{ "best_metric": null, "best_model_checkpoint": null, "epoch": 1.0331262939958592, "eval_steps": 500, "global_step": 250, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.004140786749482402, "grad_norm": 0.49736908078193665, "learning_rate": 2.4000000000000003e-06, "loss": 2.1632, "step": 1 }, { "epoch": 0.008281573498964804, "grad_norm": 0.4018385708332062, "learning_rate": 4.800000000000001e-06, "loss": 2.1448, "step": 2 }, { "epoch": 0.012422360248447204, "grad_norm": 0.48689907789230347, "learning_rate": 7.2e-06, "loss": 2.3454, "step": 3 }, { "epoch": 0.016563146997929608, "grad_norm": 0.5226960182189941, "learning_rate": 9.600000000000001e-06, "loss": 2.0872, "step": 4 }, { "epoch": 0.020703933747412008, "grad_norm": 0.44197356700897217, "learning_rate": 1.2e-05, "loss": 2.0461, "step": 5 }, { "epoch": 0.024844720496894408, "grad_norm": 0.3927185833454132, "learning_rate": 1.44e-05, "loss": 2.0965, "step": 6 }, { "epoch": 0.028985507246376812, "grad_norm": 0.37648865580558777, "learning_rate": 1.6800000000000002e-05, "loss": 1.7218, "step": 7 }, { "epoch": 0.033126293995859216, "grad_norm": 0.14497901499271393, "learning_rate": 1.9200000000000003e-05, "loss": 1.8762, "step": 8 }, { "epoch": 0.037267080745341616, "grad_norm": 0.07990705966949463, "learning_rate": 2.16e-05, "loss": 1.8117, "step": 9 }, { "epoch": 0.041407867494824016, "grad_norm": 0.08823492377996445, "learning_rate": 2.4e-05, "loss": 1.9386, "step": 10 }, { "epoch": 0.045548654244306416, "grad_norm": 0.11864794045686722, "learning_rate": 2.64e-05, "loss": 1.7931, "step": 11 }, { "epoch": 0.049689440993788817, "grad_norm": 0.23525194823741913, "learning_rate": 2.88e-05, "loss": 1.8439, "step": 12 }, { "epoch": 0.053830227743271224, "grad_norm": 0.16807658970355988, "learning_rate": 3.12e-05, "loss": 2.0359, "step": 13 }, { "epoch": 0.057971014492753624, "grad_norm": 0.15336070954799652, "learning_rate": 3.3600000000000004e-05, "loss": 1.9366, "step": 14 }, { "epoch": 0.062111801242236024, "grad_norm": 0.18158744275569916, "learning_rate": 3.6e-05, "loss": 1.8926, "step": 15 }, { "epoch": 0.06625258799171843, "grad_norm": 0.12008249014616013, "learning_rate": 3.8400000000000005e-05, "loss": 1.909, "step": 16 }, { "epoch": 0.07039337474120083, "grad_norm": 0.211439311504364, "learning_rate": 4.08e-05, "loss": 1.8392, "step": 17 }, { "epoch": 0.07453416149068323, "grad_norm": 0.173500657081604, "learning_rate": 4.32e-05, "loss": 1.7849, "step": 18 }, { "epoch": 0.07867494824016563, "grad_norm": 0.10626032948493958, "learning_rate": 4.5600000000000004e-05, "loss": 1.9013, "step": 19 }, { "epoch": 0.08281573498964803, "grad_norm": 0.13957469165325165, "learning_rate": 4.8e-05, "loss": 1.5716, "step": 20 }, { "epoch": 0.08695652173913043, "grad_norm": 0.08517848700284958, "learning_rate": 5.04e-05, "loss": 2.0001, "step": 21 }, { "epoch": 0.09109730848861283, "grad_norm": 0.0832364410161972, "learning_rate": 5.28e-05, "loss": 2.0204, "step": 22 }, { "epoch": 0.09523809523809523, "grad_norm": 0.09407418221235275, "learning_rate": 5.520000000000001e-05, "loss": 1.9757, "step": 23 }, { "epoch": 0.09937888198757763, "grad_norm": 0.10470325499773026, "learning_rate": 5.76e-05, "loss": 1.9063, "step": 24 }, { "epoch": 0.10351966873706005, "grad_norm": 0.07362315058708191, "learning_rate": 6e-05, "loss": 1.9674, "step": 25 }, { "epoch": 0.10766045548654245, "grad_norm": 0.07604512572288513, "learning_rate": 5.999929114583739e-05, "loss": 1.9792, "step": 26 }, { "epoch": 0.11180124223602485, "grad_norm": 0.08372924476861954, "learning_rate": 5.999716461684787e-05, "loss": 1.7242, "step": 27 }, { "epoch": 0.11594202898550725, "grad_norm": 0.05084725096821785, "learning_rate": 5.9993620513524664e-05, "loss": 1.8951, "step": 28 }, { "epoch": 0.12008281573498965, "grad_norm": 0.06014450266957283, "learning_rate": 5.99886590033513e-05, "loss": 1.9171, "step": 29 }, { "epoch": 0.12422360248447205, "grad_norm": 0.06821330636739731, "learning_rate": 5.9982280320793565e-05, "loss": 1.8141, "step": 30 }, { "epoch": 0.12836438923395446, "grad_norm": 0.07801458984613419, "learning_rate": 5.997448476728852e-05, "loss": 1.8132, "step": 31 }, { "epoch": 0.13250517598343686, "grad_norm": 0.05670145899057388, "learning_rate": 5.9965272711230184e-05, "loss": 2.0554, "step": 32 }, { "epoch": 0.13664596273291926, "grad_norm": 0.042144160717725754, "learning_rate": 5.995464458795218e-05, "loss": 1.8347, "step": 33 }, { "epoch": 0.14078674948240166, "grad_norm": 0.0534859336912632, "learning_rate": 5.994260089970716e-05, "loss": 1.7916, "step": 34 }, { "epoch": 0.14492753623188406, "grad_norm": 0.06442283093929291, "learning_rate": 5.9929142215643e-05, "loss": 1.9183, "step": 35 }, { "epoch": 0.14906832298136646, "grad_norm": 0.06278888881206512, "learning_rate": 5.991426917177598e-05, "loss": 1.728, "step": 36 }, { "epoch": 0.15320910973084886, "grad_norm": 0.09182301163673401, "learning_rate": 5.989798247096073e-05, "loss": 1.6317, "step": 37 }, { "epoch": 0.15734989648033126, "grad_norm": 0.10667438805103302, "learning_rate": 5.988028288285694e-05, "loss": 1.9076, "step": 38 }, { "epoch": 0.16149068322981366, "grad_norm": 0.0852225124835968, "learning_rate": 5.9861171243893064e-05, "loss": 1.8946, "step": 39 }, { "epoch": 0.16563146997929606, "grad_norm": 0.07862062007188797, "learning_rate": 5.984064845722676e-05, "loss": 1.8459, "step": 40 }, { "epoch": 0.16977225672877846, "grad_norm": 0.07918703556060791, "learning_rate": 5.98187154927022e-05, "loss": 1.9028, "step": 41 }, { "epoch": 0.17391304347826086, "grad_norm": 0.06476736068725586, "learning_rate": 5.9795373386804276e-05, "loss": 1.9157, "step": 42 }, { "epoch": 0.17805383022774326, "grad_norm": 0.06835038214921951, "learning_rate": 5.977062324260958e-05, "loss": 1.8086, "step": 43 }, { "epoch": 0.18219461697722567, "grad_norm": 0.0643422082066536, "learning_rate": 5.974446622973429e-05, "loss": 1.9354, "step": 44 }, { "epoch": 0.18633540372670807, "grad_norm": 0.08603407442569733, "learning_rate": 5.9716903584278915e-05, "loss": 1.9143, "step": 45 }, { "epoch": 0.19047619047619047, "grad_norm": 0.04672611877322197, "learning_rate": 5.9687936608769837e-05, "loss": 1.7765, "step": 46 }, { "epoch": 0.19461697722567287, "grad_norm": 0.04983381927013397, "learning_rate": 5.965756667209781e-05, "loss": 1.9998, "step": 47 }, { "epoch": 0.19875776397515527, "grad_norm": 0.04628973454236984, "learning_rate": 5.962579520945323e-05, "loss": 1.8665, "step": 48 }, { "epoch": 0.2028985507246377, "grad_norm": 0.0615781731903553, "learning_rate": 5.959262372225834e-05, "loss": 1.8574, "step": 49 }, { "epoch": 0.2070393374741201, "grad_norm": 0.06260473281145096, "learning_rate": 5.955805377809627e-05, "loss": 1.9896, "step": 50 }, { "epoch": 0.2111801242236025, "grad_norm": 0.04908996820449829, "learning_rate": 5.952208701063691e-05, "loss": 1.8685, "step": 51 }, { "epoch": 0.2153209109730849, "grad_norm": 0.0652541071176529, "learning_rate": 5.94847251195598e-05, "loss": 1.9012, "step": 52 }, { "epoch": 0.2194616977225673, "grad_norm": 0.05220969021320343, "learning_rate": 5.9445969870473745e-05, "loss": 1.7153, "step": 53 }, { "epoch": 0.2236024844720497, "grad_norm": 0.05003441497683525, "learning_rate": 5.940582309483338e-05, "loss": 2.0243, "step": 54 }, { "epoch": 0.2277432712215321, "grad_norm": 0.04857470095157623, "learning_rate": 5.936428668985265e-05, "loss": 1.9524, "step": 55 }, { "epoch": 0.2318840579710145, "grad_norm": 0.049168910831213, "learning_rate": 5.932136261841511e-05, "loss": 1.741, "step": 56 }, { "epoch": 0.2360248447204969, "grad_norm": 0.057303208857774734, "learning_rate": 5.9277052908981214e-05, "loss": 1.9622, "step": 57 }, { "epoch": 0.2401656314699793, "grad_norm": 0.04970083758234978, "learning_rate": 5.923135965549244e-05, "loss": 1.7606, "step": 58 }, { "epoch": 0.2443064182194617, "grad_norm": 0.048351775854825974, "learning_rate": 5.9184285017272304e-05, "loss": 2.0664, "step": 59 }, { "epoch": 0.2484472049689441, "grad_norm": 0.04087584838271141, "learning_rate": 5.9135831218924354e-05, "loss": 2.0019, "step": 60 }, { "epoch": 0.2525879917184265, "grad_norm": 0.05114104971289635, "learning_rate": 5.908600055022705e-05, "loss": 1.9351, "step": 61 }, { "epoch": 0.2567287784679089, "grad_norm": 0.04958435893058777, "learning_rate": 5.9034795366025494e-05, "loss": 1.8421, "step": 62 }, { "epoch": 0.2608695652173913, "grad_norm": 0.052330292761325836, "learning_rate": 5.898221808612025e-05, "loss": 1.7381, "step": 63 }, { "epoch": 0.2650103519668737, "grad_norm": 0.04455335810780525, "learning_rate": 5.8928271195152864e-05, "loss": 1.8632, "step": 64 }, { "epoch": 0.2691511387163561, "grad_norm": 0.050691474229097366, "learning_rate": 5.8872957242488585e-05, "loss": 1.998, "step": 65 }, { "epoch": 0.2732919254658385, "grad_norm": 0.04122067987918854, "learning_rate": 5.881627884209576e-05, "loss": 1.8917, "step": 66 }, { "epoch": 0.2774327122153209, "grad_norm": 0.04583807662129402, "learning_rate": 5.875823867242242e-05, "loss": 1.927, "step": 67 }, { "epoch": 0.2815734989648033, "grad_norm": 0.06381084024906158, "learning_rate": 5.8698839476269585e-05, "loss": 1.6846, "step": 68 }, { "epoch": 0.2857142857142857, "grad_norm": 0.049351632595062256, "learning_rate": 5.863808406066178e-05, "loss": 1.9392, "step": 69 }, { "epoch": 0.2898550724637681, "grad_norm": 0.06118392199277878, "learning_rate": 5.8575975296714274e-05, "loss": 1.7415, "step": 70 }, { "epoch": 0.2939958592132505, "grad_norm": 0.07954799383878708, "learning_rate": 5.851251611949747e-05, "loss": 1.8413, "step": 71 }, { "epoch": 0.2981366459627329, "grad_norm": 0.045418642461299896, "learning_rate": 5.8447709527898164e-05, "loss": 1.6506, "step": 72 }, { "epoch": 0.3022774327122153, "grad_norm": 0.04858332872390747, "learning_rate": 5.838155858447782e-05, "loss": 2.0256, "step": 73 }, { "epoch": 0.3064182194616977, "grad_norm": 0.046768918633461, "learning_rate": 5.831406641532789e-05, "loss": 1.9066, "step": 74 }, { "epoch": 0.3105590062111801, "grad_norm": 0.05008407309651375, "learning_rate": 5.824523620992205e-05, "loss": 1.7993, "step": 75 }, { "epoch": 0.3146997929606625, "grad_norm": 0.04596088081598282, "learning_rate": 5.8175071220965457e-05, "loss": 1.8114, "step": 76 }, { "epoch": 0.3188405797101449, "grad_norm": 0.048186447471380234, "learning_rate": 5.810357476424109e-05, "loss": 1.9843, "step": 77 }, { "epoch": 0.32298136645962733, "grad_norm": 0.05133625492453575, "learning_rate": 5.8030750218453006e-05, "loss": 1.7612, "step": 78 }, { "epoch": 0.32712215320910976, "grad_norm": 0.04953281581401825, "learning_rate": 5.795660102506671e-05, "loss": 1.7625, "step": 79 }, { "epoch": 0.33126293995859213, "grad_norm": 0.04570222645998001, "learning_rate": 5.788113068814648e-05, "loss": 1.795, "step": 80 }, { "epoch": 0.33540372670807456, "grad_norm": 0.11745952069759369, "learning_rate": 5.7804342774189835e-05, "loss": 1.7432, "step": 81 }, { "epoch": 0.33954451345755693, "grad_norm": 0.05133218690752983, "learning_rate": 5.7726240911958916e-05, "loss": 1.8884, "step": 82 }, { "epoch": 0.34368530020703936, "grad_norm": 0.050902482122182846, "learning_rate": 5.7646828792309084e-05, "loss": 1.889, "step": 83 }, { "epoch": 0.34782608695652173, "grad_norm": 0.05631539598107338, "learning_rate": 5.756611016801442e-05, "loss": 1.845, "step": 84 }, { "epoch": 0.35196687370600416, "grad_norm": 0.05162457004189491, "learning_rate": 5.7484088853590474e-05, "loss": 1.7412, "step": 85 }, { "epoch": 0.35610766045548653, "grad_norm": 0.06242730841040611, "learning_rate": 5.740076872511391e-05, "loss": 1.941, "step": 86 }, { "epoch": 0.36024844720496896, "grad_norm": 0.05125703290104866, "learning_rate": 5.731615372003939e-05, "loss": 1.7513, "step": 87 }, { "epoch": 0.36438923395445133, "grad_norm": 0.056337494403123856, "learning_rate": 5.7230247837013484e-05, "loss": 1.8812, "step": 88 }, { "epoch": 0.36853002070393376, "grad_norm": 0.056918010115623474, "learning_rate": 5.714305513568571e-05, "loss": 1.6549, "step": 89 }, { "epoch": 0.37267080745341613, "grad_norm": 0.04984583333134651, "learning_rate": 5.705457973651668e-05, "loss": 1.9668, "step": 90 }, { "epoch": 0.37681159420289856, "grad_norm": 0.0550064854323864, "learning_rate": 5.69648258205834e-05, "loss": 1.8977, "step": 91 }, { "epoch": 0.38095238095238093, "grad_norm": 0.0585719496011734, "learning_rate": 5.6873797629381675e-05, "loss": 1.6596, "step": 92 }, { "epoch": 0.38509316770186336, "grad_norm": 0.0636669397354126, "learning_rate": 5.678149946462564e-05, "loss": 1.9142, "step": 93 }, { "epoch": 0.38923395445134573, "grad_norm": 0.05703834444284439, "learning_rate": 5.6687935688044516e-05, "loss": 1.7277, "step": 94 }, { "epoch": 0.39337474120082816, "grad_norm": 0.05158121883869171, "learning_rate": 5.6593110721176475e-05, "loss": 1.9425, "step": 95 }, { "epoch": 0.39751552795031053, "grad_norm": 0.053467340767383575, "learning_rate": 5.649702904515969e-05, "loss": 1.9008, "step": 96 }, { "epoch": 0.40165631469979296, "grad_norm": 0.060619086027145386, "learning_rate": 5.6399695200520537e-05, "loss": 1.7648, "step": 97 }, { "epoch": 0.4057971014492754, "grad_norm": 0.05301009491086006, "learning_rate": 5.63011137869591e-05, "loss": 1.8785, "step": 98 }, { "epoch": 0.40993788819875776, "grad_norm": 0.05011270195245743, "learning_rate": 5.620128946313172e-05, "loss": 1.9473, "step": 99 }, { "epoch": 0.4140786749482402, "grad_norm": 0.04839683696627617, "learning_rate": 5.610022694643091e-05, "loss": 1.8244, "step": 100 }, { "epoch": 0.41821946169772256, "grad_norm": 0.058406904339790344, "learning_rate": 5.5997931012762374e-05, "loss": 1.7561, "step": 101 }, { "epoch": 0.422360248447205, "grad_norm": 0.04675458371639252, "learning_rate": 5.589440649631933e-05, "loss": 1.964, "step": 102 }, { "epoch": 0.42650103519668736, "grad_norm": 0.05772264674305916, "learning_rate": 5.578965828935409e-05, "loss": 1.8115, "step": 103 }, { "epoch": 0.4306418219461698, "grad_norm": 0.05551251769065857, "learning_rate": 5.568369134194681e-05, "loss": 1.6467, "step": 104 }, { "epoch": 0.43478260869565216, "grad_norm": 0.05348852276802063, "learning_rate": 5.557651066177161e-05, "loss": 1.7895, "step": 105 }, { "epoch": 0.4389233954451346, "grad_norm": 0.051892660558223724, "learning_rate": 5.546812131385991e-05, "loss": 1.7947, "step": 106 }, { "epoch": 0.44306418219461696, "grad_norm": 0.058433856815099716, "learning_rate": 5.535852842036107e-05, "loss": 1.8444, "step": 107 }, { "epoch": 0.4472049689440994, "grad_norm": 0.059038013219833374, "learning_rate": 5.5247737160300346e-05, "loss": 1.8436, "step": 108 }, { "epoch": 0.45134575569358176, "grad_norm": 0.052642837166786194, "learning_rate": 5.513575276933413e-05, "loss": 1.9976, "step": 109 }, { "epoch": 0.4554865424430642, "grad_norm": 0.05203791335225105, "learning_rate": 5.502258053950253e-05, "loss": 1.8925, "step": 110 }, { "epoch": 0.45962732919254656, "grad_norm": 0.05623999238014221, "learning_rate": 5.490822581897929e-05, "loss": 1.81, "step": 111 }, { "epoch": 0.463768115942029, "grad_norm": 0.06250981241464615, "learning_rate": 5.479269401181907e-05, "loss": 1.6598, "step": 112 }, { "epoch": 0.46790890269151136, "grad_norm": 0.06358765810728073, "learning_rate": 5.4675990577702005e-05, "loss": 1.6401, "step": 113 }, { "epoch": 0.4720496894409938, "grad_norm": 0.058844760060310364, "learning_rate": 5.455812103167579e-05, "loss": 1.7858, "step": 114 }, { "epoch": 0.47619047619047616, "grad_norm": 0.06053264066576958, "learning_rate": 5.443909094389497e-05, "loss": 1.7032, "step": 115 }, { "epoch": 0.4803312629399586, "grad_norm": 0.05357799679040909, "learning_rate": 5.4318905939357756e-05, "loss": 1.6963, "step": 116 }, { "epoch": 0.484472049689441, "grad_norm": 0.05877089872956276, "learning_rate": 5.4197571697640206e-05, "loss": 1.721, "step": 117 }, { "epoch": 0.4886128364389234, "grad_norm": 0.05849786847829819, "learning_rate": 5.40750939526278e-05, "loss": 1.9869, "step": 118 }, { "epoch": 0.4927536231884058, "grad_norm": 0.06864643096923828, "learning_rate": 5.395147849224451e-05, "loss": 1.7978, "step": 119 }, { "epoch": 0.4968944099378882, "grad_norm": 0.06335002183914185, "learning_rate": 5.382673115817923e-05, "loss": 2.163, "step": 120 }, { "epoch": 0.5010351966873706, "grad_norm": 0.06154783070087433, "learning_rate": 5.3700857845609764e-05, "loss": 2.0194, "step": 121 }, { "epoch": 0.505175983436853, "grad_norm": 0.06728032231330872, "learning_rate": 5.357386450292422e-05, "loss": 1.7549, "step": 122 }, { "epoch": 0.5093167701863354, "grad_norm": 0.05433879792690277, "learning_rate": 5.3445757131439915e-05, "loss": 1.9202, "step": 123 }, { "epoch": 0.5134575569358178, "grad_norm": 0.05439319089055061, "learning_rate": 5.3316541785119734e-05, "loss": 1.826, "step": 124 }, { "epoch": 0.5175983436853002, "grad_norm": 0.0665251687169075, "learning_rate": 5.318622457028609e-05, "loss": 1.435, "step": 125 }, { "epoch": 0.5217391304347826, "grad_norm": 0.05804029107093811, "learning_rate": 5.305481164533233e-05, "loss": 1.827, "step": 126 }, { "epoch": 0.525879917184265, "grad_norm": 0.06869634985923767, "learning_rate": 5.292230922043171e-05, "loss": 1.8714, "step": 127 }, { "epoch": 0.5300207039337475, "grad_norm": 0.056967902928590775, "learning_rate": 5.2788723557243936e-05, "loss": 1.7836, "step": 128 }, { "epoch": 0.5341614906832298, "grad_norm": 0.06087717413902283, "learning_rate": 5.265406096861923e-05, "loss": 1.661, "step": 129 }, { "epoch": 0.5383022774327122, "grad_norm": 0.0705471932888031, "learning_rate": 5.251832781830002e-05, "loss": 1.8054, "step": 130 }, { "epoch": 0.5424430641821946, "grad_norm": 0.06314948201179504, "learning_rate": 5.238153052062022e-05, "loss": 1.786, "step": 131 }, { "epoch": 0.546583850931677, "grad_norm": 0.06368881464004517, "learning_rate": 5.224367554020208e-05, "loss": 2.0254, "step": 132 }, { "epoch": 0.5507246376811594, "grad_norm": 0.06457039713859558, "learning_rate": 5.2104769391650726e-05, "loss": 1.8116, "step": 133 }, { "epoch": 0.5548654244306418, "grad_norm": 0.056793998926877975, "learning_rate": 5.196481863924626e-05, "loss": 1.8454, "step": 134 }, { "epoch": 0.5590062111801242, "grad_norm": 0.058062594383955, "learning_rate": 5.182382989663357e-05, "loss": 1.8074, "step": 135 }, { "epoch": 0.5631469979296067, "grad_norm": 0.05942286178469658, "learning_rate": 5.16818098265098e-05, "loss": 1.9194, "step": 136 }, { "epoch": 0.567287784679089, "grad_norm": 0.0624711774289608, "learning_rate": 5.153876514030948e-05, "loss": 1.8713, "step": 137 }, { "epoch": 0.5714285714285714, "grad_norm": 0.06994223594665527, "learning_rate": 5.139470259788736e-05, "loss": 1.8384, "step": 138 }, { "epoch": 0.5755693581780539, "grad_norm": 0.06756718456745148, "learning_rate": 5.124962900719895e-05, "loss": 1.7687, "step": 139 }, { "epoch": 0.5797101449275363, "grad_norm": 0.08007334172725677, "learning_rate": 5.110355122397885e-05, "loss": 1.7295, "step": 140 }, { "epoch": 0.5838509316770186, "grad_norm": 0.06464424729347229, "learning_rate": 5.095647615141668e-05, "loss": 1.9968, "step": 141 }, { "epoch": 0.587991718426501, "grad_norm": 0.062113020569086075, "learning_rate": 5.080841073983095e-05, "loss": 1.7497, "step": 142 }, { "epoch": 0.5921325051759835, "grad_norm": 0.06131444498896599, "learning_rate": 5.0659361986340544e-05, "loss": 1.7768, "step": 143 }, { "epoch": 0.5962732919254659, "grad_norm": 0.06630904972553253, "learning_rate": 5.0509336934534086e-05, "loss": 1.9866, "step": 144 }, { "epoch": 0.6004140786749482, "grad_norm": 0.06003854051232338, "learning_rate": 5.035834267413708e-05, "loss": 1.8859, "step": 145 }, { "epoch": 0.6045548654244306, "grad_norm": 0.07283063977956772, "learning_rate": 5.020638634067685e-05, "loss": 1.8534, "step": 146 }, { "epoch": 0.6086956521739131, "grad_norm": 0.06754714250564575, "learning_rate": 5.005347511514537e-05, "loss": 1.5808, "step": 147 }, { "epoch": 0.6128364389233955, "grad_norm": 0.060414694249629974, "learning_rate": 4.9899616223659886e-05, "loss": 1.8807, "step": 148 }, { "epoch": 0.6169772256728778, "grad_norm": 0.05546625331044197, "learning_rate": 4.974481693712145e-05, "loss": 1.937, "step": 149 }, { "epoch": 0.6211180124223602, "grad_norm": 0.07293254137039185, "learning_rate": 4.95890845708713e-05, "loss": 1.8542, "step": 150 }, { "epoch": 0.6252587991718427, "grad_norm": 0.07628627121448517, "learning_rate": 4.943242648434515e-05, "loss": 1.5924, "step": 151 }, { "epoch": 0.629399585921325, "grad_norm": 0.09479758888483047, "learning_rate": 4.927485008072549e-05, "loss": 1.7652, "step": 152 }, { "epoch": 0.6335403726708074, "grad_norm": 0.061082031577825546, "learning_rate": 4.911636280659161e-05, "loss": 1.7477, "step": 153 }, { "epoch": 0.6376811594202898, "grad_norm": 0.06984806805849075, "learning_rate": 4.8956972151567766e-05, "loss": 1.9104, "step": 154 }, { "epoch": 0.6418219461697723, "grad_norm": 0.09679781645536423, "learning_rate": 4.8796685647969267e-05, "loss": 1.7935, "step": 155 }, { "epoch": 0.6459627329192547, "grad_norm": 0.06585158407688141, "learning_rate": 4.8635510870446435e-05, "loss": 1.6618, "step": 156 }, { "epoch": 0.650103519668737, "grad_norm": 0.07509002834558487, "learning_rate": 4.8473455435626754e-05, "loss": 1.7686, "step": 157 }, { "epoch": 0.6542443064182195, "grad_norm": 0.07331015914678574, "learning_rate": 4.8310527001754874e-05, "loss": 1.7972, "step": 158 }, { "epoch": 0.6583850931677019, "grad_norm": 0.07571995258331299, "learning_rate": 4.814673326833067e-05, "loss": 1.798, "step": 159 }, { "epoch": 0.6625258799171843, "grad_norm": 0.05544979125261307, "learning_rate": 4.7982081975745476e-05, "loss": 1.8603, "step": 160 }, { "epoch": 0.6666666666666666, "grad_norm": 0.06246506795287132, "learning_rate": 4.781658090491623e-05, "loss": 2.0877, "step": 161 }, { "epoch": 0.6708074534161491, "grad_norm": 0.057248059660196304, "learning_rate": 4.765023787691779e-05, "loss": 1.857, "step": 162 }, { "epoch": 0.6749482401656315, "grad_norm": 0.0628746747970581, "learning_rate": 4.748306075261335e-05, "loss": 1.805, "step": 163 }, { "epoch": 0.6790890269151139, "grad_norm": 0.06979019939899445, "learning_rate": 4.731505743228294e-05, "loss": 1.7996, "step": 164 }, { "epoch": 0.6832298136645962, "grad_norm": 0.058253347873687744, "learning_rate": 4.714623585525009e-05, "loss": 1.9695, "step": 165 }, { "epoch": 0.6873706004140787, "grad_norm": 0.05848124623298645, "learning_rate": 4.697660399950663e-05, "loss": 1.7858, "step": 166 }, { "epoch": 0.6915113871635611, "grad_norm": 0.0602106973528862, "learning_rate": 4.680616988133572e-05, "loss": 1.9007, "step": 167 }, { "epoch": 0.6956521739130435, "grad_norm": 0.06956855952739716, "learning_rate": 4.663494155493296e-05, "loss": 1.8796, "step": 168 }, { "epoch": 0.6997929606625258, "grad_norm": 0.055345602333545685, "learning_rate": 4.64629271120258e-05, "loss": 1.7476, "step": 169 }, { "epoch": 0.7039337474120083, "grad_norm": 0.06562691926956177, "learning_rate": 4.6290134681491165e-05, "loss": 1.7378, "step": 170 }, { "epoch": 0.7080745341614907, "grad_norm": 0.07123929262161255, "learning_rate": 4.611657242897131e-05, "loss": 1.7195, "step": 171 }, { "epoch": 0.7122153209109731, "grad_norm": 0.07925646752119064, "learning_rate": 4.5942248556487914e-05, "loss": 1.8299, "step": 172 }, { "epoch": 0.7163561076604554, "grad_norm": 0.088850237429142, "learning_rate": 4.576717130205448e-05, "loss": 1.8684, "step": 173 }, { "epoch": 0.7204968944099379, "grad_norm": 0.06837620586156845, "learning_rate": 4.559134893928705e-05, "loss": 1.7766, "step": 174 }, { "epoch": 0.7246376811594203, "grad_norm": 0.06634443253278732, "learning_rate": 4.541478977701321e-05, "loss": 1.8053, "step": 175 }, { "epoch": 0.7287784679089027, "grad_norm": 0.06066809594631195, "learning_rate": 4.523750215887942e-05, "loss": 2.0255, "step": 176 }, { "epoch": 0.7329192546583851, "grad_norm": 0.07539010792970657, "learning_rate": 4.505949446295677e-05, "loss": 1.902, "step": 177 }, { "epoch": 0.7370600414078675, "grad_norm": 0.08485755324363708, "learning_rate": 4.488077510134499e-05, "loss": 1.752, "step": 178 }, { "epoch": 0.7412008281573499, "grad_norm": 0.06715612858533859, "learning_rate": 4.4701352519774986e-05, "loss": 1.8651, "step": 179 }, { "epoch": 0.7453416149068323, "grad_norm": 0.05764465034008026, "learning_rate": 4.4521235197209686e-05, "loss": 1.9279, "step": 180 }, { "epoch": 0.7494824016563147, "grad_norm": 0.0972018614411354, "learning_rate": 4.434043164544333e-05, "loss": 1.7838, "step": 181 }, { "epoch": 0.7536231884057971, "grad_norm": 0.06594452261924744, "learning_rate": 4.415895040869929e-05, "loss": 1.8846, "step": 182 }, { "epoch": 0.7577639751552795, "grad_norm": 0.0821613073348999, "learning_rate": 4.397680006322622e-05, "loss": 1.5778, "step": 183 }, { "epoch": 0.7619047619047619, "grad_norm": 0.07455030083656311, "learning_rate": 4.379398921689284e-05, "loss": 1.9354, "step": 184 }, { "epoch": 0.7660455486542443, "grad_norm": 0.07369917631149292, "learning_rate": 4.361052650878111e-05, "loss": 1.6528, "step": 185 }, { "epoch": 0.7701863354037267, "grad_norm": 0.06145176291465759, "learning_rate": 4.342642060877798e-05, "loss": 1.8605, "step": 186 }, { "epoch": 0.7743271221532091, "grad_norm": 0.0714261382818222, "learning_rate": 4.324168021716568e-05, "loss": 1.9954, "step": 187 }, { "epoch": 0.7784679089026915, "grad_norm": 0.07373001426458359, "learning_rate": 4.30563140642106e-05, "loss": 1.6576, "step": 188 }, { "epoch": 0.782608695652174, "grad_norm": 0.08491583913564682, "learning_rate": 4.287033090975068e-05, "loss": 1.8222, "step": 189 }, { "epoch": 0.7867494824016563, "grad_norm": 0.08685383945703506, "learning_rate": 4.268373954278145e-05, "loss": 1.7194, "step": 190 }, { "epoch": 0.7908902691511387, "grad_norm": 0.0834331288933754, "learning_rate": 4.249654878104073e-05, "loss": 1.7173, "step": 191 }, { "epoch": 0.7950310559006211, "grad_norm": 0.09984423220157623, "learning_rate": 4.230876747059192e-05, "loss": 1.7618, "step": 192 }, { "epoch": 0.7991718426501035, "grad_norm": 0.0643148198723793, "learning_rate": 4.2120404485405886e-05, "loss": 1.8246, "step": 193 }, { "epoch": 0.8033126293995859, "grad_norm": 0.06520809233188629, "learning_rate": 4.193146872694173e-05, "loss": 1.827, "step": 194 }, { "epoch": 0.8074534161490683, "grad_norm": 0.07631880044937134, "learning_rate": 4.174196912372605e-05, "loss": 1.9521, "step": 195 }, { "epoch": 0.8115942028985508, "grad_norm": 0.08804851770401001, "learning_rate": 4.1551914630930986e-05, "loss": 1.8057, "step": 196 }, { "epoch": 0.8157349896480331, "grad_norm": 0.10719820857048035, "learning_rate": 4.1361314229951114e-05, "loss": 1.7777, "step": 197 }, { "epoch": 0.8198757763975155, "grad_norm": 0.09046828001737595, "learning_rate": 4.117017692797894e-05, "loss": 1.8581, "step": 198 }, { "epoch": 0.8240165631469979, "grad_norm": 0.06453605741262436, "learning_rate": 4.0978511757579266e-05, "loss": 1.7737, "step": 199 }, { "epoch": 0.8281573498964804, "grad_norm": 0.06556473672389984, "learning_rate": 4.0786327776262355e-05, "loss": 1.8843, "step": 200 }, { "epoch": 0.8322981366459627, "grad_norm": 0.07110321521759033, "learning_rate": 4.059363406605589e-05, "loss": 1.8864, "step": 201 }, { "epoch": 0.8364389233954451, "grad_norm": 0.06083063408732414, "learning_rate": 4.0400439733075764e-05, "loss": 1.6101, "step": 202 }, { "epoch": 0.8405797101449275, "grad_norm": 0.0694584771990776, "learning_rate": 4.020675390709579e-05, "loss": 1.7452, "step": 203 }, { "epoch": 0.84472049689441, "grad_norm": 0.08408311009407043, "learning_rate": 4.001258574111624e-05, "loss": 1.7393, "step": 204 }, { "epoch": 0.8488612836438924, "grad_norm": 0.06838119029998779, "learning_rate": 3.9817944410931276e-05, "loss": 1.9128, "step": 205 }, { "epoch": 0.8530020703933747, "grad_norm": 0.06725747138261795, "learning_rate": 3.962283911469539e-05, "loss": 1.8047, "step": 206 }, { "epoch": 0.8571428571428571, "grad_norm": 0.07443306595087051, "learning_rate": 3.942727907248867e-05, "loss": 1.8384, "step": 207 }, { "epoch": 0.8612836438923396, "grad_norm": 0.05935392156243324, "learning_rate": 3.923127352588112e-05, "loss": 1.9675, "step": 208 }, { "epoch": 0.865424430641822, "grad_norm": 0.07299666106700897, "learning_rate": 3.903483173749589e-05, "loss": 2.092, "step": 209 }, { "epoch": 0.8695652173913043, "grad_norm": 0.062474749982357025, "learning_rate": 3.883796299057164e-05, "loss": 1.8276, "step": 210 }, { "epoch": 0.8737060041407867, "grad_norm": 0.059401869773864746, "learning_rate": 3.8640676588523735e-05, "loss": 1.7309, "step": 211 }, { "epoch": 0.8778467908902692, "grad_norm": 0.1073634922504425, "learning_rate": 3.844298185450466e-05, "loss": 1.6717, "step": 212 }, { "epoch": 0.8819875776397516, "grad_norm": 0.06048239767551422, "learning_rate": 3.824488813096342e-05, "loss": 1.854, "step": 213 }, { "epoch": 0.8861283643892339, "grad_norm": 0.06702765077352524, "learning_rate": 3.804640477920406e-05, "loss": 1.8754, "step": 214 }, { "epoch": 0.8902691511387164, "grad_norm": 0.07091647386550903, "learning_rate": 3.784754117894326e-05, "loss": 1.8767, "step": 215 }, { "epoch": 0.8944099378881988, "grad_norm": 0.06531751155853271, "learning_rate": 3.764830672786705e-05, "loss": 1.776, "step": 216 }, { "epoch": 0.8985507246376812, "grad_norm": 0.09837061166763306, "learning_rate": 3.744871084118679e-05, "loss": 1.7286, "step": 217 }, { "epoch": 0.9026915113871635, "grad_norm": 0.08499777317047119, "learning_rate": 3.7248762951194145e-05, "loss": 1.7482, "step": 218 }, { "epoch": 0.906832298136646, "grad_norm": 0.06564295291900635, "learning_rate": 3.704847250681538e-05, "loss": 1.7492, "step": 219 }, { "epoch": 0.9109730848861284, "grad_norm": 0.0832459032535553, "learning_rate": 3.684784897316485e-05, "loss": 1.8582, "step": 220 }, { "epoch": 0.9151138716356108, "grad_norm": 0.061843667179346085, "learning_rate": 3.6646901831097695e-05, "loss": 1.8591, "step": 221 }, { "epoch": 0.9192546583850931, "grad_norm": 0.09650903940200806, "learning_rate": 3.6445640576761774e-05, "loss": 1.676, "step": 222 }, { "epoch": 0.9233954451345756, "grad_norm": 0.13103087246418, "learning_rate": 3.6244074721148947e-05, "loss": 1.6361, "step": 223 }, { "epoch": 0.927536231884058, "grad_norm": 0.07348862290382385, "learning_rate": 3.6042213789645626e-05, "loss": 1.7993, "step": 224 }, { "epoch": 0.9316770186335404, "grad_norm": 0.06679573655128479, "learning_rate": 3.584006732158255e-05, "loss": 1.9934, "step": 225 }, { "epoch": 0.9358178053830227, "grad_norm": 0.06558524817228317, "learning_rate": 3.5637644869784075e-05, "loss": 1.8979, "step": 226 }, { "epoch": 0.9399585921325052, "grad_norm": 0.0905718207359314, "learning_rate": 3.543495600011674e-05, "loss": 1.9162, "step": 227 }, { "epoch": 0.9440993788819876, "grad_norm": 0.08884776383638382, "learning_rate": 3.523201029103711e-05, "loss": 1.884, "step": 228 }, { "epoch": 0.94824016563147, "grad_norm": 0.10564474761486053, "learning_rate": 3.502881733313924e-05, "loss": 1.7368, "step": 229 }, { "epoch": 0.9523809523809523, "grad_norm": 0.06858230382204056, "learning_rate": 3.482538672870141e-05, "loss": 2.0018, "step": 230 }, { "epoch": 0.9565217391304348, "grad_norm": 0.06798145174980164, "learning_rate": 3.462172809123231e-05, "loss": 1.9542, "step": 231 }, { "epoch": 0.9606625258799172, "grad_norm": 0.0749635100364685, "learning_rate": 3.441785104501683e-05, "loss": 1.8139, "step": 232 }, { "epoch": 0.9648033126293996, "grad_norm": 0.06580834090709686, "learning_rate": 3.421376522466114e-05, "loss": 1.8621, "step": 233 }, { "epoch": 0.968944099378882, "grad_norm": 0.10760274529457092, "learning_rate": 3.400948027463747e-05, "loss": 1.7851, "step": 234 }, { "epoch": 0.9730848861283644, "grad_norm": 0.09195095300674438, "learning_rate": 3.38050058488283e-05, "loss": 1.8275, "step": 235 }, { "epoch": 0.9772256728778468, "grad_norm": 0.09066396951675415, "learning_rate": 3.3600351610070144e-05, "loss": 1.7884, "step": 236 }, { "epoch": 0.9813664596273292, "grad_norm": 0.09388420730829239, "learning_rate": 3.339552722969695e-05, "loss": 1.8267, "step": 237 }, { "epoch": 0.9855072463768116, "grad_norm": 0.07875888049602509, "learning_rate": 3.319054238708301e-05, "loss": 1.8035, "step": 238 }, { "epoch": 0.989648033126294, "grad_norm": 0.09944237768650055, "learning_rate": 3.298540676918562e-05, "loss": 1.5542, "step": 239 }, { "epoch": 0.9937888198757764, "grad_norm": 0.11820376664400101, "learning_rate": 3.2780130070087196e-05, "loss": 1.7907, "step": 240 }, { "epoch": 0.9979296066252588, "grad_norm": 0.0819728672504425, "learning_rate": 3.2574721990537245e-05, "loss": 1.8663, "step": 241 }, { "epoch": 1.0, "grad_norm": 0.08972211927175522, "learning_rate": 3.236919223749394e-05, "loss": 1.9601, "step": 242 }, { "epoch": 1.0041407867494825, "grad_norm": 0.0647214949131012, "learning_rate": 3.216355052366532e-05, "loss": 1.8954, "step": 243 }, { "epoch": 1.0082815734989647, "grad_norm": 0.08813779801130295, "learning_rate": 3.195780656705039e-05, "loss": 1.6085, "step": 244 }, { "epoch": 1.0124223602484472, "grad_norm": 0.1159641295671463, "learning_rate": 3.175197009047982e-05, "loss": 1.6147, "step": 245 }, { "epoch": 1.0165631469979297, "grad_norm": 0.12031491100788116, "learning_rate": 3.1546050821156486e-05, "loss": 1.6832, "step": 246 }, { "epoch": 1.020703933747412, "grad_norm": 0.14147016406059265, "learning_rate": 3.1340058490195815e-05, "loss": 1.6109, "step": 247 }, { "epoch": 1.0248447204968945, "grad_norm": 0.09276167303323746, "learning_rate": 3.113400283216587e-05, "loss": 1.7716, "step": 248 }, { "epoch": 1.0289855072463767, "grad_norm": 0.21230283379554749, "learning_rate": 3.0927893584627405e-05, "loss": 1.6087, "step": 249 }, { "epoch": 1.0331262939958592, "grad_norm": 0.115353524684906, "learning_rate": 3.0721740487673606e-05, "loss": 1.6034, "step": 250 } ], "logging_steps": 1, "max_steps": 482, "num_input_tokens_seen": 0, "num_train_epochs": 2, "save_steps": 25, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 6.302325934758298e+18, "train_batch_size": 8, "trial_name": null, "trial_params": null }