| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.4144271570014144, | |
| "eval_steps": 42, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002828854314002829, | |
| "eval_loss": 11.916790962219238, | |
| "eval_runtime": 6.6784, | |
| "eval_samples_per_second": 89.243, | |
| "eval_steps_per_second": 11.23, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008486562942008486, | |
| "grad_norm": 0.5188692212104797, | |
| "learning_rate": 3e-05, | |
| "loss": 11.92, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.016973125884016973, | |
| "grad_norm": 0.48136115074157715, | |
| "learning_rate": 6e-05, | |
| "loss": 11.9198, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.02545968882602546, | |
| "grad_norm": 0.5018041729927063, | |
| "learning_rate": 9e-05, | |
| "loss": 11.9077, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.033946251768033946, | |
| "grad_norm": 0.6158789992332458, | |
| "learning_rate": 9.999588943391597e-05, | |
| "loss": 11.9074, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.042432814710042434, | |
| "grad_norm": 0.6823853850364685, | |
| "learning_rate": 9.99743108100344e-05, | |
| "loss": 11.9042, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.05091937765205092, | |
| "grad_norm": 0.8695465922355652, | |
| "learning_rate": 9.993424445916923e-05, | |
| "loss": 11.8991, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0594059405940594, | |
| "grad_norm": 0.9028195142745972, | |
| "learning_rate": 9.987570520365104e-05, | |
| "loss": 11.8853, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.06789250353606789, | |
| "grad_norm": 0.9360626935958862, | |
| "learning_rate": 9.979871469976196e-05, | |
| "loss": 11.8781, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.07637906647807638, | |
| "grad_norm": 0.8196120858192444, | |
| "learning_rate": 9.970330142972401e-05, | |
| "loss": 11.8677, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.08486562942008487, | |
| "grad_norm": 0.7162870168685913, | |
| "learning_rate": 9.95895006911623e-05, | |
| "loss": 11.8614, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.09335219236209336, | |
| "grad_norm": 0.5132609605789185, | |
| "learning_rate": 9.945735458404681e-05, | |
| "loss": 11.8498, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.10183875530410184, | |
| "grad_norm": 0.4584226608276367, | |
| "learning_rate": 9.930691199511775e-05, | |
| "loss": 11.8467, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.11032531824611033, | |
| "grad_norm": 0.29786884784698486, | |
| "learning_rate": 9.91382285798002e-05, | |
| "loss": 11.8511, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.1188118811881188, | |
| "grad_norm": 0.2889010012149811, | |
| "learning_rate": 9.895136674161465e-05, | |
| "loss": 11.8408, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.1188118811881188, | |
| "eval_loss": 11.839421272277832, | |
| "eval_runtime": 6.332, | |
| "eval_samples_per_second": 94.125, | |
| "eval_steps_per_second": 11.845, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.1272984441301273, | |
| "grad_norm": 0.20692946016788483, | |
| "learning_rate": 9.874639560909117e-05, | |
| "loss": 11.8396, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.13578500707213578, | |
| "grad_norm": 0.23685254156589508, | |
| "learning_rate": 9.852339101019574e-05, | |
| "loss": 11.8316, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.14427157001414428, | |
| "grad_norm": 0.2432631552219391, | |
| "learning_rate": 9.828243544427796e-05, | |
| "loss": 11.8341, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.15275813295615276, | |
| "grad_norm": 0.11745542287826538, | |
| "learning_rate": 9.802361805155097e-05, | |
| "loss": 11.8301, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.16124469589816123, | |
| "grad_norm": 0.134097158908844, | |
| "learning_rate": 9.774703458011453e-05, | |
| "loss": 11.8359, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.16973125884016974, | |
| "grad_norm": 0.19680051505565643, | |
| "learning_rate": 9.745278735053343e-05, | |
| "loss": 11.8378, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.1782178217821782, | |
| "grad_norm": 0.10566498339176178, | |
| "learning_rate": 9.714098521798465e-05, | |
| "loss": 11.832, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.1867043847241867, | |
| "grad_norm": 0.1530551165342331, | |
| "learning_rate": 9.681174353198687e-05, | |
| "loss": 11.8363, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.19519094766619519, | |
| "grad_norm": 0.1929464042186737, | |
| "learning_rate": 9.64651840937276e-05, | |
| "loss": 11.8284, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.2036775106082037, | |
| "grad_norm": 0.17411480844020844, | |
| "learning_rate": 9.610143511100354e-05, | |
| "loss": 11.8314, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.21216407355021216, | |
| "grad_norm": 0.14971987903118134, | |
| "learning_rate": 9.572063115079063e-05, | |
| "loss": 11.832, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.22065063649222066, | |
| "grad_norm": 0.18370923399925232, | |
| "learning_rate": 9.53229130894619e-05, | |
| "loss": 11.8275, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.22913719943422914, | |
| "grad_norm": 0.26103201508522034, | |
| "learning_rate": 9.490842806067095e-05, | |
| "loss": 11.8278, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.2376237623762376, | |
| "grad_norm": 0.21483545005321503, | |
| "learning_rate": 9.44773294009206e-05, | |
| "loss": 11.825, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.2376237623762376, | |
| "eval_loss": 11.825268745422363, | |
| "eval_runtime": 6.402, | |
| "eval_samples_per_second": 93.097, | |
| "eval_steps_per_second": 11.715, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.24611032531824611, | |
| "grad_norm": 0.28861185908317566, | |
| "learning_rate": 9.40297765928369e-05, | |
| "loss": 11.8219, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.2545968882602546, | |
| "grad_norm": 0.13039568066596985, | |
| "learning_rate": 9.356593520616948e-05, | |
| "loss": 11.8245, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.26308345120226306, | |
| "grad_norm": 0.1711033284664154, | |
| "learning_rate": 9.308597683653975e-05, | |
| "loss": 11.8246, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.27157001414427157, | |
| "grad_norm": 0.2108013778924942, | |
| "learning_rate": 9.259007904196023e-05, | |
| "loss": 11.8228, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.28005657708628007, | |
| "grad_norm": 0.1204076036810875, | |
| "learning_rate": 9.207842527714767e-05, | |
| "loss": 11.82, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.28854314002828857, | |
| "grad_norm": 0.1477670669555664, | |
| "learning_rate": 9.155120482565521e-05, | |
| "loss": 11.8189, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.297029702970297, | |
| "grad_norm": 0.10705884546041489, | |
| "learning_rate": 9.10086127298478e-05, | |
| "loss": 11.8169, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.3055162659123055, | |
| "grad_norm": 0.29956066608428955, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 11.8205, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.314002828854314, | |
| "grad_norm": 0.13027921319007874, | |
| "learning_rate": 8.987812213377424e-05, | |
| "loss": 11.8168, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.32248939179632247, | |
| "grad_norm": 0.13590934872627258, | |
| "learning_rate": 8.929064185241213e-05, | |
| "loss": 11.819, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.33097595473833097, | |
| "grad_norm": 0.09333682060241699, | |
| "learning_rate": 8.868862620982534e-05, | |
| "loss": 11.8267, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.33946251768033947, | |
| "grad_norm": 0.12400602549314499, | |
| "learning_rate": 8.807229791845673e-05, | |
| "loss": 11.818, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.347949080622348, | |
| "grad_norm": 0.12071343511343002, | |
| "learning_rate": 8.744188498563641e-05, | |
| "loss": 11.8166, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.3564356435643564, | |
| "grad_norm": 0.1693616658449173, | |
| "learning_rate": 8.679762062923175e-05, | |
| "loss": 11.8183, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.3564356435643564, | |
| "eval_loss": 11.819117546081543, | |
| "eval_runtime": 6.7651, | |
| "eval_samples_per_second": 88.1, | |
| "eval_steps_per_second": 11.086, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.3649222065063649, | |
| "grad_norm": 0.17696824669837952, | |
| "learning_rate": 8.613974319136958e-05, | |
| "loss": 11.8171, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.3734087694483734, | |
| "grad_norm": 0.11144156008958817, | |
| "learning_rate": 8.54684960502629e-05, | |
| "loss": 11.815, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.38189533239038187, | |
| "grad_norm": 0.16119325160980225, | |
| "learning_rate": 8.478412753017433e-05, | |
| "loss": 11.8134, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.39038189533239037, | |
| "grad_norm": 0.10234789550304413, | |
| "learning_rate": 8.408689080954998e-05, | |
| "loss": 11.8138, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.3988684582743989, | |
| "grad_norm": 0.12111084908246994, | |
| "learning_rate": 8.33770438273574e-05, | |
| "loss": 11.8152, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.4073550212164074, | |
| "grad_norm": 0.07516127824783325, | |
| "learning_rate": 8.265484918766243e-05, | |
| "loss": 11.8128, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.4158415841584158, | |
| "grad_norm": 0.23707596957683563, | |
| "learning_rate": 8.192057406248028e-05, | |
| "loss": 11.8202, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.4243281471004243, | |
| "grad_norm": 0.1228451356291771, | |
| "learning_rate": 8.117449009293668e-05, | |
| "loss": 11.8201, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.4328147100424328, | |
| "grad_norm": 0.16358840465545654, | |
| "learning_rate": 8.041687328877567e-05, | |
| "loss": 11.8141, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.44130127298444133, | |
| "grad_norm": 0.10192089527845383, | |
| "learning_rate": 7.964800392625129e-05, | |
| "loss": 11.8128, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.4497878359264498, | |
| "grad_norm": 0.07679455727338791, | |
| "learning_rate": 7.886816644444098e-05, | |
| "loss": 11.8124, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.4582743988684583, | |
| "grad_norm": 0.10075189918279648, | |
| "learning_rate": 7.807764934001874e-05, | |
| "loss": 11.8119, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.4667609618104668, | |
| "grad_norm": 0.1872919499874115, | |
| "learning_rate": 7.727674506052743e-05, | |
| "loss": 11.8203, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.4752475247524752, | |
| "grad_norm": 0.12166598439216614, | |
| "learning_rate": 7.646574989618938e-05, | |
| "loss": 11.8202, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.4752475247524752, | |
| "eval_loss": 11.818514823913574, | |
| "eval_runtime": 6.4158, | |
| "eval_samples_per_second": 92.895, | |
| "eval_steps_per_second": 11.69, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.4837340876944837, | |
| "grad_norm": 0.13749000430107117, | |
| "learning_rate": 7.564496387029532e-05, | |
| "loss": 11.8156, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.49222065063649223, | |
| "grad_norm": 0.07802052795886993, | |
| "learning_rate": 7.481469062821252e-05, | |
| "loss": 11.8182, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.5007072135785007, | |
| "grad_norm": 0.150814950466156, | |
| "learning_rate": 7.39752373250527e-05, | |
| "loss": 11.8179, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.5091937765205092, | |
| "grad_norm": 0.1514790952205658, | |
| "learning_rate": 7.312691451204178e-05, | |
| "loss": 11.8099, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.5176803394625177, | |
| "grad_norm": 0.13362684845924377, | |
| "learning_rate": 7.227003602163295e-05, | |
| "loss": 11.8172, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.5261669024045261, | |
| "grad_norm": 0.09337490051984787, | |
| "learning_rate": 7.14049188514063e-05, | |
| "loss": 11.8184, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.5346534653465347, | |
| "grad_norm": 0.08015663921833038, | |
| "learning_rate": 7.05318830467969e-05, | |
| "loss": 11.8158, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.5431400282885431, | |
| "grad_norm": 0.16405069828033447, | |
| "learning_rate": 6.965125158269619e-05, | |
| "loss": 11.816, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.5516265912305516, | |
| "grad_norm": 0.14057497680187225, | |
| "learning_rate": 6.876335024396872e-05, | |
| "loss": 11.8147, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.5601131541725601, | |
| "grad_norm": 0.1409187614917755, | |
| "learning_rate": 6.786850750493006e-05, | |
| "loss": 11.8157, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.5685997171145686, | |
| "grad_norm": 0.1987845003604889, | |
| "learning_rate": 6.696705440782938e-05, | |
| "loss": 11.8185, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 0.5770862800565771, | |
| "grad_norm": 0.10339465737342834, | |
| "learning_rate": 6.605932444038229e-05, | |
| "loss": 11.815, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 0.5855728429985856, | |
| "grad_norm": 0.12926329672336578, | |
| "learning_rate": 6.514565341239861e-05, | |
| "loss": 11.818, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 0.594059405940594, | |
| "grad_norm": 0.07949727028608322, | |
| "learning_rate": 6.422637933155162e-05, | |
| "loss": 11.8151, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.594059405940594, | |
| "eval_loss": 11.818094253540039, | |
| "eval_runtime": 6.6444, | |
| "eval_samples_per_second": 89.7, | |
| "eval_steps_per_second": 11.288, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.6025459688826026, | |
| "grad_norm": 0.18179267644882202, | |
| "learning_rate": 6.330184227833376e-05, | |
| "loss": 11.8178, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 0.611032531824611, | |
| "grad_norm": 0.12221992760896683, | |
| "learning_rate": 6.237238428024572e-05, | |
| "loss": 11.8145, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 0.6195190947666195, | |
| "grad_norm": 0.07228324562311172, | |
| "learning_rate": 6.143834918526527e-05, | |
| "loss": 11.8137, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 0.628005657708628, | |
| "grad_norm": 0.11851081997156143, | |
| "learning_rate": 6.0500082534642464e-05, | |
| "loss": 11.8156, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 0.6364922206506365, | |
| "grad_norm": 0.08459550887346268, | |
| "learning_rate": 5.955793143506863e-05, | |
| "loss": 11.8108, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.6449787835926449, | |
| "grad_norm": 0.07968215644359589, | |
| "learning_rate": 5.861224443026595e-05, | |
| "loss": 11.8181, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 0.6534653465346535, | |
| "grad_norm": 0.1503295600414276, | |
| "learning_rate": 5.766337137204579e-05, | |
| "loss": 11.8167, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 0.6619519094766619, | |
| "grad_norm": 0.08652139455080032, | |
| "learning_rate": 5.6711663290882776e-05, | |
| "loss": 11.8122, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 0.6704384724186704, | |
| "grad_norm": 0.08518210798501968, | |
| "learning_rate": 5.575747226605298e-05, | |
| "loss": 11.8164, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 0.6789250353606789, | |
| "grad_norm": 0.12115988880395889, | |
| "learning_rate": 5.480115129538409e-05, | |
| "loss": 11.8114, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.6874115983026874, | |
| "grad_norm": 0.13773323595523834, | |
| "learning_rate": 5.384305416466584e-05, | |
| "loss": 11.815, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 0.695898161244696, | |
| "grad_norm": 0.10262436419725418, | |
| "learning_rate": 5.288353531676873e-05, | |
| "loss": 11.8163, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 0.7043847241867044, | |
| "grad_norm": 0.12103616446256638, | |
| "learning_rate": 5.192294972051992e-05, | |
| "loss": 11.8176, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 0.7128712871287128, | |
| "grad_norm": 0.09017164260149002, | |
| "learning_rate": 5.0961652739384356e-05, | |
| "loss": 11.8221, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 0.7128712871287128, | |
| "eval_loss": 11.818002700805664, | |
| "eval_runtime": 6.3716, | |
| "eval_samples_per_second": 93.539, | |
| "eval_steps_per_second": 11.771, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 0.7213578500707214, | |
| "grad_norm": 0.050791915506124496, | |
| "learning_rate": 5e-05, | |
| "loss": 11.8143, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.7298444130127298, | |
| "grad_norm": 0.1059621125459671, | |
| "learning_rate": 4.903834726061565e-05, | |
| "loss": 11.8175, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 0.7383309759547383, | |
| "grad_norm": 0.07910209894180298, | |
| "learning_rate": 4.807705027948008e-05, | |
| "loss": 11.8104, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 0.7468175388967468, | |
| "grad_norm": 0.11326657980680466, | |
| "learning_rate": 4.711646468323129e-05, | |
| "loss": 11.8178, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 0.7553041018387553, | |
| "grad_norm": 0.15818099677562714, | |
| "learning_rate": 4.6156945835334184e-05, | |
| "loss": 11.8152, | |
| "step": 267 | |
| }, | |
| { | |
| "epoch": 0.7637906647807637, | |
| "grad_norm": 0.08803381770849228, | |
| "learning_rate": 4.5198848704615914e-05, | |
| "loss": 11.8165, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.7722772277227723, | |
| "grad_norm": 0.13214413821697235, | |
| "learning_rate": 4.424252773394704e-05, | |
| "loss": 11.8183, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 0.7807637906647807, | |
| "grad_norm": 0.0714588537812233, | |
| "learning_rate": 4.328833670911724e-05, | |
| "loss": 11.8207, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 0.7892503536067893, | |
| "grad_norm": 0.3612169325351715, | |
| "learning_rate": 4.23366286279542e-05, | |
| "loss": 11.81, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 0.7977369165487977, | |
| "grad_norm": 0.10489798337221146, | |
| "learning_rate": 4.138775556973406e-05, | |
| "loss": 11.8155, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 0.8062234794908062, | |
| "grad_norm": 0.07869977504014969, | |
| "learning_rate": 4.04420685649314e-05, | |
| "loss": 11.8183, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.8147100424328148, | |
| "grad_norm": 0.1785990297794342, | |
| "learning_rate": 3.9499917465357534e-05, | |
| "loss": 11.8151, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 0.8231966053748232, | |
| "grad_norm": 0.08096058666706085, | |
| "learning_rate": 3.856165081473474e-05, | |
| "loss": 11.8138, | |
| "step": 291 | |
| }, | |
| { | |
| "epoch": 0.8316831683168316, | |
| "grad_norm": 0.11269628256559372, | |
| "learning_rate": 3.762761571975429e-05, | |
| "loss": 11.8173, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 0.8316831683168316, | |
| "eval_loss": 11.817937850952148, | |
| "eval_runtime": 6.604, | |
| "eval_samples_per_second": 90.248, | |
| "eval_steps_per_second": 11.357, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 0.8401697312588402, | |
| "grad_norm": 0.11685353517532349, | |
| "learning_rate": 3.6698157721666246e-05, | |
| "loss": 11.8211, | |
| "step": 297 | |
| }, | |
| { | |
| "epoch": 0.8486562942008486, | |
| "grad_norm": 0.10467521101236343, | |
| "learning_rate": 3.5773620668448384e-05, | |
| "loss": 11.8131, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.8571428571428571, | |
| "grad_norm": 0.08696059882640839, | |
| "learning_rate": 3.48543465876014e-05, | |
| "loss": 11.8151, | |
| "step": 303 | |
| }, | |
| { | |
| "epoch": 0.8656294200848657, | |
| "grad_norm": 0.21422286331653595, | |
| "learning_rate": 3.3940675559617724e-05, | |
| "loss": 11.817, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 0.8741159830268741, | |
| "grad_norm": 0.09098684042692184, | |
| "learning_rate": 3.303294559217063e-05, | |
| "loss": 11.8177, | |
| "step": 309 | |
| }, | |
| { | |
| "epoch": 0.8826025459688827, | |
| "grad_norm": 0.11003749072551727, | |
| "learning_rate": 3.213149249506997e-05, | |
| "loss": 11.8127, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 0.8910891089108911, | |
| "grad_norm": 0.10718018561601639, | |
| "learning_rate": 3.12366497560313e-05, | |
| "loss": 11.8152, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.8995756718528995, | |
| "grad_norm": 0.058545950800180435, | |
| "learning_rate": 3.0348748417303823e-05, | |
| "loss": 11.8117, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 0.9080622347949081, | |
| "grad_norm": 0.15917275846004486, | |
| "learning_rate": 2.9468116953203107e-05, | |
| "loss": 11.816, | |
| "step": 321 | |
| }, | |
| { | |
| "epoch": 0.9165487977369166, | |
| "grad_norm": 0.08903782814741135, | |
| "learning_rate": 2.8595081148593738e-05, | |
| "loss": 11.8119, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 0.925035360678925, | |
| "grad_norm": 0.10488823056221008, | |
| "learning_rate": 2.772996397836704e-05, | |
| "loss": 11.8185, | |
| "step": 327 | |
| }, | |
| { | |
| "epoch": 0.9335219236209336, | |
| "grad_norm": 0.09897799789905548, | |
| "learning_rate": 2.687308548795825e-05, | |
| "loss": 11.8194, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.942008486562942, | |
| "grad_norm": 0.10232014954090118, | |
| "learning_rate": 2.6024762674947313e-05, | |
| "loss": 11.8139, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 0.9504950495049505, | |
| "grad_norm": 0.07098989188671112, | |
| "learning_rate": 2.5185309371787513e-05, | |
| "loss": 11.8159, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 0.9504950495049505, | |
| "eval_loss": 11.817768096923828, | |
| "eval_runtime": 6.6321, | |
| "eval_samples_per_second": 89.866, | |
| "eval_steps_per_second": 11.309, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 0.958981612446959, | |
| "grad_norm": 0.1141035333275795, | |
| "learning_rate": 2.43550361297047e-05, | |
| "loss": 11.8135, | |
| "step": 339 | |
| }, | |
| { | |
| "epoch": 0.9674681753889675, | |
| "grad_norm": 0.15841831266880035, | |
| "learning_rate": 2.353425010381063e-05, | |
| "loss": 11.8191, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 0.9759547383309759, | |
| "grad_norm": 0.1034071147441864, | |
| "learning_rate": 2.272325493947257e-05, | |
| "loss": 11.8196, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.9844413012729845, | |
| "grad_norm": 0.1345403790473938, | |
| "learning_rate": 2.192235065998126e-05, | |
| "loss": 11.8162, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 0.9929278642149929, | |
| "grad_norm": 0.06921133399009705, | |
| "learning_rate": 2.1131833555559037e-05, | |
| "loss": 11.8178, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 1.0014144271570014, | |
| "grad_norm": 0.22766686975955963, | |
| "learning_rate": 2.0351996073748713e-05, | |
| "loss": 13.7864, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 1.00990099009901, | |
| "grad_norm": 0.15477143228054047, | |
| "learning_rate": 1.9583126711224343e-05, | |
| "loss": 11.817, | |
| "step": 357 | |
| }, | |
| { | |
| "epoch": 1.0183875530410185, | |
| "grad_norm": 0.23170539736747742, | |
| "learning_rate": 1.8825509907063327e-05, | |
| "loss": 11.8147, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.0268741159830268, | |
| "grad_norm": 0.06929183006286621, | |
| "learning_rate": 1.807942593751973e-05, | |
| "loss": 11.8198, | |
| "step": 363 | |
| }, | |
| { | |
| "epoch": 1.0353606789250354, | |
| "grad_norm": 0.15376947820186615, | |
| "learning_rate": 1.7345150812337564e-05, | |
| "loss": 11.8151, | |
| "step": 366 | |
| }, | |
| { | |
| "epoch": 1.043847241867044, | |
| "grad_norm": 0.2093440443277359, | |
| "learning_rate": 1.66229561726426e-05, | |
| "loss": 11.8205, | |
| "step": 369 | |
| }, | |
| { | |
| "epoch": 1.0523338048090523, | |
| "grad_norm": 0.1123834103345871, | |
| "learning_rate": 1.5913109190450032e-05, | |
| "loss": 11.8159, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 1.0608203677510608, | |
| "grad_norm": 0.22159625589847565, | |
| "learning_rate": 1.5215872469825682e-05, | |
| "loss": 11.8144, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 1.0693069306930694, | |
| "grad_norm": 0.12495719641447067, | |
| "learning_rate": 1.4531503949737108e-05, | |
| "loss": 11.8175, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 1.0693069306930694, | |
| "eval_loss": 11.817733764648438, | |
| "eval_runtime": 6.6332, | |
| "eval_samples_per_second": 89.851, | |
| "eval_steps_per_second": 11.307, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 1.0777934936350777, | |
| "grad_norm": 0.12858428061008453, | |
| "learning_rate": 1.3860256808630428e-05, | |
| "loss": 11.8168, | |
| "step": 381 | |
| }, | |
| { | |
| "epoch": 1.0862800565770863, | |
| "grad_norm": 0.1034870445728302, | |
| "learning_rate": 1.3202379370768252e-05, | |
| "loss": 11.8184, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 1.0947666195190948, | |
| "grad_norm": 0.19289083778858185, | |
| "learning_rate": 1.2558115014363592e-05, | |
| "loss": 11.8211, | |
| "step": 387 | |
| }, | |
| { | |
| "epoch": 1.1032531824611032, | |
| "grad_norm": 0.15419146418571472, | |
| "learning_rate": 1.1927702081543279e-05, | |
| "loss": 11.8142, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.1117397454031117, | |
| "grad_norm": 0.15567056834697723, | |
| "learning_rate": 1.1311373790174657e-05, | |
| "loss": 11.8155, | |
| "step": 393 | |
| }, | |
| { | |
| "epoch": 1.1202263083451203, | |
| "grad_norm": 0.13290712237358093, | |
| "learning_rate": 1.0709358147587884e-05, | |
| "loss": 11.8208, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 1.1287128712871288, | |
| "grad_norm": 0.09749293327331543, | |
| "learning_rate": 1.0121877866225781e-05, | |
| "loss": 11.8177, | |
| "step": 399 | |
| }, | |
| { | |
| "epoch": 1.1371994342291372, | |
| "grad_norm": 0.120842345058918, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 11.8156, | |
| "step": 402 | |
| }, | |
| { | |
| "epoch": 1.1456859971711457, | |
| "grad_norm": 0.09248703718185425, | |
| "learning_rate": 8.991387270152201e-06, | |
| "loss": 11.8186, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 1.154172560113154, | |
| "grad_norm": 0.12557213008403778, | |
| "learning_rate": 8.448795174344804e-06, | |
| "loss": 11.8199, | |
| "step": 408 | |
| }, | |
| { | |
| "epoch": 1.1626591230551626, | |
| "grad_norm": 0.17817071080207825, | |
| "learning_rate": 7.921574722852343e-06, | |
| "loss": 11.8154, | |
| "step": 411 | |
| }, | |
| { | |
| "epoch": 1.1711456859971712, | |
| "grad_norm": 0.10258757323026657, | |
| "learning_rate": 7.409920958039795e-06, | |
| "loss": 11.8124, | |
| "step": 414 | |
| }, | |
| { | |
| "epoch": 1.1796322489391797, | |
| "grad_norm": 0.16313178837299347, | |
| "learning_rate": 6.9140231634602485e-06, | |
| "loss": 11.815, | |
| "step": 417 | |
| }, | |
| { | |
| "epoch": 1.188118811881188, | |
| "grad_norm": 0.10050709545612335, | |
| "learning_rate": 6.43406479383053e-06, | |
| "loss": 11.8149, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.188118811881188, | |
| "eval_loss": 11.817734718322754, | |
| "eval_runtime": 6.4421, | |
| "eval_samples_per_second": 92.516, | |
| "eval_steps_per_second": 11.642, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.1966053748231966, | |
| "grad_norm": 0.09405164420604706, | |
| "learning_rate": 5.9702234071631e-06, | |
| "loss": 11.8103, | |
| "step": 423 | |
| }, | |
| { | |
| "epoch": 1.2050919377652052, | |
| "grad_norm": 0.07892228662967682, | |
| "learning_rate": 5.5226705990794155e-06, | |
| "loss": 11.8166, | |
| "step": 426 | |
| }, | |
| { | |
| "epoch": 1.2135785007072135, | |
| "grad_norm": 0.09944994747638702, | |
| "learning_rate": 5.091571939329048e-06, | |
| "loss": 11.8157, | |
| "step": 429 | |
| }, | |
| { | |
| "epoch": 1.222065063649222, | |
| "grad_norm": 0.09870926290750504, | |
| "learning_rate": 4.677086910538092e-06, | |
| "loss": 11.8141, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 1.2305516265912306, | |
| "grad_norm": 0.16009728610515594, | |
| "learning_rate": 4.279368849209381e-06, | |
| "loss": 11.8126, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 1.239038189533239, | |
| "grad_norm": 0.10148247331380844, | |
| "learning_rate": 3.898564888996476e-06, | |
| "loss": 11.8173, | |
| "step": 438 | |
| }, | |
| { | |
| "epoch": 1.2475247524752475, | |
| "grad_norm": 0.057802699506282806, | |
| "learning_rate": 3.534815906272404e-06, | |
| "loss": 11.8136, | |
| "step": 441 | |
| }, | |
| { | |
| "epoch": 1.256011315417256, | |
| "grad_norm": 0.059853699058294296, | |
| "learning_rate": 3.18825646801314e-06, | |
| "loss": 11.8178, | |
| "step": 444 | |
| }, | |
| { | |
| "epoch": 1.2644978783592644, | |
| "grad_norm": 0.11142271012067795, | |
| "learning_rate": 2.8590147820153513e-06, | |
| "loss": 11.8121, | |
| "step": 447 | |
| }, | |
| { | |
| "epoch": 1.272984441301273, | |
| "grad_norm": 0.12580835819244385, | |
| "learning_rate": 2.547212649466568e-06, | |
| "loss": 11.8092, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.2814710042432815, | |
| "grad_norm": 0.09984395653009415, | |
| "learning_rate": 2.2529654198854835e-06, | |
| "loss": 11.8177, | |
| "step": 453 | |
| }, | |
| { | |
| "epoch": 1.28995756718529, | |
| "grad_norm": 0.06916932761669159, | |
| "learning_rate": 1.9763819484490355e-06, | |
| "loss": 11.8155, | |
| "step": 456 | |
| }, | |
| { | |
| "epoch": 1.2984441301272984, | |
| "grad_norm": 0.15921108424663544, | |
| "learning_rate": 1.7175645557220566e-06, | |
| "loss": 11.813, | |
| "step": 459 | |
| }, | |
| { | |
| "epoch": 1.306930693069307, | |
| "grad_norm": 0.08516174554824829, | |
| "learning_rate": 1.4766089898042678e-06, | |
| "loss": 11.81, | |
| "step": 462 | |
| }, | |
| { | |
| "epoch": 1.306930693069307, | |
| "eval_loss": 11.817733764648438, | |
| "eval_runtime": 6.4426, | |
| "eval_samples_per_second": 92.509, | |
| "eval_steps_per_second": 11.641, | |
| "step": 462 | |
| }, | |
| { | |
| "epoch": 1.3154172560113153, | |
| "grad_norm": 0.09070340543985367, | |
| "learning_rate": 1.2536043909088191e-06, | |
| "loss": 11.8145, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 1.3239038189533239, | |
| "grad_norm": 0.0519736111164093, | |
| "learning_rate": 1.0486332583853563e-06, | |
| "loss": 11.8139, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 1.3323903818953324, | |
| "grad_norm": 0.09727457165718079, | |
| "learning_rate": 8.617714201998084e-07, | |
| "loss": 11.8145, | |
| "step": 471 | |
| }, | |
| { | |
| "epoch": 1.340876944837341, | |
| "grad_norm": 0.0795770063996315, | |
| "learning_rate": 6.93088004882253e-07, | |
| "loss": 11.8154, | |
| "step": 474 | |
| }, | |
| { | |
| "epoch": 1.3493635077793493, | |
| "grad_norm": 0.09474173188209534, | |
| "learning_rate": 5.426454159531913e-07, | |
| "loss": 11.8169, | |
| "step": 477 | |
| }, | |
| { | |
| "epoch": 1.3578500707213579, | |
| "grad_norm": 0.13217829167842865, | |
| "learning_rate": 4.104993088376974e-07, | |
| "loss": 11.8165, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.3663366336633662, | |
| "grad_norm": 0.11465727537870407, | |
| "learning_rate": 2.966985702759828e-07, | |
| "loss": 11.8173, | |
| "step": 483 | |
| }, | |
| { | |
| "epoch": 1.3748231966053748, | |
| "grad_norm": 0.12922833859920502, | |
| "learning_rate": 2.012853002380466e-07, | |
| "loss": 11.8154, | |
| "step": 486 | |
| }, | |
| { | |
| "epoch": 1.3833097595473833, | |
| "grad_norm": 0.05712132155895233, | |
| "learning_rate": 1.2429479634897267e-07, | |
| "loss": 11.814, | |
| "step": 489 | |
| }, | |
| { | |
| "epoch": 1.391796322489392, | |
| "grad_norm": 0.09231238812208176, | |
| "learning_rate": 6.575554083078084e-08, | |
| "loss": 11.8135, | |
| "step": 492 | |
| }, | |
| { | |
| "epoch": 1.4002828854314002, | |
| "grad_norm": 0.08613143861293793, | |
| "learning_rate": 2.568918996560532e-08, | |
| "loss": 11.819, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 1.4087694483734088, | |
| "grad_norm": 0.11459596455097198, | |
| "learning_rate": 4.110566084036816e-09, | |
| "loss": 11.8119, | |
| "step": 498 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 500, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 42, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3067553218560.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |