": 3.368850277351612, | |
| "learning_rate": 9.953022754369114e-07, | |
| "loss": 0.8832, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.16850291639662995, | |
| "grad_norm": 3.3163787130271003, | |
| "learning_rate": 9.943176257655565e-07, | |
| "loss": 0.8923, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.18146467919637072, | |
| "grad_norm": 3.242609823802845, | |
| "learning_rate": 9.932399450135765e-07, | |
| "loss": 0.8883, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.19442644199611148, | |
| "grad_norm": 3.402686266652709, | |
| "learning_rate": 9.920694360015862e-07, | |
| "loss": 0.8639, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.20738820479585224, | |
| "grad_norm": 3.404608035399376, | |
| "learning_rate": 9.908063190205739e-07, | |
| "loss": 0.8732, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.220349967595593, | |
| "grad_norm": 3.3975642435264732, | |
| "learning_rate": 9.894508317904417e-07, | |
| "loss": 0.8883, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.23331173039533376, | |
| "grad_norm": 3.558535819762842, | |
| "learning_rate": 9.88003229415267e-07, | |
| "loss": 0.8671, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.24627349319507452, | |
| "grad_norm": 3.6228022238357815, | |
| "learning_rate": 9.864637843352913e-07, | |
| "loss": 0.8771, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.2592352559948153, | |
| "grad_norm": 3.6210872209063174, | |
| "learning_rate": 9.848327862756466e-07, | |
| "loss": 0.8611, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.2592352559948153, | |
| "eval_loss": 0.8652921915054321, | |
| "eval_runtime": 190.2747, | |
| "eval_samples_per_second": 57.648, | |
| "eval_steps_per_second": 0.904, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.27219701879455604, | |
| "grad_norm": 3.312411561694666, | |
| "learning_rate": 9.831105421918285e-07, | |
| "loss": 0.8547, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.2851587815942968, | |
| "grad_norm": 3.4066727133401598, | |
| "learning_rate": 9.81297376211928e-07, | |
| "loss": 0.8369, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.29812054439403757, | |
| "grad_norm": 3.2867314575644575, | |
| "learning_rate": 9.79393629575629e-07, | |
| "loss": 0.8403, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.31108230719377833, | |
| "grad_norm": 3.599628911972995, | |
| "learning_rate": 9.773996605699875e-07, | |
| "loss": 0.8437, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.32404406999351915, | |
| "grad_norm": 3.3280113051932183, | |
| "learning_rate": 9.753158444620013e-07, | |
| "loss": 0.8295, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.3370058327932599, | |
| "grad_norm": 3.3041114591018035, | |
| "learning_rate": 9.73142573427984e-07, | |
| "loss": 0.8416, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.34996759559300067, | |
| "grad_norm": 3.1677202986884647, | |
| "learning_rate": 9.708802564797578e-07, | |
| "loss": 0.8372, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.36292935839274143, | |
| "grad_norm": 3.4261833858436126, | |
| "learning_rate": 9.685293193876765e-07, | |
| "loss": 0.8407, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.3758911211924822, | |
| "grad_norm": 3.2025888685071995, | |
| "learning_rate": 9.660902046004953e-07, | |
| "loss": 0.8218, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.38885288399222295, | |
| "grad_norm": 3.3672158659218945, | |
| "learning_rate": 9.635633711621011e-07, | |
| "loss": 0.8257, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.38885288399222295, | |
| "eval_loss": 0.8396357893943787, | |
| "eval_runtime": 190.236, | |
| "eval_samples_per_second": 57.66, | |
| "eval_steps_per_second": 0.904, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.4018146467919637, | |
| "grad_norm": 3.5382812532295653, | |
| "learning_rate": 9.609492946251208e-07, | |
| "loss": 0.8335, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.4147764095917045, | |
| "grad_norm": 3.2987076575989396, | |
| "learning_rate": 9.58248466961421e-07, | |
| "loss": 0.8274, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.42773817239144524, | |
| "grad_norm": 3.209384087480358, | |
| "learning_rate": 9.554613964695188e-07, | |
| "loss": 0.8419, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.440699935191186, | |
| "grad_norm": 3.2525057388499867, | |
| "learning_rate": 9.525886076789193e-07, | |
| "loss": 0.8264, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.45366169799092676, | |
| "grad_norm": 3.2659862173369225, | |
| "learning_rate": 9.496306412513988e-07, | |
| "loss": 0.813, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.4666234607906675, | |
| "grad_norm": 3.617112426560761, | |
| "learning_rate": 9.465880538792517e-07, | |
| "loss": 0.8209, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.4795852235904083, | |
| "grad_norm": 3.8241965496757055, | |
| "learning_rate": 9.434614181805202e-07, | |
| "loss": 0.8246, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.49254698639014904, | |
| "grad_norm": 3.389966079797953, | |
| "learning_rate": 9.402513225912271e-07, | |
| "loss": 0.8236, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.5055087491898899, | |
| "grad_norm": 3.31422039420999, | |
| "learning_rate": 9.36958371254632e-07, | |
| "loss": 0.8158, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.5184705119896306, | |
| "grad_norm": 3.365373850064581, | |
| "learning_rate": 9.335831839075302e-07, | |
| "loss": 0.8308, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.5184705119896306, | |
| "eval_loss": 0.8231202960014343, | |
| "eval_runtime": 190.2867, | |
| "eval_samples_per_second": 57.645, | |
| "eval_steps_per_second": 0.904, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.5314322747893714, | |
| "grad_norm": 3.441006121650103, | |
| "learning_rate": 9.301263957636179e-07, | |
| "loss": 0.8191, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.5443940375891121, | |
| "grad_norm": 3.428707563220311, | |
| "learning_rate": 9.265886573939446e-07, | |
| "loss": 0.8191, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.5573558003888529, | |
| "grad_norm": 3.5640266455568166, | |
| "learning_rate": 9.229706346044747e-07, | |
| "loss": 0.8255, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.5703175631885936, | |
| "grad_norm": 3.551803069534866, | |
| "learning_rate": 9.192730083107818e-07, | |
| "loss": 0.8164, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.5832793259883344, | |
| "grad_norm": 3.414031666969802, | |
| "learning_rate": 9.154964744099005e-07, | |
| "loss": 0.7939, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.5962410887880751, | |
| "grad_norm": 3.442613850161029, | |
| "learning_rate": 9.116417436493573e-07, | |
| "loss": 0.8034, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.609202851587816, | |
| "grad_norm": 3.462275139287757, | |
| "learning_rate": 9.077095414934075e-07, | |
| "loss": 0.8063, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.6221646143875567, | |
| "grad_norm": 3.447345184549608, | |
| "learning_rate": 9.037006079865015e-07, | |
| "loss": 0.8233, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.6351263771872975, | |
| "grad_norm": 3.5938927981457933, | |
| "learning_rate": 8.996156976140086e-07, | |
| "loss": 0.8283, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.6480881399870383, | |
| "grad_norm": 3.5811512536833523, | |
| "learning_rate": 8.95455579160221e-07, | |
| "loss": 0.8168, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.6480881399870383, | |
| "eval_loss": 0.810850977897644, | |
| "eval_runtime": 190.2136, | |
| "eval_samples_per_second": 57.667, | |
| "eval_steps_per_second": 0.904, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.661049902786779, | |
| "grad_norm": 3.3124363238635715, | |
| "learning_rate": 8.912210355636689e-07, | |
| "loss": 0.7922, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.6740116655865198, | |
| "grad_norm": 3.3955357238579693, | |
| "learning_rate": 8.8691286376977e-07, | |
| "loss": 0.8044, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.6869734283862605, | |
| "grad_norm": 3.1989325895717053, | |
| "learning_rate": 8.825318745808439e-07, | |
| "loss": 0.7933, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.6999351911860013, | |
| "grad_norm": 3.393447117563635, | |
| "learning_rate": 8.780788925035177e-07, | |
| "loss": 0.8018, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.712896953985742, | |
| "grad_norm": 3.2831528447418132, | |
| "learning_rate": 8.735547555935537e-07, | |
| "loss": 0.7961, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.7258587167854829, | |
| "grad_norm": 3.4250845276838486, | |
| "learning_rate": 8.689603152981262e-07, | |
| "loss": 0.812, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.7388204795852236, | |
| "grad_norm": 3.2575625313957035, | |
| "learning_rate": 8.64296436295578e-07, | |
| "loss": 0.7971, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.7517822423849644, | |
| "grad_norm": 3.5149123785883014, | |
| "learning_rate": 8.595639963326879e-07, | |
| "loss": 0.8067, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.7647440051847051, | |
| "grad_norm": 3.5091201056207533, | |
| "learning_rate": 8.547638860594764e-07, | |
| "loss": 0.8155, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.7777057679844459, | |
| "grad_norm": 3.5343144588793036, | |
| "learning_rate": 8.49897008861586e-07, | |
| "loss": 0.8021, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.7777057679844459, | |
| "eval_loss": 0.800530195236206, | |
| "eval_runtime": 190.6317, | |
| "eval_samples_per_second": 57.54, | |
| "eval_steps_per_second": 0.902, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.7906675307841866, | |
| "grad_norm": 3.3863012076670542, | |
| "learning_rate": 8.449642806902622e-07, | |
| "loss": 0.7993, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.8036292935839274, | |
| "grad_norm": 3.5586423328389585, | |
| "learning_rate": 8.399666298899706e-07, | |
| "loss": 0.7918, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.8165910563836681, | |
| "grad_norm": 3.12605831331216, | |
| "learning_rate": 8.34904997023682e-07, | |
| "loss": 0.7943, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.829552819183409, | |
| "grad_norm": 3.365606947704741, | |
| "learning_rate": 8.297803346958569e-07, | |
| "loss": 0.783, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.8425145819831497, | |
| "grad_norm": 3.525340806653281, | |
| "learning_rate": 8.245936073731651e-07, | |
| "loss": 0.7976, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.8554763447828905, | |
| "grad_norm": 3.244247748765073, | |
| "learning_rate": 8.193457912029712e-07, | |
| "loss": 0.7807, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.8684381075826313, | |
| "grad_norm": 3.299152179523224, | |
| "learning_rate": 8.140378738296232e-07, | |
| "loss": 0.7836, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.881399870382372, | |
| "grad_norm": 3.6966297262494683, | |
| "learning_rate": 8.086708542085767e-07, | |
| "loss": 0.8063, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.8943616331821128, | |
| "grad_norm": 3.459714731085819, | |
| "learning_rate": 8.032457424183909e-07, | |
| "loss": 0.7911, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.9073233959818535, | |
| "grad_norm": 3.0350617290741373, | |
| "learning_rate": 7.977635594706298e-07, | |
| "loss": 0.7741, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.9073233959818535, | |
| "eval_loss": 0.7928882837295532, | |
| "eval_runtime": 190.396, | |
| "eval_samples_per_second": 57.612, | |
| "eval_steps_per_second": 0.903, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.9202851587815943, | |
| "grad_norm": 3.3620653686755686, | |
| "learning_rate": 7.922253371177082e-07, | |
| "loss": 0.7932, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.933246921581335, | |
| "grad_norm": 3.278928351388705, | |
| "learning_rate": 7.866321176587128e-07, | |
| "loss": 0.7871, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.9462086843810759, | |
| "grad_norm": 3.296771284934289, | |
| "learning_rate": 7.809849537432431e-07, | |
| "loss": 0.7792, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.9591704471808166, | |
| "grad_norm": 4.571766433220969, | |
| "learning_rate": 7.752849081732991e-07, | |
| "loss": 0.788, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.9721322099805574, | |
| "grad_norm": 3.4508851083525007, | |
| "learning_rate": 7.695330537032627e-07, | |
| "loss": 0.7614, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.9850939727802981, | |
| "grad_norm": 3.4026555887076433, | |
| "learning_rate": 7.637304728380037e-07, | |
| "loss": 0.7964, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.9980557355800389, | |
| "grad_norm": 3.4049969426822644, | |
| "learning_rate": 7.5787825762915e-07, | |
| "loss": 0.7659, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 1.0110174983797797, | |
| "grad_norm": 3.7467236394334593, | |
| "learning_rate": 7.519775094695648e-07, | |
| "loss": 0.729, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.0239792611795204, | |
| "grad_norm": 3.3057229188741797, | |
| "learning_rate": 7.460293388860614e-07, | |
| "loss": 0.7421, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 1.0369410239792611, | |
| "grad_norm": 3.1846298307152545, | |
| "learning_rate": 7.400348653304021e-07, | |
| "loss": 0.7155, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.0369410239792611, | |
| "eval_loss": 0.7879951596260071, | |
| "eval_runtime": 190.5219, | |
| "eval_samples_per_second": 57.573, | |
| "eval_steps_per_second": 0.903, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.0499027867790018, | |
| "grad_norm": 3.555528496823252, | |
| "learning_rate": 7.33995216968615e-07, | |
| "loss": 0.721, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 1.0628645495787428, | |
| "grad_norm": 3.17101772663646, | |
| "learning_rate": 7.279115304686733e-07, | |
| "loss": 0.7251, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.0758263123784835, | |
| "grad_norm": 3.4524740982989575, | |
| "learning_rate": 7.217849507865723e-07, | |
| "loss": 0.7079, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 1.0887880751782242, | |
| "grad_norm": 3.5488503758648604, | |
| "learning_rate": 7.156166309508481e-07, | |
| "loss": 0.716, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.101749837977965, | |
| "grad_norm": 3.2843814722509754, | |
| "learning_rate": 7.094077318455761e-07, | |
| "loss": 0.7248, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 1.1147116007777058, | |
| "grad_norm": 3.5818373829792436, | |
| "learning_rate": 7.031594219918915e-07, | |
| "loss": 0.7282, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.1276733635774465, | |
| "grad_norm": 3.545436547315646, | |
| "learning_rate": 6.968728773280729e-07, | |
| "loss": 0.7214, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 1.1406351263771872, | |
| "grad_norm": 3.7309987258945956, | |
| "learning_rate": 6.905492809882285e-07, | |
| "loss": 0.7149, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.1535968891769282, | |
| "grad_norm": 3.342264257213339, | |
| "learning_rate": 6.841898230796302e-07, | |
| "loss": 0.7118, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 1.1665586519766689, | |
| "grad_norm": 3.5498283019941668, | |
| "learning_rate": 6.777957004587331e-07, | |
| "loss": 0.7322, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.1665586519766689, | |
| "eval_loss": 0.7836564779281616, | |
| "eval_runtime": 190.524, | |
| "eval_samples_per_second": 57.573, | |
| "eval_steps_per_second": 0.903, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.1795204147764096, | |
| "grad_norm": 3.4407614110968274, | |
| "learning_rate": 6.713681165059271e-07, | |
| "loss": 0.731, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 1.1924821775761503, | |
| "grad_norm": 3.606482531048048, | |
| "learning_rate": 6.649082808990585e-07, | |
| "loss": 0.7263, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.2054439403758912, | |
| "grad_norm": 3.4160389968965834, | |
| "learning_rate": 6.584174093857675e-07, | |
| "loss": 0.7138, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 1.218405703175632, | |
| "grad_norm": 3.6414465107657885, | |
| "learning_rate": 6.518967235546841e-07, | |
| "loss": 0.7131, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.2313674659753726, | |
| "grad_norm": 3.5928947738604835, | |
| "learning_rate": 6.453474506055227e-07, | |
| "loss": 0.7056, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 1.2443292287751135, | |
| "grad_norm": 3.3876054178886337, | |
| "learning_rate": 6.387708231181228e-07, | |
| "loss": 0.7142, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.2572909915748542, | |
| "grad_norm": 3.9025269357210606, | |
| "learning_rate": 6.321680788204757e-07, | |
| "loss": 0.7295, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 1.270252754374595, | |
| "grad_norm": 3.6340219528437747, | |
| "learning_rate": 6.255404603557833e-07, | |
| "loss": 0.6984, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.2832145171743357, | |
| "grad_norm": 3.441153025186208, | |
| "learning_rate": 6.188892150485902e-07, | |
| "loss": 0.7286, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 1.2961762799740764, | |
| "grad_norm": 3.509621524777449, | |
| "learning_rate": 6.122155946700381e-07, | |
| "loss": 0.7214, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.2961762799740764, | |
| "eval_loss": 0.7790202498435974, | |
| "eval_runtime": 190.1439, | |
| "eval_samples_per_second": 57.688, | |
| "eval_steps_per_second": 0.905, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.3091380427738173, | |
| "grad_norm": 3.9718306817617957, | |
| "learning_rate": 6.055208552022787e-07, | |
| "loss": 0.7183, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 1.322099805573558, | |
| "grad_norm": 3.6250018779596203, | |
| "learning_rate": 5.988062566020986e-07, | |
| "loss": 0.7188, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.3350615683732987, | |
| "grad_norm": 3.58876192132372, | |
| "learning_rate": 5.920730625637933e-07, | |
| "loss": 0.6976, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 1.3480233311730396, | |
| "grad_norm": 3.463594237695507, | |
| "learning_rate": 5.85322540281338e-07, | |
| "loss": 0.7274, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.3609850939727803, | |
| "grad_norm": 3.755952042482129, | |
| "learning_rate": 5.785559602099018e-07, | |
| "loss": 0.7084, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 1.373946856772521, | |
| "grad_norm": 3.306784860944235, | |
| "learning_rate": 5.717745958267459e-07, | |
| "loss": 0.7119, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.3869086195722617, | |
| "grad_norm": 3.534119314182442, | |
| "learning_rate": 5.649797233915538e-07, | |
| "loss": 0.7086, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 1.3998703823720027, | |
| "grad_norm": 3.236567266341926, | |
| "learning_rate": 5.581726217062386e-07, | |
| "loss": 0.716, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.4128321451717434, | |
| "grad_norm": 3.4785698979562456, | |
| "learning_rate": 5.513545718742701e-07, | |
| "loss": 0.7071, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 1.425793907971484, | |
| "grad_norm": 3.675603397627949, | |
| "learning_rate": 5.445268570595708e-07, | |
| "loss": 0.6936, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.425793907971484, | |
| "eval_loss": 0.7752651572227478, | |
| "eval_runtime": 190.3759, | |
| "eval_samples_per_second": 57.618, | |
| "eval_steps_per_second": 0.903, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.4387556707712248, | |
| "grad_norm": 3.399382435225056, | |
| "learning_rate": 5.376907622450228e-07, | |
| "loss": 0.7155, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 1.4517174335709657, | |
| "grad_norm": 3.564747777066771, | |
| "learning_rate": 5.308475739906328e-07, | |
| "loss": 0.7086, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.4646791963707064, | |
| "grad_norm": 3.346047715273763, | |
| "learning_rate": 5.239985801913999e-07, | |
| "loss": 0.7136, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 1.4776409591704471, | |
| "grad_norm": 3.716468641603961, | |
| "learning_rate": 5.171450698349329e-07, | |
| "loss": 0.7208, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.490602721970188, | |
| "grad_norm": 3.8457195513896703, | |
| "learning_rate": 5.102883327588608e-07, | |
| "loss": 0.7055, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 1.5035644847699285, | |
| "grad_norm": 3.6398948460452325, | |
| "learning_rate": 5.034296594080848e-07, | |
| "loss": 0.6824, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.5165262475696695, | |
| "grad_norm": 3.3427427312285425, | |
| "learning_rate": 4.965703405919153e-07, | |
| "loss": 0.733, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 1.5294880103694104, | |
| "grad_norm": 3.7140860027489504, | |
| "learning_rate": 4.897116672411394e-07, | |
| "loss": 0.7011, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.5424497731691509, | |
| "grad_norm": 3.810495577054968, | |
| "learning_rate": 4.828549301650673e-07, | |
| "loss": 0.7216, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 1.5554115359688918, | |
| "grad_norm": 3.4920510717873925, | |
| "learning_rate": 4.760014198086001e-07, | |
| "loss": 0.7046, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.5554115359688918, | |
| "eval_loss": 0.7716971039772034, | |
| "eval_runtime": 190.4272, | |
| "eval_samples_per_second": 57.602, | |
| "eval_steps_per_second": 0.903, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.5683732987686325, | |
| "grad_norm": 3.7379962063873244, | |
| "learning_rate": 4.691524260093672e-07, | |
| "loss": 0.7177, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 1.5813350615683732, | |
| "grad_norm": 3.5163342715426493, | |
| "learning_rate": 4.6230923775497714e-07, | |
| "loss": 0.698, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.5942968243681142, | |
| "grad_norm": 3.7752520950220316, | |
| "learning_rate": 4.554731429404293e-07, | |
| "loss": 0.7068, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 1.6072585871678549, | |
| "grad_norm": 3.6497035959305637, | |
| "learning_rate": 4.486454281257299e-07, | |
| "loss": 0.7105, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.6202203499675956, | |
| "grad_norm": 3.3786220834131817, | |
| "learning_rate": 4.4182737829376135e-07, | |
| "loss": 0.7002, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 1.6331821127673365, | |
| "grad_norm": 3.745654045093921, | |
| "learning_rate": 4.35020276608446e-07, | |
| "loss": 0.7132, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.646143875567077, | |
| "grad_norm": 3.7550095562633294, | |
| "learning_rate": 4.2822540417325394e-07, | |
| "loss": 0.7239, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 1.659105638366818, | |
| "grad_norm": 3.6978911774202743, | |
| "learning_rate": 4.2144403979009823e-07, | |
| "loss": 0.708, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.6720674011665586, | |
| "grad_norm": 3.380536692165867, | |
| "learning_rate": 4.1467745971866214e-07, | |
| "loss": 0.7152, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 1.6850291639662993, | |
| "grad_norm": 3.7325575613565922, | |
| "learning_rate": 4.0792693743620686e-07, | |
| "loss": 0.6967, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.6850291639662993, | |
| "eval_loss": 0.7689746618270874, | |
| "eval_runtime": 191.11, | |
| "eval_samples_per_second": 57.396, | |
| "eval_steps_per_second": 0.9, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.6979909267660402, | |
| "grad_norm": 3.51032707119909, | |
| "learning_rate": 4.0119374339790133e-07, | |
| "loss": 0.7024, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 1.710952689565781, | |
| "grad_norm": 3.6309443687197933, | |
| "learning_rate": 3.944791447977213e-07, | |
| "loss": 0.7242, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.7239144523655217, | |
| "grad_norm": 3.4720213982057175, | |
| "learning_rate": 3.87784405329962e-07, | |
| "loss": 0.7089, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 1.7368762151652626, | |
| "grad_norm": 3.503078080597499, | |
| "learning_rate": 3.8111078495140973e-07, | |
| "loss": 0.7219, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.7498379779650033, | |
| "grad_norm": 3.801326705711802, | |
| "learning_rate": 3.7445953964421684e-07, | |
| "loss": 0.7078, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 1.762799740764744, | |
| "grad_norm": 3.673701397433746, | |
| "learning_rate": 3.678319211795242e-07, | |
| "loss": 0.7263, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.775761503564485, | |
| "grad_norm": 3.4237663715763023, | |
| "learning_rate": 3.6122917688187717e-07, | |
| "loss": 0.6994, | |
| "step": 685 | |
| }, | |
| { | |
| "epoch": 1.7887232663642254, | |
| "grad_norm": 3.705157971233802, | |
| "learning_rate": 3.546525493944773e-07, | |
| "loss": 0.7112, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.8016850291639663, | |
| "grad_norm": 3.785127652648907, | |
| "learning_rate": 3.48103276445316e-07, | |
| "loss": 0.7145, | |
| "step": 695 | |
| }, | |
| { | |
| "epoch": 1.814646791963707, | |
| "grad_norm": 3.3911683616136177, | |
| "learning_rate": 3.4158259061423255e-07, | |
| "loss": 0.7197, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.814646791963707, | |
| "eval_loss": 0.765801727771759, | |
| "eval_runtime": 190.378, | |
| "eval_samples_per_second": 57.617, | |
| "eval_steps_per_second": 0.903, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.8276085547634477, | |
| "grad_norm": 3.3840783324475994, | |
| "learning_rate": 3.3509171910094156e-07, | |
| "loss": 0.7008, | |
| "step": 705 | |
| }, | |
| { | |
| "epoch": 1.8405703175631887, | |
| "grad_norm": 3.612580310866905, | |
| "learning_rate": 3.286318834940729e-07, | |
| "loss": 0.7101, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.8535320803629294, | |
| "grad_norm": 3.7400467933207557, | |
| "learning_rate": 3.2220429954126686e-07, | |
| "loss": 0.6797, | |
| "step": 715 | |
| }, | |
| { | |
| "epoch": 1.86649384316267, | |
| "grad_norm": 3.6560156110852464, | |
| "learning_rate": 3.158101769203698e-07, | |
| "loss": 0.7056, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.879455605962411, | |
| "grad_norm": 3.707238700659647, | |
| "learning_rate": 3.0945071901177145e-07, | |
| "loss": 0.7093, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 1.8924173687621515, | |
| "grad_norm": 3.606777649061402, | |
| "learning_rate": 3.031271226719271e-07, | |
| "loss": 0.7084, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 1.9053791315618924, | |
| "grad_norm": 3.582291971931833, | |
| "learning_rate": 2.968405780081084e-07, | |
| "loss": 0.7072, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 1.9183408943616331, | |
| "grad_norm": 3.6451496181338103, | |
| "learning_rate": 2.905922681544238e-07, | |
| "loss": 0.6969, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.9313026571613738, | |
| "grad_norm": 3.4586471118745656, | |
| "learning_rate": 2.8438336904915184e-07, | |
| "loss": 0.6882, | |
| "step": 745 | |
| }, | |
| { | |
| "epoch": 1.9442644199611148, | |
| "grad_norm": 3.7194825643308853, | |
| "learning_rate": 2.7821504921342774e-07, | |
| "loss": 0.704, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.9442644199611148, | |
| "eval_loss": 0.7632837295532227, | |
| "eval_runtime": 190.2948, | |
| "eval_samples_per_second": 57.642, | |
| "eval_steps_per_second": 0.904, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.9572261827608555, | |
| "grad_norm": 3.5452530896647696, | |
| "learning_rate": 2.7208846953132683e-07, | |
| "loss": 0.6927, | |
| "step": 755 | |
| }, | |
| { | |
| "epoch": 1.9701879455605962, | |
| "grad_norm": 3.5705371811039504, | |
| "learning_rate": 2.66004783031385e-07, | |
| "loss": 0.7037, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 1.983149708360337, | |
| "grad_norm": 3.4298716866923624, | |
| "learning_rate": 2.599651346695979e-07, | |
| "loss": 0.6926, | |
| "step": 765 | |
| }, | |
| { | |
| "epoch": 1.9961114711600778, | |
| "grad_norm": 3.7912871601195284, | |
| "learning_rate": 2.539706611139385e-07, | |
| "loss": 0.7111, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 2.0090732339598185, | |
| "grad_norm": 3.769564370048527, | |
| "learning_rate": 2.480224905304352e-07, | |
| "loss": 0.6801, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 2.0220349967595594, | |
| "grad_norm": 3.418564384607543, | |
| "learning_rate": 2.4212174237085005e-07, | |
| "loss": 0.663, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 2.0349967595593, | |
| "grad_norm": 3.730605140988728, | |
| "learning_rate": 2.3626952716199644e-07, | |
| "loss": 0.6784, | |
| "step": 785 | |
| }, | |
| { | |
| "epoch": 2.047958522359041, | |
| "grad_norm": 3.7129740066342882, | |
| "learning_rate": 2.3046694629673712e-07, | |
| "loss": 0.6293, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 2.060920285158782, | |
| "grad_norm": 3.6275068157375108, | |
| "learning_rate": 2.247150918267008e-07, | |
| "loss": 0.6489, | |
| "step": 795 | |
| }, | |
| { | |
| "epoch": 2.0738820479585223, | |
| "grad_norm": 3.625813889475341, | |
| "learning_rate": 2.1901504625675688e-07, | |
| "loss": 0.6546, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.0738820479585223, | |
| "eval_loss": 0.7677435874938965, | |
| "eval_runtime": 190.4024, | |
| "eval_samples_per_second": 57.61, | |
| "eval_steps_per_second": 0.903, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.086843810758263, | |
| "grad_norm": 3.4182137647327764, | |
| "learning_rate": 2.1336788234128729e-07, | |
| "loss": 0.6676, | |
| "step": 805 | |
| }, | |
| { | |
| "epoch": 2.0998055735580037, | |
| "grad_norm": 3.6556183671319293, | |
| "learning_rate": 2.0777466288229205e-07, | |
| "loss": 0.6629, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 2.1127673363577446, | |
| "grad_norm": 3.744401914160934, | |
| "learning_rate": 2.0223644052937028e-07, | |
| "loss": 0.6418, | |
| "step": 815 | |
| }, | |
| { | |
| "epoch": 2.1257290991574855, | |
| "grad_norm": 3.865359361945009, | |
| "learning_rate": 1.9675425758160924e-07, | |
| "loss": 0.6531, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 2.138690861957226, | |
| "grad_norm": 3.69643616461443, | |
| "learning_rate": 1.9132914579142338e-07, | |
| "loss": 0.6346, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 2.151652624756967, | |
| "grad_norm": 3.7535585023145797, | |
| "learning_rate": 1.8596212617037693e-07, | |
| "loss": 0.6654, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 2.164614387556708, | |
| "grad_norm": 4.0159793685962475, | |
| "learning_rate": 1.8065420879702887e-07, | |
| "loss": 0.6649, | |
| "step": 835 | |
| }, | |
| { | |
| "epoch": 2.1775761503564484, | |
| "grad_norm": 3.644285842038128, | |
| "learning_rate": 1.7540639262683487e-07, | |
| "loss": 0.6433, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 2.1905379131561893, | |
| "grad_norm": 3.9056650075753665, | |
| "learning_rate": 1.70219665304143e-07, | |
| "loss": 0.6769, | |
| "step": 845 | |
| }, | |
| { | |
| "epoch": 2.20349967595593, | |
| "grad_norm": 3.7184862818541933, | |
| "learning_rate": 1.6509500297631785e-07, | |
| "loss": 0.651, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 2.20349967595593, | |
| "eval_loss": 0.7672791481018066, | |
| "eval_runtime": 190.5782, | |
| "eval_samples_per_second": 57.556, | |
| "eval_steps_per_second": 0.903, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 2.2164614387556707, | |
| "grad_norm": 3.8299853960357906, | |
| "learning_rate": 1.6003337011002927e-07, | |
| "loss": 0.6564, | |
| "step": 855 | |
| }, | |
| { | |
| "epoch": 2.2294232015554116, | |
| "grad_norm": 3.8417509954938085, | |
| "learning_rate": 1.5503571930973785e-07, | |
| "loss": 0.6426, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 2.242384964355152, | |
| "grad_norm": 3.647265480928013, | |
| "learning_rate": 1.5010299113841397e-07, | |
| "loss": 0.6518, | |
| "step": 865 | |
| }, | |
| { | |
| "epoch": 2.255346727154893, | |
| "grad_norm": 3.5486365560504827, | |
| "learning_rate": 1.4523611394052355e-07, | |
| "loss": 0.6475, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 2.268308489954634, | |
| "grad_norm": 3.4682735371792526, | |
| "learning_rate": 1.4043600366731213e-07, | |
| "loss": 0.662, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 2.2812702527543745, | |
| "grad_norm": 3.824875125016563, | |
| "learning_rate": 1.3570356370442189e-07, | |
| "loss": 0.6552, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 2.2942320155541154, | |
| "grad_norm": 3.828027807398829, | |
| "learning_rate": 1.3103968470187382e-07, | |
| "loss": 0.6476, | |
| "step": 885 | |
| }, | |
| { | |
| "epoch": 2.3071937783538563, | |
| "grad_norm": 3.842354090272816, | |
| "learning_rate": 1.2644524440644627e-07, | |
| "loss": 0.6685, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 2.320155541153597, | |
| "grad_norm": 3.6920011302134044, | |
| "learning_rate": 1.2192110749648232e-07, | |
| "loss": 0.6655, | |
| "step": 895 | |
| }, | |
| { | |
| "epoch": 2.3331173039533377, | |
| "grad_norm": 3.7425896847607256, | |
| "learning_rate": 1.1746812541915607e-07, | |
| "loss": 0.6601, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.3331173039533377, | |
| "eval_loss": 0.7666835188865662, | |
| "eval_runtime": 190.628, | |
| "eval_samples_per_second": 57.541, | |
| "eval_steps_per_second": 0.902, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.346079066753078, | |
| "grad_norm": 3.9070327756742107, | |
| "learning_rate": 1.1308713623022986e-07, | |
| "loss": 0.6627, | |
| "step": 905 | |
| }, | |
| { | |
| "epoch": 2.359040829552819, | |
| "grad_norm": 3.7802235911895217, | |
| "learning_rate": 1.0877896443633117e-07, | |
| "loss": 0.6593, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 2.37200259235256, | |
| "grad_norm": 3.61433280563944, | |
| "learning_rate": 1.045444208397791e-07, | |
| "loss": 0.6709, | |
| "step": 915 | |
| }, | |
| { | |
| "epoch": 2.3849643551523005, | |
| "grad_norm": 3.972094909530566, | |
| "learning_rate": 1.0038430238599154e-07, | |
| "loss": 0.651, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 2.3979261179520415, | |
| "grad_norm": 3.796273978107305, | |
| "learning_rate": 9.629939201349852e-08, | |
| "loss": 0.6588, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 2.4108878807517824, | |
| "grad_norm": 3.7293416826903525, | |
| "learning_rate": 9.229045850659251e-08, | |
| "loss": 0.656, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 2.423849643551523, | |
| "grad_norm": 3.6150556912476945, | |
| "learning_rate": 8.835825635064265e-08, | |
| "loss": 0.6603, | |
| "step": 935 | |
| }, | |
| { | |
| "epoch": 2.436811406351264, | |
| "grad_norm": 3.5117438967831145, | |
| "learning_rate": 8.450352559009949e-08, | |
| "loss": 0.6572, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 2.4497731691510047, | |
| "grad_norm": 3.599439277396364, | |
| "learning_rate": 8.072699168921825e-08, | |
| "loss": 0.6523, | |
| "step": 945 | |
| }, | |
| { | |
| "epoch": 2.462734931950745, | |
| "grad_norm": 3.815395750371357, | |
| "learning_rate": 7.70293653955254e-08, | |
| "loss": 0.6669, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 2.462734931950745, | |
| "eval_loss": 0.7661544680595398, | |
| "eval_runtime": 190.5379, | |
| "eval_samples_per_second": 57.569, | |
| "eval_steps_per_second": 0.903, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 2.475696694750486, | |
| "grad_norm": 3.83907673537174, | |
| "learning_rate": 7.341134260605536e-08, | |
| "loss": 0.6467, | |
| "step": 955 | |
| }, | |
| { | |
| "epoch": 2.488658457550227, | |
| "grad_norm": 3.71914525200344, | |
| "learning_rate": 6.987360423638205e-08, | |
| "loss": 0.6451, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 2.5016202203499676, | |
| "grad_norm": 3.8744678609767926, | |
| "learning_rate": 6.641681609246979e-08, | |
| "loss": 0.6499, | |
| "step": 965 | |
| }, | |
| { | |
| "epoch": 2.5145819831497085, | |
| "grad_norm": 3.839049543501993, | |
| "learning_rate": 6.304162874536795e-08, | |
| "loss": 0.6381, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 2.527543745949449, | |
| "grad_norm": 3.890978467270095, | |
| "learning_rate": 5.974867740877281e-08, | |
| "loss": 0.6611, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 2.54050550874919, | |
| "grad_norm": 3.655850976914982, | |
| "learning_rate": 5.653858181947979e-08, | |
| "loss": 0.6511, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 2.5534672715489304, | |
| "grad_norm": 3.553408249450878, | |
| "learning_rate": 5.341194612074823e-08, | |
| "loss": 0.645, | |
| "step": 985 | |
| }, | |
| { | |
| "epoch": 2.5664290343486713, | |
| "grad_norm": 3.772171071477516, | |
| "learning_rate": 5.0369358748601096e-08, | |
| "loss": 0.664, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 2.5793907971484122, | |
| "grad_norm": 3.9844066962823783, | |
| "learning_rate": 4.74113923210806e-08, | |
| "loss": 0.6768, | |
| "step": 995 | |
| }, | |
| { | |
| "epoch": 2.5923525599481527, | |
| "grad_norm": 3.709224867062063, | |
| "learning_rate": 4.453860353048111e-08, | |
| "loss": 0.6566, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.5923525599481527, | |
| "eval_loss": 0.7657259702682495, | |
| "eval_runtime": 190.4841, | |
| "eval_samples_per_second": 57.585, | |
| "eval_steps_per_second": 0.903, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.6053143227478937, | |
| "grad_norm": 3.6125710008133014, | |
| "learning_rate": 4.1751533038578866e-08, | |
| "loss": 0.6588, | |
| "step": 1005 | |
| }, | |
| { | |
| "epoch": 2.6182760855476346, | |
| "grad_norm": 3.9281818636928305, | |
| "learning_rate": 3.9050705374879086e-08, | |
| "loss": 0.6451, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 2.631237848347375, | |
| "grad_norm": 3.6915219360218794, | |
| "learning_rate": 3.6436628837898773e-08, | |
| "loss": 0.6537, | |
| "step": 1015 | |
| }, | |
| { | |
| "epoch": 2.644199611147116, | |
| "grad_norm": 3.8956742656352756, | |
| "learning_rate": 3.390979539950478e-08, | |
| "loss": 0.6646, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 2.657161373946857, | |
| "grad_norm": 3.693338526233881, | |
| "learning_rate": 3.1470680612323494e-08, | |
| "loss": 0.6398, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 2.6701231367465974, | |
| "grad_norm": 3.676860096119893, | |
| "learning_rate": 2.9119743520242213e-08, | |
| "loss": 0.656, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 2.6830848995463383, | |
| "grad_norm": 3.839586455095117, | |
| "learning_rate": 2.6857426572016007e-08, | |
| "loss": 0.6522, | |
| "step": 1035 | |
| }, | |
| { | |
| "epoch": 2.6960466623460793, | |
| "grad_norm": 3.7505570827639754, | |
| "learning_rate": 2.468415553799874e-08, | |
| "loss": 0.661, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 2.7090084251458197, | |
| "grad_norm": 3.74016254328062, | |
| "learning_rate": 2.2600339430012438e-08, | |
| "loss": 0.6543, | |
| "step": 1045 | |
| }, | |
| { | |
| "epoch": 2.7219701879455607, | |
| "grad_norm": 4.044963430877048, | |
| "learning_rate": 2.0606370424370966e-08, | |
| "loss": 0.6654, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 2.7219701879455607, | |
| "eval_loss": 0.765480101108551, | |
| "eval_runtime": 190.595, | |
| "eval_samples_per_second": 57.551, | |
| "eval_steps_per_second": 0.902, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 2.7349319507453016, | |
| "grad_norm": 3.8050950373574115, | |
| "learning_rate": 1.8702623788072024e-08, | |
| "loss": 0.6585, | |
| "step": 1055 | |
| }, | |
| { | |
| "epoch": 2.747893713545042, | |
| "grad_norm": 3.7424493675710604, | |
| "learning_rate": 1.688945780817147e-08, | |
| "loss": 0.6765, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 2.760855476344783, | |
| "grad_norm": 3.7803862294906496, | |
| "learning_rate": 1.516721372435342e-08, | |
| "loss": 0.6578, | |
| "step": 1065 | |
| }, | |
| { | |
| "epoch": 2.7738172391445235, | |
| "grad_norm": 3.7879361506176332, | |
| "learning_rate": 1.3536215664708583e-08, | |
| "loss": 0.6681, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 2.7867790019442644, | |
| "grad_norm": 3.8430280460507524, | |
| "learning_rate": 1.1996770584732919e-08, | |
| "loss": 0.6412, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 2.7997407647440054, | |
| "grad_norm": 3.741428860483068, | |
| "learning_rate": 1.0549168209558312e-08, | |
| "loss": 0.6748, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 2.812702527543746, | |
| "grad_norm": 3.7122256590189564, | |
| "learning_rate": 9.193680979426189e-09, | |
| "loss": 0.6433, | |
| "step": 1085 | |
| }, | |
| { | |
| "epoch": 2.8256642903434868, | |
| "grad_norm": 3.6981576894413415, | |
| "learning_rate": 7.930563998413797e-09, | |
| "loss": 0.6621, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 2.8386260531432272, | |
| "grad_norm": 3.7162009738597526, | |
| "learning_rate": 6.760054986423458e-09, | |
| "loss": 0.6623, | |
| "step": 1095 | |
| }, | |
| { | |
| "epoch": 2.851587815942968, | |
| "grad_norm": 3.76189814784874, | |
| "learning_rate": 5.6823742344433435e-09, | |
| "loss": 0.6389, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.851587815942968, | |
| "eval_loss": 0.7652862668037415, | |
| "eval_runtime": 190.4719, | |
| "eval_samples_per_second": 57.589, | |
| "eval_steps_per_second": 0.903, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.864549578742709, | |
| "grad_norm": 4.07593882169201, | |
| "learning_rate": 4.697724563088645e-09, | |
| "loss": 0.6616, | |
| "step": 1105 | |
| }, | |
| { | |
| "epoch": 2.8775113415424496, | |
| "grad_norm": 3.95049669925965, | |
| "learning_rate": 3.806291284430274e-09, | |
| "loss": 0.6678, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 2.8904731043421905, | |
| "grad_norm": 3.692127174629793, | |
| "learning_rate": 3.008242167119257e-09, | |
| "loss": 0.6533, | |
| "step": 1115 | |
| }, | |
| { | |
| "epoch": 2.9034348671419314, | |
| "grad_norm": 3.9224928557653254, | |
| "learning_rate": 2.303727404812217e-09, | |
| "loss": 0.6568, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 2.916396629941672, | |
| "grad_norm": 3.700977024408014, | |
| "learning_rate": 1.6928795879049828e-09, | |
| "loss": 0.658, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 2.929358392741413, | |
| "grad_norm": 3.671559049022848, | |
| "learning_rate": 1.1758136785788853e-09, | |
| "loss": 0.6591, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 2.942320155541154, | |
| "grad_norm": 3.9515548315685107, | |
| "learning_rate": 7.526269891646175e-10, | |
| "loss": 0.6448, | |
| "step": 1135 | |
| }, | |
| { | |
| "epoch": 2.9552819183408943, | |
| "grad_norm": 3.6083444577524615, | |
| "learning_rate": 4.233991638281642e-10, | |
| "loss": 0.6421, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 2.968243681140635, | |
| "grad_norm": 3.6842766767841733, | |
| "learning_rate": 1.8819216358156865e-10, | |
| "loss": 0.6606, | |
| "step": 1145 | |
| }, | |
| { | |
| "epoch": 2.981205443940376, | |
| "grad_norm": 4.03690890015612, | |
| "learning_rate": 4.7050254621872064e-11, | |
| "loss": 0.6574, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 2.981205443940376, | |
| "eval_loss": 0.7652673125267029, | |
| "eval_runtime": 190.6904, | |
| "eval_samples_per_second": 57.523, | |
| "eval_steps_per_second": 0.902, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 2.9941672067401166, | |
| "grad_norm": 4.036929712704943, | |
| "learning_rate": 0.0, | |
| "loss": 0.6573, | |
| "step": 1155 | |
| }, | |
| { | |
| "epoch": 2.9941672067401166, | |
| "step": 1155, | |
| "total_flos": 6810169535102976.0, | |
| "train_loss": 0.7440064066932315, | |
| "train_runtime": 19885.6035, | |
| "train_samples_per_second": 14.893, | |
| "train_steps_per_second": 0.058 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 1155, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6810169535102976.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |