| { | |
| "best_metric": 1.53940749168396, | |
| "best_model_checkpoint": "data/paligemma2-3b-pt-224-sft-lora-vamos_10pct_gpt5_mini_cocoqa_localized_narratives_fixed/checkpoint-3119", | |
| "epoch": 1.0, | |
| "eval_steps": 3119, | |
| "global_step": 6237, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000160333493666827, | |
| "grad_norm": 5.209284782409668, | |
| "learning_rate": 1.6025641025641025e-07, | |
| "loss": 8.2025, | |
| "mean_token_accuracy": 0.257368803024292, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00320666987333654, | |
| "grad_norm": 5.846069812774658, | |
| "learning_rate": 3.205128205128205e-06, | |
| "loss": 8.8548, | |
| "mean_token_accuracy": 0.2286823886005502, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00641333974667308, | |
| "grad_norm": 6.527371406555176, | |
| "learning_rate": 6.41025641025641e-06, | |
| "loss": 8.6095, | |
| "mean_token_accuracy": 0.236174263805151, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.00962000962000962, | |
| "grad_norm": 6.7473320960998535, | |
| "learning_rate": 9.615384615384616e-06, | |
| "loss": 7.0858, | |
| "mean_token_accuracy": 0.24544834867119789, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.01282667949334616, | |
| "grad_norm": 3.6053383350372314, | |
| "learning_rate": 1.282051282051282e-05, | |
| "loss": 5.0951, | |
| "mean_token_accuracy": 0.2442556582391262, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.0160333493666827, | |
| "grad_norm": 1.8141255378723145, | |
| "learning_rate": 1.602564102564103e-05, | |
| "loss": 4.0162, | |
| "mean_token_accuracy": 0.29175431579351424, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.01924001924001924, | |
| "grad_norm": 1.9441587924957275, | |
| "learning_rate": 1.923076923076923e-05, | |
| "loss": 3.3901, | |
| "mean_token_accuracy": 0.33477348536252977, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.02244668911335578, | |
| "grad_norm": 2.866448402404785, | |
| "learning_rate": 2.2435897435897437e-05, | |
| "loss": 3.0645, | |
| "mean_token_accuracy": 0.36781402975320815, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.02565335898669232, | |
| "grad_norm": 6.173582553863525, | |
| "learning_rate": 2.564102564102564e-05, | |
| "loss": 2.8851, | |
| "mean_token_accuracy": 0.3857575759291649, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.02886002886002886, | |
| "grad_norm": 2.632821798324585, | |
| "learning_rate": 2.8846153846153845e-05, | |
| "loss": 2.625, | |
| "mean_token_accuracy": 0.42856554985046386, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.0320666987333654, | |
| "grad_norm": 3.801175594329834, | |
| "learning_rate": 3.205128205128206e-05, | |
| "loss": 2.5486, | |
| "mean_token_accuracy": 0.44293054938316345, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.03527336860670194, | |
| "grad_norm": 2.8042311668395996, | |
| "learning_rate": 3.525641025641026e-05, | |
| "loss": 2.4267, | |
| "mean_token_accuracy": 0.46162763684988023, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.03848003848003848, | |
| "grad_norm": 5.13622522354126, | |
| "learning_rate": 3.846153846153846e-05, | |
| "loss": 2.3457, | |
| "mean_token_accuracy": 0.46204862743616104, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.04168670835337502, | |
| "grad_norm": 8.156232833862305, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 2.3276, | |
| "mean_token_accuracy": 0.4628546267747879, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.04489337822671156, | |
| "grad_norm": 5.940677642822266, | |
| "learning_rate": 4.4871794871794874e-05, | |
| "loss": 2.3121, | |
| "mean_token_accuracy": 0.4677517533302307, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.0481000481000481, | |
| "grad_norm": 3.2402215003967285, | |
| "learning_rate": 4.8076923076923084e-05, | |
| "loss": 2.2948, | |
| "mean_token_accuracy": 0.4685308575630188, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.05130671797338464, | |
| "grad_norm": 4.654311656951904, | |
| "learning_rate": 5.128205128205128e-05, | |
| "loss": 2.2764, | |
| "mean_token_accuracy": 0.46919394135475156, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.05451338784672118, | |
| "grad_norm": 6.181347370147705, | |
| "learning_rate": 5.448717948717948e-05, | |
| "loss": 2.2516, | |
| "mean_token_accuracy": 0.4718445986509323, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.05772005772005772, | |
| "grad_norm": 4.977773189544678, | |
| "learning_rate": 5.769230769230769e-05, | |
| "loss": 2.3078, | |
| "mean_token_accuracy": 0.46173652708530427, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.06092672759339426, | |
| "grad_norm": 2.649177074432373, | |
| "learning_rate": 6.089743589743589e-05, | |
| "loss": 2.2364, | |
| "mean_token_accuracy": 0.4723318055272102, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.0641333974667308, | |
| "grad_norm": 2.475168228149414, | |
| "learning_rate": 6.410256410256412e-05, | |
| "loss": 2.2404, | |
| "mean_token_accuracy": 0.4773345053195953, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.06734006734006734, | |
| "grad_norm": 3.376347541809082, | |
| "learning_rate": 6.730769230769232e-05, | |
| "loss": 2.1923, | |
| "mean_token_accuracy": 0.48165750354528425, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.07054673721340388, | |
| "grad_norm": 2.1181466579437256, | |
| "learning_rate": 7.051282051282052e-05, | |
| "loss": 2.1944, | |
| "mean_token_accuracy": 0.47836676687002183, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.07375340708674041, | |
| "grad_norm": 3.304994583129883, | |
| "learning_rate": 7.371794871794872e-05, | |
| "loss": 2.2055, | |
| "mean_token_accuracy": 0.47685392051935194, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.07696007696007696, | |
| "grad_norm": 3.5151872634887695, | |
| "learning_rate": 7.692307692307693e-05, | |
| "loss": 2.171, | |
| "mean_token_accuracy": 0.4798412054777145, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.0801667468334135, | |
| "grad_norm": 2.439455509185791, | |
| "learning_rate": 8.012820512820514e-05, | |
| "loss": 2.1592, | |
| "mean_token_accuracy": 0.48496305793523786, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.08337341670675004, | |
| "grad_norm": 3.069302797317505, | |
| "learning_rate": 8.333333333333334e-05, | |
| "loss": 2.0884, | |
| "mean_token_accuracy": 0.4890993982553482, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.08658008658008658, | |
| "grad_norm": 5.592751979827881, | |
| "learning_rate": 8.653846153846155e-05, | |
| "loss": 2.1425, | |
| "mean_token_accuracy": 0.48478382378816604, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.08978675645342311, | |
| "grad_norm": 2.7817585468292236, | |
| "learning_rate": 8.974358974358975e-05, | |
| "loss": 2.1501, | |
| "mean_token_accuracy": 0.4846224099397659, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.09299342632675967, | |
| "grad_norm": 3.0570271015167236, | |
| "learning_rate": 9.294871794871795e-05, | |
| "loss": 2.1297, | |
| "mean_token_accuracy": 0.4879722028970718, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.0962000962000962, | |
| "grad_norm": 2.257469415664673, | |
| "learning_rate": 9.615384615384617e-05, | |
| "loss": 2.1088, | |
| "mean_token_accuracy": 0.4889796242117882, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.09940676607343274, | |
| "grad_norm": 5.005424499511719, | |
| "learning_rate": 9.935897435897437e-05, | |
| "loss": 2.1248, | |
| "mean_token_accuracy": 0.48695541769266126, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.10261343594676928, | |
| "grad_norm": 2.763110637664795, | |
| "learning_rate": 9.999799512762136e-05, | |
| "loss": 2.0852, | |
| "mean_token_accuracy": 0.4945754811167717, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.10582010582010581, | |
| "grad_norm": 2.5508882999420166, | |
| "learning_rate": 9.998985060913877e-05, | |
| "loss": 2.1155, | |
| "mean_token_accuracy": 0.48479859828948973, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.10902677569344237, | |
| "grad_norm": 1.9309931993484497, | |
| "learning_rate": 9.99754421597847e-05, | |
| "loss": 2.0774, | |
| "mean_token_accuracy": 0.4935262441635132, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.1122334455667789, | |
| "grad_norm": 2.175483465194702, | |
| "learning_rate": 9.995477158499624e-05, | |
| "loss": 2.0698, | |
| "mean_token_accuracy": 0.4930373579263687, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.11544011544011544, | |
| "grad_norm": 2.2829439640045166, | |
| "learning_rate": 9.992784147488018e-05, | |
| "loss": 2.064, | |
| "mean_token_accuracy": 0.4933862343430519, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.11864678531345198, | |
| "grad_norm": 1.5809357166290283, | |
| "learning_rate": 9.989465520388845e-05, | |
| "loss": 2.0323, | |
| "mean_token_accuracy": 0.5016711667180062, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.12185345518678851, | |
| "grad_norm": 2.230652332305908, | |
| "learning_rate": 9.985521693039529e-05, | |
| "loss": 2.075, | |
| "mean_token_accuracy": 0.4931314527988434, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.12506012506012507, | |
| "grad_norm": 1.8354729413986206, | |
| "learning_rate": 9.980953159617621e-05, | |
| "loss": 2.0748, | |
| "mean_token_accuracy": 0.4964547500014305, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.1282667949334616, | |
| "grad_norm": 2.15897274017334, | |
| "learning_rate": 9.975760492578874e-05, | |
| "loss": 2.0301, | |
| "mean_token_accuracy": 0.4994760677218437, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.13147346480679814, | |
| "grad_norm": 2.6074705123901367, | |
| "learning_rate": 9.969944342585508e-05, | |
| "loss": 1.9838, | |
| "mean_token_accuracy": 0.5075768753886223, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.13468013468013468, | |
| "grad_norm": 1.7504245042800903, | |
| "learning_rate": 9.963505438424693e-05, | |
| "loss": 2.0732, | |
| "mean_token_accuracy": 0.49125437140464784, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.13788680455347122, | |
| "grad_norm": 2.214726686477661, | |
| "learning_rate": 9.956444586917213e-05, | |
| "loss": 2.0329, | |
| "mean_token_accuracy": 0.4968407765030861, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.14109347442680775, | |
| "grad_norm": 1.6134241819381714, | |
| "learning_rate": 9.948762672816377e-05, | |
| "loss": 2.0392, | |
| "mean_token_accuracy": 0.4989665150642395, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.1443001443001443, | |
| "grad_norm": 1.3124563694000244, | |
| "learning_rate": 9.94046065869715e-05, | |
| "loss": 2.0265, | |
| "mean_token_accuracy": 0.5022040411829949, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.14750681417348083, | |
| "grad_norm": 2.182892084121704, | |
| "learning_rate": 9.931539584835553e-05, | |
| "loss": 2.0258, | |
| "mean_token_accuracy": 0.4994161993265152, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.1507134840468174, | |
| "grad_norm": 2.158780813217163, | |
| "learning_rate": 9.922000569078288e-05, | |
| "loss": 2.038, | |
| "mean_token_accuracy": 0.49309421628713607, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.15392015392015393, | |
| "grad_norm": 1.8986632823944092, | |
| "learning_rate": 9.911844806702692e-05, | |
| "loss": 2.0521, | |
| "mean_token_accuracy": 0.4916775792837143, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.15712682379349047, | |
| "grad_norm": 2.2148079872131348, | |
| "learning_rate": 9.901073570266946e-05, | |
| "loss": 2.046, | |
| "mean_token_accuracy": 0.4920832559466362, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.160333493666827, | |
| "grad_norm": 2.105100393295288, | |
| "learning_rate": 9.889688209450627e-05, | |
| "loss": 2.0154, | |
| "mean_token_accuracy": 0.5017145529389382, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.16354016354016354, | |
| "grad_norm": 1.9177722930908203, | |
| "learning_rate": 9.877690150885588e-05, | |
| "loss": 2.0133, | |
| "mean_token_accuracy": 0.502875691652298, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.16674683341350008, | |
| "grad_norm": 1.3427209854125977, | |
| "learning_rate": 9.865080897977188e-05, | |
| "loss": 1.9948, | |
| "mean_token_accuracy": 0.505776722729206, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.16995350328683662, | |
| "grad_norm": 2.0759928226470947, | |
| "learning_rate": 9.851862030715919e-05, | |
| "loss": 1.9401, | |
| "mean_token_accuracy": 0.5120617598295212, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.17316017316017315, | |
| "grad_norm": 1.2468688488006592, | |
| "learning_rate": 9.838035205479419e-05, | |
| "loss": 1.9913, | |
| "mean_token_accuracy": 0.5054045274853707, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.1763668430335097, | |
| "grad_norm": 1.2889540195465088, | |
| "learning_rate": 9.823602154824927e-05, | |
| "loss": 1.9963, | |
| "mean_token_accuracy": 0.505834324657917, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.17957351290684623, | |
| "grad_norm": 1.4190268516540527, | |
| "learning_rate": 9.808564687272178e-05, | |
| "loss": 1.9797, | |
| "mean_token_accuracy": 0.5044485762715339, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.1827801827801828, | |
| "grad_norm": 1.7106951475143433, | |
| "learning_rate": 9.792924687076801e-05, | |
| "loss": 1.9863, | |
| "mean_token_accuracy": 0.5070938616991043, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.18598685265351933, | |
| "grad_norm": 1.247165322303772, | |
| "learning_rate": 9.776684113994204e-05, | |
| "loss": 1.9723, | |
| "mean_token_accuracy": 0.5093738153576851, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.18919352252685587, | |
| "grad_norm": 1.4030295610427856, | |
| "learning_rate": 9.759845003034007e-05, | |
| "loss": 1.9756, | |
| "mean_token_accuracy": 0.5056015223264694, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.1924001924001924, | |
| "grad_norm": 1.243714690208435, | |
| "learning_rate": 9.74240946420506e-05, | |
| "loss": 1.9513, | |
| "mean_token_accuracy": 0.5091609105467796, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.19560686227352894, | |
| "grad_norm": 0.9765139222145081, | |
| "learning_rate": 9.724379682251036e-05, | |
| "loss": 1.9808, | |
| "mean_token_accuracy": 0.50465277582407, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 0.19881353214686548, | |
| "grad_norm": 1.4885112047195435, | |
| "learning_rate": 9.705757916376682e-05, | |
| "loss": 1.9993, | |
| "mean_token_accuracy": 0.5045629054307937, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.20202020202020202, | |
| "grad_norm": 1.258948802947998, | |
| "learning_rate": 9.686546499964731e-05, | |
| "loss": 1.9868, | |
| "mean_token_accuracy": 0.5066259905695916, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.20522687189353855, | |
| "grad_norm": 1.192187786102295, | |
| "learning_rate": 9.666747840283512e-05, | |
| "loss": 1.9444, | |
| "mean_token_accuracy": 0.5078241482377053, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 0.2084335417668751, | |
| "grad_norm": 1.1449286937713623, | |
| "learning_rate": 9.646364418185325e-05, | |
| "loss": 1.9964, | |
| "mean_token_accuracy": 0.5036799103021622, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.21164021164021163, | |
| "grad_norm": 1.2843917608261108, | |
| "learning_rate": 9.62539878779556e-05, | |
| "loss": 1.9857, | |
| "mean_token_accuracy": 0.5052528932690621, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 0.2148468815135482, | |
| "grad_norm": 1.1665757894515991, | |
| "learning_rate": 9.603853576192674e-05, | |
| "loss": 1.9676, | |
| "mean_token_accuracy": 0.5088991582393646, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 0.21805355138688473, | |
| "grad_norm": 1.0627950429916382, | |
| "learning_rate": 9.581731483078995e-05, | |
| "loss": 1.9494, | |
| "mean_token_accuracy": 0.512041249871254, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 0.22126022126022127, | |
| "grad_norm": 1.3954745531082153, | |
| "learning_rate": 9.559035280442443e-05, | |
| "loss": 1.9352, | |
| "mean_token_accuracy": 0.5163529127836227, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 0.2244668911335578, | |
| "grad_norm": 2.581529378890991, | |
| "learning_rate": 9.535767812209185e-05, | |
| "loss": 1.966, | |
| "mean_token_accuracy": 0.5078106135129928, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.22767356100689434, | |
| "grad_norm": 1.995743751525879, | |
| "learning_rate": 9.511931993887289e-05, | |
| "loss": 1.9278, | |
| "mean_token_accuracy": 0.5141927003860474, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 0.23088023088023088, | |
| "grad_norm": 1.3608646392822266, | |
| "learning_rate": 9.487530812201384e-05, | |
| "loss": 1.9464, | |
| "mean_token_accuracy": 0.5119614064693451, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 0.23408690075356742, | |
| "grad_norm": 2.1510233879089355, | |
| "learning_rate": 9.462567324718428e-05, | |
| "loss": 1.972, | |
| "mean_token_accuracy": 0.5053435668349266, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 0.23729357062690395, | |
| "grad_norm": 1.3489898443222046, | |
| "learning_rate": 9.437044659464568e-05, | |
| "loss": 1.9406, | |
| "mean_token_accuracy": 0.5107260003685952, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 0.2405002405002405, | |
| "grad_norm": 2.1510982513427734, | |
| "learning_rate": 9.410966014533196e-05, | |
| "loss": 1.9501, | |
| "mean_token_accuracy": 0.5109146684408188, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.24370691037357703, | |
| "grad_norm": 1.3027640581130981, | |
| "learning_rate": 9.384334657684207e-05, | |
| "loss": 1.9162, | |
| "mean_token_accuracy": 0.5180920317769051, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 0.24691358024691357, | |
| "grad_norm": 1.6839220523834229, | |
| "learning_rate": 9.357153925934543e-05, | |
| "loss": 1.932, | |
| "mean_token_accuracy": 0.5122836321592331, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 0.25012025012025013, | |
| "grad_norm": 1.5489161014556885, | |
| "learning_rate": 9.329427225140042e-05, | |
| "loss": 1.9287, | |
| "mean_token_accuracy": 0.5156795844435692, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 0.25332691999358664, | |
| "grad_norm": 1.1957494020462036, | |
| "learning_rate": 9.301158029568684e-05, | |
| "loss": 1.8905, | |
| "mean_token_accuracy": 0.5207541212439537, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 0.2565335898669232, | |
| "grad_norm": 1.2413902282714844, | |
| "learning_rate": 9.272349881465236e-05, | |
| "loss": 1.9309, | |
| "mean_token_accuracy": 0.5141352891921998, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.2597402597402597, | |
| "grad_norm": 1.3737406730651855, | |
| "learning_rate": 9.243006390607403e-05, | |
| "loss": 1.9565, | |
| "mean_token_accuracy": 0.5097300469875335, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 0.2629469296135963, | |
| "grad_norm": 1.24127197265625, | |
| "learning_rate": 9.213131233853511e-05, | |
| "loss": 1.945, | |
| "mean_token_accuracy": 0.513680812716484, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 0.26615359948693285, | |
| "grad_norm": 1.2227799892425537, | |
| "learning_rate": 9.182728154681772e-05, | |
| "loss": 1.945, | |
| "mean_token_accuracy": 0.5159043714404106, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 0.26936026936026936, | |
| "grad_norm": 1.4925428628921509, | |
| "learning_rate": 9.151800962721218e-05, | |
| "loss": 1.959, | |
| "mean_token_accuracy": 0.5081851810216904, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 0.2725669392336059, | |
| "grad_norm": 1.154524564743042, | |
| "learning_rate": 9.12035353327434e-05, | |
| "loss": 1.9162, | |
| "mean_token_accuracy": 0.517485597729683, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.27577360910694243, | |
| "grad_norm": 1.1241073608398438, | |
| "learning_rate": 9.08838980683149e-05, | |
| "loss": 1.9477, | |
| "mean_token_accuracy": 0.5126137733459473, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 0.278980278980279, | |
| "grad_norm": 1.8384186029434204, | |
| "learning_rate": 9.055913788577128e-05, | |
| "loss": 1.9197, | |
| "mean_token_accuracy": 0.5140128180384635, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 0.2821869488536155, | |
| "grad_norm": 1.3156044483184814, | |
| "learning_rate": 9.02292954788796e-05, | |
| "loss": 1.9079, | |
| "mean_token_accuracy": 0.5170748963952064, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 0.28539361872695207, | |
| "grad_norm": 1.449820876121521, | |
| "learning_rate": 8.98944121782301e-05, | |
| "loss": 1.9342, | |
| "mean_token_accuracy": 0.5114595577120781, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 0.2886002886002886, | |
| "grad_norm": 1.6988258361816406, | |
| "learning_rate": 8.955452994605753e-05, | |
| "loss": 1.9449, | |
| "mean_token_accuracy": 0.5123026236891747, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.29180695847362514, | |
| "grad_norm": 1.0350065231323242, | |
| "learning_rate": 8.920969137098303e-05, | |
| "loss": 1.9213, | |
| "mean_token_accuracy": 0.5155784547328949, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 0.29501362834696165, | |
| "grad_norm": 1.1465715169906616, | |
| "learning_rate": 8.885993966267753e-05, | |
| "loss": 1.8896, | |
| "mean_token_accuracy": 0.5216770812869072, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 0.2982202982202982, | |
| "grad_norm": 1.1059490442276, | |
| "learning_rate": 8.850531864644749e-05, | |
| "loss": 1.8978, | |
| "mean_token_accuracy": 0.5205768331885338, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 0.3014269680936348, | |
| "grad_norm": 1.199690818786621, | |
| "learning_rate": 8.81458727577434e-05, | |
| "loss": 1.9053, | |
| "mean_token_accuracy": 0.5151138812303543, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 0.3046336379669713, | |
| "grad_norm": 1.373304009437561, | |
| "learning_rate": 8.77816470365918e-05, | |
| "loss": 1.9276, | |
| "mean_token_accuracy": 0.5131517440080643, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.30784030784030786, | |
| "grad_norm": 1.4349356889724731, | |
| "learning_rate": 8.741268712195166e-05, | |
| "loss": 1.8921, | |
| "mean_token_accuracy": 0.5225584238767624, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 0.31104697771364437, | |
| "grad_norm": 1.0764795541763306, | |
| "learning_rate": 8.703903924599548e-05, | |
| "loss": 1.8639, | |
| "mean_token_accuracy": 0.5256009042263031, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 0.31425364758698093, | |
| "grad_norm": 1.946021318435669, | |
| "learning_rate": 8.666075022831643e-05, | |
| "loss": 1.881, | |
| "mean_token_accuracy": 0.5257818832993507, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 0.31746031746031744, | |
| "grad_norm": 1.2787318229675293, | |
| "learning_rate": 8.627786747006145e-05, | |
| "loss": 1.8966, | |
| "mean_token_accuracy": 0.523352475464344, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 0.320666987333654, | |
| "grad_norm": 1.7891284227371216, | |
| "learning_rate": 8.589043894799185e-05, | |
| "loss": 1.93, | |
| "mean_token_accuracy": 0.5103022322058678, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.3238736572069905, | |
| "grad_norm": 1.8391680717468262, | |
| "learning_rate": 8.549851320847156e-05, | |
| "loss": 1.8785, | |
| "mean_token_accuracy": 0.5231836125254631, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 0.3270803270803271, | |
| "grad_norm": 1.2025116682052612, | |
| "learning_rate": 8.510213936138403e-05, | |
| "loss": 1.8816, | |
| "mean_token_accuracy": 0.5240169554948807, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 0.33028699695366365, | |
| "grad_norm": 1.1192851066589355, | |
| "learning_rate": 8.470136707397868e-05, | |
| "loss": 1.8948, | |
| "mean_token_accuracy": 0.5194600358605385, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 0.33349366682700016, | |
| "grad_norm": 1.521708369255066, | |
| "learning_rate": 8.42962465646473e-05, | |
| "loss": 1.8973, | |
| "mean_token_accuracy": 0.5208257511258125, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 0.3367003367003367, | |
| "grad_norm": 1.6692718267440796, | |
| "learning_rate": 8.388682859663152e-05, | |
| "loss": 1.887, | |
| "mean_token_accuracy": 0.5233332857489585, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.33990700657367323, | |
| "grad_norm": 1.4780927896499634, | |
| "learning_rate": 8.347316447166195e-05, | |
| "loss": 1.8915, | |
| "mean_token_accuracy": 0.523545055091381, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 0.3431136764470098, | |
| "grad_norm": 1.7447547912597656, | |
| "learning_rate": 8.305530602352985e-05, | |
| "loss": 1.8826, | |
| "mean_token_accuracy": 0.5198934078216553, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 0.3463203463203463, | |
| "grad_norm": 1.1051859855651855, | |
| "learning_rate": 8.263330561159222e-05, | |
| "loss": 1.8792, | |
| "mean_token_accuracy": 0.5219237297773361, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 0.34952701619368287, | |
| "grad_norm": 1.2067945003509521, | |
| "learning_rate": 8.220721611421087e-05, | |
| "loss": 1.8989, | |
| "mean_token_accuracy": 0.5167458400130271, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 0.3527336860670194, | |
| "grad_norm": 1.3066425323486328, | |
| "learning_rate": 8.177709092212663e-05, | |
| "loss": 1.8421, | |
| "mean_token_accuracy": 0.5322213441133499, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.35594035594035595, | |
| "grad_norm": 1.0397696495056152, | |
| "learning_rate": 8.134298393176916e-05, | |
| "loss": 1.9187, | |
| "mean_token_accuracy": 0.5156819596886635, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 0.35914702581369246, | |
| "grad_norm": 1.3601312637329102, | |
| "learning_rate": 8.090494953850365e-05, | |
| "loss": 1.8785, | |
| "mean_token_accuracy": 0.5235566765069961, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 0.362353695687029, | |
| "grad_norm": 1.2964980602264404, | |
| "learning_rate": 8.046304262981478e-05, | |
| "loss": 1.8908, | |
| "mean_token_accuracy": 0.5194398432970047, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 0.3655603655603656, | |
| "grad_norm": 1.3470860719680786, | |
| "learning_rate": 8.001731857842906e-05, | |
| "loss": 1.9171, | |
| "mean_token_accuracy": 0.51639633923769, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 0.3687670354337021, | |
| "grad_norm": 1.3893637657165527, | |
| "learning_rate": 7.956783323537652e-05, | |
| "loss": 1.8682, | |
| "mean_token_accuracy": 0.5249380469322205, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.37197370530703866, | |
| "grad_norm": 1.5145325660705566, | |
| "learning_rate": 7.911464292299222e-05, | |
| "loss": 1.8457, | |
| "mean_token_accuracy": 0.527319672703743, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 0.37518037518037517, | |
| "grad_norm": 1.0269887447357178, | |
| "learning_rate": 7.865780442785891e-05, | |
| "loss": 1.8765, | |
| "mean_token_accuracy": 0.5214496284723282, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 0.37838704505371173, | |
| "grad_norm": 1.409474492073059, | |
| "learning_rate": 7.81973749936914e-05, | |
| "loss": 1.8571, | |
| "mean_token_accuracy": 0.5259096622467041, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 0.38159371492704824, | |
| "grad_norm": 1.0306053161621094, | |
| "learning_rate": 7.77334123141638e-05, | |
| "loss": 1.9028, | |
| "mean_token_accuracy": 0.5194058448076249, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 0.3848003848003848, | |
| "grad_norm": 1.076977014541626, | |
| "learning_rate": 7.726597452568007e-05, | |
| "loss": 1.8671, | |
| "mean_token_accuracy": 0.5254542633891106, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.3880070546737213, | |
| "grad_norm": 2.2276298999786377, | |
| "learning_rate": 7.679512020008948e-05, | |
| "loss": 1.8584, | |
| "mean_token_accuracy": 0.5245337873697281, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 0.3912137245470579, | |
| "grad_norm": 1.356619119644165, | |
| "learning_rate": 7.632090833734723e-05, | |
| "loss": 1.8601, | |
| "mean_token_accuracy": 0.5262611448764801, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 0.3944203944203944, | |
| "grad_norm": 1.5250309705734253, | |
| "learning_rate": 7.584339835812151e-05, | |
| "loss": 1.8671, | |
| "mean_token_accuracy": 0.520966699719429, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 0.39762706429373096, | |
| "grad_norm": 0.9932346940040588, | |
| "learning_rate": 7.536265009634789e-05, | |
| "loss": 1.8354, | |
| "mean_token_accuracy": 0.5302907466888428, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 0.4008337341670675, | |
| "grad_norm": 1.4524379968643188, | |
| "learning_rate": 7.487872379173187e-05, | |
| "loss": 1.8471, | |
| "mean_token_accuracy": 0.527701361477375, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.40404040404040403, | |
| "grad_norm": 1.6131216287612915, | |
| "learning_rate": 7.439168008220057e-05, | |
| "loss": 1.8791, | |
| "mean_token_accuracy": 0.5199943497776985, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 0.4072470739137406, | |
| "grad_norm": 1.2683628797531128, | |
| "learning_rate": 7.390157999630463e-05, | |
| "loss": 1.862, | |
| "mean_token_accuracy": 0.5257236033678054, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 0.4104537437870771, | |
| "grad_norm": 1.3786700963974, | |
| "learning_rate": 7.340848494557098e-05, | |
| "loss": 1.8329, | |
| "mean_token_accuracy": 0.5322318792343139, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 0.4136604136604137, | |
| "grad_norm": 1.2964134216308594, | |
| "learning_rate": 7.291245671680781e-05, | |
| "loss": 1.8378, | |
| "mean_token_accuracy": 0.5295253932476044, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 0.4168670835337502, | |
| "grad_norm": 1.2435472011566162, | |
| "learning_rate": 7.241355746436243e-05, | |
| "loss": 1.843, | |
| "mean_token_accuracy": 0.528707692027092, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.42007375340708675, | |
| "grad_norm": 1.6479510068893433, | |
| "learning_rate": 7.191184970233299e-05, | |
| "loss": 1.8559, | |
| "mean_token_accuracy": 0.5243293821811676, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 0.42328042328042326, | |
| "grad_norm": 1.4122897386550903, | |
| "learning_rate": 7.140739629673531e-05, | |
| "loss": 1.8584, | |
| "mean_token_accuracy": 0.5285557866096496, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 0.4264870931537598, | |
| "grad_norm": 1.2838547229766846, | |
| "learning_rate": 7.09002604576255e-05, | |
| "loss": 1.8609, | |
| "mean_token_accuracy": 0.5250947296619415, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 0.4296937630270964, | |
| "grad_norm": 1.5833513736724854, | |
| "learning_rate": 7.03905057311794e-05, | |
| "loss": 1.8246, | |
| "mean_token_accuracy": 0.5320859342813492, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 0.4329004329004329, | |
| "grad_norm": 1.5128042697906494, | |
| "learning_rate": 6.987819599173007e-05, | |
| "loss": 1.8332, | |
| "mean_token_accuracy": 0.5332021147012711, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.43610710277376946, | |
| "grad_norm": 1.0662071704864502, | |
| "learning_rate": 6.936339543376411e-05, | |
| "loss": 1.8757, | |
| "mean_token_accuracy": 0.5246989518404007, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 0.43931377264710597, | |
| "grad_norm": 1.0444306135177612, | |
| "learning_rate": 6.884616856387768e-05, | |
| "loss": 1.8411, | |
| "mean_token_accuracy": 0.5272899508476258, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 0.44252044252044254, | |
| "grad_norm": 1.4123362302780151, | |
| "learning_rate": 6.832658019269374e-05, | |
| "loss": 1.8165, | |
| "mean_token_accuracy": 0.5287312120199203, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 0.44572711239377905, | |
| "grad_norm": 1.2641295194625854, | |
| "learning_rate": 6.780469542674088e-05, | |
| "loss": 1.8581, | |
| "mean_token_accuracy": 0.5240399688482285, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 0.4489337822671156, | |
| "grad_norm": 1.055584192276001, | |
| "learning_rate": 6.728057966029529e-05, | |
| "loss": 1.7969, | |
| "mean_token_accuracy": 0.536593297123909, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.4521404521404521, | |
| "grad_norm": 1.2474592924118042, | |
| "learning_rate": 6.675429856718652e-05, | |
| "loss": 1.8295, | |
| "mean_token_accuracy": 0.5313476771116257, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 0.4553471220137887, | |
| "grad_norm": 1.1250567436218262, | |
| "learning_rate": 6.62259180925684e-05, | |
| "loss": 1.8102, | |
| "mean_token_accuracy": 0.5341511443257332, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 0.4585537918871252, | |
| "grad_norm": 1.2222751379013062, | |
| "learning_rate": 6.569550444465568e-05, | |
| "loss": 1.8343, | |
| "mean_token_accuracy": 0.5306926101446152, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 0.46176046176046176, | |
| "grad_norm": 1.24721097946167, | |
| "learning_rate": 6.516312408642804e-05, | |
| "loss": 1.8142, | |
| "mean_token_accuracy": 0.5346602320671081, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 0.4649671316337983, | |
| "grad_norm": 1.3725354671478271, | |
| "learning_rate": 6.462884372730191e-05, | |
| "loss": 1.8515, | |
| "mean_token_accuracy": 0.525643666088581, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.46817380150713483, | |
| "grad_norm": 1.5340793132781982, | |
| "learning_rate": 6.409273031477152e-05, | |
| "loss": 1.8405, | |
| "mean_token_accuracy": 0.5296775609254837, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 0.4713804713804714, | |
| "grad_norm": 1.4171345233917236, | |
| "learning_rate": 6.355485102602012e-05, | |
| "loss": 1.801, | |
| "mean_token_accuracy": 0.5374062955379486, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 0.4745871412538079, | |
| "grad_norm": 1.0726767778396606, | |
| "learning_rate": 6.301527325950242e-05, | |
| "loss": 1.8177, | |
| "mean_token_accuracy": 0.5328266575932503, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 0.4777938111271445, | |
| "grad_norm": 2.005058526992798, | |
| "learning_rate": 6.247406462649927e-05, | |
| "loss": 1.8109, | |
| "mean_token_accuracy": 0.5314099788665771, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 0.481000481000481, | |
| "grad_norm": 1.5543380975723267, | |
| "learning_rate": 6.193129294264569e-05, | |
| "loss": 1.8432, | |
| "mean_token_accuracy": 0.5261458426713943, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.48420715087381755, | |
| "grad_norm": 1.353722333908081, | |
| "learning_rate": 6.138702621943334e-05, | |
| "loss": 1.8178, | |
| "mean_token_accuracy": 0.5276563599705696, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 0.48741382074715406, | |
| "grad_norm": 1.1928757429122925, | |
| "learning_rate": 6.0841332655688344e-05, | |
| "loss": 1.8318, | |
| "mean_token_accuracy": 0.5304355949163437, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 0.4906204906204906, | |
| "grad_norm": 1.672419786453247, | |
| "learning_rate": 6.029428062902571e-05, | |
| "loss": 1.7971, | |
| "mean_token_accuracy": 0.5380920082330704, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 0.49382716049382713, | |
| "grad_norm": 1.231449842453003, | |
| "learning_rate": 5.97459386872814e-05, | |
| "loss": 1.8096, | |
| "mean_token_accuracy": 0.5327497273683548, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 0.4970338303671637, | |
| "grad_norm": 1.3776133060455322, | |
| "learning_rate": 5.919637553992293e-05, | |
| "loss": 1.8465, | |
| "mean_token_accuracy": 0.5253860056400299, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.5000801667468334, | |
| "eval_loss": 1.53940749168396, | |
| "eval_mean_token_accuracy": 0.5933501680610359, | |
| "eval_runtime": 1941.3293, | |
| "eval_samples_per_second": 255.351, | |
| "eval_steps_per_second": 1.995, | |
| "step": 3119 | |
| }, | |
| { | |
| "epoch": 0.5002405002405003, | |
| "grad_norm": 1.2065333127975464, | |
| "learning_rate": 5.864566004943983e-05, | |
| "loss": 1.8275, | |
| "mean_token_accuracy": 0.5308977961540222, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 0.5034471701138368, | |
| "grad_norm": 1.3010640144348145, | |
| "learning_rate": 5.8093861222714916e-05, | |
| "loss": 1.8368, | |
| "mean_token_accuracy": 0.5273123070597648, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 0.5066538399871733, | |
| "grad_norm": 1.4349629878997803, | |
| "learning_rate": 5.754104820237741e-05, | |
| "loss": 1.8404, | |
| "mean_token_accuracy": 0.5281692713499069, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 0.5098605098605099, | |
| "grad_norm": 1.23130202293396, | |
| "learning_rate": 5.698729025813908e-05, | |
| "loss": 1.8004, | |
| "mean_token_accuracy": 0.5355510145425797, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 0.5130671797338464, | |
| "grad_norm": 1.785715937614441, | |
| "learning_rate": 5.643265677811456e-05, | |
| "loss": 1.8103, | |
| "mean_token_accuracy": 0.5327317580580712, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.5162738496071829, | |
| "grad_norm": 1.1478352546691895, | |
| "learning_rate": 5.587721726012657e-05, | |
| "loss": 1.7974, | |
| "mean_token_accuracy": 0.5378333508968354, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 0.5194805194805194, | |
| "grad_norm": 1.545850396156311, | |
| "learning_rate": 5.532104130299771e-05, | |
| "loss": 1.8375, | |
| "mean_token_accuracy": 0.5303584784269333, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 0.522687189353856, | |
| "grad_norm": 1.295379638671875, | |
| "learning_rate": 5.476419859782942e-05, | |
| "loss": 1.8123, | |
| "mean_token_accuracy": 0.5323598384857178, | |
| "step": 3260 | |
| }, | |
| { | |
| "epoch": 0.5258938592271926, | |
| "grad_norm": 1.2239121198654175, | |
| "learning_rate": 5.4206758919269295e-05, | |
| "loss": 1.7824, | |
| "mean_token_accuracy": 0.5379300057888031, | |
| "step": 3280 | |
| }, | |
| { | |
| "epoch": 0.5291005291005291, | |
| "grad_norm": 1.1906960010528564, | |
| "learning_rate": 5.3648792116768166e-05, | |
| "loss": 1.8102, | |
| "mean_token_accuracy": 0.5297588974237442, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.5323071989738657, | |
| "grad_norm": 1.3106406927108765, | |
| "learning_rate": 5.3090368105827614e-05, | |
| "loss": 1.8291, | |
| "mean_token_accuracy": 0.5299944818019867, | |
| "step": 3320 | |
| }, | |
| { | |
| "epoch": 0.5355138688472022, | |
| "grad_norm": 1.4072366952896118, | |
| "learning_rate": 5.2531556859239305e-05, | |
| "loss": 1.7814, | |
| "mean_token_accuracy": 0.5385793894529343, | |
| "step": 3340 | |
| }, | |
| { | |
| "epoch": 0.5387205387205387, | |
| "grad_norm": 1.286926031112671, | |
| "learning_rate": 5.197242839831706e-05, | |
| "loss": 1.8002, | |
| "mean_token_accuracy": 0.5365041673183442, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 0.5419272085938752, | |
| "grad_norm": 1.1429330110549927, | |
| "learning_rate": 5.141305278412302e-05, | |
| "loss": 1.7974, | |
| "mean_token_accuracy": 0.5361256092786789, | |
| "step": 3380 | |
| }, | |
| { | |
| "epoch": 0.5451338784672118, | |
| "grad_norm": 1.544176459312439, | |
| "learning_rate": 5.085350010868855e-05, | |
| "loss": 1.8282, | |
| "mean_token_accuracy": 0.5302288249135018, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.5483405483405484, | |
| "grad_norm": 1.5704865455627441, | |
| "learning_rate": 5.029384048623154e-05, | |
| "loss": 1.8004, | |
| "mean_token_accuracy": 0.5345340296626091, | |
| "step": 3420 | |
| }, | |
| { | |
| "epoch": 0.5515472182138849, | |
| "grad_norm": 1.841884970664978, | |
| "learning_rate": 4.973414404437077e-05, | |
| "loss": 1.8273, | |
| "mean_token_accuracy": 0.527743574976921, | |
| "step": 3440 | |
| }, | |
| { | |
| "epoch": 0.5547538880872214, | |
| "grad_norm": 1.3873976469039917, | |
| "learning_rate": 4.917448091533865e-05, | |
| "loss": 1.7882, | |
| "mean_token_accuracy": 0.537655171751976, | |
| "step": 3460 | |
| }, | |
| { | |
| "epoch": 0.557960557960558, | |
| "grad_norm": 1.487434983253479, | |
| "learning_rate": 4.861492122719339e-05, | |
| "loss": 1.836, | |
| "mean_token_accuracy": 0.5291041225194931, | |
| "step": 3480 | |
| }, | |
| { | |
| "epoch": 0.5611672278338945, | |
| "grad_norm": 1.2233349084854126, | |
| "learning_rate": 4.805553509503154e-05, | |
| "loss": 1.7568, | |
| "mean_token_accuracy": 0.5442848384380341, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.564373897707231, | |
| "grad_norm": 1.4371830224990845, | |
| "learning_rate": 4.749639261220247e-05, | |
| "loss": 1.7868, | |
| "mean_token_accuracy": 0.5362420290708542, | |
| "step": 3520 | |
| }, | |
| { | |
| "epoch": 0.5675805675805676, | |
| "grad_norm": 1.703787088394165, | |
| "learning_rate": 4.6937563841525297e-05, | |
| "loss": 1.8198, | |
| "mean_token_accuracy": 0.5284188359975814, | |
| "step": 3540 | |
| }, | |
| { | |
| "epoch": 0.5707872374539041, | |
| "grad_norm": 1.2655363082885742, | |
| "learning_rate": 4.637911880650967e-05, | |
| "loss": 1.8046, | |
| "mean_token_accuracy": 0.533089104294777, | |
| "step": 3560 | |
| }, | |
| { | |
| "epoch": 0.5739939073272406, | |
| "grad_norm": 1.2529635429382324, | |
| "learning_rate": 4.582112748258166e-05, | |
| "loss": 1.7947, | |
| "mean_token_accuracy": 0.5354443103075027, | |
| "step": 3580 | |
| }, | |
| { | |
| "epoch": 0.5772005772005772, | |
| "grad_norm": 1.6291149854660034, | |
| "learning_rate": 4.526365978831552e-05, | |
| "loss": 1.796, | |
| "mean_token_accuracy": 0.5359267443418503, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.5804072470739138, | |
| "grad_norm": 1.2783862352371216, | |
| "learning_rate": 4.470678557667249e-05, | |
| "loss": 1.8099, | |
| "mean_token_accuracy": 0.5307971924543381, | |
| "step": 3620 | |
| }, | |
| { | |
| "epoch": 0.5836139169472503, | |
| "grad_norm": 1.50846529006958, | |
| "learning_rate": 4.415057462624812e-05, | |
| "loss": 1.7749, | |
| "mean_token_accuracy": 0.5401669204235077, | |
| "step": 3640 | |
| }, | |
| { | |
| "epoch": 0.5868205868205868, | |
| "grad_norm": 1.3859307765960693, | |
| "learning_rate": 4.3595096632528644e-05, | |
| "loss": 1.7742, | |
| "mean_token_accuracy": 0.539221653342247, | |
| "step": 3660 | |
| }, | |
| { | |
| "epoch": 0.5900272566939233, | |
| "grad_norm": 1.4361897706985474, | |
| "learning_rate": 4.304042119915776e-05, | |
| "loss": 1.77, | |
| "mean_token_accuracy": 0.5435908734798431, | |
| "step": 3680 | |
| }, | |
| { | |
| "epoch": 0.5932339265672599, | |
| "grad_norm": 1.4237632751464844, | |
| "learning_rate": 4.24866178292152e-05, | |
| "loss": 1.7885, | |
| "mean_token_accuracy": 0.5361862421035767, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.5964405964405964, | |
| "grad_norm": 1.2441941499710083, | |
| "learning_rate": 4.193375591650758e-05, | |
| "loss": 1.7841, | |
| "mean_token_accuracy": 0.5414396733045578, | |
| "step": 3720 | |
| }, | |
| { | |
| "epoch": 0.599647266313933, | |
| "grad_norm": 1.211448073387146, | |
| "learning_rate": 4.1381904736873075e-05, | |
| "loss": 1.8035, | |
| "mean_token_accuracy": 0.5305454939603805, | |
| "step": 3740 | |
| }, | |
| { | |
| "epoch": 0.6028539361872696, | |
| "grad_norm": 1.489575982093811, | |
| "learning_rate": 4.0831133439500954e-05, | |
| "loss": 1.7602, | |
| "mean_token_accuracy": 0.5400284379720688, | |
| "step": 3760 | |
| }, | |
| { | |
| "epoch": 0.6060606060606061, | |
| "grad_norm": 1.2525299787521362, | |
| "learning_rate": 4.0281511038266876e-05, | |
| "loss": 1.7575, | |
| "mean_token_accuracy": 0.5439072847366333, | |
| "step": 3780 | |
| }, | |
| { | |
| "epoch": 0.6092672759339426, | |
| "grad_norm": 1.388637661933899, | |
| "learning_rate": 3.9733106403085074e-05, | |
| "loss": 1.764, | |
| "mean_token_accuracy": 0.5406429708003998, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.6124739458072791, | |
| "grad_norm": 1.2612781524658203, | |
| "learning_rate": 3.918598825127885e-05, | |
| "loss": 1.7477, | |
| "mean_token_accuracy": 0.54590525329113, | |
| "step": 3820 | |
| }, | |
| { | |
| "epoch": 0.6156806156806157, | |
| "grad_norm": 1.5898454189300537, | |
| "learning_rate": 3.86402251389699e-05, | |
| "loss": 1.7659, | |
| "mean_token_accuracy": 0.541855725646019, | |
| "step": 3840 | |
| }, | |
| { | |
| "epoch": 0.6188872855539522, | |
| "grad_norm": 1.2260034084320068, | |
| "learning_rate": 3.809588545248794e-05, | |
| "loss": 1.7809, | |
| "mean_token_accuracy": 0.536695247888565, | |
| "step": 3860 | |
| }, | |
| { | |
| "epoch": 0.6220939554272887, | |
| "grad_norm": 1.3900277614593506, | |
| "learning_rate": 3.7553037399801705e-05, | |
| "loss": 1.7894, | |
| "mean_token_accuracy": 0.537989217042923, | |
| "step": 3880 | |
| }, | |
| { | |
| "epoch": 0.6253006253006252, | |
| "grad_norm": 1.377323031425476, | |
| "learning_rate": 3.701174900197218e-05, | |
| "loss": 1.7522, | |
| "mean_token_accuracy": 0.5395979732275009, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 0.6285072951739619, | |
| "grad_norm": 1.9669792652130127, | |
| "learning_rate": 3.647208808462921e-05, | |
| "loss": 1.7819, | |
| "mean_token_accuracy": 0.5357579261064529, | |
| "step": 3920 | |
| }, | |
| { | |
| "epoch": 0.6317139650472984, | |
| "grad_norm": 1.3700226545333862, | |
| "learning_rate": 3.5934122269472804e-05, | |
| "loss": 1.7622, | |
| "mean_token_accuracy": 0.5406556934118271, | |
| "step": 3940 | |
| }, | |
| { | |
| "epoch": 0.6349206349206349, | |
| "grad_norm": 1.5546220541000366, | |
| "learning_rate": 3.5397918965799785e-05, | |
| "loss": 1.7627, | |
| "mean_token_accuracy": 0.538935711979866, | |
| "step": 3960 | |
| }, | |
| { | |
| "epoch": 0.6381273047939715, | |
| "grad_norm": 1.45100736618042, | |
| "learning_rate": 3.486354536205712e-05, | |
| "loss": 1.8306, | |
| "mean_token_accuracy": 0.5290844351053238, | |
| "step": 3980 | |
| }, | |
| { | |
| "epoch": 0.641333974667308, | |
| "grad_norm": 1.2580472230911255, | |
| "learning_rate": 3.433106841742297e-05, | |
| "loss": 1.783, | |
| "mean_token_accuracy": 0.5352891981601715, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.6445406445406445, | |
| "grad_norm": 1.4428609609603882, | |
| "learning_rate": 3.380055485341644e-05, | |
| "loss": 1.7703, | |
| "mean_token_accuracy": 0.5361766919493676, | |
| "step": 4020 | |
| }, | |
| { | |
| "epoch": 0.647747314413981, | |
| "grad_norm": 1.542856216430664, | |
| "learning_rate": 3.3272071145537076e-05, | |
| "loss": 1.7793, | |
| "mean_token_accuracy": 0.532473573088646, | |
| "step": 4040 | |
| }, | |
| { | |
| "epoch": 0.6509539842873177, | |
| "grad_norm": 1.307385802268982, | |
| "learning_rate": 3.27456835149352e-05, | |
| "loss": 1.7739, | |
| "mean_token_accuracy": 0.5393928498029709, | |
| "step": 4060 | |
| }, | |
| { | |
| "epoch": 0.6541606541606542, | |
| "grad_norm": 1.7225542068481445, | |
| "learning_rate": 3.222145792011422e-05, | |
| "loss": 1.7755, | |
| "mean_token_accuracy": 0.5320593371987343, | |
| "step": 4080 | |
| }, | |
| { | |
| "epoch": 0.6573673240339907, | |
| "grad_norm": 1.3483141660690308, | |
| "learning_rate": 3.1699460048665594e-05, | |
| "loss": 1.7686, | |
| "mean_token_accuracy": 0.5363360077142716, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 0.6605739939073273, | |
| "grad_norm": 1.4043909311294556, | |
| "learning_rate": 3.117975530903813e-05, | |
| "loss": 1.7762, | |
| "mean_token_accuracy": 0.5329029619693756, | |
| "step": 4120 | |
| }, | |
| { | |
| "epoch": 0.6637806637806638, | |
| "grad_norm": 1.434023380279541, | |
| "learning_rate": 3.0662408822341864e-05, | |
| "loss": 1.7682, | |
| "mean_token_accuracy": 0.5406565859913826, | |
| "step": 4140 | |
| }, | |
| { | |
| "epoch": 0.6669873336540003, | |
| "grad_norm": 1.3568503856658936, | |
| "learning_rate": 3.014748541418817e-05, | |
| "loss": 1.7466, | |
| "mean_token_accuracy": 0.5411790430545806, | |
| "step": 4160 | |
| }, | |
| { | |
| "epoch": 0.6701940035273368, | |
| "grad_norm": 1.4412897825241089, | |
| "learning_rate": 2.9635049606566888e-05, | |
| "loss": 1.7796, | |
| "mean_token_accuracy": 0.5351216167211532, | |
| "step": 4180 | |
| }, | |
| { | |
| "epoch": 0.6734006734006734, | |
| "grad_norm": 1.4259061813354492, | |
| "learning_rate": 2.9125165609761463e-05, | |
| "loss": 1.7679, | |
| "mean_token_accuracy": 0.535513336956501, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.67660734327401, | |
| "grad_norm": 1.517968773841858, | |
| "learning_rate": 2.8617897314302994e-05, | |
| "loss": 1.7773, | |
| "mean_token_accuracy": 0.5354954585433006, | |
| "step": 4220 | |
| }, | |
| { | |
| "epoch": 0.6798140131473465, | |
| "grad_norm": 1.5838121175765991, | |
| "learning_rate": 2.811330828296471e-05, | |
| "loss": 1.738, | |
| "mean_token_accuracy": 0.545210886001587, | |
| "step": 4240 | |
| }, | |
| { | |
| "epoch": 0.683020683020683, | |
| "grad_norm": 1.4874238967895508, | |
| "learning_rate": 2.761146174279717e-05, | |
| "loss": 1.8067, | |
| "mean_token_accuracy": 0.5296819597482681, | |
| "step": 4260 | |
| }, | |
| { | |
| "epoch": 0.6862273528940196, | |
| "grad_norm": 1.4804911613464355, | |
| "learning_rate": 2.71124205772056e-05, | |
| "loss": 1.798, | |
| "mean_token_accuracy": 0.5329511255025864, | |
| "step": 4280 | |
| }, | |
| { | |
| "epoch": 0.6894340227673561, | |
| "grad_norm": 1.4983785152435303, | |
| "learning_rate": 2.6616247318070507e-05, | |
| "loss": 1.7766, | |
| "mean_token_accuracy": 0.536483982205391, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 0.6926406926406926, | |
| "grad_norm": 1.352418065071106, | |
| "learning_rate": 2.612300413791209e-05, | |
| "loss": 1.749, | |
| "mean_token_accuracy": 0.5425525337457657, | |
| "step": 4320 | |
| }, | |
| { | |
| "epoch": 0.6958473625140292, | |
| "grad_norm": 1.5389214754104614, | |
| "learning_rate": 2.5632752842099694e-05, | |
| "loss": 1.7613, | |
| "mean_token_accuracy": 0.5400553539395332, | |
| "step": 4340 | |
| }, | |
| { | |
| "epoch": 0.6990540323873657, | |
| "grad_norm": 1.481913685798645, | |
| "learning_rate": 2.5145554861107524e-05, | |
| "loss": 1.7863, | |
| "mean_token_accuracy": 0.5332476675510407, | |
| "step": 4360 | |
| }, | |
| { | |
| "epoch": 0.7022607022607023, | |
| "grad_norm": 1.5351461172103882, | |
| "learning_rate": 2.466147124281703e-05, | |
| "loss": 1.7434, | |
| "mean_token_accuracy": 0.5411887526512146, | |
| "step": 4380 | |
| }, | |
| { | |
| "epoch": 0.7054673721340388, | |
| "grad_norm": 1.6004550457000732, | |
| "learning_rate": 2.4180562644867406e-05, | |
| "loss": 1.7678, | |
| "mean_token_accuracy": 0.5376534581184387, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 0.7086740420073754, | |
| "grad_norm": 1.4997788667678833, | |
| "learning_rate": 2.3702889327054884e-05, | |
| "loss": 1.7566, | |
| "mean_token_accuracy": 0.5398379743099213, | |
| "step": 4420 | |
| }, | |
| { | |
| "epoch": 0.7118807118807119, | |
| "grad_norm": 1.638317584991455, | |
| "learning_rate": 2.3228511143782033e-05, | |
| "loss": 1.7624, | |
| "mean_token_accuracy": 0.5378725945949554, | |
| "step": 4440 | |
| }, | |
| { | |
| "epoch": 0.7150873817540484, | |
| "grad_norm": 1.343430757522583, | |
| "learning_rate": 2.2757487536557714e-05, | |
| "loss": 1.751, | |
| "mean_token_accuracy": 0.5400015458464622, | |
| "step": 4460 | |
| }, | |
| { | |
| "epoch": 0.7182940516273849, | |
| "grad_norm": 1.2288793325424194, | |
| "learning_rate": 2.2289877526548764e-05, | |
| "loss": 1.727, | |
| "mean_token_accuracy": 0.547047358751297, | |
| "step": 4480 | |
| }, | |
| { | |
| "epoch": 0.7215007215007215, | |
| "grad_norm": 1.4691182374954224, | |
| "learning_rate": 2.1825739707184494e-05, | |
| "loss": 1.7667, | |
| "mean_token_accuracy": 0.5362445533275604, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.724707391374058, | |
| "grad_norm": 1.5017502307891846, | |
| "learning_rate": 2.1365132236814668e-05, | |
| "loss": 1.765, | |
| "mean_token_accuracy": 0.5372408896684646, | |
| "step": 4520 | |
| }, | |
| { | |
| "epoch": 0.7279140612473946, | |
| "grad_norm": 1.5174387693405151, | |
| "learning_rate": 2.090811283142196e-05, | |
| "loss": 1.7615, | |
| "mean_token_accuracy": 0.5439996913075447, | |
| "step": 4540 | |
| }, | |
| { | |
| "epoch": 0.7311207311207312, | |
| "grad_norm": 1.453343391418457, | |
| "learning_rate": 2.0454738757390014e-05, | |
| "loss": 1.7372, | |
| "mean_token_accuracy": 0.540667149424553, | |
| "step": 4560 | |
| }, | |
| { | |
| "epoch": 0.7343274009940677, | |
| "grad_norm": 1.578175663948059, | |
| "learning_rate": 2.0005066824327673e-05, | |
| "loss": 1.7301, | |
| "mean_token_accuracy": 0.5443789809942245, | |
| "step": 4580 | |
| }, | |
| { | |
| "epoch": 0.7375340708674042, | |
| "grad_norm": 1.8367490768432617, | |
| "learning_rate": 1.9559153377950474e-05, | |
| "loss": 1.7255, | |
| "mean_token_accuracy": 0.5449193373322487, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 0.7407407407407407, | |
| "grad_norm": 1.5051259994506836, | |
| "learning_rate": 1.911705429302038e-05, | |
| "loss": 1.7553, | |
| "mean_token_accuracy": 0.5398281931877136, | |
| "step": 4620 | |
| }, | |
| { | |
| "epoch": 0.7439474106140773, | |
| "grad_norm": 1.4641402959823608, | |
| "learning_rate": 1.8678824966344416e-05, | |
| "loss": 1.7288, | |
| "mean_token_accuracy": 0.5467408001422882, | |
| "step": 4640 | |
| }, | |
| { | |
| "epoch": 0.7471540804874138, | |
| "grad_norm": 1.3909623622894287, | |
| "learning_rate": 1.824452030983316e-05, | |
| "loss": 1.7688, | |
| "mean_token_accuracy": 0.5377537578344345, | |
| "step": 4660 | |
| }, | |
| { | |
| "epoch": 0.7503607503607503, | |
| "grad_norm": 1.541202187538147, | |
| "learning_rate": 1.7814194743620172e-05, | |
| "loss": 1.7575, | |
| "mean_token_accuracy": 0.538825261592865, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 0.7535674202340868, | |
| "grad_norm": 1.4056111574172974, | |
| "learning_rate": 1.7387902189242826e-05, | |
| "loss": 1.7503, | |
| "mean_token_accuracy": 0.542974105477333, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 0.7567740901074235, | |
| "grad_norm": 1.5985795259475708, | |
| "learning_rate": 1.6965696062885815e-05, | |
| "loss": 1.6876, | |
| "mean_token_accuracy": 0.5525155961513519, | |
| "step": 4720 | |
| }, | |
| { | |
| "epoch": 0.75998075998076, | |
| "grad_norm": 1.958160161972046, | |
| "learning_rate": 1.6547629268687785e-05, | |
| "loss": 1.7879, | |
| "mean_token_accuracy": 0.5341216132044793, | |
| "step": 4740 | |
| }, | |
| { | |
| "epoch": 0.7631874298540965, | |
| "grad_norm": 1.5259677171707153, | |
| "learning_rate": 1.6133754192112353e-05, | |
| "loss": 1.7234, | |
| "mean_token_accuracy": 0.5443064093589782, | |
| "step": 4760 | |
| }, | |
| { | |
| "epoch": 0.7663940997274331, | |
| "grad_norm": 1.8299003839492798, | |
| "learning_rate": 1.572412269338386e-05, | |
| "loss": 1.7196, | |
| "mean_token_accuracy": 0.5485717713832855, | |
| "step": 4780 | |
| }, | |
| { | |
| "epoch": 0.7696007696007696, | |
| "grad_norm": 1.6229146718978882, | |
| "learning_rate": 1.5318786100989192e-05, | |
| "loss": 1.7261, | |
| "mean_token_accuracy": 0.5422624379396439, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 0.7728074394741061, | |
| "grad_norm": 1.5998332500457764, | |
| "learning_rate": 1.491779520524607e-05, | |
| "loss": 1.7342, | |
| "mean_token_accuracy": 0.5412924766540528, | |
| "step": 4820 | |
| }, | |
| { | |
| "epoch": 0.7760141093474426, | |
| "grad_norm": 1.6178627014160156, | |
| "learning_rate": 1.4521200251938777e-05, | |
| "loss": 1.7244, | |
| "mean_token_accuracy": 0.5459949374198914, | |
| "step": 4840 | |
| }, | |
| { | |
| "epoch": 0.7792207792207793, | |
| "grad_norm": 1.718936800956726, | |
| "learning_rate": 1.4129050936022215e-05, | |
| "loss": 1.758, | |
| "mean_token_accuracy": 0.5395539492368698, | |
| "step": 4860 | |
| }, | |
| { | |
| "epoch": 0.7824274490941158, | |
| "grad_norm": 1.6473840475082397, | |
| "learning_rate": 1.3741396395394918e-05, | |
| "loss": 1.7264, | |
| "mean_token_accuracy": 0.5445165723562241, | |
| "step": 4880 | |
| }, | |
| { | |
| "epoch": 0.7856341189674523, | |
| "grad_norm": 1.7518523931503296, | |
| "learning_rate": 1.3358285204741827e-05, | |
| "loss": 1.7462, | |
| "mean_token_accuracy": 0.5401648759841919, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 0.7888407888407888, | |
| "grad_norm": 1.577514410018921, | |
| "learning_rate": 1.2979765369447743e-05, | |
| "loss": 1.7665, | |
| "mean_token_accuracy": 0.5372074097394943, | |
| "step": 4920 | |
| }, | |
| { | |
| "epoch": 0.7920474587141254, | |
| "grad_norm": 1.666795253753662, | |
| "learning_rate": 1.2605884319582045e-05, | |
| "loss": 1.7359, | |
| "mean_token_accuracy": 0.54544777572155, | |
| "step": 4940 | |
| }, | |
| { | |
| "epoch": 0.7952541285874619, | |
| "grad_norm": 1.4499692916870117, | |
| "learning_rate": 1.2236688903955452e-05, | |
| "loss": 1.7604, | |
| "mean_token_accuracy": 0.5361103504896164, | |
| "step": 4960 | |
| }, | |
| { | |
| "epoch": 0.7984607984607984, | |
| "grad_norm": 1.79007887840271, | |
| "learning_rate": 1.1872225384249769e-05, | |
| "loss": 1.734, | |
| "mean_token_accuracy": 0.5440937787294388, | |
| "step": 4980 | |
| }, | |
| { | |
| "epoch": 0.801667468334135, | |
| "grad_norm": 1.8798636198043823, | |
| "learning_rate": 1.1512539429221058e-05, | |
| "loss": 1.7989, | |
| "mean_token_accuracy": 0.5301632598042488, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.8048741382074716, | |
| "grad_norm": 1.6248602867126465, | |
| "learning_rate": 1.1157676108977134e-05, | |
| "loss": 1.7415, | |
| "mean_token_accuracy": 0.5421714842319488, | |
| "step": 5020 | |
| }, | |
| { | |
| "epoch": 0.8080808080808081, | |
| "grad_norm": 1.626051425933838, | |
| "learning_rate": 1.0807679889330163e-05, | |
| "loss": 1.7699, | |
| "mean_token_accuracy": 0.5368034273386002, | |
| "step": 5040 | |
| }, | |
| { | |
| "epoch": 0.8112874779541446, | |
| "grad_norm": 1.6709613800048828, | |
| "learning_rate": 1.0462594626224886e-05, | |
| "loss": 1.7285, | |
| "mean_token_accuracy": 0.5429899528622627, | |
| "step": 5060 | |
| }, | |
| { | |
| "epoch": 0.8144941478274812, | |
| "grad_norm": 1.5203421115875244, | |
| "learning_rate": 1.012246356024325e-05, | |
| "loss": 1.7242, | |
| "mean_token_accuracy": 0.5429270610213279, | |
| "step": 5080 | |
| }, | |
| { | |
| "epoch": 0.8177008177008177, | |
| "grad_norm": 1.6060646772384644, | |
| "learning_rate": 9.78732931118625e-06, | |
| "loss": 1.7546, | |
| "mean_token_accuracy": 0.5418932989239693, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 0.8209074875741542, | |
| "grad_norm": 1.7185138463974, | |
| "learning_rate": 9.457233872733479e-06, | |
| "loss": 1.7366, | |
| "mean_token_accuracy": 0.5420786947011947, | |
| "step": 5120 | |
| }, | |
| { | |
| "epoch": 0.8241141574474908, | |
| "grad_norm": 1.499786615371704, | |
| "learning_rate": 9.132218607181109e-06, | |
| "loss": 1.7197, | |
| "mean_token_accuracy": 0.5424094408750534, | |
| "step": 5140 | |
| }, | |
| { | |
| "epoch": 0.8273208273208273, | |
| "grad_norm": 1.7282419204711914, | |
| "learning_rate": 8.812324240259096e-06, | |
| "loss": 1.75, | |
| "mean_token_accuracy": 0.5413718745112419, | |
| "step": 5160 | |
| }, | |
| { | |
| "epoch": 0.8305274971941639, | |
| "grad_norm": 1.539486050605774, | |
| "learning_rate": 8.497590856028026e-06, | |
| "loss": 1.7148, | |
| "mean_token_accuracy": 0.5459024518728256, | |
| "step": 5180 | |
| }, | |
| { | |
| "epoch": 0.8337341670675004, | |
| "grad_norm": 1.6102161407470703, | |
| "learning_rate": 8.188057891856426e-06, | |
| "loss": 1.7215, | |
| "mean_token_accuracy": 0.544721120595932, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 0.836940836940837, | |
| "grad_norm": 1.4731084108352661, | |
| "learning_rate": 7.883764133479139e-06, | |
| "loss": 1.7334, | |
| "mean_token_accuracy": 0.5424891680479049, | |
| "step": 5220 | |
| }, | |
| { | |
| "epoch": 0.8401475068141735, | |
| "grad_norm": 1.6069941520690918, | |
| "learning_rate": 7.5847477101372855e-06, | |
| "loss": 1.7146, | |
| "mean_token_accuracy": 0.5504184126853943, | |
| "step": 5240 | |
| }, | |
| { | |
| "epoch": 0.84335417668751, | |
| "grad_norm": 1.6103508472442627, | |
| "learning_rate": 7.291046089800496e-06, | |
| "loss": 1.7645, | |
| "mean_token_accuracy": 0.5386257976293564, | |
| "step": 5260 | |
| }, | |
| { | |
| "epoch": 0.8465608465608465, | |
| "grad_norm": 1.575320839881897, | |
| "learning_rate": 7.002696074472076e-06, | |
| "loss": 1.7392, | |
| "mean_token_accuracy": 0.5386416122317315, | |
| "step": 5280 | |
| }, | |
| { | |
| "epoch": 0.8497675164341831, | |
| "grad_norm": 1.6121926307678223, | |
| "learning_rate": 6.719733795577504e-06, | |
| "loss": 1.7426, | |
| "mean_token_accuracy": 0.5400305777788162, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 0.8529741863075196, | |
| "grad_norm": 1.8504875898361206, | |
| "learning_rate": 6.442194709437089e-06, | |
| "loss": 1.7193, | |
| "mean_token_accuracy": 0.546892175078392, | |
| "step": 5320 | |
| }, | |
| { | |
| "epoch": 0.8561808561808562, | |
| "grad_norm": 1.537227988243103, | |
| "learning_rate": 6.170113592823057e-06, | |
| "loss": 1.7108, | |
| "mean_token_accuracy": 0.5477687418460846, | |
| "step": 5340 | |
| }, | |
| { | |
| "epoch": 0.8593875260541928, | |
| "grad_norm": 1.7463566064834595, | |
| "learning_rate": 5.90352453860199e-06, | |
| "loss": 1.7716, | |
| "mean_token_accuracy": 0.5326795309782029, | |
| "step": 5360 | |
| }, | |
| { | |
| "epoch": 0.8625941959275293, | |
| "grad_norm": 1.628735065460205, | |
| "learning_rate": 5.642460951462747e-06, | |
| "loss": 1.7015, | |
| "mean_token_accuracy": 0.5511958628892899, | |
| "step": 5380 | |
| }, | |
| { | |
| "epoch": 0.8658008658008658, | |
| "grad_norm": 1.5532407760620117, | |
| "learning_rate": 5.3869555437307985e-06, | |
| "loss": 1.7055, | |
| "mean_token_accuracy": 0.5501611769199372, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 0.8690075356742023, | |
| "grad_norm": 1.3285646438598633, | |
| "learning_rate": 5.137040331269211e-06, | |
| "loss": 1.6782, | |
| "mean_token_accuracy": 0.5495849221944809, | |
| "step": 5420 | |
| }, | |
| { | |
| "epoch": 0.8722142055475389, | |
| "grad_norm": 1.8813681602478027, | |
| "learning_rate": 4.892746629466899e-06, | |
| "loss": 1.7268, | |
| "mean_token_accuracy": 0.5474593430757523, | |
| "step": 5440 | |
| }, | |
| { | |
| "epoch": 0.8754208754208754, | |
| "grad_norm": 1.5516417026519775, | |
| "learning_rate": 4.654105049314744e-06, | |
| "loss": 1.7426, | |
| "mean_token_accuracy": 0.544597877562046, | |
| "step": 5460 | |
| }, | |
| { | |
| "epoch": 0.8786275452942119, | |
| "grad_norm": 1.6854817867279053, | |
| "learning_rate": 4.421145493569861e-06, | |
| "loss": 1.7039, | |
| "mean_token_accuracy": 0.5486319988965989, | |
| "step": 5480 | |
| }, | |
| { | |
| "epoch": 0.8818342151675485, | |
| "grad_norm": 1.6205663681030273, | |
| "learning_rate": 4.19389715300868e-06, | |
| "loss": 1.708, | |
| "mean_token_accuracy": 0.5509619444608689, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.8850408850408851, | |
| "grad_norm": 1.7468833923339844, | |
| "learning_rate": 3.972388502769226e-06, | |
| "loss": 1.7353, | |
| "mean_token_accuracy": 0.5436493963003158, | |
| "step": 5520 | |
| }, | |
| { | |
| "epoch": 0.8882475549142216, | |
| "grad_norm": 1.6175867319107056, | |
| "learning_rate": 3.7566472987830726e-06, | |
| "loss": 1.7306, | |
| "mean_token_accuracy": 0.5433537870645523, | |
| "step": 5540 | |
| }, | |
| { | |
| "epoch": 0.8914542247875581, | |
| "grad_norm": 1.6812947988510132, | |
| "learning_rate": 3.546700574297385e-06, | |
| "loss": 1.7391, | |
| "mean_token_accuracy": 0.5441039055585861, | |
| "step": 5560 | |
| }, | |
| { | |
| "epoch": 0.8946608946608947, | |
| "grad_norm": 1.6716430187225342, | |
| "learning_rate": 3.3425746364875834e-06, | |
| "loss": 1.7076, | |
| "mean_token_accuracy": 0.5486252635717392, | |
| "step": 5580 | |
| }, | |
| { | |
| "epoch": 0.8978675645342312, | |
| "grad_norm": 1.838515281677246, | |
| "learning_rate": 3.144295063160929e-06, | |
| "loss": 1.7275, | |
| "mean_token_accuracy": 0.5441503524780273, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 0.9010742344075677, | |
| "grad_norm": 1.9950391054153442, | |
| "learning_rate": 2.9518866995515038e-06, | |
| "loss": 1.713, | |
| "mean_token_accuracy": 0.5466269612312317, | |
| "step": 5620 | |
| }, | |
| { | |
| "epoch": 0.9042809042809042, | |
| "grad_norm": 1.6081202030181885, | |
| "learning_rate": 2.765373655207021e-06, | |
| "loss": 1.7294, | |
| "mean_token_accuracy": 0.5423602730035781, | |
| "step": 5640 | |
| }, | |
| { | |
| "epoch": 0.9074875741542409, | |
| "grad_norm": 1.6213099956512451, | |
| "learning_rate": 2.5847793009678212e-06, | |
| "loss": 1.723, | |
| "mean_token_accuracy": 0.5430870592594147, | |
| "step": 5660 | |
| }, | |
| { | |
| "epoch": 0.9106942440275774, | |
| "grad_norm": 1.8376996517181396, | |
| "learning_rate": 2.4101262660383594e-06, | |
| "loss": 1.7215, | |
| "mean_token_accuracy": 0.5455273285508155, | |
| "step": 5680 | |
| }, | |
| { | |
| "epoch": 0.9139009139009139, | |
| "grad_norm": 1.6142514944076538, | |
| "learning_rate": 2.241436435151717e-06, | |
| "loss": 1.7415, | |
| "mean_token_accuracy": 0.5425774544477463, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 0.9171075837742504, | |
| "grad_norm": 2.0796701908111572, | |
| "learning_rate": 2.078730945827351e-06, | |
| "loss": 1.7411, | |
| "mean_token_accuracy": 0.5402660548686982, | |
| "step": 5720 | |
| }, | |
| { | |
| "epoch": 0.920314253647587, | |
| "grad_norm": 1.64828622341156, | |
| "learning_rate": 1.9220301857224455e-06, | |
| "loss": 1.7002, | |
| "mean_token_accuracy": 0.5491351515054703, | |
| "step": 5740 | |
| }, | |
| { | |
| "epoch": 0.9235209235209235, | |
| "grad_norm": 1.402880311012268, | |
| "learning_rate": 1.7713537900772958e-06, | |
| "loss": 1.7124, | |
| "mean_token_accuracy": 0.5458125352859498, | |
| "step": 5760 | |
| }, | |
| { | |
| "epoch": 0.92672759339426, | |
| "grad_norm": 1.4213367700576782, | |
| "learning_rate": 1.626720639254914e-06, | |
| "loss": 1.6927, | |
| "mean_token_accuracy": 0.5488159418106079, | |
| "step": 5780 | |
| }, | |
| { | |
| "epoch": 0.9299342632675967, | |
| "grad_norm": 1.6133363246917725, | |
| "learning_rate": 1.4881488563752377e-06, | |
| "loss": 1.7388, | |
| "mean_token_accuracy": 0.5443336263298988, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 0.9331409331409332, | |
| "grad_norm": 1.4495124816894531, | |
| "learning_rate": 1.3556558050442425e-06, | |
| "loss": 1.704, | |
| "mean_token_accuracy": 0.546082928776741, | |
| "step": 5820 | |
| }, | |
| { | |
| "epoch": 0.9363476030142697, | |
| "grad_norm": 1.6041686534881592, | |
| "learning_rate": 1.2292580871782144e-06, | |
| "loss": 1.7317, | |
| "mean_token_accuracy": 0.5426234900951385, | |
| "step": 5840 | |
| }, | |
| { | |
| "epoch": 0.9395542728876062, | |
| "grad_norm": 1.742559790611267, | |
| "learning_rate": 1.1089715409234313e-06, | |
| "loss": 1.7058, | |
| "mean_token_accuracy": 0.547260707616806, | |
| "step": 5860 | |
| }, | |
| { | |
| "epoch": 0.9427609427609428, | |
| "grad_norm": 1.509397029876709, | |
| "learning_rate": 9.948112386716168e-07, | |
| "loss": 1.6986, | |
| "mean_token_accuracy": 0.5505899757146835, | |
| "step": 5880 | |
| }, | |
| { | |
| "epoch": 0.9459676126342793, | |
| "grad_norm": 1.6833570003509521, | |
| "learning_rate": 8.86791485171301e-07, | |
| "loss": 1.7469, | |
| "mean_token_accuracy": 0.5377726525068283, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 0.9491742825076158, | |
| "grad_norm": 1.5239343643188477, | |
| "learning_rate": 7.849258157353546e-07, | |
| "loss": 1.7162, | |
| "mean_token_accuracy": 0.5405813604593277, | |
| "step": 5920 | |
| }, | |
| { | |
| "epoch": 0.9523809523809523, | |
| "grad_norm": 1.7833971977233887, | |
| "learning_rate": 6.892269945449781e-07, | |
| "loss": 1.7317, | |
| "mean_token_accuracy": 0.545667690038681, | |
| "step": 5940 | |
| }, | |
| { | |
| "epoch": 0.955587622254289, | |
| "grad_norm": 1.5971351861953735, | |
| "learning_rate": 5.997070130503101e-07, | |
| "loss": 1.7468, | |
| "mean_token_accuracy": 0.5399376690387726, | |
| "step": 5960 | |
| }, | |
| { | |
| "epoch": 0.9587942921276255, | |
| "grad_norm": 1.791557788848877, | |
| "learning_rate": 5.163770884678065e-07, | |
| "loss": 1.7308, | |
| "mean_token_accuracy": 0.5437323659658432, | |
| "step": 5980 | |
| }, | |
| { | |
| "epoch": 0.962000962000962, | |
| "grad_norm": 1.9151041507720947, | |
| "learning_rate": 4.392476623747366e-07, | |
| "loss": 1.741, | |
| "mean_token_accuracy": 0.5398768007755279, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.9652076318742986, | |
| "grad_norm": 1.6582918167114258, | |
| "learning_rate": 3.6832839940075805e-07, | |
| "loss": 1.7006, | |
| "mean_token_accuracy": 0.5496091902256012, | |
| "step": 6020 | |
| }, | |
| { | |
| "epoch": 0.9684143017476351, | |
| "grad_norm": 1.8586136102676392, | |
| "learning_rate": 3.0362818601693543e-07, | |
| "loss": 1.7186, | |
| "mean_token_accuracy": 0.54738067984581, | |
| "step": 6040 | |
| }, | |
| { | |
| "epoch": 0.9716209716209716, | |
| "grad_norm": 1.8676416873931885, | |
| "learning_rate": 2.451551294222087e-07, | |
| "loss": 1.7165, | |
| "mean_token_accuracy": 0.5441298902034759, | |
| "step": 6060 | |
| }, | |
| { | |
| "epoch": 0.9748276414943081, | |
| "grad_norm": 1.6972177028656006, | |
| "learning_rate": 1.929165565275448e-07, | |
| "loss": 1.7179, | |
| "mean_token_accuracy": 0.543172636628151, | |
| "step": 6080 | |
| }, | |
| { | |
| "epoch": 0.9780343113676447, | |
| "grad_norm": 1.5021824836730957, | |
| "learning_rate": 1.4691901303782173e-07, | |
| "loss": 1.7311, | |
| "mean_token_accuracy": 0.5438661694526672, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 0.9812409812409812, | |
| "grad_norm": 1.6856005191802979, | |
| "learning_rate": 1.0716826263165725e-07, | |
| "loss": 1.7283, | |
| "mean_token_accuracy": 0.5454312190413475, | |
| "step": 6120 | |
| }, | |
| { | |
| "epoch": 0.9844476511143178, | |
| "grad_norm": 1.5837814807891846, | |
| "learning_rate": 7.366928623916413e-08, | |
| "loss": 1.7156, | |
| "mean_token_accuracy": 0.5453536838293076, | |
| "step": 6140 | |
| }, | |
| { | |
| "epoch": 0.9876543209876543, | |
| "grad_norm": 1.9022527933120728, | |
| "learning_rate": 4.64262814178551e-08, | |
| "loss": 1.7011, | |
| "mean_token_accuracy": 0.5509391695261001, | |
| "step": 6160 | |
| }, | |
| { | |
| "epoch": 0.9908609908609909, | |
| "grad_norm": 1.4848562479019165, | |
| "learning_rate": 2.544266182662458e-08, | |
| "loss": 1.6851, | |
| "mean_token_accuracy": 0.5534208327531814, | |
| "step": 6180 | |
| }, | |
| { | |
| "epoch": 0.9940676607343274, | |
| "grad_norm": 1.5964195728302002, | |
| "learning_rate": 1.0721056798057572e-08, | |
| "loss": 1.7122, | |
| "mean_token_accuracy": 0.5429927557706833, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 0.9972743306076639, | |
| "grad_norm": 1.8827787637710571, | |
| "learning_rate": 2.2633110089265163e-09, | |
| "loss": 1.7211, | |
| "mean_token_accuracy": 0.5458635985851288, | |
| "step": 6220 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "mean_token_accuracy": 0.5422730375738705, | |
| "step": 6237, | |
| "total_flos": 3.9136612672224625e+18, | |
| "train_loss": 1.9499194212634154, | |
| "train_runtime": 7999.3345, | |
| "train_samples_per_second": 99.791, | |
| "train_steps_per_second": 0.78 | |
| } | |
| ], | |
| "logging_steps": 20, | |
| "max_steps": 6237, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3119, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.9136612672224625e+18, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |