| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.998994974874372, | |
| "eval_steps": 500, | |
| "global_step": 1119, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02680067001675042, | |
| "grad_norm": 31.10676739208888, | |
| "learning_rate": 5e-06, | |
| "loss": 1.0442, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05360134003350084, | |
| "grad_norm": 4.120159718355311, | |
| "learning_rate": 5e-06, | |
| "loss": 0.955, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.08040201005025126, | |
| "grad_norm": 2.339286993290118, | |
| "learning_rate": 5e-06, | |
| "loss": 0.9144, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.10720268006700168, | |
| "grad_norm": 1.0759658796503169, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8882, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.13400335008375208, | |
| "grad_norm": 0.6453086287600575, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8699, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.16080402010050251, | |
| "grad_norm": 1.1160652028087201, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8652, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.18760469011725292, | |
| "grad_norm": 0.6258812701119981, | |
| "learning_rate": 5e-06, | |
| "loss": 0.848, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.21440536013400335, | |
| "grad_norm": 0.5590720583080133, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8463, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.24120603015075376, | |
| "grad_norm": 0.6795899721647743, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8393, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.26800670016750416, | |
| "grad_norm": 1.1809098922748584, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8335, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.2948073701842546, | |
| "grad_norm": 0.8420170258665194, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8354, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.32160804020100503, | |
| "grad_norm": 0.6851931492236875, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8311, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.34840871021775544, | |
| "grad_norm": 0.9823271515850558, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8338, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.37520938023450584, | |
| "grad_norm": 0.7764734742568185, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8308, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.4020100502512563, | |
| "grad_norm": 0.8463569347395117, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8223, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.4288107202680067, | |
| "grad_norm": 0.7229327877216101, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8265, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.4556113902847571, | |
| "grad_norm": 0.7406267992443841, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8192, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.4824120603015075, | |
| "grad_norm": 0.5245160572062765, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8175, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.509212730318258, | |
| "grad_norm": 0.5446187756240741, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8173, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.5360134003350083, | |
| "grad_norm": 0.5387389341379448, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8152, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.5628140703517588, | |
| "grad_norm": 0.5942914061122081, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8158, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.5896147403685092, | |
| "grad_norm": 0.7289915117140335, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8157, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.6164154103852596, | |
| "grad_norm": 0.6166043522729069, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8154, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.6432160804020101, | |
| "grad_norm": 0.5402182876037194, | |
| "learning_rate": 5e-06, | |
| "loss": 0.81, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.6700167504187605, | |
| "grad_norm": 0.702136667602188, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8086, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.6968174204355109, | |
| "grad_norm": 0.5548041175483877, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8067, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.7236180904522613, | |
| "grad_norm": 0.5933880054884063, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8046, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.7504187604690117, | |
| "grad_norm": 0.6218650700836093, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8045, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.7772194304857621, | |
| "grad_norm": 0.6636079178178366, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8029, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.8040201005025126, | |
| "grad_norm": 0.7578337185188113, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8017, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.830820770519263, | |
| "grad_norm": 0.5964607129683942, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8039, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.8576214405360134, | |
| "grad_norm": 0.5731797399351095, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8018, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.8844221105527639, | |
| "grad_norm": 1.2550493135376506, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7994, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.9112227805695142, | |
| "grad_norm": 0.9368889967347727, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8074, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.9380234505862647, | |
| "grad_norm": 0.5921834072388994, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8049, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.964824120603015, | |
| "grad_norm": 0.5216457733637546, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8019, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.9916247906197655, | |
| "grad_norm": 0.6220842275028926, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7989, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.9996649916247906, | |
| "eval_loss": 0.7980747222900391, | |
| "eval_runtime": 396.9204, | |
| "eval_samples_per_second": 25.33, | |
| "eval_steps_per_second": 0.398, | |
| "step": 373 | |
| }, | |
| { | |
| "epoch": 1.018425460636516, | |
| "grad_norm": 0.8379563173937747, | |
| "learning_rate": 5e-06, | |
| "loss": 0.846, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.0452261306532664, | |
| "grad_norm": 0.7007106059150332, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7553, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.0720268006700167, | |
| "grad_norm": 0.6985327962246497, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7609, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.0988274706867671, | |
| "grad_norm": 0.8231254452075508, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7594, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.1256281407035176, | |
| "grad_norm": 0.5396289186374543, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7555, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.152428810720268, | |
| "grad_norm": 0.5275185306049085, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7554, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.1792294807370185, | |
| "grad_norm": 0.5322161709304825, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7592, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.2060301507537687, | |
| "grad_norm": 0.6335605844571386, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7569, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.2328308207705192, | |
| "grad_norm": 0.6175137584423412, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7545, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.2596314907872697, | |
| "grad_norm": 0.5525760530230355, | |
| "learning_rate": 5e-06, | |
| "loss": 0.755, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.2864321608040201, | |
| "grad_norm": 0.8168923150097971, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7546, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.3132328308207706, | |
| "grad_norm": 0.576393540227948, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7613, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.3400335008375208, | |
| "grad_norm": 0.5454484709306812, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7558, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.3668341708542713, | |
| "grad_norm": 0.519519630849878, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7513, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.3936348408710217, | |
| "grad_norm": 0.5412825055890007, | |
| "learning_rate": 5e-06, | |
| "loss": 0.757, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.4204355108877722, | |
| "grad_norm": 0.6663985833801256, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7549, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.4472361809045227, | |
| "grad_norm": 0.5433262572367299, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7546, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.474036850921273, | |
| "grad_norm": 0.4990591351939153, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7483, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.5008375209380236, | |
| "grad_norm": 0.5826918311899233, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7554, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.5276381909547738, | |
| "grad_norm": 0.5498876689910938, | |
| "learning_rate": 5e-06, | |
| "loss": 0.747, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.5544388609715243, | |
| "grad_norm": 0.5033534721843692, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7563, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.5812395309882747, | |
| "grad_norm": 0.5475928059702524, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7597, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.608040201005025, | |
| "grad_norm": 0.5483658876220942, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7538, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.6348408710217757, | |
| "grad_norm": 0.550772312369244, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7552, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.661641541038526, | |
| "grad_norm": 0.541814614413297, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7556, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.6884422110552764, | |
| "grad_norm": 0.5623412222166373, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7523, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.7152428810720268, | |
| "grad_norm": 0.5486383001151054, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7548, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.742043551088777, | |
| "grad_norm": 0.6450442334835524, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7506, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.7688442211055277, | |
| "grad_norm": 0.5093346834442244, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7526, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.795644891122278, | |
| "grad_norm": 0.5882959805663536, | |
| "learning_rate": 5e-06, | |
| "loss": 0.756, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.8224455611390284, | |
| "grad_norm": 0.6121773592899815, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7516, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.849246231155779, | |
| "grad_norm": 0.5053865601023015, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7552, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.8760469011725294, | |
| "grad_norm": 0.49653124526114595, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7506, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.9028475711892798, | |
| "grad_norm": 0.5356438120020067, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7512, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.92964824120603, | |
| "grad_norm": 0.4792312103436412, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7523, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.9564489112227805, | |
| "grad_norm": 0.5887442908787863, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7489, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 1.983249581239531, | |
| "grad_norm": 0.6013288648401325, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7568, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.9993299832495812, | |
| "eval_loss": 0.7848142385482788, | |
| "eval_runtime": 399.6688, | |
| "eval_samples_per_second": 25.156, | |
| "eval_steps_per_second": 0.395, | |
| "step": 746 | |
| }, | |
| { | |
| "epoch": 2.0100502512562812, | |
| "grad_norm": 0.7899358115042834, | |
| "learning_rate": 5e-06, | |
| "loss": 0.806, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 2.036850921273032, | |
| "grad_norm": 0.5438655957140969, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7051, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 2.063651591289782, | |
| "grad_norm": 0.5954978197528383, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7054, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 2.090452261306533, | |
| "grad_norm": 0.5330734638287157, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7057, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 2.117252931323283, | |
| "grad_norm": 0.5719591031814022, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7074, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 2.1440536013400333, | |
| "grad_norm": 0.5749015032749988, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7035, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.170854271356784, | |
| "grad_norm": 0.7000012184675283, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7045, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 2.1976549413735342, | |
| "grad_norm": 0.5221545575547275, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7085, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 2.224455611390285, | |
| "grad_norm": 0.5590282858104586, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7067, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 2.251256281407035, | |
| "grad_norm": 0.680247988597194, | |
| "learning_rate": 5e-06, | |
| "loss": 0.712, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 2.2780569514237854, | |
| "grad_norm": 0.5724224597541392, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7132, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 2.304857621440536, | |
| "grad_norm": 0.5890303699337465, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7126, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 2.3316582914572863, | |
| "grad_norm": 0.7060913656445702, | |
| "learning_rate": 5e-06, | |
| "loss": 0.71, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 2.358458961474037, | |
| "grad_norm": 0.5199319551859399, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7095, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 2.3852596314907872, | |
| "grad_norm": 0.5667231972196302, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7091, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 2.4120603015075375, | |
| "grad_norm": 0.5776579179225979, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7061, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.438860971524288, | |
| "grad_norm": 0.5068031699453062, | |
| "learning_rate": 5e-06, | |
| "loss": 0.709, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 2.4656616415410384, | |
| "grad_norm": 0.5622723362640956, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7092, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 2.492462311557789, | |
| "grad_norm": 0.6678938168210493, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7074, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 2.5192629815745393, | |
| "grad_norm": 0.7495016986714225, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7123, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 2.5460636515912896, | |
| "grad_norm": 0.5890832065298138, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7117, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 2.5728643216080402, | |
| "grad_norm": 0.5358789200826624, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7123, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 2.5996649916247905, | |
| "grad_norm": 0.7046518448288711, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7124, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 2.626465661641541, | |
| "grad_norm": 0.5598275583119999, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7095, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 2.6532663316582914, | |
| "grad_norm": 0.6175269384061102, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7098, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 2.6800670016750416, | |
| "grad_norm": 0.5833546621317353, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7114, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.7068676716917923, | |
| "grad_norm": 0.5577868241277573, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7126, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 2.7336683417085426, | |
| "grad_norm": 0.5384748297588693, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7107, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 2.7604690117252932, | |
| "grad_norm": 0.6077432046061476, | |
| "learning_rate": 5e-06, | |
| "loss": 0.708, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 2.7872696817420435, | |
| "grad_norm": 0.5845658826184227, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7166, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 2.8140703517587937, | |
| "grad_norm": 0.5139932571124606, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7112, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 2.8408710217755444, | |
| "grad_norm": 0.5214647759988249, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7083, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 2.8676716917922946, | |
| "grad_norm": 0.6459251681734683, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7165, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 2.8944723618090453, | |
| "grad_norm": 0.6289426280816557, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7126, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 2.9212730318257956, | |
| "grad_norm": 0.4931010807851759, | |
| "learning_rate": 5e-06, | |
| "loss": 0.709, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 2.948073701842546, | |
| "grad_norm": 0.5257070901798452, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7131, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.9748743718592965, | |
| "grad_norm": 0.5735309103540566, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7167, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 2.998994974874372, | |
| "eval_loss": 0.784430980682373, | |
| "eval_runtime": 398.3496, | |
| "eval_samples_per_second": 25.239, | |
| "eval_steps_per_second": 0.397, | |
| "step": 1119 | |
| }, | |
| { | |
| "epoch": 2.998994974874372, | |
| "step": 1119, | |
| "total_flos": 1874157297991680.0, | |
| "train_loss": 0.7673776837946369, | |
| "train_runtime": 65939.4578, | |
| "train_samples_per_second": 8.691, | |
| "train_steps_per_second": 0.017 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1119, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1874157297991680.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |