| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.7398638650488311, | |
| "eval_steps": 200, | |
| "global_step": 2500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0002959455460195324, | |
| "eval_loss": 11.929207801818848, | |
| "eval_runtime": 36.681, | |
| "eval_samples_per_second": 40.948, | |
| "eval_steps_per_second": 10.251, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002959455460195324, | |
| "grad_norm": 0.212890625, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 11.9295, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.005918910920390648, | |
| "grad_norm": 0.263671875, | |
| "learning_rate": 3.2000000000000005e-05, | |
| "loss": 11.9301, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.008878366380585973, | |
| "grad_norm": 0.375, | |
| "learning_rate": 4.8e-05, | |
| "loss": 11.9292, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.011837821840781295, | |
| "grad_norm": 0.47265625, | |
| "learning_rate": 6.400000000000001e-05, | |
| "loss": 11.926, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.01479727730097662, | |
| "grad_norm": 0.84375, | |
| "learning_rate": 8e-05, | |
| "loss": 11.9345, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.017756732761171946, | |
| "grad_norm": 0.244140625, | |
| "learning_rate": 9.6e-05, | |
| "loss": 11.9293, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.020716188221367268, | |
| "grad_norm": 0.255859375, | |
| "learning_rate": 0.00011200000000000001, | |
| "loss": 11.9289, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.02367564368156259, | |
| "grad_norm": 0.34375, | |
| "learning_rate": 0.00012800000000000002, | |
| "loss": 11.9291, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.026635099141757917, | |
| "grad_norm": 0.453125, | |
| "learning_rate": 0.000144, | |
| "loss": 11.9271, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.02959455460195324, | |
| "grad_norm": 0.80859375, | |
| "learning_rate": 0.00016, | |
| "loss": 11.9272, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.032554010062148565, | |
| "grad_norm": 0.23046875, | |
| "learning_rate": 0.00017600000000000002, | |
| "loss": 11.9286, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.03551346552234389, | |
| "grad_norm": 0.322265625, | |
| "learning_rate": 0.000192, | |
| "loss": 11.9239, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.03847292098253921, | |
| "grad_norm": 0.4296875, | |
| "learning_rate": 0.0001999978128380225, | |
| "loss": 11.929, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.041432376442734536, | |
| "grad_norm": 0.5, | |
| "learning_rate": 0.0001999803161162393, | |
| "loss": 11.9268, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.04439183190292986, | |
| "grad_norm": 1.2578125, | |
| "learning_rate": 0.00019994532573409262, | |
| "loss": 11.9198, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.04735128736312518, | |
| "grad_norm": 0.400390625, | |
| "learning_rate": 0.00019989284781388617, | |
| "loss": 11.9145, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.05031074282332051, | |
| "grad_norm": 0.5234375, | |
| "learning_rate": 0.00019982289153773646, | |
| "loss": 11.9004, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.053270198283515834, | |
| "grad_norm": 0.796875, | |
| "learning_rate": 0.00019973546914596623, | |
| "loss": 11.8792, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.05622965374371116, | |
| "grad_norm": 0.7109375, | |
| "learning_rate": 0.00019963059593496268, | |
| "loss": 11.8308, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.05918910920390648, | |
| "grad_norm": 0.7734375, | |
| "learning_rate": 0.00019950829025450114, | |
| "loss": 11.78, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.05918910920390648, | |
| "eval_loss": 11.750052452087402, | |
| "eval_runtime": 37.1832, | |
| "eval_samples_per_second": 40.395, | |
| "eval_steps_per_second": 10.112, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.062148564664101805, | |
| "grad_norm": 0.451171875, | |
| "learning_rate": 0.0001993685735045343, | |
| "loss": 11.7099, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.06510802012429713, | |
| "grad_norm": 0.435546875, | |
| "learning_rate": 0.0001992114701314478, | |
| "loss": 11.6724, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.06806747558449246, | |
| "grad_norm": 0.33203125, | |
| "learning_rate": 0.000199037007623783, | |
| "loss": 11.6468, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.07102693104468778, | |
| "grad_norm": 0.625, | |
| "learning_rate": 0.00019884521650742715, | |
| "loss": 11.6114, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.0739863865048831, | |
| "grad_norm": 0.9296875, | |
| "learning_rate": 0.00019863613034027224, | |
| "loss": 11.6611, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.07694584196507842, | |
| "grad_norm": 0.482421875, | |
| "learning_rate": 0.0001984097857063434, | |
| "loss": 11.4853, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.07990529742527375, | |
| "grad_norm": 0.41796875, | |
| "learning_rate": 0.0001981662222093976, | |
| "loss": 11.4982, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.08286475288546907, | |
| "grad_norm": 0.59375, | |
| "learning_rate": 0.00019790548246599447, | |
| "loss": 11.4479, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.0858242083456644, | |
| "grad_norm": 1.0078125, | |
| "learning_rate": 0.00019762761209803927, | |
| "loss": 11.3621, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.08878366380585972, | |
| "grad_norm": 1.921875, | |
| "learning_rate": 0.0001973326597248006, | |
| "loss": 11.3921, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.09174311926605505, | |
| "grad_norm": 0.400390625, | |
| "learning_rate": 0.00019702067695440332, | |
| "loss": 11.2354, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.09470257472625036, | |
| "grad_norm": 0.490234375, | |
| "learning_rate": 0.00019669171837479873, | |
| "loss": 11.2262, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.09766203018644569, | |
| "grad_norm": 0.5234375, | |
| "learning_rate": 0.00019634584154421317, | |
| "loss": 11.1823, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.10062148564664102, | |
| "grad_norm": 0.46875, | |
| "learning_rate": 0.00019598310698107702, | |
| "loss": 11.1421, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.10358094110683634, | |
| "grad_norm": 1.203125, | |
| "learning_rate": 0.00019560357815343577, | |
| "loss": 11.1708, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.10654039656703167, | |
| "grad_norm": 0.52734375, | |
| "learning_rate": 0.00019520732146784491, | |
| "loss": 11.1091, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.109499852027227, | |
| "grad_norm": 0.67578125, | |
| "learning_rate": 0.0001947944062577507, | |
| "loss": 11.0413, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.11245930748742232, | |
| "grad_norm": 0.44921875, | |
| "learning_rate": 0.00019436490477135878, | |
| "loss": 11.0481, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.11541876294761765, | |
| "grad_norm": 0.640625, | |
| "learning_rate": 0.00019391889215899299, | |
| "loss": 11.1447, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.11837821840781296, | |
| "grad_norm": 1.203125, | |
| "learning_rate": 0.0001934564464599461, | |
| "loss": 10.974, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.11837821840781296, | |
| "eval_loss": 11.000988006591797, | |
| "eval_runtime": 37.2684, | |
| "eval_samples_per_second": 40.302, | |
| "eval_steps_per_second": 10.089, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.12133767386800828, | |
| "grad_norm": 0.390625, | |
| "learning_rate": 0.00019297764858882514, | |
| "loss": 10.9578, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.12429712932820361, | |
| "grad_norm": 0.484375, | |
| "learning_rate": 0.00019248258232139388, | |
| "loss": 10.9818, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.12725658478839894, | |
| "grad_norm": 0.703125, | |
| "learning_rate": 0.00019197133427991436, | |
| "loss": 11.0032, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.13021604024859426, | |
| "grad_norm": 0.93359375, | |
| "learning_rate": 0.00019144399391799043, | |
| "loss": 10.9693, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.1331754957087896, | |
| "grad_norm": 1.046875, | |
| "learning_rate": 0.00019090065350491626, | |
| "loss": 10.868, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.1361349511689849, | |
| "grad_norm": 0.5390625, | |
| "learning_rate": 0.0001903414081095315, | |
| "loss": 10.8865, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.13909440662918024, | |
| "grad_norm": 0.44921875, | |
| "learning_rate": 0.00018976635558358722, | |
| "loss": 10.8515, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.14205386208937557, | |
| "grad_norm": 0.62890625, | |
| "learning_rate": 0.00018917559654462474, | |
| "loss": 10.8165, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.1450133175495709, | |
| "grad_norm": 1.796875, | |
| "learning_rate": 0.00018856923435837022, | |
| "loss": 10.8031, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.1479727730097662, | |
| "grad_norm": 1.34375, | |
| "learning_rate": 0.0001879473751206489, | |
| "loss": 10.9148, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.15093222846996152, | |
| "grad_norm": 0.427734375, | |
| "learning_rate": 0.00018731012763882133, | |
| "loss": 10.7621, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.15389168393015684, | |
| "grad_norm": 0.453125, | |
| "learning_rate": 0.00018665760341274505, | |
| "loss": 10.7243, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.15685113939035217, | |
| "grad_norm": 0.60546875, | |
| "learning_rate": 0.00018598991661526572, | |
| "loss": 10.7943, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.1598105948505475, | |
| "grad_norm": 0.546875, | |
| "learning_rate": 0.00018530718407223974, | |
| "loss": 10.906, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.16277005031074282, | |
| "grad_norm": 0.92578125, | |
| "learning_rate": 0.00018460952524209355, | |
| "loss": 10.6987, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.16572950577093815, | |
| "grad_norm": 0.474609375, | |
| "learning_rate": 0.00018389706219492147, | |
| "loss": 10.7486, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.16868896123113347, | |
| "grad_norm": 0.50390625, | |
| "learning_rate": 0.00018316991959112716, | |
| "loss": 10.6635, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.1716484166913288, | |
| "grad_norm": 0.474609375, | |
| "learning_rate": 0.00018242822465961176, | |
| "loss": 10.7392, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.17460787215152412, | |
| "grad_norm": 0.640625, | |
| "learning_rate": 0.00018167210717551224, | |
| "loss": 10.7092, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.17756732761171945, | |
| "grad_norm": 0.95703125, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 10.6928, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.17756732761171945, | |
| "eval_loss": 10.68582820892334, | |
| "eval_runtime": 36.9332, | |
| "eval_samples_per_second": 40.668, | |
| "eval_steps_per_second": 10.181, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.18052678307191478, | |
| "grad_norm": 0.46484375, | |
| "learning_rate": 0.00018011713624460608, | |
| "loss": 10.6538, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.1834862385321101, | |
| "grad_norm": 0.46875, | |
| "learning_rate": 0.00017931855487268782, | |
| "loss": 10.6665, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.18644569399230543, | |
| "grad_norm": 0.5546875, | |
| "learning_rate": 0.0001785060950503568, | |
| "loss": 10.7167, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.18940514945250073, | |
| "grad_norm": 0.71484375, | |
| "learning_rate": 0.00017767989893455698, | |
| "loss": 10.6671, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.19236460491269605, | |
| "grad_norm": 0.80078125, | |
| "learning_rate": 0.00017684011108568592, | |
| "loss": 10.5523, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.19532406037289138, | |
| "grad_norm": 0.48046875, | |
| "learning_rate": 0.00017598687844230088, | |
| "loss": 10.5617, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.1982835158330867, | |
| "grad_norm": 0.478515625, | |
| "learning_rate": 0.00017512035029540885, | |
| "loss": 10.5959, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.20124297129328203, | |
| "grad_norm": 0.52734375, | |
| "learning_rate": 0.000174240678262345, | |
| "loss": 10.5951, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.20420242675347736, | |
| "grad_norm": 0.875, | |
| "learning_rate": 0.000173348016260244, | |
| "loss": 10.6666, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.20716188221367268, | |
| "grad_norm": 1.109375, | |
| "learning_rate": 0.00017244252047910892, | |
| "loss": 10.6388, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.210121337673868, | |
| "grad_norm": 0.54296875, | |
| "learning_rate": 0.00017152434935448256, | |
| "loss": 10.5324, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.21308079313406333, | |
| "grad_norm": 0.462890625, | |
| "learning_rate": 0.0001705936635397259, | |
| "loss": 10.5407, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.21604024859425866, | |
| "grad_norm": 0.6484375, | |
| "learning_rate": 0.00016965062587790823, | |
| "loss": 10.6078, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.218999704054454, | |
| "grad_norm": 0.57421875, | |
| "learning_rate": 0.00016869540137331445, | |
| "loss": 10.5359, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.2219591595146493, | |
| "grad_norm": 0.828125, | |
| "learning_rate": 0.00016772815716257412, | |
| "loss": 10.6545, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.22491861497484464, | |
| "grad_norm": 0.52734375, | |
| "learning_rate": 0.00016674906248541726, | |
| "loss": 10.5454, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.22787807043503996, | |
| "grad_norm": 1.296875, | |
| "learning_rate": 0.00016575828865506245, | |
| "loss": 10.511, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.2308375258952353, | |
| "grad_norm": 0.53515625, | |
| "learning_rate": 0.0001647560090282419, | |
| "loss": 10.6402, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.2337969813554306, | |
| "grad_norm": 0.69921875, | |
| "learning_rate": 0.000163742398974869, | |
| "loss": 10.5585, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.23675643681562591, | |
| "grad_norm": 1.1875, | |
| "learning_rate": 0.0001627176358473537, | |
| "loss": 10.9148, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.23675643681562591, | |
| "eval_loss": 10.609786033630371, | |
| "eval_runtime": 36.7987, | |
| "eval_samples_per_second": 40.817, | |
| "eval_steps_per_second": 10.218, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.23971589227582124, | |
| "grad_norm": 0.5390625, | |
| "learning_rate": 0.0001616818989495711, | |
| "loss": 10.5589, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.24267534773601657, | |
| "grad_norm": 0.49609375, | |
| "learning_rate": 0.00016063536950548826, | |
| "loss": 10.5171, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.2456348031962119, | |
| "grad_norm": 0.48828125, | |
| "learning_rate": 0.0001595782306274553, | |
| "loss": 10.5991, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.24859425865640722, | |
| "grad_norm": 0.6640625, | |
| "learning_rate": 0.00015851066728416618, | |
| "loss": 10.5204, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.25155371411660254, | |
| "grad_norm": 1.4296875, | |
| "learning_rate": 0.00015743286626829437, | |
| "loss": 10.7165, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.25451316957679787, | |
| "grad_norm": 0.5, | |
| "learning_rate": 0.00015634501616380967, | |
| "loss": 10.5418, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.2574726250369932, | |
| "grad_norm": 0.546875, | |
| "learning_rate": 0.00015524730731298134, | |
| "loss": 10.4562, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.2604320804971885, | |
| "grad_norm": 0.478515625, | |
| "learning_rate": 0.0001541399317830738, | |
| "loss": 10.5918, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.26339153595738385, | |
| "grad_norm": 0.6796875, | |
| "learning_rate": 0.0001530230833327405, | |
| "loss": 10.6648, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.2663509914175792, | |
| "grad_norm": 0.8359375, | |
| "learning_rate": 0.00015189695737812152, | |
| "loss": 10.5443, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.2693104468777745, | |
| "grad_norm": 0.470703125, | |
| "learning_rate": 0.0001507617509586517, | |
| "loss": 10.6068, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.2722699023379698, | |
| "grad_norm": 0.51171875, | |
| "learning_rate": 0.00014961766270258422, | |
| "loss": 10.4622, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.27522935779816515, | |
| "grad_norm": 0.5625, | |
| "learning_rate": 0.00014846489279223652, | |
| "loss": 10.5733, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.2781888132583605, | |
| "grad_norm": 0.7578125, | |
| "learning_rate": 0.0001473036429289641, | |
| "loss": 10.6282, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.2811482687185558, | |
| "grad_norm": 1.109375, | |
| "learning_rate": 0.0001461341162978688, | |
| "loss": 10.5981, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.28410772417875113, | |
| "grad_norm": 0.455078125, | |
| "learning_rate": 0.00014495651753224705, | |
| "loss": 10.5467, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.28706717963894646, | |
| "grad_norm": 0.5390625, | |
| "learning_rate": 0.00014377105267778518, | |
| "loss": 10.5648, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.2900266350991418, | |
| "grad_norm": 0.56640625, | |
| "learning_rate": 0.00014257792915650728, | |
| "loss": 10.5147, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.2929860905593371, | |
| "grad_norm": 0.59765625, | |
| "learning_rate": 0.00014137735573048233, | |
| "loss": 10.5981, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.2959455460195324, | |
| "grad_norm": 1.15625, | |
| "learning_rate": 0.00014016954246529696, | |
| "loss": 10.6606, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.2959455460195324, | |
| "eval_loss": 10.593103408813477, | |
| "eval_runtime": 36.8208, | |
| "eval_samples_per_second": 40.792, | |
| "eval_steps_per_second": 10.212, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.2989050014797277, | |
| "grad_norm": 0.462890625, | |
| "learning_rate": 0.00013895470069330004, | |
| "loss": 10.6059, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 0.30186445693992303, | |
| "grad_norm": 0.578125, | |
| "learning_rate": 0.00013773304297662559, | |
| "loss": 10.4836, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.30482391240011836, | |
| "grad_norm": 0.55078125, | |
| "learning_rate": 0.00013650478307000057, | |
| "loss": 10.5972, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 0.3077833678603137, | |
| "grad_norm": 0.859375, | |
| "learning_rate": 0.00013527013588334415, | |
| "loss": 10.5497, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.310742823320509, | |
| "grad_norm": 1.96875, | |
| "learning_rate": 0.00013402931744416433, | |
| "loss": 10.7067, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.31370227878070434, | |
| "grad_norm": 0.466796875, | |
| "learning_rate": 0.00013278254485975976, | |
| "loss": 10.5917, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.31666173424089966, | |
| "grad_norm": 0.498046875, | |
| "learning_rate": 0.00013153003627923218, | |
| "loss": 10.5851, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 0.319621189701095, | |
| "grad_norm": 0.5, | |
| "learning_rate": 0.00013027201085531634, | |
| "loss": 10.6517, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.3225806451612903, | |
| "grad_norm": 0.69921875, | |
| "learning_rate": 0.00012900868870603503, | |
| "loss": 10.6547, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 0.32554010062148564, | |
| "grad_norm": 1.3046875, | |
| "learning_rate": 0.00012774029087618446, | |
| "loss": 10.8434, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.32849955608168097, | |
| "grad_norm": 0.53125, | |
| "learning_rate": 0.00012646703929865817, | |
| "loss": 10.4926, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 0.3314590115418763, | |
| "grad_norm": 0.51171875, | |
| "learning_rate": 0.00012518915675561483, | |
| "loss": 10.5161, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.3344184670020716, | |
| "grad_norm": 0.5390625, | |
| "learning_rate": 0.00012390686683949798, | |
| "loss": 10.5611, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 0.33737792246226694, | |
| "grad_norm": 0.921875, | |
| "learning_rate": 0.00012262039391391404, | |
| "loss": 10.5226, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.34033737792246227, | |
| "grad_norm": 1.5390625, | |
| "learning_rate": 0.0001213299630743747, | |
| "loss": 10.7565, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.3432968333826576, | |
| "grad_norm": 0.466796875, | |
| "learning_rate": 0.00012003580010891213, | |
| "loss": 10.5453, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.3462562888428529, | |
| "grad_norm": 0.5703125, | |
| "learning_rate": 0.00011873813145857249, | |
| "loss": 10.4892, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 0.34921574430304825, | |
| "grad_norm": 0.59765625, | |
| "learning_rate": 0.00011743718417779517, | |
| "loss": 10.6995, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.3521751997632436, | |
| "grad_norm": 0.69140625, | |
| "learning_rate": 0.00011613318589468511, | |
| "loss": 10.6222, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 0.3551346552234389, | |
| "grad_norm": 1.0390625, | |
| "learning_rate": 0.0001148263647711842, | |
| "loss": 10.5748, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.3551346552234389, | |
| "eval_loss": 10.591147422790527, | |
| "eval_runtime": 36.8986, | |
| "eval_samples_per_second": 40.706, | |
| "eval_steps_per_second": 10.19, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.3580941106836342, | |
| "grad_norm": 0.57421875, | |
| "learning_rate": 0.0001135169494631497, | |
| "loss": 10.541, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 0.36105356614382955, | |
| "grad_norm": 0.58984375, | |
| "learning_rate": 0.00011220516908034601, | |
| "loss": 10.5805, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 0.3640130216040249, | |
| "grad_norm": 0.52734375, | |
| "learning_rate": 0.00011089125314635726, | |
| "loss": 10.6207, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 0.3669724770642202, | |
| "grad_norm": 0.734375, | |
| "learning_rate": 0.00010957543155842702, | |
| "loss": 10.6731, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.36993193252441553, | |
| "grad_norm": 0.765625, | |
| "learning_rate": 0.00010825793454723325, | |
| "loss": 10.5913, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.37289138798461086, | |
| "grad_norm": 0.490234375, | |
| "learning_rate": 0.00010693899263660441, | |
| "loss": 10.5151, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.3758508434448062, | |
| "grad_norm": 0.515625, | |
| "learning_rate": 0.00010561883660318455, | |
| "loss": 10.5782, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 0.37881029890500145, | |
| "grad_norm": 1.1015625, | |
| "learning_rate": 0.00010429769743605407, | |
| "loss": 10.5898, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 0.3817697543651968, | |
| "grad_norm": 0.60546875, | |
| "learning_rate": 0.00010297580629631325, | |
| "loss": 10.5216, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 0.3847292098253921, | |
| "grad_norm": 1.4921875, | |
| "learning_rate": 0.00010165339447663587, | |
| "loss": 10.4868, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.38768866528558743, | |
| "grad_norm": 0.44140625, | |
| "learning_rate": 0.00010033069336079952, | |
| "loss": 10.6363, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 0.39064812074578276, | |
| "grad_norm": 0.515625, | |
| "learning_rate": 9.900793438320037e-05, | |
| "loss": 10.55, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 0.3936075762059781, | |
| "grad_norm": 0.703125, | |
| "learning_rate": 9.768534898835862e-05, | |
| "loss": 10.6171, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 0.3965670316661734, | |
| "grad_norm": 0.69140625, | |
| "learning_rate": 9.636316859042259e-05, | |
| "loss": 10.6343, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 0.39952648712636873, | |
| "grad_norm": 1.171875, | |
| "learning_rate": 9.504162453267777e-05, | |
| "loss": 10.6261, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.40248594258656406, | |
| "grad_norm": 0.49609375, | |
| "learning_rate": 9.372094804706867e-05, | |
| "loss": 10.566, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 0.4054453980467594, | |
| "grad_norm": 0.54296875, | |
| "learning_rate": 9.24013702137397e-05, | |
| "loss": 10.5186, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 0.4084048535069547, | |
| "grad_norm": 0.5546875, | |
| "learning_rate": 9.108312192060298e-05, | |
| "loss": 10.6343, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 0.41136430896715004, | |
| "grad_norm": 0.83984375, | |
| "learning_rate": 8.97664338229395e-05, | |
| "loss": 10.6551, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 0.41432376442734536, | |
| "grad_norm": 2.859375, | |
| "learning_rate": 8.845153630304139e-05, | |
| "loss": 10.6436, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.41432376442734536, | |
| "eval_loss": 10.585193634033203, | |
| "eval_runtime": 37.153, | |
| "eval_samples_per_second": 40.427, | |
| "eval_steps_per_second": 10.12, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.4172832198875407, | |
| "grad_norm": 0.53125, | |
| "learning_rate": 8.713865942990141e-05, | |
| "loss": 10.5189, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 0.420242675347736, | |
| "grad_norm": 0.53515625, | |
| "learning_rate": 8.582803291895758e-05, | |
| "loss": 10.4783, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 0.42320213080793134, | |
| "grad_norm": 0.5390625, | |
| "learning_rate": 8.451988609189987e-05, | |
| "loss": 10.6285, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 0.42616158626812667, | |
| "grad_norm": 0.63671875, | |
| "learning_rate": 8.321444783654524e-05, | |
| "loss": 10.7481, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 0.429121041728322, | |
| "grad_norm": 1.0703125, | |
| "learning_rate": 8.191194656678904e-05, | |
| "loss": 10.6971, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.4320804971885173, | |
| "grad_norm": 0.5078125, | |
| "learning_rate": 8.061261018263919e-05, | |
| "loss": 10.5323, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 0.43503995264871265, | |
| "grad_norm": 0.51171875, | |
| "learning_rate": 7.931666603034033e-05, | |
| "loss": 10.4634, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 0.437999408108908, | |
| "grad_norm": 0.6171875, | |
| "learning_rate": 7.80243408625947e-05, | |
| "loss": 10.5384, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 0.4409588635691033, | |
| "grad_norm": 0.76953125, | |
| "learning_rate": 7.673586079888698e-05, | |
| "loss": 10.699, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 0.4439183190292986, | |
| "grad_norm": 1.5390625, | |
| "learning_rate": 7.54514512859201e-05, | |
| "loss": 10.5729, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.44687777448949395, | |
| "grad_norm": 0.455078125, | |
| "learning_rate": 7.417133705816837e-05, | |
| "loss": 10.5262, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 0.4498372299496893, | |
| "grad_norm": 0.6640625, | |
| "learning_rate": 7.289574209855559e-05, | |
| "loss": 10.5102, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 0.4527966854098846, | |
| "grad_norm": 0.5703125, | |
| "learning_rate": 7.16248895992645e-05, | |
| "loss": 10.6538, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 0.45575614087007993, | |
| "grad_norm": 0.83203125, | |
| "learning_rate": 7.035900192268464e-05, | |
| "loss": 10.4972, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 0.45871559633027525, | |
| "grad_norm": 0.90625, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 10.646, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.4616750517904706, | |
| "grad_norm": 0.494140625, | |
| "learning_rate": 6.784300610496048e-05, | |
| "loss": 10.564, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 0.46463450725066585, | |
| "grad_norm": 0.57421875, | |
| "learning_rate": 6.65933381902329e-05, | |
| "loss": 10.5419, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 0.4675939627108612, | |
| "grad_norm": 0.5703125, | |
| "learning_rate": 6.534951547402322e-05, | |
| "loss": 10.6451, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 0.4705534181710565, | |
| "grad_norm": 0.7578125, | |
| "learning_rate": 6.411175558929152e-05, | |
| "loss": 10.7074, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 0.47351287363125183, | |
| "grad_norm": 0.98046875, | |
| "learning_rate": 6.28802751081779e-05, | |
| "loss": 10.5774, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.47351287363125183, | |
| "eval_loss": 10.587952613830566, | |
| "eval_runtime": 36.8828, | |
| "eval_samples_per_second": 40.724, | |
| "eval_steps_per_second": 10.194, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.47647232909144716, | |
| "grad_norm": 0.67578125, | |
| "learning_rate": 6.165528950410884e-05, | |
| "loss": 10.5619, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 0.4794317845516425, | |
| "grad_norm": 0.515625, | |
| "learning_rate": 6.0437013114095195e-05, | |
| "loss": 10.5488, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 0.4823912400118378, | |
| "grad_norm": 0.7421875, | |
| "learning_rate": 5.922565910122967e-05, | |
| "loss": 10.5892, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 0.48535069547203313, | |
| "grad_norm": 1.25, | |
| "learning_rate": 5.8021439417389444e-05, | |
| "loss": 10.5812, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 0.48831015093222846, | |
| "grad_norm": 1.03125, | |
| "learning_rate": 5.6824564766150726e-05, | |
| "loss": 10.6534, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.4912696063924238, | |
| "grad_norm": 0.71484375, | |
| "learning_rate": 5.563524456592163e-05, | |
| "loss": 10.5558, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 0.4942290618526191, | |
| "grad_norm": 0.52734375, | |
| "learning_rate": 5.4453686913300074e-05, | |
| "loss": 10.5613, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 0.49718851731281444, | |
| "grad_norm": 0.59375, | |
| "learning_rate": 5.328009854666303e-05, | |
| "loss": 10.5469, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 0.5001479727730098, | |
| "grad_norm": 0.9140625, | |
| "learning_rate": 5.2114684809993044e-05, | |
| "loss": 10.5022, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 0.5031074282332051, | |
| "grad_norm": 1.546875, | |
| "learning_rate": 5.095764961694922e-05, | |
| "loss": 10.6632, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.5060668836934004, | |
| "grad_norm": 0.443359375, | |
| "learning_rate": 4.980919541518796e-05, | |
| "loss": 10.4854, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 0.5090263391535957, | |
| "grad_norm": 0.54296875, | |
| "learning_rate": 4.866952315094088e-05, | |
| "loss": 10.5273, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 0.511985794613791, | |
| "grad_norm": 0.54296875, | |
| "learning_rate": 4.753883223385467e-05, | |
| "loss": 10.6483, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 0.5149452500739864, | |
| "grad_norm": 0.62890625, | |
| "learning_rate": 4.6417320502100316e-05, | |
| "loss": 10.6292, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 0.5179047055341817, | |
| "grad_norm": 1.7421875, | |
| "learning_rate": 4.530518418775733e-05, | |
| "loss": 10.7312, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.520864160994377, | |
| "grad_norm": 0.53515625, | |
| "learning_rate": 4.4202617882478405e-05, | |
| "loss": 10.5379, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 0.5238236164545723, | |
| "grad_norm": 0.45703125, | |
| "learning_rate": 4.310981450344189e-05, | |
| "loss": 10.4813, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 0.5267830719147677, | |
| "grad_norm": 0.6328125, | |
| "learning_rate": 4.2026965259596666e-05, | |
| "loss": 10.5114, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 0.529742527374963, | |
| "grad_norm": 0.62109375, | |
| "learning_rate": 4.0954259618206295e-05, | |
| "loss": 10.5907, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 0.5327019828351583, | |
| "grad_norm": 2.421875, | |
| "learning_rate": 3.9891885271697496e-05, | |
| "loss": 10.707, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.5327019828351583, | |
| "eval_loss": 10.581239700317383, | |
| "eval_runtime": 36.7089, | |
| "eval_samples_per_second": 40.917, | |
| "eval_steps_per_second": 10.243, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.5356614382953536, | |
| "grad_norm": 0.474609375, | |
| "learning_rate": 3.884002810481958e-05, | |
| "loss": 10.5549, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 0.538620893755549, | |
| "grad_norm": 0.4765625, | |
| "learning_rate": 3.779887216211995e-05, | |
| "loss": 10.4945, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 0.5415803492157443, | |
| "grad_norm": 0.6484375, | |
| "learning_rate": 3.676859961574162e-05, | |
| "loss": 10.5344, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 0.5445398046759397, | |
| "grad_norm": 0.66015625, | |
| "learning_rate": 3.574939073354838e-05, | |
| "loss": 10.549, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 0.5474992601361349, | |
| "grad_norm": 0.81640625, | |
| "learning_rate": 3.4741423847583134e-05, | |
| "loss": 10.5827, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 0.5504587155963303, | |
| "grad_norm": 0.62109375, | |
| "learning_rate": 3.3744875322865034e-05, | |
| "loss": 10.5722, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 0.5534181710565256, | |
| "grad_norm": 0.578125, | |
| "learning_rate": 3.275991952653054e-05, | |
| "loss": 10.546, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 0.556377626516721, | |
| "grad_norm": 0.6328125, | |
| "learning_rate": 3.178672879732435e-05, | |
| "loss": 10.6028, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 0.5593370819769162, | |
| "grad_norm": 0.58984375, | |
| "learning_rate": 3.0825473415445074e-05, | |
| "loss": 10.5864, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 0.5622965374371116, | |
| "grad_norm": 1.4140625, | |
| "learning_rate": 2.9876321572751144e-05, | |
| "loss": 10.7022, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.5652559928973069, | |
| "grad_norm": 0.5, | |
| "learning_rate": 2.8939439343332086e-05, | |
| "loss": 10.5185, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 0.5682154483575023, | |
| "grad_norm": 0.55078125, | |
| "learning_rate": 2.8014990654450325e-05, | |
| "loss": 10.4229, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 0.5711749038176975, | |
| "grad_norm": 0.74609375, | |
| "learning_rate": 2.7103137257858868e-05, | |
| "loss": 10.5086, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 0.5741343592778929, | |
| "grad_norm": 0.609375, | |
| "learning_rate": 2.6204038701499056e-05, | |
| "loss": 10.6154, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 0.5770938147380882, | |
| "grad_norm": 1.3671875, | |
| "learning_rate": 2.5317852301584643e-05, | |
| "loss": 10.5829, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 0.5800532701982836, | |
| "grad_norm": 0.5390625, | |
| "learning_rate": 2.4444733115075823e-05, | |
| "loss": 10.5711, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 0.5830127256584788, | |
| "grad_norm": 0.5078125, | |
| "learning_rate": 2.3584833912548888e-05, | |
| "loss": 10.5423, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 0.5859721811186742, | |
| "grad_norm": 0.66796875, | |
| "learning_rate": 2.2738305151465645e-05, | |
| "loss": 10.499, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 0.5889316365788695, | |
| "grad_norm": 0.6640625, | |
| "learning_rate": 2.190529494984782e-05, | |
| "loss": 10.5815, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 0.5918910920390648, | |
| "grad_norm": 1.0390625, | |
| "learning_rate": 2.1085949060360654e-05, | |
| "loss": 10.5304, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.5918910920390648, | |
| "eval_loss": 10.586631774902344, | |
| "eval_runtime": 37.0599, | |
| "eval_samples_per_second": 40.529, | |
| "eval_steps_per_second": 10.146, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.5948505474992601, | |
| "grad_norm": 0.52734375, | |
| "learning_rate": 2.0280410844810428e-05, | |
| "loss": 10.5051, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 0.5978100029594554, | |
| "grad_norm": 0.51953125, | |
| "learning_rate": 1.9488821249060297e-05, | |
| "loss": 10.497, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 0.6007694584196508, | |
| "grad_norm": 0.58984375, | |
| "learning_rate": 1.871131877836879e-05, | |
| "loss": 10.5321, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 0.6037289138798461, | |
| "grad_norm": 0.609375, | |
| "learning_rate": 1.7948039473155554e-05, | |
| "loss": 10.5627, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 0.6066883693400414, | |
| "grad_norm": 1.2734375, | |
| "learning_rate": 1.7199116885197995e-05, | |
| "loss": 10.6749, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 0.6096478248002367, | |
| "grad_norm": 0.46875, | |
| "learning_rate": 1.646468205426377e-05, | |
| "loss": 10.5196, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 0.6126072802604321, | |
| "grad_norm": 0.51953125, | |
| "learning_rate": 1.5744863485182537e-05, | |
| "loss": 10.5294, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 0.6155667357206274, | |
| "grad_norm": 0.5546875, | |
| "learning_rate": 1.5039787125361326e-05, | |
| "loss": 10.5178, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 0.6185261911808227, | |
| "grad_norm": 0.703125, | |
| "learning_rate": 1.4349576342747462e-05, | |
| "loss": 10.6195, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 0.621485646641018, | |
| "grad_norm": 0.94921875, | |
| "learning_rate": 1.3674351904242611e-05, | |
| "loss": 10.5954, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.6244451021012134, | |
| "grad_norm": 0.458984375, | |
| "learning_rate": 1.3014231954572287e-05, | |
| "loss": 10.5128, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 0.6274045575614087, | |
| "grad_norm": 0.52734375, | |
| "learning_rate": 1.2369331995613665e-05, | |
| "loss": 10.4853, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 0.630364013021604, | |
| "grad_norm": 0.58984375, | |
| "learning_rate": 1.173976486618631e-05, | |
| "loss": 10.5693, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 0.6333234684817993, | |
| "grad_norm": 0.5859375, | |
| "learning_rate": 1.1125640722308628e-05, | |
| "loss": 10.6354, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 0.6362829239419947, | |
| "grad_norm": 1.7734375, | |
| "learning_rate": 1.0527067017923654e-05, | |
| "loss": 10.6234, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 0.63924237940219, | |
| "grad_norm": 0.486328125, | |
| "learning_rate": 9.944148486097793e-06, | |
| "loss": 10.5555, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 0.6422018348623854, | |
| "grad_norm": 0.515625, | |
| "learning_rate": 9.376987120695545e-06, | |
| "loss": 10.5214, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 0.6451612903225806, | |
| "grad_norm": 0.62109375, | |
| "learning_rate": 8.825682158533554e-06, | |
| "loss": 10.5274, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 0.648120745782776, | |
| "grad_norm": 0.79296875, | |
| "learning_rate": 8.290330062017016e-06, | |
| "loss": 10.6728, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 0.6510802012429713, | |
| "grad_norm": 1.109375, | |
| "learning_rate": 7.771024502261526e-06, | |
| "loss": 10.6148, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.6510802012429713, | |
| "eval_loss": 10.584245681762695, | |
| "eval_runtime": 37.0238, | |
| "eval_samples_per_second": 40.569, | |
| "eval_steps_per_second": 10.156, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.6540396567031667, | |
| "grad_norm": 0.486328125, | |
| "learning_rate": 7.267856342703461e-06, | |
| "loss": 10.5768, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 0.6569991121633619, | |
| "grad_norm": 0.51171875, | |
| "learning_rate": 6.780913623201346e-06, | |
| "loss": 10.4856, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 0.6599585676235573, | |
| "grad_norm": 0.859375, | |
| "learning_rate": 6.310281544631546e-06, | |
| "loss": 10.6694, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 0.6629180230837526, | |
| "grad_norm": 0.57421875, | |
| "learning_rate": 5.856042453980526e-06, | |
| "loss": 10.5306, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 0.665877478543948, | |
| "grad_norm": 0.80078125, | |
| "learning_rate": 5.418275829936537e-06, | |
| "loss": 10.525, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 0.6688369340041432, | |
| "grad_norm": 0.55859375, | |
| "learning_rate": 4.997058268983135e-06, | |
| "loss": 10.6271, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 0.6717963894643386, | |
| "grad_norm": 0.53125, | |
| "learning_rate": 4.592463471997022e-06, | |
| "loss": 10.4891, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 0.6747558449245339, | |
| "grad_norm": 0.546875, | |
| "learning_rate": 4.204562231352516e-06, | |
| "loss": 10.5647, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 0.6777153003847292, | |
| "grad_norm": 0.63671875, | |
| "learning_rate": 3.83342241853496e-06, | |
| "loss": 10.506, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 0.6806747558449245, | |
| "grad_norm": 0.87109375, | |
| "learning_rate": 3.4791089722651436e-06, | |
| "loss": 10.6414, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.6836342113051198, | |
| "grad_norm": 0.478515625, | |
| "learning_rate": 3.1416838871368924e-06, | |
| "loss": 10.4905, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 0.6865936667653152, | |
| "grad_norm": 0.55078125, | |
| "learning_rate": 2.821206202769899e-06, | |
| "loss": 10.5434, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 0.6895531222255105, | |
| "grad_norm": 0.796875, | |
| "learning_rate": 2.5177319934794e-06, | |
| "loss": 10.6355, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 0.6925125776857058, | |
| "grad_norm": 0.8984375, | |
| "learning_rate": 2.2313143584648423e-06, | |
| "loss": 10.5647, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 0.6954720331459011, | |
| "grad_norm": 0.84765625, | |
| "learning_rate": 1.9620034125190644e-06, | |
| "loss": 10.7043, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 0.6984314886060965, | |
| "grad_norm": 0.5, | |
| "learning_rate": 1.7098462772596302e-06, | |
| "loss": 10.4649, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 0.7013909440662918, | |
| "grad_norm": 0.5078125, | |
| "learning_rate": 1.4748870728839347e-06, | |
| "loss": 10.4574, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 0.7043503995264871, | |
| "grad_norm": 0.578125, | |
| "learning_rate": 1.2571669104494256e-06, | |
| "loss": 10.4982, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 0.7073098549866824, | |
| "grad_norm": 0.9453125, | |
| "learning_rate": 1.0567238846803996e-06, | |
| "loss": 10.5488, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 0.7102693104468778, | |
| "grad_norm": 0.796875, | |
| "learning_rate": 8.735930673024806e-07, | |
| "loss": 10.4931, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.7102693104468778, | |
| "eval_loss": 10.585838317871094, | |
| "eval_runtime": 36.7691, | |
| "eval_samples_per_second": 40.85, | |
| "eval_steps_per_second": 10.226, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.7132287659070731, | |
| "grad_norm": 0.498046875, | |
| "learning_rate": 7.078065009060941e-07, | |
| "loss": 10.4885, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 0.7161882213672685, | |
| "grad_norm": 0.50390625, | |
| "learning_rate": 5.593931933399854e-07, | |
| "loss": 10.5281, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 0.7191476768274637, | |
| "grad_norm": 0.78125, | |
| "learning_rate": 4.2837911263562404e-07, | |
| "loss": 10.4985, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 0.7221071322876591, | |
| "grad_norm": 0.6328125, | |
| "learning_rate": 3.1478718246357173e-07, | |
| "loss": 10.6174, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 0.7250665877478544, | |
| "grad_norm": 0.99609375, | |
| "learning_rate": 2.1863727812254653e-07, | |
| "loss": 10.7935, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 0.7280260432080498, | |
| "grad_norm": 0.51953125, | |
| "learning_rate": 1.3994622306173765e-07, | |
| "loss": 10.5046, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 0.730985498668245, | |
| "grad_norm": 0.484375, | |
| "learning_rate": 7.872778593728258e-08, | |
| "loss": 10.5646, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 0.7339449541284404, | |
| "grad_norm": 0.6953125, | |
| "learning_rate": 3.499267820307184e-08, | |
| "loss": 10.5978, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 0.7369044095886357, | |
| "grad_norm": 0.6484375, | |
| "learning_rate": 8.748552236603757e-09, | |
| "loss": 10.6151, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 0.7398638650488311, | |
| "grad_norm": 1.140625, | |
| "learning_rate": 0.0, | |
| "loss": 10.6938, | |
| "step": 2500 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 2500, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 400, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 244972781568.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |