| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.9982238010657194, | |
| "eval_steps": 500, | |
| "global_step": 1266, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.023682652457075192, | |
| "grad_norm": 11.580180719970365, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8801, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.047365304914150384, | |
| "grad_norm": 5.694386546554053, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7848, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07104795737122557, | |
| "grad_norm": 0.7928365185740414, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7523, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.09473060982830077, | |
| "grad_norm": 1.0064056553225857, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7311, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.11841326228537596, | |
| "grad_norm": 0.8588102677301916, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7244, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.14209591474245115, | |
| "grad_norm": 0.7370273691645304, | |
| "learning_rate": 5e-06, | |
| "loss": 0.706, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.16577856719952636, | |
| "grad_norm": 0.7411369649066072, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7186, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.18946121965660154, | |
| "grad_norm": 1.2615112159678439, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6969, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.21314387211367672, | |
| "grad_norm": 0.4974656315107545, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6972, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.23682652457075193, | |
| "grad_norm": 0.5147576667313654, | |
| "learning_rate": 5e-06, | |
| "loss": 0.68, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.2605091770278271, | |
| "grad_norm": 0.4710033839515121, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6812, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.2841918294849023, | |
| "grad_norm": 0.48270825897847935, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6846, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.30787448194197753, | |
| "grad_norm": 0.790240185510984, | |
| "learning_rate": 5e-06, | |
| "loss": 0.676, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.3315571343990527, | |
| "grad_norm": 0.8104277282528387, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6742, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.3552397868561279, | |
| "grad_norm": 0.578671757224867, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6757, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.3789224393132031, | |
| "grad_norm": 0.5874201118510068, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6754, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.40260509177027826, | |
| "grad_norm": 0.4917631935458892, | |
| "learning_rate": 5e-06, | |
| "loss": 0.67, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.42628774422735344, | |
| "grad_norm": 0.6038925351396778, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6667, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.4499703966844287, | |
| "grad_norm": 0.5111399599850822, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6667, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.47365304914150386, | |
| "grad_norm": 0.5213320224608164, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6683, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.49733570159857904, | |
| "grad_norm": 0.48719340333216493, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6654, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.5210183540556542, | |
| "grad_norm": 0.7087017510753161, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6756, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.5447010065127295, | |
| "grad_norm": 0.5190899878624864, | |
| "learning_rate": 5e-06, | |
| "loss": 0.659, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.5683836589698046, | |
| "grad_norm": 0.45436323557307495, | |
| "learning_rate": 5e-06, | |
| "loss": 0.667, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.5920663114268798, | |
| "grad_norm": 0.5064142167200019, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6657, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.6157489638839551, | |
| "grad_norm": 0.634114764397902, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6566, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.6394316163410302, | |
| "grad_norm": 0.5074368322778877, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6566, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.6631142687981054, | |
| "grad_norm": 0.6267290730783063, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6576, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.6867969212551805, | |
| "grad_norm": 0.6348222091289437, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6636, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.7104795737122558, | |
| "grad_norm": 0.5413257273118547, | |
| "learning_rate": 5e-06, | |
| "loss": 0.66, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.7341622261693309, | |
| "grad_norm": 0.47592664539666046, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6595, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.7578448786264061, | |
| "grad_norm": 0.478428145343345, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6555, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.7815275310834814, | |
| "grad_norm": 0.6373996447619408, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6546, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.8052101835405565, | |
| "grad_norm": 0.4755583991704758, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6537, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.8288928359976317, | |
| "grad_norm": 0.47716917902843486, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6596, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.8525754884547069, | |
| "grad_norm": 0.4644937496582173, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6546, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.8762581409117821, | |
| "grad_norm": 0.4239705934033583, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6523, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.8999407933688574, | |
| "grad_norm": 0.510195972449156, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6545, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.9236234458259325, | |
| "grad_norm": 0.8218655966870532, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6575, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.9473060982830077, | |
| "grad_norm": 0.778122168525512, | |
| "learning_rate": 5e-06, | |
| "loss": 0.642, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.9709887507400828, | |
| "grad_norm": 0.515457826896854, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6542, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.9946714031971581, | |
| "grad_norm": 0.5282551277749459, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6414, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.9994079336885732, | |
| "eval_loss": 0.6519263386726379, | |
| "eval_runtime": 224.2129, | |
| "eval_samples_per_second": 50.742, | |
| "eval_steps_per_second": 0.397, | |
| "step": 422 | |
| }, | |
| { | |
| "epoch": 1.0183540556542332, | |
| "grad_norm": 0.6600161274484254, | |
| "learning_rate": 5e-06, | |
| "loss": 0.616, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.0420367081113084, | |
| "grad_norm": 0.5013360565903009, | |
| "learning_rate": 5e-06, | |
| "loss": 0.613, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.0657193605683837, | |
| "grad_norm": 0.5420218599698048, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6043, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.089402013025459, | |
| "grad_norm": 0.5550600850970575, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6116, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.1130846654825342, | |
| "grad_norm": 0.5711211097551357, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6114, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.1367673179396092, | |
| "grad_norm": 0.4738237703033311, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6004, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.1604499703966844, | |
| "grad_norm": 0.519995665132958, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6069, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.1841326228537596, | |
| "grad_norm": 0.5719251310502527, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6152, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.2078152753108349, | |
| "grad_norm": 0.42275665886846947, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6117, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.2314979277679101, | |
| "grad_norm": 0.5168994422728499, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6188, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.2551805802249851, | |
| "grad_norm": 0.4960517990662579, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6074, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.2788632326820604, | |
| "grad_norm": 0.4972749506521509, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6124, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.3025458851391356, | |
| "grad_norm": 0.4512891659935728, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6116, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.3262285375962108, | |
| "grad_norm": 0.5486800171063785, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6118, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.349911190053286, | |
| "grad_norm": 0.4960949423919287, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6086, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.373593842510361, | |
| "grad_norm": 0.7111942461169334, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6083, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.3972764949674363, | |
| "grad_norm": 0.6185227863814267, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6037, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.4209591474245116, | |
| "grad_norm": 0.6854895211681724, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6057, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.4446417998815868, | |
| "grad_norm": 0.498807007502488, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6089, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.468324452338662, | |
| "grad_norm": 0.4784601661555535, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6047, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.492007104795737, | |
| "grad_norm": 0.47899370881340453, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6025, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.5156897572528123, | |
| "grad_norm": 0.5028475227733583, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6097, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.5393724097098875, | |
| "grad_norm": 0.44305542706371875, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6049, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.5630550621669625, | |
| "grad_norm": 0.44715347654354887, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6095, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.586737714624038, | |
| "grad_norm": 0.5007577942426897, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6061, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.610420367081113, | |
| "grad_norm": 0.5700146554097163, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6086, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.6341030195381883, | |
| "grad_norm": 0.5159365931584635, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6113, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.6577856719952635, | |
| "grad_norm": 0.5437452800969841, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6044, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.6814683244523385, | |
| "grad_norm": 0.6343168684170412, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6044, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.705150976909414, | |
| "grad_norm": 0.47604360281895153, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6065, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.728833629366489, | |
| "grad_norm": 0.6030663856542576, | |
| "learning_rate": 5e-06, | |
| "loss": 0.607, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 1.7525162818235642, | |
| "grad_norm": 0.5300503522678514, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6066, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.7761989342806395, | |
| "grad_norm": 0.4618010387153902, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6093, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.7998815867377145, | |
| "grad_norm": 0.4342864081355629, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6045, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 1.82356423919479, | |
| "grad_norm": 0.4523387457254953, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6049, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 1.847246891651865, | |
| "grad_norm": 0.5145138329314661, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6056, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 1.8709295441089402, | |
| "grad_norm": 0.43672760333779226, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6136, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 1.8946121965660154, | |
| "grad_norm": 0.5495600074734466, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6057, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.9182948490230904, | |
| "grad_norm": 0.559949134805628, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6045, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 1.941977501480166, | |
| "grad_norm": 0.4650635136990293, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6122, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 1.965660153937241, | |
| "grad_norm": 0.5401564592759, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6092, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 1.9893428063943162, | |
| "grad_norm": 0.456052398569066, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6064, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 1.9988158673771461, | |
| "eval_loss": 0.6422228217124939, | |
| "eval_runtime": 225.1134, | |
| "eval_samples_per_second": 50.539, | |
| "eval_steps_per_second": 0.395, | |
| "step": 844 | |
| }, | |
| { | |
| "epoch": 2.0130254588513914, | |
| "grad_norm": 0.6189993607524042, | |
| "learning_rate": 5e-06, | |
| "loss": 0.582, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 2.0367081113084664, | |
| "grad_norm": 0.5740784935763802, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5607, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 2.060390763765542, | |
| "grad_norm": 0.5964396961918896, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5646, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 2.084073416222617, | |
| "grad_norm": 0.5507692139006432, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5664, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 2.1077560686796923, | |
| "grad_norm": 0.5018720611836012, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5631, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 2.1314387211367674, | |
| "grad_norm": 0.6003460231298862, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5679, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.1551213735938424, | |
| "grad_norm": 0.5290328026637183, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5637, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 2.178804026050918, | |
| "grad_norm": 0.45527710086603834, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5618, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 2.202486678507993, | |
| "grad_norm": 0.4740063474020259, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5653, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 2.2261693309650683, | |
| "grad_norm": 0.48997671873108534, | |
| "learning_rate": 5e-06, | |
| "loss": 0.565, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 2.2498519834221433, | |
| "grad_norm": 0.49914808237901415, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5675, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 2.2735346358792183, | |
| "grad_norm": 0.596920997938112, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5656, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 2.297217288336294, | |
| "grad_norm": 0.5735564153703901, | |
| "learning_rate": 5e-06, | |
| "loss": 0.565, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 2.320899940793369, | |
| "grad_norm": 0.5519912742369928, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5713, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 2.3445825932504443, | |
| "grad_norm": 0.4675640643082247, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5755, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 2.3682652457075193, | |
| "grad_norm": 0.4361312913430622, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5717, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.3919478981645943, | |
| "grad_norm": 0.4640032816908529, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5689, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 2.4156305506216698, | |
| "grad_norm": 0.44037996481930514, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5643, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 2.4393132030787448, | |
| "grad_norm": 0.5045787949778652, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5638, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 2.4629958555358202, | |
| "grad_norm": 0.4621573812643278, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5587, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 2.4866785079928952, | |
| "grad_norm": 0.5264078685670218, | |
| "learning_rate": 5e-06, | |
| "loss": 0.563, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 2.5103611604499703, | |
| "grad_norm": 0.5343460789042177, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5694, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 2.5340438129070457, | |
| "grad_norm": 0.5325193577248657, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5691, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 2.5577264653641207, | |
| "grad_norm": 0.5468298911750293, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5749, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 2.581409117821196, | |
| "grad_norm": 0.5781509084959986, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5749, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 2.605091770278271, | |
| "grad_norm": 0.5270742215186335, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5649, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.6287744227353462, | |
| "grad_norm": 0.5368871058088638, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5653, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 2.6524570751924217, | |
| "grad_norm": 0.4678129428884298, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5666, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 2.6761397276494967, | |
| "grad_norm": 0.5495858339889211, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5776, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 2.699822380106572, | |
| "grad_norm": 0.4436260648403391, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5733, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 2.723505032563647, | |
| "grad_norm": 0.46368684704169655, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5706, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 2.747187685020722, | |
| "grad_norm": 0.4702868949052167, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5687, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 2.7708703374777977, | |
| "grad_norm": 0.5006009407591486, | |
| "learning_rate": 5e-06, | |
| "loss": 0.565, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 2.7945529899348727, | |
| "grad_norm": 0.4916863056579115, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5728, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 2.818235642391948, | |
| "grad_norm": 0.6631146094885297, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5684, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 2.841918294849023, | |
| "grad_norm": 0.4673828810760241, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5656, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.865600947306098, | |
| "grad_norm": 0.4232627921898123, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5662, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 2.8892835997631736, | |
| "grad_norm": 0.45632210985931476, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5649, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 2.9129662522202486, | |
| "grad_norm": 0.47501442992489695, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5671, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 2.936648904677324, | |
| "grad_norm": 0.5162383441649955, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5626, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 2.960331557134399, | |
| "grad_norm": 0.47876663087966187, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5661, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 2.984014209591474, | |
| "grad_norm": 0.45472166434431854, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5685, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 2.9982238010657194, | |
| "eval_loss": 0.6428163051605225, | |
| "eval_runtime": 225.5335, | |
| "eval_samples_per_second": 50.445, | |
| "eval_steps_per_second": 0.395, | |
| "step": 1266 | |
| }, | |
| { | |
| "epoch": 2.9982238010657194, | |
| "step": 1266, | |
| "total_flos": 2120178393415680.0, | |
| "train_loss": 0.6184906803224512, | |
| "train_runtime": 37764.6257, | |
| "train_samples_per_second": 17.171, | |
| "train_steps_per_second": 0.034 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1266, | |
| "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": 2120178393415680.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |