| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.1191663819610522, | |
| "eval_steps": 100, | |
| "global_step": 1024, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01093269559275709, | |
| "grad_norm": 165.28294372558594, | |
| "learning_rate": 0.0002, | |
| "loss": 624.4996, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02186539118551418, | |
| "grad_norm": Infinity, | |
| "learning_rate": 0.00019996112676182827, | |
| "loss": 546.1801, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03279808677827127, | |
| "grad_norm": 205.6680450439453, | |
| "learning_rate": 0.0001998267889368103, | |
| "loss": 510.2819, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.04373078237102836, | |
| "grad_norm": 128.06765747070312, | |
| "learning_rate": 0.00019959663551763642, | |
| "loss": 497.8397, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.05466347796378545, | |
| "grad_norm": 146.53973388671875, | |
| "learning_rate": 0.0001992708874098054, | |
| "loss": 495.9984, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06559617355654254, | |
| "grad_norm": 99.703857421875, | |
| "learning_rate": 0.0001988498572723623, | |
| "loss": 494.1846, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.07652886914929963, | |
| "grad_norm": 151.4725341796875, | |
| "learning_rate": 0.00019833394921780245, | |
| "loss": 490.978, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.08746156474205671, | |
| "grad_norm": 112.11941528320312, | |
| "learning_rate": 0.00019772365842419677, | |
| "loss": 480.1951, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.0983942603348138, | |
| "grad_norm": 155.3424530029297, | |
| "learning_rate": 0.0001970195706599109, | |
| "loss": 471.4008, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.1093269559275709, | |
| "grad_norm": 175.84173583984375, | |
| "learning_rate": 0.00019622236172137374, | |
| "loss": 468.4172, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.1093269559275709, | |
| "eval_loss": 7.324180603027344, | |
| "eval_runtime": 58.3519, | |
| "eval_samples_per_second": 160.509, | |
| "eval_steps_per_second": 10.043, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.12025965152032798, | |
| "grad_norm": 149.00534057617188, | |
| "learning_rate": 0.0001953327967844356, | |
| "loss": 465.3731, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.13119234711308508, | |
| "grad_norm": 236.33877563476562, | |
| "learning_rate": 0.0001943517296699384, | |
| "loss": 464.0816, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.14212504270584217, | |
| "grad_norm": 147.4077606201172, | |
| "learning_rate": 0.00019328010202420258, | |
| "loss": 463.7079, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.15305773829859926, | |
| "grad_norm": 136.97933959960938, | |
| "learning_rate": 0.00019211894241521758, | |
| "loss": 460.7253, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.16399043389135634, | |
| "grad_norm": 67.10714721679688, | |
| "learning_rate": 0.0001908693653454033, | |
| "loss": 454.1115, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.17492312948411343, | |
| "grad_norm": 157.962158203125, | |
| "learning_rate": 0.00018953257018189024, | |
| "loss": 451.1601, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.1858558250768705, | |
| "grad_norm": 124.69608306884766, | |
| "learning_rate": 0.00018810984000534458, | |
| "loss": 454.4596, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.1967885206696276, | |
| "grad_norm": 102.23240661621094, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 455.1331, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.20772121626238468, | |
| "grad_norm": 118.30726623535156, | |
| "learning_rate": 0.00018501211803518468, | |
| "loss": 453.586, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.2186539118551418, | |
| "grad_norm": 98.61111450195312, | |
| "learning_rate": 0.00018334009949228061, | |
| "loss": 451.1779, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.2186539118551418, | |
| "eval_loss": 6.999808311462402, | |
| "eval_runtime": 58.2479, | |
| "eval_samples_per_second": 160.795, | |
| "eval_steps_per_second": 10.06, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.22958660744789888, | |
| "grad_norm": 105.02420043945312, | |
| "learning_rate": 0.00018158808958398338, | |
| "loss": 449.5652, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.24051930304065597, | |
| "grad_norm": 236.24205017089844, | |
| "learning_rate": 0.00017975776992173344, | |
| "loss": 449.9907, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.25145199863341305, | |
| "grad_norm": 111.67731475830078, | |
| "learning_rate": 0.00017785089728011798, | |
| "loss": 448.5767, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.26238469422617017, | |
| "grad_norm": 118.7121810913086, | |
| "learning_rate": 0.00017586930191068655, | |
| "loss": 448.7768, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.2733173898189272, | |
| "grad_norm": 78.55050659179688, | |
| "learning_rate": 0.00017381488578524173, | |
| "loss": 447.5193, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.28425008541168434, | |
| "grad_norm": 143.79925537109375, | |
| "learning_rate": 0.00017168962077029147, | |
| "loss": 443.3945, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.2951827810044414, | |
| "grad_norm": 107.96155548095703, | |
| "learning_rate": 0.00016949554673441534, | |
| "loss": 440.8445, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.3061154765971985, | |
| "grad_norm": 86.58111572265625, | |
| "learning_rate": 0.00016723476959036083, | |
| "loss": 439.1689, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.31704817218995557, | |
| "grad_norm": 224.989013671875, | |
| "learning_rate": 0.0001649094592737497, | |
| "loss": 444.2089, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.3279808677827127, | |
| "grad_norm": 114.99178314208984, | |
| "learning_rate": 0.00016252184766033342, | |
| "loss": 449.9366, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.3279808677827127, | |
| "eval_loss": 7.026218414306641, | |
| "eval_runtime": 58.1336, | |
| "eval_samples_per_second": 161.112, | |
| "eval_steps_per_second": 10.08, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.33891356337546974, | |
| "grad_norm": 66.66151428222656, | |
| "learning_rate": 0.0001600742264237979, | |
| "loss": 446.0257, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.34984625896822685, | |
| "grad_norm": 83.69017791748047, | |
| "learning_rate": 0.00015756894483617267, | |
| "loss": 438.0339, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.36077895456098397, | |
| "grad_norm": 71.6341552734375, | |
| "learning_rate": 0.0001550084075129563, | |
| "loss": 435.6428, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.371711650153741, | |
| "grad_norm": 76.65645599365234, | |
| "learning_rate": 0.00015239507210512194, | |
| "loss": 437.0487, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.38264434574649814, | |
| "grad_norm": 207.73638916015625, | |
| "learning_rate": 0.00014973144694021876, | |
| "loss": 437.2165, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.3935770413392552, | |
| "grad_norm": 90.09326171875, | |
| "learning_rate": 0.00014702008861483266, | |
| "loss": 447.2774, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.4045097369320123, | |
| "grad_norm": 60.52599334716797, | |
| "learning_rate": 0.00014426359954071796, | |
| "loss": 442.0876, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.41544243252476937, | |
| "grad_norm": 55.786434173583984, | |
| "learning_rate": 0.00014146462544695426, | |
| "loss": 435.3542, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.4263751281175265, | |
| "grad_norm": 185.42239379882812, | |
| "learning_rate": 0.00013862585284052714, | |
| "loss": 431.46, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.4373078237102836, | |
| "grad_norm": 90.76365661621094, | |
| "learning_rate": 0.00013575000642776893, | |
| "loss": 435.4126, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.4373078237102836, | |
| "eval_loss": 6.82781982421875, | |
| "eval_runtime": 58.072, | |
| "eval_samples_per_second": 161.283, | |
| "eval_steps_per_second": 10.091, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.44824051930304065, | |
| "grad_norm": 70.12236022949219, | |
| "learning_rate": 0.0001328398464991355, | |
| "loss": 436.4229, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.45917321489579777, | |
| "grad_norm": 55.41183090209961, | |
| "learning_rate": 0.00012989816627982848, | |
| "loss": 434.1986, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.4701059104885548, | |
| "grad_norm": 247.78492736816406, | |
| "learning_rate": 0.00012692778924880603, | |
| "loss": 432.3758, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.48103860608131194, | |
| "grad_norm": 130.10150146484375, | |
| "learning_rate": 0.0001239315664287558, | |
| "loss": 438.7516, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.491971301674069, | |
| "grad_norm": 124.00569915771484, | |
| "learning_rate": 0.00012091237364963071, | |
| "loss": 443.4303, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.5029039972668261, | |
| "grad_norm": 70.69654846191406, | |
| "learning_rate": 0.00011787310878837422, | |
| "loss": 439.3571, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.5138366928595832, | |
| "grad_norm": 48.626583099365234, | |
| "learning_rate": 0.00011481668898748475, | |
| "loss": 433.0221, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.5247693884523403, | |
| "grad_norm": 47.17863464355469, | |
| "learning_rate": 0.00011174604785508813, | |
| "loss": 428.8387, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.5357020840450973, | |
| "grad_norm": 84.66542053222656, | |
| "learning_rate": 0.00010866413264920678, | |
| "loss": 426.4283, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.5466347796378545, | |
| "grad_norm": 213.61886596679688, | |
| "learning_rate": 0.00010557390144892684, | |
| "loss": 427.7443, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.5466347796378545, | |
| "eval_loss": 6.722092151641846, | |
| "eval_runtime": 58.1233, | |
| "eval_samples_per_second": 161.14, | |
| "eval_steps_per_second": 10.082, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.5575674752306116, | |
| "grad_norm": 122.73770141601562, | |
| "learning_rate": 0.0001024783203151793, | |
| "loss": 433.5011, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.5685001708233687, | |
| "grad_norm": 101.38385009765625, | |
| "learning_rate": 9.938036044386005e-05, | |
| "loss": 435.1738, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.5794328664161257, | |
| "grad_norm": 114.54944610595703, | |
| "learning_rate": 9.628299531402117e-05, | |
| "loss": 434.8967, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.5903655620088828, | |
| "grad_norm": 84.79987335205078, | |
| "learning_rate": 9.318919783387094e-05, | |
| "loss": 432.9765, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.6012982576016399, | |
| "grad_norm": 61.6598014831543, | |
| "learning_rate": 9.010193748732155e-05, | |
| "loss": 430.1559, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.612230953194397, | |
| "grad_norm": 99.44583129882812, | |
| "learning_rate": 8.702417748382385e-05, | |
| "loss": 429.6009, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.6231636487871541, | |
| "grad_norm": 74.24359130859375, | |
| "learning_rate": 8.395887191422397e-05, | |
| "loss": 430.6433, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.6340963443799111, | |
| "grad_norm": 62.34027099609375, | |
| "learning_rate": 8.090896291537273e-05, | |
| "loss": 429.9604, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.6450290399726682, | |
| "grad_norm": 142.7094268798828, | |
| "learning_rate": 7.787737784620803e-05, | |
| "loss": 432.6778, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.6559617355654254, | |
| "grad_norm": 86.1541748046875, | |
| "learning_rate": 7.486702647802213e-05, | |
| "loss": 433.9323, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.6559617355654254, | |
| "eval_loss": 6.775545120239258, | |
| "eval_runtime": 58.0771, | |
| "eval_samples_per_second": 161.268, | |
| "eval_steps_per_second": 10.09, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.6668944311581825, | |
| "grad_norm": 62.604488372802734, | |
| "learning_rate": 7.188079820160904e-05, | |
| "loss": 431.3976, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.6778271267509395, | |
| "grad_norm": 86.99163818359375, | |
| "learning_rate": 6.892155925397436e-05, | |
| "loss": 429.0467, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.6887598223436966, | |
| "grad_norm": 60.84334945678711, | |
| "learning_rate": 6.59921499672677e-05, | |
| "loss": 426.724, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.6996925179364537, | |
| "grad_norm": 63.2689208984375, | |
| "learning_rate": 6.309538204257977e-05, | |
| "loss": 426.1021, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.7106252135292108, | |
| "grad_norm": 100.661865234375, | |
| "learning_rate": 6.02340358512196e-05, | |
| "loss": 426.2488, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.7215579091219679, | |
| "grad_norm": 98.77324676513672, | |
| "learning_rate": 5.7410857766062966e-05, | |
| "loss": 426.7232, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.7324906047147249, | |
| "grad_norm": 83.56670379638672, | |
| "learning_rate": 5.4628557525532976e-05, | |
| "loss": 429.1631, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.743423300307482, | |
| "grad_norm": 123.90058135986328, | |
| "learning_rate": 5.188980563274315e-05, | |
| "loss": 430.625, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.7543559959002392, | |
| "grad_norm": 96.76585388183594, | |
| "learning_rate": 4.9197230792299195e-05, | |
| "loss": 430.7337, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.7652886914929963, | |
| "grad_norm": 110.13320922851562, | |
| "learning_rate": 4.6553417387219886e-05, | |
| "loss": 429.4984, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.7652886914929963, | |
| "eval_loss": 6.70954704284668, | |
| "eval_runtime": 58.0031, | |
| "eval_samples_per_second": 161.474, | |
| "eval_steps_per_second": 10.103, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.7762213870857533, | |
| "grad_norm": 88.53307342529297, | |
| "learning_rate": 4.396090299839852e-05, | |
| "loss": 429.292, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.7871540826785104, | |
| "grad_norm": 83.58421325683594, | |
| "learning_rate": 4.1422175968985955e-05, | |
| "loss": 428.1954, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.7980867782712675, | |
| "grad_norm": 68.06840515136719, | |
| "learning_rate": 3.8939673016032953e-05, | |
| "loss": 427.5196, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.8090194738640246, | |
| "grad_norm": 101.87394714355469, | |
| "learning_rate": 3.651577689168405e-05, | |
| "loss": 426.9831, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.8199521694567817, | |
| "grad_norm": 91.1787338256836, | |
| "learning_rate": 3.415281409616844e-05, | |
| "loss": 426.4039, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.8308848650495387, | |
| "grad_norm": 76.29208374023438, | |
| "learning_rate": 3.185305264478159e-05, | |
| "loss": 427.1363, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.8418175606422958, | |
| "grad_norm": 106.453369140625, | |
| "learning_rate": 2.9618699891002843e-05, | |
| "loss": 428.5345, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.852750256235053, | |
| "grad_norm": 77.79237365722656, | |
| "learning_rate": 2.745190040783646e-05, | |
| "loss": 428.4736, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.8636829518278101, | |
| "grad_norm": 78.0290756225586, | |
| "learning_rate": 2.5354733929410977e-05, | |
| "loss": 427.3446, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.8746156474205672, | |
| "grad_norm": 82.6236801147461, | |
| "learning_rate": 2.332921335481205e-05, | |
| "loss": 426.4013, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.8746156474205672, | |
| "eval_loss": 6.655261516571045, | |
| "eval_runtime": 57.9158, | |
| "eval_samples_per_second": 161.718, | |
| "eval_steps_per_second": 10.118, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.8855483430133242, | |
| "grad_norm": 88.00137329101562, | |
| "learning_rate": 2.137728281606475e-05, | |
| "loss": 425.3787, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.8964810386060813, | |
| "grad_norm": 68.48820495605469, | |
| "learning_rate": 2e-05, | |
| "loss": 425.5655, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.9074137341988384, | |
| "grad_norm": 99.16329956054688, | |
| "learning_rate": 2e-05, | |
| "loss": 425.2563, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.9183464297915955, | |
| "grad_norm": 82.26581573486328, | |
| "learning_rate": 2e-05, | |
| "loss": 424.7282, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.9292791253843525, | |
| "grad_norm": 76.19690704345703, | |
| "learning_rate": 2e-05, | |
| "loss": 424.4672, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.9402118209771096, | |
| "grad_norm": 76.67041778564453, | |
| "learning_rate": 2e-05, | |
| "loss": 424.8196, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.9511445165698668, | |
| "grad_norm": 91.26239013671875, | |
| "learning_rate": 2e-05, | |
| "loss": 424.8494, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.9620772121626239, | |
| "grad_norm": 87.45671844482422, | |
| "learning_rate": 2e-05, | |
| "loss": 424.553, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.973009907755381, | |
| "grad_norm": 83.90388488769531, | |
| "learning_rate": 2e-05, | |
| "loss": 424.6736, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.983942603348138, | |
| "grad_norm": 92.74352264404297, | |
| "learning_rate": 2e-05, | |
| "loss": 425.6448, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.983942603348138, | |
| "eval_loss": 6.660056114196777, | |
| "eval_runtime": 57.8375, | |
| "eval_samples_per_second": 161.937, | |
| "eval_steps_per_second": 10.132, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.9948752989408951, | |
| "grad_norm": 82.22098541259766, | |
| "learning_rate": 2e-05, | |
| "loss": 426.0456, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 1.0054663477963786, | |
| "grad_norm": 85.19371032714844, | |
| "learning_rate": 2e-05, | |
| "loss": 413.45, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 1.0163990433891357, | |
| "grad_norm": 114.56877899169922, | |
| "learning_rate": 2e-05, | |
| "loss": 426.7532, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 1.0273317389818928, | |
| "grad_norm": 101.91117858886719, | |
| "learning_rate": 2e-05, | |
| "loss": 426.5692, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 1.03826443457465, | |
| "grad_norm": 98.91850280761719, | |
| "learning_rate": 2e-05, | |
| "loss": 427.7487, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.049197130167407, | |
| "grad_norm": 124.97265625, | |
| "learning_rate": 2e-05, | |
| "loss": 427.6109, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 1.060129825760164, | |
| "grad_norm": 118.64958190917969, | |
| "learning_rate": 2e-05, | |
| "loss": 427.6372, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 1.071062521352921, | |
| "grad_norm": 109.47184753417969, | |
| "learning_rate": 2e-05, | |
| "loss": 428.8791, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 1.0819952169456781, | |
| "grad_norm": 130.62338256835938, | |
| "learning_rate": 2e-05, | |
| "loss": 429.3186, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 1.0929279125384352, | |
| "grad_norm": 127.20825958251953, | |
| "learning_rate": 2e-05, | |
| "loss": 429.1682, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.0929279125384352, | |
| "eval_loss": 6.715859413146973, | |
| "eval_runtime": 57.8946, | |
| "eval_samples_per_second": 161.777, | |
| "eval_steps_per_second": 10.122, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.1038606081311924, | |
| "grad_norm": 105.07234191894531, | |
| "learning_rate": 2e-05, | |
| "loss": 429.3496, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 1.1147933037239495, | |
| "grad_norm": 143.77236938476562, | |
| "learning_rate": 2e-05, | |
| "loss": 429.6381, | |
| "step": 1020 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1024, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 1024, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8.705517388910559e+18, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |