| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 1005, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.029850746268656716, | |
| "grad_norm": 9.961305925410098, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8067, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05970149253731343, | |
| "grad_norm": 1.0752052367545273, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7212, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.08955223880597014, | |
| "grad_norm": 2.6880106756208657, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7037, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.11940298507462686, | |
| "grad_norm": 2.468677125810121, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6808, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.14925373134328357, | |
| "grad_norm": 1.2259453137557428, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6673, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1791044776119403, | |
| "grad_norm": 0.8046965924721278, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6673, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.208955223880597, | |
| "grad_norm": 0.8755706624782442, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6525, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.23880597014925373, | |
| "grad_norm": 0.9212844875335406, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6468, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.26865671641791045, | |
| "grad_norm": 1.12468469232501, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6393, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.29850746268656714, | |
| "grad_norm": 0.6121939679063821, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6349, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.3283582089552239, | |
| "grad_norm": 0.6139174959470913, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6341, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.3582089552238806, | |
| "grad_norm": 0.5251117188495569, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6331, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.3880597014925373, | |
| "grad_norm": 0.5494317456200198, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6329, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.417910447761194, | |
| "grad_norm": 0.4941836924989687, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6351, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.44776119402985076, | |
| "grad_norm": 0.47052093951365964, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6209, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.47761194029850745, | |
| "grad_norm": 1.1146519645525566, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6305, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.5074626865671642, | |
| "grad_norm": 0.8473149334181534, | |
| "learning_rate": 5e-06, | |
| "loss": 0.629, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.5373134328358209, | |
| "grad_norm": 0.7499567580667779, | |
| "learning_rate": 5e-06, | |
| "loss": 0.63, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.5671641791044776, | |
| "grad_norm": 0.5639441343205728, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6218, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.5970149253731343, | |
| "grad_norm": 1.1342411031324615, | |
| "learning_rate": 5e-06, | |
| "loss": 0.622, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.6268656716417911, | |
| "grad_norm": 0.6456096595420062, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6232, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.6567164179104478, | |
| "grad_norm": 0.5879709496150657, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6236, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.6865671641791045, | |
| "grad_norm": 0.8978920811236428, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6099, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.7164179104477612, | |
| "grad_norm": 0.8274630792281841, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6108, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.746268656716418, | |
| "grad_norm": 0.6457291165426283, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6092, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.7761194029850746, | |
| "grad_norm": 0.5847180410958434, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6118, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.8059701492537313, | |
| "grad_norm": 0.9144134579449927, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6135, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.835820895522388, | |
| "grad_norm": 1.6213022633122485, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6149, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.8656716417910447, | |
| "grad_norm": 0.5755669090329376, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6193, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.8955223880597015, | |
| "grad_norm": 0.5239632952956513, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6152, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.9253731343283582, | |
| "grad_norm": 0.5078873832450146, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6142, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.9552238805970149, | |
| "grad_norm": 0.7451903752568965, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6067, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.9850746268656716, | |
| "grad_norm": 0.5114709685939808, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5999, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.6080397367477417, | |
| "eval_runtime": 59.4897, | |
| "eval_samples_per_second": 151.673, | |
| "eval_steps_per_second": 0.605, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 1.0149253731343284, | |
| "grad_norm": 0.6428823077249859, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5862, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.044776119402985, | |
| "grad_norm": 0.749643554288035, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5592, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.0746268656716418, | |
| "grad_norm": 0.46129260605818906, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5729, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.1044776119402986, | |
| "grad_norm": 0.6289609209087915, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5567, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.1343283582089552, | |
| "grad_norm": 0.605218538340198, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5637, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.164179104477612, | |
| "grad_norm": 0.5995330578684349, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5636, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.1940298507462686, | |
| "grad_norm": 0.6108058300152777, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5511, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.2238805970149254, | |
| "grad_norm": 0.5091266989811818, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5658, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.2537313432835822, | |
| "grad_norm": 0.497382336824621, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5648, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.2835820895522387, | |
| "grad_norm": 0.6009692943343384, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5632, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.3134328358208955, | |
| "grad_norm": 0.6663676150345131, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5539, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.3432835820895521, | |
| "grad_norm": 0.5153693458150974, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5604, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.373134328358209, | |
| "grad_norm": 0.4650717684546587, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5637, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.4029850746268657, | |
| "grad_norm": 0.5337571428788572, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5627, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.4328358208955223, | |
| "grad_norm": 0.5056863786298517, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5634, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.462686567164179, | |
| "grad_norm": 0.5950623554639968, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5642, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.4925373134328357, | |
| "grad_norm": 0.6247670785942998, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5625, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.5223880597014925, | |
| "grad_norm": 0.4901169936700308, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5627, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.5522388059701493, | |
| "grad_norm": 0.47156500447116634, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5687, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.582089552238806, | |
| "grad_norm": 0.493610926847214, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5597, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.6119402985074627, | |
| "grad_norm": 0.5267761487869876, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5616, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.6417910447761193, | |
| "grad_norm": 0.44433923391234365, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5576, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.671641791044776, | |
| "grad_norm": 0.4991219923642928, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5585, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.7014925373134329, | |
| "grad_norm": 0.4559161332352475, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5561, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.7313432835820897, | |
| "grad_norm": 0.44695659572809443, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5558, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.7611940298507462, | |
| "grad_norm": 0.6551282471596537, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5651, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.7910447761194028, | |
| "grad_norm": 0.590104074031775, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5666, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.8208955223880596, | |
| "grad_norm": 0.5262721423268055, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5579, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.8507462686567164, | |
| "grad_norm": 0.5025495933022038, | |
| "learning_rate": 5e-06, | |
| "loss": 0.561, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.8805970149253732, | |
| "grad_norm": 0.5437285628032003, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5671, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.9104477611940298, | |
| "grad_norm": 0.5830114249621688, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5569, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.9402985074626866, | |
| "grad_norm": 0.5691476967866934, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5584, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.9701492537313432, | |
| "grad_norm": 0.49823732746182914, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5571, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.4853362249094826, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5557, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.5995889902114868, | |
| "eval_runtime": 59.329, | |
| "eval_samples_per_second": 152.084, | |
| "eval_steps_per_second": 0.607, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 2.029850746268657, | |
| "grad_norm": 0.530250772889861, | |
| "learning_rate": 5e-06, | |
| "loss": 0.513, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 2.0597014925373136, | |
| "grad_norm": 0.5342911362277831, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5108, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 2.08955223880597, | |
| "grad_norm": 0.5434518597947492, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5105, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.1194029850746268, | |
| "grad_norm": 0.6286537295202244, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5123, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 2.1492537313432836, | |
| "grad_norm": 0.5956472591858897, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5065, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 2.1791044776119404, | |
| "grad_norm": 0.5608264698424108, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5112, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 2.208955223880597, | |
| "grad_norm": 0.529984658854658, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5078, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 2.2388059701492535, | |
| "grad_norm": 0.539168879551667, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5105, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 2.2686567164179103, | |
| "grad_norm": 0.5397218859742641, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5098, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 2.298507462686567, | |
| "grad_norm": 0.5080172238267691, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5094, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 2.328358208955224, | |
| "grad_norm": 0.5269231995045524, | |
| "learning_rate": 5e-06, | |
| "loss": 0.508, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 2.3582089552238807, | |
| "grad_norm": 0.485045053682394, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5115, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 2.388059701492537, | |
| "grad_norm": 0.6198237538120879, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5083, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.417910447761194, | |
| "grad_norm": 0.602606300035839, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5151, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 2.4477611940298507, | |
| "grad_norm": 0.5667564011219249, | |
| "learning_rate": 5e-06, | |
| "loss": 0.519, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 2.4776119402985075, | |
| "grad_norm": 0.5104272153178098, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5081, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 2.5074626865671643, | |
| "grad_norm": 0.4892216848477563, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5082, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 2.5373134328358207, | |
| "grad_norm": 0.520250022509386, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5148, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 2.5671641791044775, | |
| "grad_norm": 0.6047039208024556, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5098, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 2.5970149253731343, | |
| "grad_norm": 0.4743086712519712, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5085, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 2.626865671641791, | |
| "grad_norm": 0.5601721301492414, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5151, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 2.656716417910448, | |
| "grad_norm": 0.5312045710978154, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5144, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 2.6865671641791042, | |
| "grad_norm": 0.5148689817919981, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5104, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.716417910447761, | |
| "grad_norm": 0.5394739876753407, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5168, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 2.746268656716418, | |
| "grad_norm": 0.49195076728876497, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5124, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 2.7761194029850746, | |
| "grad_norm": 0.5138809386584957, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5173, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 2.8059701492537314, | |
| "grad_norm": 0.48130331745070326, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5108, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 2.835820895522388, | |
| "grad_norm": 0.4863446722303473, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5137, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 2.8656716417910446, | |
| "grad_norm": 0.4977491076164347, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5156, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 2.8955223880597014, | |
| "grad_norm": 0.5201471021840797, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5165, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 2.925373134328358, | |
| "grad_norm": 0.5049475021594374, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5109, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 2.955223880597015, | |
| "grad_norm": 0.5648245603044626, | |
| "learning_rate": 5e-06, | |
| "loss": 0.518, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 2.9850746268656714, | |
| "grad_norm": 0.5144681511781752, | |
| "learning_rate": 5e-06, | |
| "loss": 0.504, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.6035678386688232, | |
| "eval_runtime": 59.1481, | |
| "eval_samples_per_second": 152.549, | |
| "eval_steps_per_second": 0.609, | |
| "step": 1005 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 1005, | |
| "total_flos": 1682574913044480.0, | |
| "train_loss": 0.5704716248298759, | |
| "train_runtime": 8778.2325, | |
| "train_samples_per_second": 58.585, | |
| "train_steps_per_second": 0.114 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1005, | |
| "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": 1682574913044480.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |