| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 1269, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02364066193853428, | |
| "grad_norm": 1.5809403657913208, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8881, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04728132387706856, | |
| "grad_norm": 1.8624894618988037, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7858, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07092198581560284, | |
| "grad_norm": 2.2767162322998047, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7546, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.09456264775413711, | |
| "grad_norm": 1.0326734781265259, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7357, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1182033096926714, | |
| "grad_norm": 1.808580756187439, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7237, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.14184397163120568, | |
| "grad_norm": 0.6697216629981995, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7205, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.16548463356973994, | |
| "grad_norm": 1.1802719831466675, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7088, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.18912529550827423, | |
| "grad_norm": 0.6576663255691528, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7001, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.2127659574468085, | |
| "grad_norm": 0.6217890977859497, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6909, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.2364066193853428, | |
| "grad_norm": 0.6629725694656372, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6971, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.26004728132387706, | |
| "grad_norm": 0.8252314329147339, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6761, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.28368794326241137, | |
| "grad_norm": 0.6688860654830933, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6834, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.3073286052009456, | |
| "grad_norm": 0.5039113759994507, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6771, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.3309692671394799, | |
| "grad_norm": 0.5916517376899719, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6793, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.3546099290780142, | |
| "grad_norm": 0.575602650642395, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6831, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.37825059101654845, | |
| "grad_norm": 0.5347154140472412, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6757, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.40189125295508277, | |
| "grad_norm": 0.6461175084114075, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6727, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.425531914893617, | |
| "grad_norm": 0.6578442454338074, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6707, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.4491725768321513, | |
| "grad_norm": 0.6522397398948669, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6737, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.4728132387706856, | |
| "grad_norm": 0.7096086740493774, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6648, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.49645390070921985, | |
| "grad_norm": 0.7721654772758484, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6645, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.5200945626477541, | |
| "grad_norm": 0.9510824680328369, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6656, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.5437352245862884, | |
| "grad_norm": 0.7571592926979065, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6651, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.5673758865248227, | |
| "grad_norm": 0.6714581847190857, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6573, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.5910165484633569, | |
| "grad_norm": 0.5642537474632263, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6657, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.6146572104018913, | |
| "grad_norm": 0.6235966086387634, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6539, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.6382978723404256, | |
| "grad_norm": 0.5237038731575012, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6608, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.6619385342789598, | |
| "grad_norm": 0.5012194514274597, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6621, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.6855791962174941, | |
| "grad_norm": 0.5406949520111084, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6592, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.7092198581560284, | |
| "grad_norm": 0.5066617727279663, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6532, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.7328605200945626, | |
| "grad_norm": 0.4942592680454254, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6649, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.7565011820330969, | |
| "grad_norm": 0.4350595474243164, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6584, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.7801418439716312, | |
| "grad_norm": 0.48511239886283875, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6551, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.8037825059101655, | |
| "grad_norm": 0.5006919503211975, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6511, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.8274231678486997, | |
| "grad_norm": 0.7380832433700562, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6539, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.851063829787234, | |
| "grad_norm": 0.5691511034965515, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6486, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.8747044917257684, | |
| "grad_norm": 0.542851448059082, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6516, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.8983451536643026, | |
| "grad_norm": 0.6073257923126221, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6566, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.9219858156028369, | |
| "grad_norm": 1.0101559162139893, | |
| "learning_rate": 5e-06, | |
| "loss": 0.646, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.9456264775413712, | |
| "grad_norm": 0.5881345868110657, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6531, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.9692671394799054, | |
| "grad_norm": 0.5613337755203247, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6466, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.9929078014184397, | |
| "grad_norm": 0.5331344604492188, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6519, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.650029182434082, | |
| "eval_runtime": 39.2092, | |
| "eval_samples_per_second": 290.442, | |
| "eval_steps_per_second": 1.148, | |
| "step": 423 | |
| }, | |
| { | |
| "epoch": 1.016548463356974, | |
| "grad_norm": 0.6450212597846985, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6193, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.0401891252955082, | |
| "grad_norm": 0.5882251858711243, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6118, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.0638297872340425, | |
| "grad_norm": 0.5410990118980408, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6112, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.0874704491725768, | |
| "grad_norm": 0.7050241827964783, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6095, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.1111111111111112, | |
| "grad_norm": 0.6384491920471191, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6167, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.1347517730496455, | |
| "grad_norm": 0.5661244988441467, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6116, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.1583924349881798, | |
| "grad_norm": 0.4538739025592804, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6191, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.1820330969267139, | |
| "grad_norm": 0.4373492896556854, | |
| "learning_rate": 5e-06, | |
| "loss": 0.612, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.2056737588652482, | |
| "grad_norm": 0.4394100606441498, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6119, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.2293144208037825, | |
| "grad_norm": 0.45556795597076416, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6078, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.2529550827423168, | |
| "grad_norm": 0.5348520278930664, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6083, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.2765957446808511, | |
| "grad_norm": 0.548928439617157, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6103, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.3002364066193852, | |
| "grad_norm": 0.5856196284294128, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6121, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.3238770685579198, | |
| "grad_norm": 0.4891395568847656, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6091, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.3475177304964538, | |
| "grad_norm": 0.45980435609817505, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6144, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.3711583924349882, | |
| "grad_norm": 0.4417429566383362, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6086, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.3947990543735225, | |
| "grad_norm": 0.48172110319137573, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6084, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.4184397163120568, | |
| "grad_norm": 0.5505414009094238, | |
| "learning_rate": 5e-06, | |
| "loss": 0.609, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.442080378250591, | |
| "grad_norm": 0.48917776346206665, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6079, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.4657210401891252, | |
| "grad_norm": 0.5522086024284363, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6066, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.4893617021276595, | |
| "grad_norm": 0.4694415032863617, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6168, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.5130023640661938, | |
| "grad_norm": 0.4723762273788452, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6083, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.5366430260047281, | |
| "grad_norm": 0.4519807696342468, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6108, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.5602836879432624, | |
| "grad_norm": 0.4712272584438324, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6115, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.5839243498817965, | |
| "grad_norm": 0.4411340355873108, | |
| "learning_rate": 5e-06, | |
| "loss": 0.604, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.607565011820331, | |
| "grad_norm": 0.45366063714027405, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6055, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.6312056737588652, | |
| "grad_norm": 0.5291415452957153, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6089, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.6548463356973995, | |
| "grad_norm": 0.4964240491390228, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6107, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.6784869976359338, | |
| "grad_norm": 0.4780677855014801, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6086, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.702127659574468, | |
| "grad_norm": 0.5142894983291626, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6028, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.7257683215130024, | |
| "grad_norm": 0.43228575587272644, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6075, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 1.7494089834515365, | |
| "grad_norm": 0.46347859501838684, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6123, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.773049645390071, | |
| "grad_norm": 0.5133971571922302, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6033, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.7966903073286051, | |
| "grad_norm": 0.5592248439788818, | |
| "learning_rate": 5e-06, | |
| "loss": 0.603, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 1.8203309692671394, | |
| "grad_norm": 0.4413076639175415, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6129, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 1.8439716312056738, | |
| "grad_norm": 0.5284017324447632, | |
| "learning_rate": 5e-06, | |
| "loss": 0.609, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 1.867612293144208, | |
| "grad_norm": 0.5193566083908081, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6116, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 1.8912529550827424, | |
| "grad_norm": 0.4190606474876404, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5997, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.9148936170212765, | |
| "grad_norm": 0.4558718800544739, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5988, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 1.938534278959811, | |
| "grad_norm": 0.4878173768520355, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6092, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 1.962174940898345, | |
| "grad_norm": 0.4382663667201996, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6058, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 1.9858156028368794, | |
| "grad_norm": 0.49692317843437195, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6088, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.6398401260375977, | |
| "eval_runtime": 38.8232, | |
| "eval_samples_per_second": 293.33, | |
| "eval_steps_per_second": 1.159, | |
| "step": 846 | |
| }, | |
| { | |
| "epoch": 2.0094562647754137, | |
| "grad_norm": 0.6104748249053955, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5878, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 2.033096926713948, | |
| "grad_norm": 0.5593996644020081, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5595, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 2.0567375886524824, | |
| "grad_norm": 0.5715161561965942, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5664, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 2.0803782505910164, | |
| "grad_norm": 0.4689047932624817, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5594, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 2.104018912529551, | |
| "grad_norm": 0.4636439383029938, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5666, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 2.127659574468085, | |
| "grad_norm": 0.5165823101997375, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5651, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.1513002364066196, | |
| "grad_norm": 0.4929666519165039, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5712, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 2.1749408983451537, | |
| "grad_norm": 0.6087996363639832, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5693, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 2.198581560283688, | |
| "grad_norm": 0.6086291074752808, | |
| "learning_rate": 5e-06, | |
| "loss": 0.569, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 2.2222222222222223, | |
| "grad_norm": 0.5552637577056885, | |
| "learning_rate": 5e-06, | |
| "loss": 0.565, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 2.2458628841607564, | |
| "grad_norm": 0.4776444435119629, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5686, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 2.269503546099291, | |
| "grad_norm": 0.4616422653198242, | |
| "learning_rate": 5e-06, | |
| "loss": 0.567, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 2.293144208037825, | |
| "grad_norm": 0.5176410675048828, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5755, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 2.3167848699763596, | |
| "grad_norm": 0.47728076577186584, | |
| "learning_rate": 5e-06, | |
| "loss": 0.566, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 2.3404255319148937, | |
| "grad_norm": 0.4709567725658417, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5641, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 2.3640661938534278, | |
| "grad_norm": 0.7246980667114258, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5632, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.3877068557919623, | |
| "grad_norm": 0.5151357650756836, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5652, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 2.4113475177304964, | |
| "grad_norm": 0.46736642718315125, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5739, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 2.434988179669031, | |
| "grad_norm": 0.43881499767303467, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5671, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 2.458628841607565, | |
| "grad_norm": 0.4691537022590637, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5691, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 2.482269503546099, | |
| "grad_norm": 0.4675734043121338, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5667, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 2.5059101654846336, | |
| "grad_norm": 0.5383506417274475, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5715, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 2.5295508274231677, | |
| "grad_norm": 0.5362086892127991, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5596, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 2.5531914893617023, | |
| "grad_norm": 0.5002833008766174, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5704, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 2.5768321513002364, | |
| "grad_norm": 0.43481341004371643, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5671, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 2.6004728132387704, | |
| "grad_norm": 0.5383955836296082, | |
| "learning_rate": 5e-06, | |
| "loss": 0.566, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.624113475177305, | |
| "grad_norm": 0.5254177451133728, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5742, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 2.6477541371158395, | |
| "grad_norm": 0.5556529760360718, | |
| "learning_rate": 5e-06, | |
| "loss": 0.569, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 2.6713947990543736, | |
| "grad_norm": 0.7989609241485596, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5718, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 2.6950354609929077, | |
| "grad_norm": 0.4934903681278229, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5675, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 2.7186761229314422, | |
| "grad_norm": 0.47960445284843445, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5699, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 2.7423167848699763, | |
| "grad_norm": 0.462834894657135, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5712, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 2.7659574468085104, | |
| "grad_norm": 0.4646831452846527, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5661, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 2.789598108747045, | |
| "grad_norm": 0.4419684112071991, | |
| "learning_rate": 5e-06, | |
| "loss": 0.573, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 2.813238770685579, | |
| "grad_norm": 0.512622058391571, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5717, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 2.8368794326241136, | |
| "grad_norm": 0.4194084107875824, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5619, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.8605200945626477, | |
| "grad_norm": 0.4545256793498993, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5699, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 2.884160756501182, | |
| "grad_norm": 0.4438764154911041, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5725, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 2.9078014184397163, | |
| "grad_norm": 0.4500187039375305, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5685, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 2.9314420803782504, | |
| "grad_norm": 0.5051234364509583, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5696, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 2.955082742316785, | |
| "grad_norm": 0.5184685587882996, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5713, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 2.978723404255319, | |
| "grad_norm": 0.5309048891067505, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5839, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.6423146724700928, | |
| "eval_runtime": 39.1245, | |
| "eval_samples_per_second": 291.071, | |
| "eval_steps_per_second": 1.15, | |
| "step": 1269 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 1269, | |
| "total_flos": 5.9918252490593665e+19, | |
| "train_loss": 0.6196046063428418, | |
| "train_runtime": 9031.2946, | |
| "train_samples_per_second": 71.874, | |
| "train_steps_per_second": 0.141 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1269, | |
| "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": 5.9918252490593665e+19, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |