| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 146, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00684931506849315, | |
| "grad_norm": 19.29674702806549, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 1.7245, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0136986301369863, | |
| "grad_norm": 19.21857209627261, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 1.7229, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.02054794520547945, | |
| "grad_norm": 17.41514384667566, | |
| "learning_rate": 1.2e-05, | |
| "loss": 1.5905, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0273972602739726, | |
| "grad_norm": 11.529843794329034, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 0.8558, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.03424657534246575, | |
| "grad_norm": 10.40509960722128, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4032, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0410958904109589, | |
| "grad_norm": 7.504234388952183, | |
| "learning_rate": 1.9997517932672592e-05, | |
| "loss": 0.1401, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.04794520547945205, | |
| "grad_norm": 3.122635162419864, | |
| "learning_rate": 1.999007296282201e-05, | |
| "loss": 0.0589, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0547945205479452, | |
| "grad_norm": 1.0239540198472452, | |
| "learning_rate": 1.9977668786231536e-05, | |
| "loss": 0.015, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.06164383561643835, | |
| "grad_norm": 0.7641911750868134, | |
| "learning_rate": 1.9960311560501457e-05, | |
| "loss": 0.0112, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0684931506849315, | |
| "grad_norm": 0.7361915045518228, | |
| "learning_rate": 1.993800990199235e-05, | |
| "loss": 0.0198, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.07534246575342465, | |
| "grad_norm": 0.48133196299135517, | |
| "learning_rate": 1.9910774881547803e-05, | |
| "loss": 0.0233, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0821917808219178, | |
| "grad_norm": 0.45830620408895073, | |
| "learning_rate": 1.9878620018998696e-05, | |
| "loss": 0.0205, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.08904109589041095, | |
| "grad_norm": 0.40251365492026353, | |
| "learning_rate": 1.984156127645178e-05, | |
| "loss": 0.0135, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0958904109589041, | |
| "grad_norm": 0.21100873184731916, | |
| "learning_rate": 1.979961705036587e-05, | |
| "loss": 0.01, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.10273972602739725, | |
| "grad_norm": 0.10663215007709867, | |
| "learning_rate": 1.975280816241959e-05, | |
| "loss": 0.0059, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.1095890410958904, | |
| "grad_norm": 0.2136985001931379, | |
| "learning_rate": 1.970115784917523e-05, | |
| "loss": 0.0066, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.11643835616438356, | |
| "grad_norm": 0.19320727681702302, | |
| "learning_rate": 1.964469175054377e-05, | |
| "loss": 0.0061, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.1232876712328767, | |
| "grad_norm": 0.22488490193570698, | |
| "learning_rate": 1.9583437897056915e-05, | |
| "loss": 0.0054, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.13013698630136986, | |
| "grad_norm": 0.12949314004112783, | |
| "learning_rate": 1.9517426695952358e-05, | |
| "loss": 0.0048, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.136986301369863, | |
| "grad_norm": 0.07325589720293409, | |
| "learning_rate": 1.944669091607919e-05, | |
| "loss": 0.0046, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.14383561643835616, | |
| "grad_norm": 0.2667026911328205, | |
| "learning_rate": 1.9371265671631038e-05, | |
| "loss": 0.0049, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.1506849315068493, | |
| "grad_norm": 0.23774565539015635, | |
| "learning_rate": 1.9291188404714876e-05, | |
| "loss": 0.0047, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.15753424657534246, | |
| "grad_norm": 0.06311021183333536, | |
| "learning_rate": 1.920649886676429e-05, | |
| "loss": 0.0038, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.1643835616438356, | |
| "grad_norm": 0.18265444495687314, | |
| "learning_rate": 1.9117239098806296e-05, | |
| "loss": 0.0036, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.17123287671232876, | |
| "grad_norm": 0.17871695956695147, | |
| "learning_rate": 1.902345341059164e-05, | |
| "loss": 0.0034, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.1780821917808219, | |
| "grad_norm": 0.14022615585862463, | |
| "learning_rate": 1.8925188358598815e-05, | |
| "loss": 0.003, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.18493150684931506, | |
| "grad_norm": 0.4217735239695949, | |
| "learning_rate": 1.882249272292282e-05, | |
| "loss": 0.0036, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.1917808219178082, | |
| "grad_norm": 0.2745329088554571, | |
| "learning_rate": 1.871541748306005e-05, | |
| "loss": 0.003, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.19863013698630136, | |
| "grad_norm": 0.23380507547266036, | |
| "learning_rate": 1.8604015792601395e-05, | |
| "loss": 0.0028, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.2054794520547945, | |
| "grad_norm": 0.1428536424621058, | |
| "learning_rate": 1.8488342952846074e-05, | |
| "loss": 0.0023, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.21232876712328766, | |
| "grad_norm": 0.16718027431083146, | |
| "learning_rate": 1.8368456385349333e-05, | |
| "loss": 0.0025, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.2191780821917808, | |
| "grad_norm": 0.18797868021085826, | |
| "learning_rate": 1.8244415603417603e-05, | |
| "loss": 0.0027, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.22602739726027396, | |
| "grad_norm": 0.12331990781903307, | |
| "learning_rate": 1.8116282182565313e-05, | |
| "loss": 0.0024, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.2328767123287671, | |
| "grad_norm": 0.16756761059169867, | |
| "learning_rate": 1.7984119729947944e-05, | |
| "loss": 0.002, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.23972602739726026, | |
| "grad_norm": 0.14512823117742887, | |
| "learning_rate": 1.7847993852786612e-05, | |
| "loss": 0.0022, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.2465753424657534, | |
| "grad_norm": 0.033276917673730214, | |
| "learning_rate": 1.7707972125799738e-05, | |
| "loss": 0.0018, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.2534246575342466, | |
| "grad_norm": 0.05328530240886233, | |
| "learning_rate": 1.7564124057658057e-05, | |
| "loss": 0.0017, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.2602739726027397, | |
| "grad_norm": 0.17408349740736515, | |
| "learning_rate": 1.7416521056479577e-05, | |
| "loss": 0.0024, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.2671232876712329, | |
| "grad_norm": 0.1289878517079893, | |
| "learning_rate": 1.7265236394381634e-05, | |
| "loss": 0.002, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.273972602739726, | |
| "grad_norm": 0.07727670281756385, | |
| "learning_rate": 1.711034517110761e-05, | |
| "loss": 0.0018, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.2808219178082192, | |
| "grad_norm": 0.0935035121293635, | |
| "learning_rate": 1.6951924276746425e-05, | |
| "loss": 0.002, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.2876712328767123, | |
| "grad_norm": 0.10355890785277629, | |
| "learning_rate": 1.6790052353563254e-05, | |
| "loss": 0.0022, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.2945205479452055, | |
| "grad_norm": 0.04714349399211733, | |
| "learning_rate": 1.6624809756960445e-05, | |
| "loss": 0.0013, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.3013698630136986, | |
| "grad_norm": 0.054834818605121315, | |
| "learning_rate": 1.6456278515588023e-05, | |
| "loss": 0.0015, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.3082191780821918, | |
| "grad_norm": 0.06250829705501665, | |
| "learning_rate": 1.6284542290623568e-05, | |
| "loss": 0.0013, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.3150684931506849, | |
| "grad_norm": 0.0563640070785858, | |
| "learning_rate": 1.6109686334241655e-05, | |
| "loss": 0.0016, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.3219178082191781, | |
| "grad_norm": 0.09704124691215613, | |
| "learning_rate": 1.5931797447293553e-05, | |
| "loss": 0.0017, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.3287671232876712, | |
| "grad_norm": 0.07610196592393692, | |
| "learning_rate": 1.5750963936218104e-05, | |
| "loss": 0.0014, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.3356164383561644, | |
| "grad_norm": 0.11034470568619353, | |
| "learning_rate": 1.5567275569205216e-05, | |
| "loss": 0.0018, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.3424657534246575, | |
| "grad_norm": 0.05344287464292232, | |
| "learning_rate": 1.5380823531633727e-05, | |
| "loss": 0.0019, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3493150684931507, | |
| "grad_norm": 0.06818765213019927, | |
| "learning_rate": 1.5191700380805754e-05, | |
| "loss": 0.001, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.3561643835616438, | |
| "grad_norm": 0.07736500670457502, | |
| "learning_rate": 1.5000000000000002e-05, | |
| "loss": 0.0013, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.363013698630137, | |
| "grad_norm": 0.08416203716950547, | |
| "learning_rate": 1.4805817551866839e-05, | |
| "loss": 0.0013, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.3698630136986301, | |
| "grad_norm": 0.08000624861117452, | |
| "learning_rate": 1.460924943118828e-05, | |
| "loss": 0.0017, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.3767123287671233, | |
| "grad_norm": 0.026831863602624892, | |
| "learning_rate": 1.4410393217026317e-05, | |
| "loss": 0.0014, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.3835616438356164, | |
| "grad_norm": 0.026046969137480933, | |
| "learning_rate": 1.4209347624283352e-05, | |
| "loss": 0.0012, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.3904109589041096, | |
| "grad_norm": 0.06996591904539229, | |
| "learning_rate": 1.4006212454698798e-05, | |
| "loss": 0.0015, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.3972602739726027, | |
| "grad_norm": 0.08076573337383759, | |
| "learning_rate": 1.3801088547306149e-05, | |
| "loss": 0.0015, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.4041095890410959, | |
| "grad_norm": 0.06814214008336002, | |
| "learning_rate": 1.3594077728375129e-05, | |
| "loss": 0.0013, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.410958904109589, | |
| "grad_norm": 0.045916785375625435, | |
| "learning_rate": 1.3385282760863758e-05, | |
| "loss": 0.0017, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.4178082191780822, | |
| "grad_norm": 0.03587505653315555, | |
| "learning_rate": 1.3174807293405427e-05, | |
| "loss": 0.0012, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.4246575342465753, | |
| "grad_norm": 0.04958824946765545, | |
| "learning_rate": 1.2962755808856341e-05, | |
| "loss": 0.0017, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.4315068493150685, | |
| "grad_norm": 0.055768018261520134, | |
| "learning_rate": 1.2749233572428805e-05, | |
| "loss": 0.0015, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.4383561643835616, | |
| "grad_norm": 0.022968020713589454, | |
| "learning_rate": 1.2534346579436158e-05, | |
| "loss": 0.0012, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.4452054794520548, | |
| "grad_norm": 0.029150590324992027, | |
| "learning_rate": 1.2318201502675285e-05, | |
| "loss": 0.0017, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.4520547945205479, | |
| "grad_norm": 0.0838087444466505, | |
| "learning_rate": 1.210090563947278e-05, | |
| "loss": 0.0012, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.4589041095890411, | |
| "grad_norm": 0.03256867146120048, | |
| "learning_rate": 1.1882566858421137e-05, | |
| "loss": 0.0014, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.4657534246575342, | |
| "grad_norm": 0.05522775344747511, | |
| "learning_rate": 1.1663293545831302e-05, | |
| "loss": 0.0016, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.4726027397260274, | |
| "grad_norm": 0.04414044075585935, | |
| "learning_rate": 1.1443194551928267e-05, | |
| "loss": 0.0015, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.4794520547945205, | |
| "grad_norm": 0.03049587207603872, | |
| "learning_rate": 1.1222379136816347e-05, | |
| "loss": 0.0012, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.4863013698630137, | |
| "grad_norm": 0.04682460462951094, | |
| "learning_rate": 1.1000956916240985e-05, | |
| "loss": 0.0012, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.4931506849315068, | |
| "grad_norm": 0.05892485409761165, | |
| "learning_rate": 1.0779037807174032e-05, | |
| "loss": 0.0011, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 0.03550653877962121, | |
| "learning_rate": 1.0556731973249486e-05, | |
| "loss": 0.0013, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.5068493150684932, | |
| "grad_norm": 0.0894703655391614, | |
| "learning_rate": 1.0334149770076747e-05, | |
| "loss": 0.0008, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.5136986301369864, | |
| "grad_norm": 0.030497628260740314, | |
| "learning_rate": 1.0111401690458655e-05, | |
| "loss": 0.0013, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.5205479452054794, | |
| "grad_norm": 0.06677410842425625, | |
| "learning_rate": 9.888598309541347e-06, | |
| "loss": 0.0017, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.5273972602739726, | |
| "grad_norm": 0.07484818283470532, | |
| "learning_rate": 9.665850229923258e-06, | |
| "loss": 0.0011, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.5342465753424658, | |
| "grad_norm": 0.025732343070697165, | |
| "learning_rate": 9.443268026750521e-06, | |
| "loss": 0.0008, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.541095890410959, | |
| "grad_norm": 0.034210499510211344, | |
| "learning_rate": 9.22096219282597e-06, | |
| "loss": 0.0007, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.547945205479452, | |
| "grad_norm": 0.10015949753448726, | |
| "learning_rate": 8.999043083759016e-06, | |
| "loss": 0.0015, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.5547945205479452, | |
| "grad_norm": 0.09275161932686507, | |
| "learning_rate": 8.777620863183658e-06, | |
| "loss": 0.0011, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.5616438356164384, | |
| "grad_norm": 0.05947458847354757, | |
| "learning_rate": 8.556805448071736e-06, | |
| "loss": 0.0008, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.5684931506849316, | |
| "grad_norm": 0.0294571121538469, | |
| "learning_rate": 8.336706454168701e-06, | |
| "loss": 0.001, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.5753424657534246, | |
| "grad_norm": 0.04241767860802742, | |
| "learning_rate": 8.117433141578865e-06, | |
| "loss": 0.0011, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.5821917808219178, | |
| "grad_norm": 0.06495783919409748, | |
| "learning_rate": 7.89909436052722e-06, | |
| "loss": 0.0016, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.589041095890411, | |
| "grad_norm": 0.032464640498104755, | |
| "learning_rate": 7.681798497324717e-06, | |
| "loss": 0.0013, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.5958904109589042, | |
| "grad_norm": 0.05908691816887433, | |
| "learning_rate": 7.465653420563846e-06, | |
| "loss": 0.0013, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.6027397260273972, | |
| "grad_norm": 0.027918707497596708, | |
| "learning_rate": 7.2507664275712e-06, | |
| "loss": 0.0009, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.6095890410958904, | |
| "grad_norm": 0.04718877763216423, | |
| "learning_rate": 7.037244191143662e-06, | |
| "loss": 0.0012, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.6164383561643836, | |
| "grad_norm": 0.029120200990469487, | |
| "learning_rate": 6.8251927065945755e-06, | |
| "loss": 0.0009, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.6232876712328768, | |
| "grad_norm": 0.04632805174112383, | |
| "learning_rate": 6.614717239136246e-06, | |
| "loss": 0.0008, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.6301369863013698, | |
| "grad_norm": 0.02233614952979064, | |
| "learning_rate": 6.405922271624874e-06, | |
| "loss": 0.0012, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.636986301369863, | |
| "grad_norm": 0.03987865814667557, | |
| "learning_rate": 6.1989114526938535e-06, | |
| "loss": 0.0007, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.6438356164383562, | |
| "grad_norm": 0.04518664140322487, | |
| "learning_rate": 5.993787545301204e-06, | |
| "loss": 0.0013, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.6506849315068494, | |
| "grad_norm": 0.05916217857082617, | |
| "learning_rate": 5.790652375716653e-06, | |
| "loss": 0.0012, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.6575342465753424, | |
| "grad_norm": 0.05563218539193664, | |
| "learning_rate": 5.589606782973683e-06, | |
| "loss": 0.0013, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.6643835616438356, | |
| "grad_norm": 0.06101113089335977, | |
| "learning_rate": 5.39075056881172e-06, | |
| "loss": 0.0008, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.6712328767123288, | |
| "grad_norm": 0.028524450712115297, | |
| "learning_rate": 5.194182448133163e-06, | |
| "loss": 0.0008, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.678082191780822, | |
| "grad_norm": 0.04585647335088978, | |
| "learning_rate": 5.000000000000003e-06, | |
| "loss": 0.001, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.684931506849315, | |
| "grad_norm": 0.03557767533880564, | |
| "learning_rate": 4.808299619194251e-06, | |
| "loss": 0.001, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.6917808219178082, | |
| "grad_norm": 0.035139350217428346, | |
| "learning_rate": 4.619176468366274e-06, | |
| "loss": 0.0012, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.6986301369863014, | |
| "grad_norm": 0.03923989663420306, | |
| "learning_rate": 4.432724430794786e-06, | |
| "loss": 0.0014, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.7054794520547946, | |
| "grad_norm": 0.05465108299814873, | |
| "learning_rate": 4.2490360637818965e-06, | |
| "loss": 0.001, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.7123287671232876, | |
| "grad_norm": 0.05277740141204182, | |
| "learning_rate": 4.0682025527064486e-06, | |
| "loss": 0.0012, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.7191780821917808, | |
| "grad_norm": 0.04069062627827433, | |
| "learning_rate": 3.890313665758348e-06, | |
| "loss": 0.001, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.726027397260274, | |
| "grad_norm": 0.027683781214485625, | |
| "learning_rate": 3.7154577093764334e-06, | |
| "loss": 0.0012, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.7328767123287672, | |
| "grad_norm": 0.04082961220757915, | |
| "learning_rate": 3.543721484411976e-06, | |
| "loss": 0.0013, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.7397260273972602, | |
| "grad_norm": 0.057665851827404115, | |
| "learning_rate": 3.3751902430395558e-06, | |
| "loss": 0.0012, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.7465753424657534, | |
| "grad_norm": 0.03184853057743126, | |
| "learning_rate": 3.209947646436752e-06, | |
| "loss": 0.0015, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.7534246575342466, | |
| "grad_norm": 0.03058775070190777, | |
| "learning_rate": 3.0480757232535773e-06, | |
| "loss": 0.001, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.7602739726027398, | |
| "grad_norm": 0.021197542044870794, | |
| "learning_rate": 2.889654828892393e-06, | |
| "loss": 0.001, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.7671232876712328, | |
| "grad_norm": 0.026836346212118074, | |
| "learning_rate": 2.73476360561837e-06, | |
| "loss": 0.001, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.773972602739726, | |
| "grad_norm": 0.02567047668470243, | |
| "learning_rate": 2.5834789435204245e-06, | |
| "loss": 0.0013, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.7808219178082192, | |
| "grad_norm": 0.02644076542732853, | |
| "learning_rate": 2.4358759423419476e-06, | |
| "loss": 0.001, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.7876712328767124, | |
| "grad_norm": 0.028839912523458685, | |
| "learning_rate": 2.2920278742002677e-06, | |
| "loss": 0.0011, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.7945205479452054, | |
| "grad_norm": 0.04738085952559155, | |
| "learning_rate": 2.1520061472133903e-06, | |
| "loss": 0.0017, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.8013698630136986, | |
| "grad_norm": 0.06809650532157646, | |
| "learning_rate": 2.0158802700520576e-06, | |
| "loss": 0.0011, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.8082191780821918, | |
| "grad_norm": 0.023735350189323164, | |
| "learning_rate": 1.8837178174346882e-06, | |
| "loss": 0.0012, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.815068493150685, | |
| "grad_norm": 0.04205761142071848, | |
| "learning_rate": 1.7555843965823992e-06, | |
| "loss": 0.0014, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.821917808219178, | |
| "grad_norm": 0.036552531951304985, | |
| "learning_rate": 1.6315436146506702e-06, | |
| "loss": 0.0008, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.8287671232876712, | |
| "grad_norm": 0.04975466008883568, | |
| "learning_rate": 1.5116570471539294e-06, | |
| "loss": 0.0014, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.8356164383561644, | |
| "grad_norm": 0.04244581829003469, | |
| "learning_rate": 1.3959842073986085e-06, | |
| "loss": 0.0017, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.8424657534246576, | |
| "grad_norm": 0.03061287445805811, | |
| "learning_rate": 1.2845825169399506e-06, | |
| "loss": 0.0014, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.8493150684931506, | |
| "grad_norm": 0.03212166979592859, | |
| "learning_rate": 1.1775072770771833e-06, | |
| "loss": 0.001, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.8561643835616438, | |
| "grad_norm": 0.030081381253936994, | |
| "learning_rate": 1.074811641401189e-06, | |
| "loss": 0.0009, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.863013698630137, | |
| "grad_norm": 0.02162685436714291, | |
| "learning_rate": 9.765465894083637e-07, | |
| "loss": 0.0011, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.8698630136986302, | |
| "grad_norm": 0.06344389689997086, | |
| "learning_rate": 8.827609011937066e-07, | |
| "loss": 0.001, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.8767123287671232, | |
| "grad_norm": 0.028695281312298433, | |
| "learning_rate": 7.935011332357113e-07, | |
| "loss": 0.0013, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.8835616438356164, | |
| "grad_norm": 0.04658193757911157, | |
| "learning_rate": 7.088115952851238e-07, | |
| "loss": 0.0008, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.8904109589041096, | |
| "grad_norm": 0.06588466626095466, | |
| "learning_rate": 6.287343283689662e-07, | |
| "loss": 0.0012, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.8972602739726028, | |
| "grad_norm": 0.0596321795178758, | |
| "learning_rate": 5.533090839208133e-07, | |
| "loss": 0.0009, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.9041095890410958, | |
| "grad_norm": 0.026161831276280006, | |
| "learning_rate": 4.825733040476465e-07, | |
| "loss": 0.0013, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.910958904109589, | |
| "grad_norm": 0.05665994704513745, | |
| "learning_rate": 4.165621029430855e-07, | |
| "loss": 0.0012, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.9178082191780822, | |
| "grad_norm": 0.03186905845651481, | |
| "learning_rate": 3.553082494562354e-07, | |
| "loss": 0.0013, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.9246575342465754, | |
| "grad_norm": 0.026290462399068817, | |
| "learning_rate": 2.988421508247741e-07, | |
| "loss": 0.001, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.9315068493150684, | |
| "grad_norm": 0.027234972781248173, | |
| "learning_rate": 2.4719183758041056e-07, | |
| "loss": 0.0014, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.9383561643835616, | |
| "grad_norm": 0.02358313731833951, | |
| "learning_rate": 2.0038294963413251e-07, | |
| "loss": 0.0012, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.9452054794520548, | |
| "grad_norm": 0.024465700570268718, | |
| "learning_rate": 1.5843872354822099e-07, | |
| "loss": 0.0012, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.952054794520548, | |
| "grad_norm": 0.026052644199600516, | |
| "learning_rate": 1.21379981001305e-07, | |
| "loss": 0.0013, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.958904109589041, | |
| "grad_norm": 0.03726493241217445, | |
| "learning_rate": 8.922511845219972e-08, | |
| "loss": 0.0013, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.9657534246575342, | |
| "grad_norm": 0.02392684919003666, | |
| "learning_rate": 6.199009800765265e-08, | |
| "loss": 0.0008, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.9726027397260274, | |
| "grad_norm": 0.03581373833161317, | |
| "learning_rate": 3.96884394985475e-08, | |
| "loss": 0.0009, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.9794520547945206, | |
| "grad_norm": 0.051353061359069495, | |
| "learning_rate": 2.2331213768468363e-08, | |
| "loss": 0.0011, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.9863013698630136, | |
| "grad_norm": 0.03743681014771785, | |
| "learning_rate": 9.927037177993593e-09, | |
| "loss": 0.0013, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.9931506849315068, | |
| "grad_norm": 0.040135491167517835, | |
| "learning_rate": 2.4820673274095207e-09, | |
| "loss": 0.0016, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.032445402371938076, | |
| "learning_rate": 0.0, | |
| "loss": 0.0012, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 146, | |
| "total_flos": 2.8412514950499533e+17, | |
| "train_loss": 0.046784546577901105, | |
| "train_runtime": 2768.684, | |
| "train_samples_per_second": 6.743, | |
| "train_steps_per_second": 0.053 | |
| } | |
| ], | |
| "logging_steps": 1.0, | |
| "max_steps": 146, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 2000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.8412514950499533e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |