{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 1.0, "eval_steps": 500, "global_step": 533, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.001876172607879925, "grad_norm": 13.30275821685791, "learning_rate": 0.0, "loss": 1.1937, "step": 1 }, { "epoch": 0.00375234521575985, "grad_norm": 13.791933059692383, "learning_rate": 3.7037037037037036e-07, "loss": 1.1867, "step": 2 }, { "epoch": 0.005628517823639775, "grad_norm": 13.11504077911377, "learning_rate": 7.407407407407407e-07, "loss": 1.1638, "step": 3 }, { "epoch": 0.0075046904315197, "grad_norm": 13.519221305847168, "learning_rate": 1.111111111111111e-06, "loss": 1.1875, "step": 4 }, { "epoch": 0.009380863039399626, "grad_norm": 13.415589332580566, "learning_rate": 1.4814814814814815e-06, "loss": 1.2118, "step": 5 }, { "epoch": 0.01125703564727955, "grad_norm": 12.372065544128418, "learning_rate": 1.8518518518518519e-06, "loss": 1.1666, "step": 6 }, { "epoch": 0.013133208255159476, "grad_norm": 10.053466796875, "learning_rate": 2.222222222222222e-06, "loss": 1.0824, "step": 7 }, { "epoch": 0.0150093808630394, "grad_norm": 7.384225368499756, "learning_rate": 2.5925925925925925e-06, "loss": 1.0465, "step": 8 }, { "epoch": 0.016885553470919325, "grad_norm": 5.936990737915039, "learning_rate": 2.962962962962963e-06, "loss": 0.9748, "step": 9 }, { "epoch": 0.01876172607879925, "grad_norm": 5.118947982788086, "learning_rate": 3.3333333333333333e-06, "loss": 0.9498, "step": 10 }, { "epoch": 0.020637898686679174, "grad_norm": 2.2925024032592773, "learning_rate": 3.7037037037037037e-06, "loss": 0.8612, "step": 11 }, { "epoch": 0.0225140712945591, "grad_norm": 2.1615967750549316, "learning_rate": 4.074074074074074e-06, "loss": 0.8523, "step": 12 }, { "epoch": 0.024390243902439025, "grad_norm": 1.967605710029602, "learning_rate": 4.444444444444444e-06, "loss": 0.852, "step": 13 }, { "epoch": 0.02626641651031895, "grad_norm": 2.0044472217559814, "learning_rate": 4.814814814814815e-06, "loss": 0.8223, "step": 14 }, { "epoch": 0.028142589118198873, "grad_norm": 1.8968573808670044, "learning_rate": 5.185185185185185e-06, "loss": 0.784, "step": 15 }, { "epoch": 0.0300187617260788, "grad_norm": 2.0519533157348633, "learning_rate": 5.555555555555557e-06, "loss": 0.7962, "step": 16 }, { "epoch": 0.03189493433395872, "grad_norm": 1.8372418880462646, "learning_rate": 5.925925925925926e-06, "loss": 0.7928, "step": 17 }, { "epoch": 0.03377110694183865, "grad_norm": 1.6606271266937256, "learning_rate": 6.296296296296297e-06, "loss": 0.7741, "step": 18 }, { "epoch": 0.03564727954971857, "grad_norm": 1.4279577732086182, "learning_rate": 6.666666666666667e-06, "loss": 0.7726, "step": 19 }, { "epoch": 0.0375234521575985, "grad_norm": 1.1227573156356812, "learning_rate": 7.0370370370370375e-06, "loss": 0.7226, "step": 20 }, { "epoch": 0.039399624765478425, "grad_norm": 1.1973068714141846, "learning_rate": 7.4074074074074075e-06, "loss": 0.7286, "step": 21 }, { "epoch": 0.04127579737335835, "grad_norm": 1.053694248199463, "learning_rate": 7.77777777777778e-06, "loss": 0.7125, "step": 22 }, { "epoch": 0.043151969981238276, "grad_norm": 0.8389816284179688, "learning_rate": 8.148148148148148e-06, "loss": 0.7081, "step": 23 }, { "epoch": 0.0450281425891182, "grad_norm": 0.7549389004707336, "learning_rate": 8.518518518518519e-06, "loss": 0.6835, "step": 24 }, { "epoch": 0.04690431519699812, "grad_norm": 0.7767587304115295, "learning_rate": 8.888888888888888e-06, "loss": 0.6772, "step": 25 }, { "epoch": 0.04878048780487805, "grad_norm": 0.7495452165603638, "learning_rate": 9.25925925925926e-06, "loss": 0.6365, "step": 26 }, { "epoch": 0.05065666041275797, "grad_norm": 0.6553788185119629, "learning_rate": 9.62962962962963e-06, "loss": 0.6428, "step": 27 }, { "epoch": 0.0525328330206379, "grad_norm": 0.6172502636909485, "learning_rate": 1e-05, "loss": 0.6557, "step": 28 }, { "epoch": 0.054409005628517824, "grad_norm": 0.6201605796813965, "learning_rate": 1.037037037037037e-05, "loss": 0.6371, "step": 29 }, { "epoch": 0.05628517823639775, "grad_norm": 0.6146591901779175, "learning_rate": 1.0740740740740742e-05, "loss": 0.6211, "step": 30 }, { "epoch": 0.058161350844277676, "grad_norm": 0.6061451435089111, "learning_rate": 1.1111111111111113e-05, "loss": 0.6179, "step": 31 }, { "epoch": 0.0600375234521576, "grad_norm": 0.5912018418312073, "learning_rate": 1.1481481481481482e-05, "loss": 0.611, "step": 32 }, { "epoch": 0.06191369606003752, "grad_norm": 0.5214031934738159, "learning_rate": 1.1851851851851852e-05, "loss": 0.6025, "step": 33 }, { "epoch": 0.06378986866791744, "grad_norm": 0.5357693433761597, "learning_rate": 1.2222222222222224e-05, "loss": 0.6057, "step": 34 }, { "epoch": 0.06566604127579738, "grad_norm": 0.5372332334518433, "learning_rate": 1.2592592592592593e-05, "loss": 0.6085, "step": 35 }, { "epoch": 0.0675422138836773, "grad_norm": 0.5066092014312744, "learning_rate": 1.2962962962962964e-05, "loss": 0.5833, "step": 36 }, { "epoch": 0.06941838649155722, "grad_norm": 0.5455030798912048, "learning_rate": 1.3333333333333333e-05, "loss": 0.5954, "step": 37 }, { "epoch": 0.07129455909943715, "grad_norm": 0.4855195879936218, "learning_rate": 1.3703703703703706e-05, "loss": 0.5732, "step": 38 }, { "epoch": 0.07317073170731707, "grad_norm": 0.7693135142326355, "learning_rate": 1.4074074074074075e-05, "loss": 0.5762, "step": 39 }, { "epoch": 0.075046904315197, "grad_norm": 0.4799287021160126, "learning_rate": 1.4444444444444446e-05, "loss": 0.6114, "step": 40 }, { "epoch": 0.07692307692307693, "grad_norm": 0.4819142520427704, "learning_rate": 1.4814814814814815e-05, "loss": 0.5855, "step": 41 }, { "epoch": 0.07879924953095685, "grad_norm": 0.49574413895606995, "learning_rate": 1.5185185185185187e-05, "loss": 0.5762, "step": 42 }, { "epoch": 0.08067542213883677, "grad_norm": 0.4454074501991272, "learning_rate": 1.555555555555556e-05, "loss": 0.5777, "step": 43 }, { "epoch": 0.0825515947467167, "grad_norm": 0.44248902797698975, "learning_rate": 1.5925925925925926e-05, "loss": 0.5729, "step": 44 }, { "epoch": 0.08442776735459662, "grad_norm": 0.46763530373573303, "learning_rate": 1.6296296296296297e-05, "loss": 0.5741, "step": 45 }, { "epoch": 0.08630393996247655, "grad_norm": 0.42297661304473877, "learning_rate": 1.6666666666666667e-05, "loss": 0.5488, "step": 46 }, { "epoch": 0.08818011257035648, "grad_norm": 0.49024441838264465, "learning_rate": 1.7037037037037038e-05, "loss": 0.5786, "step": 47 }, { "epoch": 0.0900562851782364, "grad_norm": 0.4836975038051605, "learning_rate": 1.740740740740741e-05, "loss": 0.549, "step": 48 }, { "epoch": 0.09193245778611632, "grad_norm": 0.4239577054977417, "learning_rate": 1.7777777777777777e-05, "loss": 0.5448, "step": 49 }, { "epoch": 0.09380863039399624, "grad_norm": 0.4513685405254364, "learning_rate": 1.814814814814815e-05, "loss": 0.5412, "step": 50 }, { "epoch": 0.09568480300187618, "grad_norm": 0.45834019780158997, "learning_rate": 1.851851851851852e-05, "loss": 0.555, "step": 51 }, { "epoch": 0.0975609756097561, "grad_norm": 0.44011378288269043, "learning_rate": 1.888888888888889e-05, "loss": 0.5427, "step": 52 }, { "epoch": 0.09943714821763602, "grad_norm": 0.4496270418167114, "learning_rate": 1.925925925925926e-05, "loss": 0.5371, "step": 53 }, { "epoch": 0.10131332082551595, "grad_norm": 0.41629332304000854, "learning_rate": 1.962962962962963e-05, "loss": 0.5204, "step": 54 }, { "epoch": 0.10318949343339587, "grad_norm": 0.45103877782821655, "learning_rate": 2e-05, "loss": 0.5648, "step": 55 }, { "epoch": 0.1050656660412758, "grad_norm": 0.4260631501674652, "learning_rate": 1.999978492141723e-05, "loss": 0.5491, "step": 56 }, { "epoch": 0.10694183864915573, "grad_norm": 0.46286889910697937, "learning_rate": 1.999913969492067e-05, "loss": 0.521, "step": 57 }, { "epoch": 0.10881801125703565, "grad_norm": 0.43611228466033936, "learning_rate": 1.99980643482652e-05, "loss": 0.5296, "step": 58 }, { "epoch": 0.11069418386491557, "grad_norm": 0.4539852738380432, "learning_rate": 1.9996558927707637e-05, "loss": 0.5463, "step": 59 }, { "epoch": 0.1125703564727955, "grad_norm": 0.42966416478157043, "learning_rate": 1.9994623498004717e-05, "loss": 0.5446, "step": 60 }, { "epoch": 0.11444652908067542, "grad_norm": 0.4595656394958496, "learning_rate": 1.9992258142410335e-05, "loss": 0.5443, "step": 61 }, { "epoch": 0.11632270168855535, "grad_norm": 0.4296264052391052, "learning_rate": 1.9989462962671957e-05, "loss": 0.5388, "step": 62 }, { "epoch": 0.11819887429643527, "grad_norm": 0.45982134342193604, "learning_rate": 1.998623807902625e-05, "loss": 0.5281, "step": 63 }, { "epoch": 0.1200750469043152, "grad_norm": 0.4597987234592438, "learning_rate": 1.9982583630193882e-05, "loss": 0.5351, "step": 64 }, { "epoch": 0.12195121951219512, "grad_norm": 0.45049232244491577, "learning_rate": 1.9978499773373596e-05, "loss": 0.5393, "step": 65 }, { "epoch": 0.12382739212007504, "grad_norm": 0.438589870929718, "learning_rate": 1.997398668423542e-05, "loss": 0.5374, "step": 66 }, { "epoch": 0.12570356472795496, "grad_norm": 0.4221203327178955, "learning_rate": 1.9969044556913116e-05, "loss": 0.5198, "step": 67 }, { "epoch": 0.1275797373358349, "grad_norm": 0.4725799560546875, "learning_rate": 1.9963673603995833e-05, "loss": 0.5174, "step": 68 }, { "epoch": 0.1294559099437148, "grad_norm": 0.41669028997421265, "learning_rate": 1.9957874056518954e-05, "loss": 0.5306, "step": 69 }, { "epoch": 0.13133208255159476, "grad_norm": 0.47250062227249146, "learning_rate": 1.9951646163954177e-05, "loss": 0.5067, "step": 70 }, { "epoch": 0.13320825515947468, "grad_norm": 0.47961607575416565, "learning_rate": 1.9944990194198758e-05, "loss": 0.5372, "step": 71 }, { "epoch": 0.1350844277673546, "grad_norm": 0.4163620173931122, "learning_rate": 1.993790643356401e-05, "loss": 0.5054, "step": 72 }, { "epoch": 0.13696060037523453, "grad_norm": 0.47573086619377136, "learning_rate": 1.9930395186762967e-05, "loss": 0.529, "step": 73 }, { "epoch": 0.13883677298311445, "grad_norm": 0.43163445591926575, "learning_rate": 1.9922456776897295e-05, "loss": 0.4976, "step": 74 }, { "epoch": 0.14071294559099437, "grad_norm": 0.4349230229854584, "learning_rate": 1.991409154544338e-05, "loss": 0.4964, "step": 75 }, { "epoch": 0.1425891181988743, "grad_norm": 0.41780340671539307, "learning_rate": 1.9905299852237654e-05, "loss": 0.5256, "step": 76 }, { "epoch": 0.14446529080675422, "grad_norm": 0.4596555531024933, "learning_rate": 1.9896082075461093e-05, "loss": 0.5019, "step": 77 }, { "epoch": 0.14634146341463414, "grad_norm": 0.45016729831695557, "learning_rate": 1.9886438611622973e-05, "loss": 0.533, "step": 78 }, { "epoch": 0.14821763602251406, "grad_norm": 0.45367276668548584, "learning_rate": 1.9876369875543805e-05, "loss": 0.5198, "step": 79 }, { "epoch": 0.150093808630394, "grad_norm": 0.47471052408218384, "learning_rate": 1.986587630033748e-05, "loss": 0.5106, "step": 80 }, { "epoch": 0.15196998123827393, "grad_norm": 0.45293959975242615, "learning_rate": 1.9854958337392654e-05, "loss": 0.5015, "step": 81 }, { "epoch": 0.15384615384615385, "grad_norm": 0.43654966354370117, "learning_rate": 1.9843616456353333e-05, "loss": 0.5146, "step": 82 }, { "epoch": 0.15572232645403378, "grad_norm": 0.454272598028183, "learning_rate": 1.983185114509865e-05, "loss": 0.5256, "step": 83 }, { "epoch": 0.1575984990619137, "grad_norm": 0.4107024371623993, "learning_rate": 1.9819662909721905e-05, "loss": 0.5109, "step": 84 }, { "epoch": 0.15947467166979362, "grad_norm": 0.46822798252105713, "learning_rate": 1.9807052274508773e-05, "loss": 0.5215, "step": 85 }, { "epoch": 0.16135084427767354, "grad_norm": 0.43109920620918274, "learning_rate": 1.9794019781914764e-05, "loss": 0.5403, "step": 86 }, { "epoch": 0.16322701688555347, "grad_norm": 0.44587594270706177, "learning_rate": 1.9780565992541887e-05, "loss": 0.4877, "step": 87 }, { "epoch": 0.1651031894934334, "grad_norm": 0.45819446444511414, "learning_rate": 1.976669148511453e-05, "loss": 0.4943, "step": 88 }, { "epoch": 0.1669793621013133, "grad_norm": 0.44408440589904785, "learning_rate": 1.9752396856454576e-05, "loss": 0.5095, "step": 89 }, { "epoch": 0.16885553470919323, "grad_norm": 0.4661826193332672, "learning_rate": 1.973768272145571e-05, "loss": 0.5232, "step": 90 }, { "epoch": 0.17073170731707318, "grad_norm": 0.4267039895057678, "learning_rate": 1.9722549713057008e-05, "loss": 0.5069, "step": 91 }, { "epoch": 0.1726078799249531, "grad_norm": 0.4659229516983032, "learning_rate": 1.9706998482215654e-05, "loss": 0.4994, "step": 92 }, { "epoch": 0.17448405253283303, "grad_norm": 0.4425814747810364, "learning_rate": 1.9691029697878998e-05, "loss": 0.493, "step": 93 }, { "epoch": 0.17636022514071295, "grad_norm": 0.5046799182891846, "learning_rate": 1.9674644046955732e-05, "loss": 0.5022, "step": 94 }, { "epoch": 0.17823639774859287, "grad_norm": 0.4815562069416046, "learning_rate": 1.965784223428638e-05, "loss": 0.5086, "step": 95 }, { "epoch": 0.1801125703564728, "grad_norm": 0.463766872882843, "learning_rate": 1.9640624982612943e-05, "loss": 0.4984, "step": 96 }, { "epoch": 0.18198874296435272, "grad_norm": 0.4671774208545685, "learning_rate": 1.962299303254785e-05, "loss": 0.5002, "step": 97 }, { "epoch": 0.18386491557223264, "grad_norm": 0.4975290596485138, "learning_rate": 1.960494714254206e-05, "loss": 0.5194, "step": 98 }, { "epoch": 0.18574108818011256, "grad_norm": 0.4462299644947052, "learning_rate": 1.9586488088852465e-05, "loss": 0.5137, "step": 99 }, { "epoch": 0.18761726078799248, "grad_norm": 0.46154576539993286, "learning_rate": 1.9567616665508483e-05, "loss": 0.5029, "step": 100 }, { "epoch": 0.1894934333958724, "grad_norm": 0.4629541039466858, "learning_rate": 1.954833368427792e-05, "loss": 0.5122, "step": 101 }, { "epoch": 0.19136960600375236, "grad_norm": 0.4575340151786804, "learning_rate": 1.952863997463202e-05, "loss": 0.4964, "step": 102 }, { "epoch": 0.19324577861163228, "grad_norm": 0.43607306480407715, "learning_rate": 1.950853638370982e-05, "loss": 0.5048, "step": 103 }, { "epoch": 0.1951219512195122, "grad_norm": 0.45974987745285034, "learning_rate": 1.9488023776281695e-05, "loss": 0.5003, "step": 104 }, { "epoch": 0.19699812382739212, "grad_norm": 0.52689129114151, "learning_rate": 1.946710303471214e-05, "loss": 0.5149, "step": 105 }, { "epoch": 0.19887429643527205, "grad_norm": 0.5598635077476501, "learning_rate": 1.9445775058921856e-05, "loss": 0.5218, "step": 106 }, { "epoch": 0.20075046904315197, "grad_norm": 0.4801148474216461, "learning_rate": 1.9424040766348992e-05, "loss": 0.5, "step": 107 }, { "epoch": 0.2026266416510319, "grad_norm": 0.4354962110519409, "learning_rate": 1.9401901091909733e-05, "loss": 0.4922, "step": 108 }, { "epoch": 0.2045028142589118, "grad_norm": 0.49421778321266174, "learning_rate": 1.9379356987958022e-05, "loss": 0.5101, "step": 109 }, { "epoch": 0.20637898686679174, "grad_norm": 0.4634808599948883, "learning_rate": 1.9356409424244655e-05, "loss": 0.4723, "step": 110 }, { "epoch": 0.20825515947467166, "grad_norm": 0.45459961891174316, "learning_rate": 1.9333059387875527e-05, "loss": 0.4984, "step": 111 }, { "epoch": 0.2101313320825516, "grad_norm": 0.4482363164424896, "learning_rate": 1.930930788326918e-05, "loss": 0.4992, "step": 112 }, { "epoch": 0.21200750469043153, "grad_norm": 0.46492260694503784, "learning_rate": 1.9285155932113612e-05, "loss": 0.5049, "step": 113 }, { "epoch": 0.21388367729831145, "grad_norm": 0.4934901297092438, "learning_rate": 1.9260604573322298e-05, "loss": 0.511, "step": 114 }, { "epoch": 0.21575984990619138, "grad_norm": 0.47866374254226685, "learning_rate": 1.9235654862989537e-05, "loss": 0.4813, "step": 115 }, { "epoch": 0.2176360225140713, "grad_norm": 0.4691963493824005, "learning_rate": 1.921030787434499e-05, "loss": 0.5034, "step": 116 }, { "epoch": 0.21951219512195122, "grad_norm": 0.48848795890808105, "learning_rate": 1.9184564697707545e-05, "loss": 0.4827, "step": 117 }, { "epoch": 0.22138836772983114, "grad_norm": 0.48106610774993896, "learning_rate": 1.915842644043838e-05, "loss": 0.5097, "step": 118 }, { "epoch": 0.22326454033771106, "grad_norm": 0.46916061639785767, "learning_rate": 1.913189422689337e-05, "loss": 0.501, "step": 119 }, { "epoch": 0.225140712945591, "grad_norm": 0.46038028597831726, "learning_rate": 1.910496919837469e-05, "loss": 0.5161, "step": 120 }, { "epoch": 0.2270168855534709, "grad_norm": 0.4193981885910034, "learning_rate": 1.907765251308173e-05, "loss": 0.4696, "step": 121 }, { "epoch": 0.22889305816135083, "grad_norm": 0.47197026014328003, "learning_rate": 1.9049945346061292e-05, "loss": 0.5152, "step": 122 }, { "epoch": 0.23076923076923078, "grad_norm": 0.44787487387657166, "learning_rate": 1.902184888915701e-05, "loss": 0.4983, "step": 123 }, { "epoch": 0.2326454033771107, "grad_norm": 0.5235477685928345, "learning_rate": 1.8993364350958115e-05, "loss": 0.5041, "step": 124 }, { "epoch": 0.23452157598499063, "grad_norm": 0.4769859313964844, "learning_rate": 1.8964492956747427e-05, "loss": 0.5011, "step": 125 }, { "epoch": 0.23639774859287055, "grad_norm": 0.48972049355506897, "learning_rate": 1.8935235948448653e-05, "loss": 0.4742, "step": 126 }, { "epoch": 0.23827392120075047, "grad_norm": 0.4640520215034485, "learning_rate": 1.8905594584572973e-05, "loss": 0.5005, "step": 127 }, { "epoch": 0.2401500938086304, "grad_norm": 0.467355340719223, "learning_rate": 1.8875570140164895e-05, "loss": 0.5138, "step": 128 }, { "epoch": 0.24202626641651032, "grad_norm": 0.4687252342700958, "learning_rate": 1.8845163906747407e-05, "loss": 0.497, "step": 129 }, { "epoch": 0.24390243902439024, "grad_norm": 0.4493774175643921, "learning_rate": 1.8814377192266424e-05, "loss": 0.5025, "step": 130 }, { "epoch": 0.24577861163227016, "grad_norm": 0.4495251774787903, "learning_rate": 1.8783211321034537e-05, "loss": 0.5102, "step": 131 }, { "epoch": 0.24765478424015008, "grad_norm": 0.45046165585517883, "learning_rate": 1.8751667633674023e-05, "loss": 0.4922, "step": 132 }, { "epoch": 0.24953095684803, "grad_norm": 0.4332929849624634, "learning_rate": 1.87197474870592e-05, "loss": 0.488, "step": 133 }, { "epoch": 0.25140712945590993, "grad_norm": 0.4550478160381317, "learning_rate": 1.8687452254258046e-05, "loss": 0.512, "step": 134 }, { "epoch": 0.25328330206378985, "grad_norm": 0.4503070116043091, "learning_rate": 1.8654783324473138e-05, "loss": 0.5134, "step": 135 }, { "epoch": 0.2551594746716698, "grad_norm": 0.43286991119384766, "learning_rate": 1.8621742102981906e-05, "loss": 0.4567, "step": 136 }, { "epoch": 0.2570356472795497, "grad_norm": 0.43096885085105896, "learning_rate": 1.8588330011076167e-05, "loss": 0.5206, "step": 137 }, { "epoch": 0.2589118198874296, "grad_norm": 0.4638442099094391, "learning_rate": 1.855454848600099e-05, "loss": 0.5162, "step": 138 }, { "epoch": 0.2607879924953096, "grad_norm": 0.441213458776474, "learning_rate": 1.852039898089289e-05, "loss": 0.5092, "step": 139 }, { "epoch": 0.2626641651031895, "grad_norm": 0.4825282692909241, "learning_rate": 1.8485882964717292e-05, "loss": 0.4898, "step": 140 }, { "epoch": 0.26454033771106944, "grad_norm": 0.4525107145309448, "learning_rate": 1.845100192220537e-05, "loss": 0.4945, "step": 141 }, { "epoch": 0.26641651031894936, "grad_norm": 0.515526294708252, "learning_rate": 1.841575735379016e-05, "loss": 0.4843, "step": 142 }, { "epoch": 0.2682926829268293, "grad_norm": 0.4331778287887573, "learning_rate": 1.838015077554203e-05, "loss": 0.4641, "step": 143 }, { "epoch": 0.2701688555347092, "grad_norm": 0.47300004959106445, "learning_rate": 1.8344183719103454e-05, "loss": 0.4745, "step": 144 }, { "epoch": 0.27204502814258913, "grad_norm": 0.4185693860054016, "learning_rate": 1.8307857731623133e-05, "loss": 0.4667, "step": 145 }, { "epoch": 0.27392120075046905, "grad_norm": 0.44932979345321655, "learning_rate": 1.8271174375689454e-05, "loss": 0.5011, "step": 146 }, { "epoch": 0.275797373358349, "grad_norm": 0.4410933554172516, "learning_rate": 1.8234135229263258e-05, "loss": 0.4734, "step": 147 }, { "epoch": 0.2776735459662289, "grad_norm": 0.45480766892433167, "learning_rate": 1.819674188560997e-05, "loss": 0.5067, "step": 148 }, { "epoch": 0.2795497185741088, "grad_norm": 0.4583900272846222, "learning_rate": 1.8158995953231055e-05, "loss": 0.5051, "step": 149 }, { "epoch": 0.28142589118198874, "grad_norm": 0.421601802110672, "learning_rate": 1.8120899055794848e-05, "loss": 0.4795, "step": 150 }, { "epoch": 0.28330206378986866, "grad_norm": 0.41240212321281433, "learning_rate": 1.808245283206669e-05, "loss": 0.4904, "step": 151 }, { "epoch": 0.2851782363977486, "grad_norm": 0.4446975886821747, "learning_rate": 1.8043658935838436e-05, "loss": 0.4899, "step": 152 }, { "epoch": 0.2870544090056285, "grad_norm": 0.43199482560157776, "learning_rate": 1.800451903585734e-05, "loss": 0.4833, "step": 153 }, { "epoch": 0.28893058161350843, "grad_norm": 0.42450612783432007, "learning_rate": 1.796503481575424e-05, "loss": 0.4872, "step": 154 }, { "epoch": 0.29080675422138835, "grad_norm": 0.4116723835468292, "learning_rate": 1.7925207973971163e-05, "loss": 0.4952, "step": 155 }, { "epoch": 0.2926829268292683, "grad_norm": 0.4367542266845703, "learning_rate": 1.7885040223688234e-05, "loss": 0.488, "step": 156 }, { "epoch": 0.2945590994371482, "grad_norm": 0.47015565633773804, "learning_rate": 1.7844533292750025e-05, "loss": 0.4965, "step": 157 }, { "epoch": 0.2964352720450281, "grad_norm": 0.43937620520591736, "learning_rate": 1.7803688923591194e-05, "loss": 0.4935, "step": 158 }, { "epoch": 0.29831144465290804, "grad_norm": 0.4693063795566559, "learning_rate": 1.7762508873161542e-05, "loss": 0.4862, "step": 159 }, { "epoch": 0.300187617260788, "grad_norm": 0.444977730512619, "learning_rate": 1.7720994912850452e-05, "loss": 0.4888, "step": 160 }, { "epoch": 0.30206378986866794, "grad_norm": 0.4322124719619751, "learning_rate": 1.767914882841067e-05, "loss": 0.4875, "step": 161 }, { "epoch": 0.30393996247654786, "grad_norm": 0.4464256763458252, "learning_rate": 1.7636972419881507e-05, "loss": 0.4939, "step": 162 }, { "epoch": 0.3058161350844278, "grad_norm": 0.46564194560050964, "learning_rate": 1.759446750151139e-05, "loss": 0.4987, "step": 163 }, { "epoch": 0.3076923076923077, "grad_norm": 0.5087194442749023, "learning_rate": 1.755163590167985e-05, "loss": 0.4799, "step": 164 }, { "epoch": 0.30956848030018763, "grad_norm": 0.4272122085094452, "learning_rate": 1.7508479462818836e-05, "loss": 0.4919, "step": 165 }, { "epoch": 0.31144465290806755, "grad_norm": 0.506621778011322, "learning_rate": 1.7465000041333496e-05, "loss": 0.4846, "step": 166 }, { "epoch": 0.3133208255159475, "grad_norm": 0.4598137140274048, "learning_rate": 1.7421199507522297e-05, "loss": 0.4933, "step": 167 }, { "epoch": 0.3151969981238274, "grad_norm": 0.4636599123477936, "learning_rate": 1.7377079745496586e-05, "loss": 0.4898, "step": 168 }, { "epoch": 0.3170731707317073, "grad_norm": 0.48578599095344543, "learning_rate": 1.7332642653099542e-05, "loss": 0.5115, "step": 169 }, { "epoch": 0.31894934333958724, "grad_norm": 0.5075885653495789, "learning_rate": 1.7287890141824537e-05, "loss": 0.4839, "step": 170 }, { "epoch": 0.32082551594746717, "grad_norm": 0.48771244287490845, "learning_rate": 1.724282413673291e-05, "loss": 0.5032, "step": 171 }, { "epoch": 0.3227016885553471, "grad_norm": 0.5117051005363464, "learning_rate": 1.7197446576371163e-05, "loss": 0.4806, "step": 172 }, { "epoch": 0.324577861163227, "grad_norm": 0.48115479946136475, "learning_rate": 1.7151759412687573e-05, "loss": 0.4913, "step": 173 }, { "epoch": 0.32645403377110693, "grad_norm": 0.5075434446334839, "learning_rate": 1.7105764610948212e-05, "loss": 0.4902, "step": 174 }, { "epoch": 0.32833020637898686, "grad_norm": 0.4747563898563385, "learning_rate": 1.705946414965245e-05, "loss": 0.4934, "step": 175 }, { "epoch": 0.3302063789868668, "grad_norm": 0.45580369234085083, "learning_rate": 1.7012860020447797e-05, "loss": 0.5069, "step": 176 }, { "epoch": 0.3320825515947467, "grad_norm": 0.4514389932155609, "learning_rate": 1.6965954228044265e-05, "loss": 0.4985, "step": 177 }, { "epoch": 0.3339587242026266, "grad_norm": 0.4397890567779541, "learning_rate": 1.691874879012813e-05, "loss": 0.4543, "step": 178 }, { "epoch": 0.33583489681050654, "grad_norm": 0.47879987955093384, "learning_rate": 1.6871245737275124e-05, "loss": 0.4939, "step": 179 }, { "epoch": 0.33771106941838647, "grad_norm": 0.4909740090370178, "learning_rate": 1.682344711286311e-05, "loss": 0.4951, "step": 180 }, { "epoch": 0.3395872420262664, "grad_norm": 0.46630603075027466, "learning_rate": 1.677535497298416e-05, "loss": 0.4913, "step": 181 }, { "epoch": 0.34146341463414637, "grad_norm": 0.46876662969589233, "learning_rate": 1.6726971386356137e-05, "loss": 0.4815, "step": 182 }, { "epoch": 0.3433395872420263, "grad_norm": 0.4811256229877472, "learning_rate": 1.6678298434233687e-05, "loss": 0.4892, "step": 183 }, { "epoch": 0.3452157598499062, "grad_norm": 0.44975170493125916, "learning_rate": 1.6629338210318725e-05, "loss": 0.4848, "step": 184 }, { "epoch": 0.34709193245778613, "grad_norm": 0.47891831398010254, "learning_rate": 1.658009282067036e-05, "loss": 0.4767, "step": 185 }, { "epoch": 0.34896810506566606, "grad_norm": 0.4403041899204254, "learning_rate": 1.653056438361432e-05, "loss": 0.4866, "step": 186 }, { "epoch": 0.350844277673546, "grad_norm": 0.45113885402679443, "learning_rate": 1.648075502965181e-05, "loss": 0.4777, "step": 187 }, { "epoch": 0.3527204502814259, "grad_norm": 0.44296011328697205, "learning_rate": 1.643066690136789e-05, "loss": 0.4787, "step": 188 }, { "epoch": 0.3545966228893058, "grad_norm": 0.43343913555145264, "learning_rate": 1.638030215333928e-05, "loss": 0.4725, "step": 189 }, { "epoch": 0.35647279549718575, "grad_norm": 0.4752146005630493, "learning_rate": 1.6329662952041712e-05, "loss": 0.4972, "step": 190 }, { "epoch": 0.35834896810506567, "grad_norm": 0.47067368030548096, "learning_rate": 1.6278751475756712e-05, "loss": 0.4814, "step": 191 }, { "epoch": 0.3602251407129456, "grad_norm": 0.449448823928833, "learning_rate": 1.6227569914477914e-05, "loss": 0.4948, "step": 192 }, { "epoch": 0.3621013133208255, "grad_norm": 0.43309763073921204, "learning_rate": 1.617612046981685e-05, "loss": 0.4759, "step": 193 }, { "epoch": 0.36397748592870544, "grad_norm": 0.4724906384944916, "learning_rate": 1.6124405354908246e-05, "loss": 0.4779, "step": 194 }, { "epoch": 0.36585365853658536, "grad_norm": 0.4331618845462799, "learning_rate": 1.6072426794314836e-05, "loss": 0.4936, "step": 195 }, { "epoch": 0.3677298311444653, "grad_norm": 0.4011441469192505, "learning_rate": 1.602018702393164e-05, "loss": 0.4701, "step": 196 }, { "epoch": 0.3696060037523452, "grad_norm": 0.4599146246910095, "learning_rate": 1.5967688290889817e-05, "loss": 0.4584, "step": 197 }, { "epoch": 0.3714821763602251, "grad_norm": 0.4477120637893677, "learning_rate": 1.591493285345999e-05, "loss": 0.4932, "step": 198 }, { "epoch": 0.37335834896810505, "grad_norm": 0.4366087317466736, "learning_rate": 1.5861922980955092e-05, "loss": 0.4853, "step": 199 }, { "epoch": 0.37523452157598497, "grad_norm": 0.4719770848751068, "learning_rate": 1.5808660953632783e-05, "loss": 0.4881, "step": 200 }, { "epoch": 0.3771106941838649, "grad_norm": 0.4526340961456299, "learning_rate": 1.5755149062597332e-05, "loss": 0.4972, "step": 201 }, { "epoch": 0.3789868667917448, "grad_norm": 0.4521251618862152, "learning_rate": 1.5701389609701076e-05, "loss": 0.4854, "step": 202 }, { "epoch": 0.3808630393996248, "grad_norm": 0.41455745697021484, "learning_rate": 1.5647384907445402e-05, "loss": 0.486, "step": 203 }, { "epoch": 0.3827392120075047, "grad_norm": 0.47328656911849976, "learning_rate": 1.559313727888127e-05, "loss": 0.477, "step": 204 }, { "epoch": 0.38461538461538464, "grad_norm": 0.4337882697582245, "learning_rate": 1.5538649057509307e-05, "loss": 0.4757, "step": 205 }, { "epoch": 0.38649155722326456, "grad_norm": 0.4305742681026459, "learning_rate": 1.5483922587179386e-05, "loss": 0.4907, "step": 206 }, { "epoch": 0.3883677298311445, "grad_norm": 0.4382014870643616, "learning_rate": 1.5428960221989844e-05, "loss": 0.4805, "step": 207 }, { "epoch": 0.3902439024390244, "grad_norm": 0.4552824795246124, "learning_rate": 1.537376432618621e-05, "loss": 0.476, "step": 208 }, { "epoch": 0.3921200750469043, "grad_norm": 0.430683434009552, "learning_rate": 1.5318337274059492e-05, "loss": 0.496, "step": 209 }, { "epoch": 0.39399624765478425, "grad_norm": 0.46657851338386536, "learning_rate": 1.5262681449844047e-05, "loss": 0.466, "step": 210 }, { "epoch": 0.39587242026266417, "grad_norm": 0.42215755581855774, "learning_rate": 1.5206799247615038e-05, "loss": 0.4694, "step": 211 }, { "epoch": 0.3977485928705441, "grad_norm": 0.44483405351638794, "learning_rate": 1.5150693071185441e-05, "loss": 0.4625, "step": 212 }, { "epoch": 0.399624765478424, "grad_norm": 0.4508770704269409, "learning_rate": 1.5094365334002631e-05, "loss": 0.4721, "step": 213 }, { "epoch": 0.40150093808630394, "grad_norm": 0.47280606627464294, "learning_rate": 1.5037818459044589e-05, "loss": 0.4988, "step": 214 }, { "epoch": 0.40337711069418386, "grad_norm": 0.46489429473876953, "learning_rate": 1.498105487871566e-05, "loss": 0.4775, "step": 215 }, { "epoch": 0.4052532833020638, "grad_norm": 0.45847252011299133, "learning_rate": 1.4924077034741924e-05, "loss": 0.501, "step": 216 }, { "epoch": 0.4071294559099437, "grad_norm": 0.4636571407318115, "learning_rate": 1.4866887378066169e-05, "loss": 0.4603, "step": 217 }, { "epoch": 0.4090056285178236, "grad_norm": 0.4642573893070221, "learning_rate": 1.4809488368742458e-05, "loss": 0.452, "step": 218 }, { "epoch": 0.41088180112570355, "grad_norm": 0.42232292890548706, "learning_rate": 1.4751882475830302e-05, "loss": 0.4969, "step": 219 }, { "epoch": 0.41275797373358347, "grad_norm": 0.5324833989143372, "learning_rate": 1.4694072177288464e-05, "loss": 0.4563, "step": 220 }, { "epoch": 0.4146341463414634, "grad_norm": 0.4543067514896393, "learning_rate": 1.4636059959868363e-05, "loss": 0.4663, "step": 221 }, { "epoch": 0.4165103189493433, "grad_norm": 0.45857909321784973, "learning_rate": 1.4577848319007098e-05, "loss": 0.4857, "step": 222 }, { "epoch": 0.41838649155722324, "grad_norm": 0.4585043787956238, "learning_rate": 1.4519439758720108e-05, "loss": 0.4722, "step": 223 }, { "epoch": 0.4202626641651032, "grad_norm": 0.431410551071167, "learning_rate": 1.4460836791493477e-05, "loss": 0.4857, "step": 224 }, { "epoch": 0.42213883677298314, "grad_norm": 0.4164378345012665, "learning_rate": 1.4402041938175826e-05, "loss": 0.4703, "step": 225 }, { "epoch": 0.42401500938086306, "grad_norm": 0.43511542677879333, "learning_rate": 1.43430577278699e-05, "loss": 0.5023, "step": 226 }, { "epoch": 0.425891181988743, "grad_norm": 0.4781929552555084, "learning_rate": 1.428388669782377e-05, "loss": 0.489, "step": 227 }, { "epoch": 0.4277673545966229, "grad_norm": 0.38802462816238403, "learning_rate": 1.4224531393321696e-05, "loss": 0.4669, "step": 228 }, { "epoch": 0.42964352720450283, "grad_norm": 0.3962300419807434, "learning_rate": 1.4164994367574631e-05, "loss": 0.4001, "step": 229 }, { "epoch": 0.43151969981238275, "grad_norm": 0.44593545794487, "learning_rate": 1.41052781816104e-05, "loss": 0.4861, "step": 230 }, { "epoch": 0.4333958724202627, "grad_norm": 0.4363047182559967, "learning_rate": 1.4045385404163533e-05, "loss": 0.4897, "step": 231 }, { "epoch": 0.4352720450281426, "grad_norm": 0.4661344885826111, "learning_rate": 1.3985318611564761e-05, "loss": 0.4867, "step": 232 }, { "epoch": 0.4371482176360225, "grad_norm": 0.48936548829078674, "learning_rate": 1.3925080387630217e-05, "loss": 0.4686, "step": 233 }, { "epoch": 0.43902439024390244, "grad_norm": 0.4576188623905182, "learning_rate": 1.3864673323550264e-05, "loss": 0.4811, "step": 234 }, { "epoch": 0.44090056285178236, "grad_norm": 0.44022276997566223, "learning_rate": 1.3804100017778048e-05, "loss": 0.4866, "step": 235 }, { "epoch": 0.4427767354596623, "grad_norm": 0.48328202962875366, "learning_rate": 1.3743363075917723e-05, "loss": 0.4863, "step": 236 }, { "epoch": 0.4446529080675422, "grad_norm": 0.44896700978279114, "learning_rate": 1.3682465110612361e-05, "loss": 0.4797, "step": 237 }, { "epoch": 0.44652908067542213, "grad_norm": 0.4463822841644287, "learning_rate": 1.3621408741431583e-05, "loss": 0.4676, "step": 238 }, { "epoch": 0.44840525328330205, "grad_norm": 0.4772860109806061, "learning_rate": 1.3560196594758855e-05, "loss": 0.4581, "step": 239 }, { "epoch": 0.450281425891182, "grad_norm": 0.4344514012336731, "learning_rate": 1.3498831303678525e-05, "loss": 0.4658, "step": 240 }, { "epoch": 0.4521575984990619, "grad_norm": 0.4256344735622406, "learning_rate": 1.3437315507862568e-05, "loss": 0.4817, "step": 241 }, { "epoch": 0.4540337711069418, "grad_norm": 0.44355109333992004, "learning_rate": 1.3375651853457012e-05, "loss": 0.4938, "step": 242 }, { "epoch": 0.45590994371482174, "grad_norm": 0.39970898628234863, "learning_rate": 1.331384299296814e-05, "loss": 0.474, "step": 243 }, { "epoch": 0.45778611632270166, "grad_norm": 0.43661677837371826, "learning_rate": 1.325189158514838e-05, "loss": 0.4736, "step": 244 }, { "epoch": 0.4596622889305816, "grad_norm": 0.39525124430656433, "learning_rate": 1.3189800294881926e-05, "loss": 0.4699, "step": 245 }, { "epoch": 0.46153846153846156, "grad_norm": 0.4325285851955414, "learning_rate": 1.312757179307012e-05, "loss": 0.4885, "step": 246 }, { "epoch": 0.4634146341463415, "grad_norm": 0.403023362159729, "learning_rate": 1.3065208756516557e-05, "loss": 0.4775, "step": 247 }, { "epoch": 0.4652908067542214, "grad_norm": 0.434388667345047, "learning_rate": 1.3002713867811947e-05, "loss": 0.474, "step": 248 }, { "epoch": 0.46716697936210133, "grad_norm": 0.4568539559841156, "learning_rate": 1.2940089815218703e-05, "loss": 0.4998, "step": 249 }, { "epoch": 0.46904315196998125, "grad_norm": 0.43496668338775635, "learning_rate": 1.287733929255532e-05, "loss": 0.4753, "step": 250 }, { "epoch": 0.4709193245778612, "grad_norm": 0.38006827235221863, "learning_rate": 1.28144649990805e-05, "loss": 0.4618, "step": 251 }, { "epoch": 0.4727954971857411, "grad_norm": 0.40870386362075806, "learning_rate": 1.2751469639377028e-05, "loss": 0.4708, "step": 252 }, { "epoch": 0.474671669793621, "grad_norm": 0.40516600012779236, "learning_rate": 1.2688355923235439e-05, "loss": 0.4666, "step": 253 }, { "epoch": 0.47654784240150094, "grad_norm": 0.41616344451904297, "learning_rate": 1.2625126565537458e-05, "loss": 0.4774, "step": 254 }, { "epoch": 0.47842401500938087, "grad_norm": 0.41662484407424927, "learning_rate": 1.2561784286139214e-05, "loss": 0.4696, "step": 255 }, { "epoch": 0.4803001876172608, "grad_norm": 0.46140581369400024, "learning_rate": 1.2498331809754243e-05, "loss": 0.4584, "step": 256 }, { "epoch": 0.4821763602251407, "grad_norm": 0.38339847326278687, "learning_rate": 1.2434771865836281e-05, "loss": 0.4705, "step": 257 }, { "epoch": 0.48405253283302063, "grad_norm": 0.39309021830558777, "learning_rate": 1.2371107188461868e-05, "loss": 0.4826, "step": 258 }, { "epoch": 0.48592870544090055, "grad_norm": 0.4067246615886688, "learning_rate": 1.2307340516212713e-05, "loss": 0.4745, "step": 259 }, { "epoch": 0.4878048780487805, "grad_norm": 0.3975689113140106, "learning_rate": 1.2243474592057918e-05, "loss": 0.47, "step": 260 }, { "epoch": 0.4896810506566604, "grad_norm": 0.4230562448501587, "learning_rate": 1.2179512163235973e-05, "loss": 0.4664, "step": 261 }, { "epoch": 0.4915572232645403, "grad_norm": 0.4172329008579254, "learning_rate": 1.2115455981136587e-05, "loss": 0.4624, "step": 262 }, { "epoch": 0.49343339587242024, "grad_norm": 0.3934493064880371, "learning_rate": 1.2051308801182333e-05, "loss": 0.4741, "step": 263 }, { "epoch": 0.49530956848030017, "grad_norm": 0.40225809812545776, "learning_rate": 1.1987073382710123e-05, "loss": 0.4577, "step": 264 }, { "epoch": 0.4971857410881801, "grad_norm": 0.4090576469898224, "learning_rate": 1.1922752488852512e-05, "loss": 0.4688, "step": 265 }, { "epoch": 0.49906191369606, "grad_norm": 0.39649295806884766, "learning_rate": 1.1858348886418832e-05, "loss": 0.4637, "step": 266 }, { "epoch": 0.50093808630394, "grad_norm": 0.44001370668411255, "learning_rate": 1.1793865345776193e-05, "loss": 0.4708, "step": 267 }, { "epoch": 0.5028142589118199, "grad_norm": 0.41409698128700256, "learning_rate": 1.1729304640730303e-05, "loss": 0.4764, "step": 268 }, { "epoch": 0.5046904315196998, "grad_norm": 0.4101436138153076, "learning_rate": 1.1664669548406153e-05, "loss": 0.4701, "step": 269 }, { "epoch": 0.5065666041275797, "grad_norm": 0.4108476936817169, "learning_rate": 1.159996284912855e-05, "loss": 0.4764, "step": 270 }, { "epoch": 0.5084427767354597, "grad_norm": 0.40407615900039673, "learning_rate": 1.153518732630253e-05, "loss": 0.4875, "step": 271 }, { "epoch": 0.5103189493433395, "grad_norm": 0.3871546983718872, "learning_rate": 1.1470345766293627e-05, "loss": 0.4784, "step": 272 }, { "epoch": 0.5121951219512195, "grad_norm": 0.3768629729747772, "learning_rate": 1.1405440958308001e-05, "loss": 0.4168, "step": 273 }, { "epoch": 0.5140712945590994, "grad_norm": 0.3968166708946228, "learning_rate": 1.1340475694272479e-05, "loss": 0.4451, "step": 274 }, { "epoch": 0.5159474671669794, "grad_norm": 0.38803425431251526, "learning_rate": 1.1275452768714444e-05, "loss": 0.481, "step": 275 }, { "epoch": 0.5178236397748592, "grad_norm": 0.4098987579345703, "learning_rate": 1.121037497864163e-05, "loss": 0.4644, "step": 276 }, { "epoch": 0.5196998123827392, "grad_norm": 0.41665926575660706, "learning_rate": 1.1145245123421812e-05, "loss": 0.4752, "step": 277 }, { "epoch": 0.5215759849906192, "grad_norm": 0.435349702835083, "learning_rate": 1.108006600466238e-05, "loss": 0.452, "step": 278 }, { "epoch": 0.5234521575984991, "grad_norm": 0.4160681962966919, "learning_rate": 1.101484042608983e-05, "loss": 0.4857, "step": 279 }, { "epoch": 0.525328330206379, "grad_norm": 0.38691315054893494, "learning_rate": 1.0949571193429162e-05, "loss": 0.4847, "step": 280 }, { "epoch": 0.5272045028142589, "grad_norm": 0.4164392650127411, "learning_rate": 1.088426111428319e-05, "loss": 0.4807, "step": 281 }, { "epoch": 0.5290806754221389, "grad_norm": 0.4300763010978699, "learning_rate": 1.0818912998011766e-05, "loss": 0.4534, "step": 282 }, { "epoch": 0.5309568480300187, "grad_norm": 0.40870925784111023, "learning_rate": 1.0753529655610935e-05, "loss": 0.4695, "step": 283 }, { "epoch": 0.5328330206378987, "grad_norm": 0.3918152153491974, "learning_rate": 1.0688113899592025e-05, "loss": 0.454, "step": 284 }, { "epoch": 0.5347091932457786, "grad_norm": 0.4441761374473572, "learning_rate": 1.0622668543860653e-05, "loss": 0.4816, "step": 285 }, { "epoch": 0.5365853658536586, "grad_norm": 0.4223552346229553, "learning_rate": 1.0557196403595689e-05, "loss": 0.4685, "step": 286 }, { "epoch": 0.5384615384615384, "grad_norm": 0.42374157905578613, "learning_rate": 1.0491700295128163e-05, "loss": 0.4749, "step": 287 }, { "epoch": 0.5403377110694184, "grad_norm": 0.482738196849823, "learning_rate": 1.0426183035820112e-05, "loss": 0.4808, "step": 288 }, { "epoch": 0.5422138836772983, "grad_norm": 0.4222562313079834, "learning_rate": 1.0360647443943392e-05, "loss": 0.4537, "step": 289 }, { "epoch": 0.5440900562851783, "grad_norm": 0.4363473057746887, "learning_rate": 1.0295096338558447e-05, "loss": 0.4684, "step": 290 }, { "epoch": 0.5459662288930581, "grad_norm": 0.4176522493362427, "learning_rate": 1.0229532539393051e-05, "loss": 0.4707, "step": 291 }, { "epoch": 0.5478424015009381, "grad_norm": 0.41336387395858765, "learning_rate": 1.0163958866720996e-05, "loss": 0.4852, "step": 292 }, { "epoch": 0.549718574108818, "grad_norm": 0.40363791584968567, "learning_rate": 1.00983781412408e-05, "loss": 0.4735, "step": 293 }, { "epoch": 0.551594746716698, "grad_norm": 0.42629796266555786, "learning_rate": 1.0032793183954371e-05, "loss": 0.487, "step": 294 }, { "epoch": 0.5534709193245778, "grad_norm": 0.40003812313079834, "learning_rate": 9.967206816045634e-06, "loss": 0.4626, "step": 295 }, { "epoch": 0.5553470919324578, "grad_norm": 0.3810182809829712, "learning_rate": 9.901621858759203e-06, "loss": 0.467, "step": 296 }, { "epoch": 0.5572232645403377, "grad_norm": 0.4191839098930359, "learning_rate": 9.83604113327901e-06, "loss": 0.4804, "step": 297 }, { "epoch": 0.5590994371482176, "grad_norm": 0.3994486629962921, "learning_rate": 9.77046746060695e-06, "loss": 0.4788, "step": 298 }, { "epoch": 0.5609756097560976, "grad_norm": 0.41478341817855835, "learning_rate": 9.704903661441555e-06, "loss": 0.4678, "step": 299 }, { "epoch": 0.5628517823639775, "grad_norm": 0.3982663154602051, "learning_rate": 9.63935255605661e-06, "loss": 0.4609, "step": 300 }, { "epoch": 0.5647279549718575, "grad_norm": 0.3930562138557434, "learning_rate": 9.573816964179891e-06, "loss": 0.4724, "step": 301 }, { "epoch": 0.5666041275797373, "grad_norm": 0.38638681173324585, "learning_rate": 9.50829970487184e-06, "loss": 0.4375, "step": 302 }, { "epoch": 0.5684803001876173, "grad_norm": 0.3946895897388458, "learning_rate": 9.442803596404315e-06, "loss": 0.4746, "step": 303 }, { "epoch": 0.5703564727954972, "grad_norm": 0.42083805799484253, "learning_rate": 9.377331456139352e-06, "loss": 0.4894, "step": 304 }, { "epoch": 0.5722326454033771, "grad_norm": 0.3850444257259369, "learning_rate": 9.311886100407975e-06, "loss": 0.4835, "step": 305 }, { "epoch": 0.574108818011257, "grad_norm": 0.4170306324958801, "learning_rate": 9.246470344389065e-06, "loss": 0.4502, "step": 306 }, { "epoch": 0.575984990619137, "grad_norm": 0.5081507563591003, "learning_rate": 9.181087001988236e-06, "loss": 0.456, "step": 307 }, { "epoch": 0.5778611632270169, "grad_norm": 0.40114471316337585, "learning_rate": 9.115738885716812e-06, "loss": 0.4694, "step": 308 }, { "epoch": 0.5797373358348968, "grad_norm": 0.3917900025844574, "learning_rate": 9.050428806570841e-06, "loss": 0.4803, "step": 309 }, { "epoch": 0.5816135084427767, "grad_norm": 0.3974637985229492, "learning_rate": 8.985159573910173e-06, "loss": 0.4665, "step": 310 }, { "epoch": 0.5834896810506567, "grad_norm": 0.3936939537525177, "learning_rate": 8.919933995337624e-06, "loss": 0.4894, "step": 311 }, { "epoch": 0.5853658536585366, "grad_norm": 0.3804459869861603, "learning_rate": 8.85475487657819e-06, "loss": 0.4572, "step": 312 }, { "epoch": 0.5872420262664165, "grad_norm": 0.3730376362800598, "learning_rate": 8.789625021358371e-06, "loss": 0.4665, "step": 313 }, { "epoch": 0.5891181988742964, "grad_norm": 0.39923325181007385, "learning_rate": 8.724547231285558e-06, "loss": 0.4741, "step": 314 }, { "epoch": 0.5909943714821764, "grad_norm": 0.37232276797294617, "learning_rate": 8.659524305727524e-06, "loss": 0.4625, "step": 315 }, { "epoch": 0.5928705440900562, "grad_norm": 0.3921473026275635, "learning_rate": 8.594559041692004e-06, "loss": 0.4591, "step": 316 }, { "epoch": 0.5947467166979362, "grad_norm": 0.39849600195884705, "learning_rate": 8.529654233706378e-06, "loss": 0.4559, "step": 317 }, { "epoch": 0.5966228893058161, "grad_norm": 0.39225223660469055, "learning_rate": 8.464812673697468e-06, "loss": 0.4806, "step": 318 }, { "epoch": 0.5984990619136961, "grad_norm": 0.41534101963043213, "learning_rate": 8.400037150871452e-06, "loss": 0.4573, "step": 319 }, { "epoch": 0.600375234521576, "grad_norm": 0.364001989364624, "learning_rate": 8.33533045159385e-06, "loss": 0.4441, "step": 320 }, { "epoch": 0.6022514071294559, "grad_norm": 0.4032931327819824, "learning_rate": 8.270695359269699e-06, "loss": 0.4841, "step": 321 }, { "epoch": 0.6041275797373359, "grad_norm": 0.411393940448761, "learning_rate": 8.20613465422381e-06, "loss": 0.4595, "step": 322 }, { "epoch": 0.6060037523452158, "grad_norm": 0.38068366050720215, "learning_rate": 8.141651113581173e-06, "loss": 0.4695, "step": 323 }, { "epoch": 0.6078799249530957, "grad_norm": 0.40632885694503784, "learning_rate": 8.077247511147495e-06, "loss": 0.4987, "step": 324 }, { "epoch": 0.6097560975609756, "grad_norm": 0.42743155360221863, "learning_rate": 8.012926617289879e-06, "loss": 0.4571, "step": 325 }, { "epoch": 0.6116322701688556, "grad_norm": 0.3742930591106415, "learning_rate": 7.948691198817667e-06, "loss": 0.4709, "step": 326 }, { "epoch": 0.6135084427767354, "grad_norm": 0.38311901688575745, "learning_rate": 7.884544018863414e-06, "loss": 0.4672, "step": 327 }, { "epoch": 0.6153846153846154, "grad_norm": 0.4228517413139343, "learning_rate": 7.82048783676403e-06, "loss": 0.4779, "step": 328 }, { "epoch": 0.6172607879924953, "grad_norm": 0.4097955822944641, "learning_rate": 7.756525407942087e-06, "loss": 0.459, "step": 329 }, { "epoch": 0.6191369606003753, "grad_norm": 0.3821118175983429, "learning_rate": 7.692659483787292e-06, "loss": 0.4692, "step": 330 }, { "epoch": 0.6210131332082551, "grad_norm": 0.36977776885032654, "learning_rate": 7.628892811538138e-06, "loss": 0.4581, "step": 331 }, { "epoch": 0.6228893058161351, "grad_norm": 0.39426207542419434, "learning_rate": 7.565228134163719e-06, "loss": 0.4632, "step": 332 }, { "epoch": 0.624765478424015, "grad_norm": 0.37044960260391235, "learning_rate": 7.50166819024576e-06, "loss": 0.4805, "step": 333 }, { "epoch": 0.626641651031895, "grad_norm": 0.3636074960231781, "learning_rate": 7.43821571386079e-06, "loss": 0.4649, "step": 334 }, { "epoch": 0.6285178236397748, "grad_norm": 0.40089529752731323, "learning_rate": 7.374873434462546e-06, "loss": 0.4617, "step": 335 }, { "epoch": 0.6303939962476548, "grad_norm": 0.3862261474132538, "learning_rate": 7.311644076764565e-06, "loss": 0.4946, "step": 336 }, { "epoch": 0.6322701688555347, "grad_norm": 0.38654249906539917, "learning_rate": 7.248530360622975e-06, "loss": 0.4445, "step": 337 }, { "epoch": 0.6341463414634146, "grad_norm": 0.3740447461605072, "learning_rate": 7.1855350009195e-06, "loss": 0.4556, "step": 338 }, { "epoch": 0.6360225140712945, "grad_norm": 0.40742936730384827, "learning_rate": 7.12266070744468e-06, "loss": 0.4694, "step": 339 }, { "epoch": 0.6378986866791745, "grad_norm": 0.37905779480934143, "learning_rate": 7.0599101847813e-06, "loss": 0.4759, "step": 340 }, { "epoch": 0.6397748592870544, "grad_norm": 0.4220942556858063, "learning_rate": 6.9972861321880566e-06, "loss": 0.4764, "step": 341 }, { "epoch": 0.6416510318949343, "grad_norm": 0.3825709819793701, "learning_rate": 6.9347912434834455e-06, "loss": 0.4522, "step": 342 }, { "epoch": 0.6435272045028143, "grad_norm": 0.40397360920906067, "learning_rate": 6.872428206929887e-06, "loss": 0.4756, "step": 343 }, { "epoch": 0.6454033771106942, "grad_norm": 0.42121949791908264, "learning_rate": 6.810199705118081e-06, "loss": 0.4468, "step": 344 }, { "epoch": 0.6472795497185742, "grad_norm": 0.39659222960472107, "learning_rate": 6.748108414851622e-06, "loss": 0.4609, "step": 345 }, { "epoch": 0.649155722326454, "grad_norm": 0.3952244520187378, "learning_rate": 6.6861570070318595e-06, "loss": 0.4782, "step": 346 }, { "epoch": 0.651031894934334, "grad_norm": 0.399282306432724, "learning_rate": 6.624348146542991e-06, "loss": 0.4634, "step": 347 }, { "epoch": 0.6529080675422139, "grad_norm": 0.38961517810821533, "learning_rate": 6.562684492137435e-06, "loss": 0.4639, "step": 348 }, { "epoch": 0.6547842401500938, "grad_norm": 0.40523359179496765, "learning_rate": 6.501168696321476e-06, "loss": 0.4539, "step": 349 }, { "epoch": 0.6566604127579737, "grad_norm": 0.3791859447956085, "learning_rate": 6.439803405241149e-06, "loss": 0.4681, "step": 350 }, { "epoch": 0.6585365853658537, "grad_norm": 0.41422030329704285, "learning_rate": 6.378591258568421e-06, "loss": 0.4756, "step": 351 }, { "epoch": 0.6604127579737336, "grad_norm": 0.38266244530677795, "learning_rate": 6.317534889387638e-06, "loss": 0.4744, "step": 352 }, { "epoch": 0.6622889305816135, "grad_norm": 0.3789862096309662, "learning_rate": 6.2566369240822775e-06, "loss": 0.4568, "step": 353 }, { "epoch": 0.6641651031894934, "grad_norm": 0.36977142095565796, "learning_rate": 6.1958999822219535e-06, "loss": 0.446, "step": 354 }, { "epoch": 0.6660412757973734, "grad_norm": 0.41515210270881653, "learning_rate": 6.13532667644974e-06, "loss": 0.4588, "step": 355 }, { "epoch": 0.6679174484052532, "grad_norm": 0.3867998421192169, "learning_rate": 6.074919612369787e-06, "loss": 0.4644, "step": 356 }, { "epoch": 0.6697936210131332, "grad_norm": 0.3649778664112091, "learning_rate": 6.014681388435243e-06, "loss": 0.4827, "step": 357 }, { "epoch": 0.6716697936210131, "grad_norm": 0.3807336986064911, "learning_rate": 5.95461459583647e-06, "loss": 0.4676, "step": 358 }, { "epoch": 0.6735459662288931, "grad_norm": 0.39816009998321533, "learning_rate": 5.894721818389602e-06, "loss": 0.4713, "step": 359 }, { "epoch": 0.6754221388367729, "grad_norm": 0.40490055084228516, "learning_rate": 5.83500563242537e-06, "loss": 0.4609, "step": 360 }, { "epoch": 0.6772983114446529, "grad_norm": 0.3870190978050232, "learning_rate": 5.775468606678305e-06, "loss": 0.4515, "step": 361 }, { "epoch": 0.6791744840525328, "grad_norm": 0.3919334411621094, "learning_rate": 5.7161133021762315e-06, "loss": 0.459, "step": 362 }, { "epoch": 0.6810506566604128, "grad_norm": 0.40317437052726746, "learning_rate": 5.6569422721301034e-06, "loss": 0.4919, "step": 363 }, { "epoch": 0.6829268292682927, "grad_norm": 0.4027089774608612, "learning_rate": 5.597958061824179e-06, "loss": 0.471, "step": 364 }, { "epoch": 0.6848030018761726, "grad_norm": 0.3774213492870331, "learning_rate": 5.539163208506524e-06, "loss": 0.4667, "step": 365 }, { "epoch": 0.6866791744840526, "grad_norm": 0.3761104941368103, "learning_rate": 5.480560241279891e-06, "loss": 0.4737, "step": 366 }, { "epoch": 0.6885553470919324, "grad_norm": 0.37898918986320496, "learning_rate": 5.422151680992907e-06, "loss": 0.4838, "step": 367 }, { "epoch": 0.6904315196998124, "grad_norm": 0.3650558590888977, "learning_rate": 5.363940040131641e-06, "loss": 0.4556, "step": 368 }, { "epoch": 0.6923076923076923, "grad_norm": 0.41331934928894043, "learning_rate": 5.305927822711539e-06, "loss": 0.457, "step": 369 }, { "epoch": 0.6941838649155723, "grad_norm": 0.38073617219924927, "learning_rate": 5.2481175241697024e-06, "loss": 0.4598, "step": 370 }, { "epoch": 0.6960600375234521, "grad_norm": 0.40819063782691956, "learning_rate": 5.190511631257548e-06, "loss": 0.463, "step": 371 }, { "epoch": 0.6979362101313321, "grad_norm": 0.40303105115890503, "learning_rate": 5.133112621933831e-06, "loss": 0.4705, "step": 372 }, { "epoch": 0.699812382739212, "grad_norm": 0.3903728723526001, "learning_rate": 5.075922965258077e-06, "loss": 0.4478, "step": 373 }, { "epoch": 0.701688555347092, "grad_norm": 1.0995211601257324, "learning_rate": 5.018945121284342e-06, "loss": 0.4609, "step": 374 }, { "epoch": 0.7035647279549718, "grad_norm": 0.37805426120758057, "learning_rate": 4.962181540955412e-06, "loss": 0.439, "step": 375 }, { "epoch": 0.7054409005628518, "grad_norm": 0.3795923888683319, "learning_rate": 4.905634665997371e-06, "loss": 0.4805, "step": 376 }, { "epoch": 0.7073170731707317, "grad_norm": 0.3871743083000183, "learning_rate": 4.849306928814562e-06, "loss": 0.4763, "step": 377 }, { "epoch": 0.7091932457786116, "grad_norm": 0.3588029444217682, "learning_rate": 4.793200752384963e-06, "loss": 0.4555, "step": 378 }, { "epoch": 0.7110694183864915, "grad_norm": 0.39265263080596924, "learning_rate": 4.7373185501559575e-06, "loss": 0.464, "step": 379 }, { "epoch": 0.7129455909943715, "grad_norm": 0.3756472170352936, "learning_rate": 4.681662725940514e-06, "loss": 0.4712, "step": 380 }, { "epoch": 0.7148217636022514, "grad_norm": 0.38207897543907166, "learning_rate": 4.626235673813794e-06, "loss": 0.471, "step": 381 }, { "epoch": 0.7166979362101313, "grad_norm": 0.45319947600364685, "learning_rate": 4.57103977801016e-06, "loss": 0.4579, "step": 382 }, { "epoch": 0.7185741088180112, "grad_norm": 0.37751689553260803, "learning_rate": 4.516077412820622e-06, "loss": 0.4725, "step": 383 }, { "epoch": 0.7204502814258912, "grad_norm": 0.37137770652770996, "learning_rate": 4.461350942490701e-06, "loss": 0.4512, "step": 384 }, { "epoch": 0.7223264540337712, "grad_norm": 0.37328335642814636, "learning_rate": 4.40686272111873e-06, "loss": 0.4526, "step": 385 }, { "epoch": 0.724202626641651, "grad_norm": 0.4662545919418335, "learning_rate": 4.3526150925546005e-06, "loss": 0.4715, "step": 386 }, { "epoch": 0.726078799249531, "grad_norm": 0.3949073553085327, "learning_rate": 4.298610390298926e-06, "loss": 0.4645, "step": 387 }, { "epoch": 0.7279549718574109, "grad_norm": 0.3606877326965332, "learning_rate": 4.244850937402669e-06, "loss": 0.4627, "step": 388 }, { "epoch": 0.7298311444652908, "grad_norm": 0.3852671682834625, "learning_rate": 4.191339046367219e-06, "loss": 0.4689, "step": 389 }, { "epoch": 0.7317073170731707, "grad_norm": 0.4201098084449768, "learning_rate": 4.138077019044911e-06, "loss": 0.468, "step": 390 }, { "epoch": 0.7335834896810507, "grad_norm": 0.3923519551753998, "learning_rate": 4.085067146540015e-06, "loss": 0.4599, "step": 391 }, { "epoch": 0.7354596622889306, "grad_norm": 0.36301520466804504, "learning_rate": 4.032311709110185e-06, "loss": 0.455, "step": 392 }, { "epoch": 0.7373358348968105, "grad_norm": 0.3901977241039276, "learning_rate": 3.979812976068362e-06, "loss": 0.4511, "step": 393 }, { "epoch": 0.7392120075046904, "grad_norm": 0.3626657724380493, "learning_rate": 3.927573205685167e-06, "loss": 0.4614, "step": 394 }, { "epoch": 0.7410881801125704, "grad_norm": 0.3936521112918854, "learning_rate": 3.875594645091755e-06, "loss": 0.4673, "step": 395 }, { "epoch": 0.7429643527204502, "grad_norm": 0.38001248240470886, "learning_rate": 3.823879530183155e-06, "loss": 0.48, "step": 396 }, { "epoch": 0.7448405253283302, "grad_norm": 0.37876972556114197, "learning_rate": 3.7724300855220906e-06, "loss": 0.4646, "step": 397 }, { "epoch": 0.7467166979362101, "grad_norm": 0.41002485156059265, "learning_rate": 3.7212485242432885e-06, "loss": 0.4622, "step": 398 }, { "epoch": 0.7485928705440901, "grad_norm": 0.3855739235877991, "learning_rate": 3.670337047958288e-06, "loss": 0.4426, "step": 399 }, { "epoch": 0.7504690431519699, "grad_norm": 0.3790871202945709, "learning_rate": 3.619697846660719e-06, "loss": 0.4592, "step": 400 }, { "epoch": 0.7523452157598499, "grad_norm": 0.3793615698814392, "learning_rate": 3.5693330986321096e-06, "loss": 0.4674, "step": 401 }, { "epoch": 0.7542213883677298, "grad_norm": 0.38816037774086, "learning_rate": 3.5192449703481877e-06, "loss": 0.4758, "step": 402 }, { "epoch": 0.7560975609756098, "grad_norm": 0.380281001329422, "learning_rate": 3.4694356163856814e-06, "loss": 0.4584, "step": 403 }, { "epoch": 0.7579737335834896, "grad_norm": 0.3708191215991974, "learning_rate": 3.419907179329641e-06, "loss": 0.4686, "step": 404 }, { "epoch": 0.7598499061913696, "grad_norm": 0.36141806840896606, "learning_rate": 3.3706617896812775e-06, "loss": 0.4498, "step": 405 }, { "epoch": 0.7617260787992496, "grad_norm": 0.35164591670036316, "learning_rate": 3.3217015657663145e-06, "loss": 0.455, "step": 406 }, { "epoch": 0.7636022514071295, "grad_norm": 0.3529546856880188, "learning_rate": 3.273028613643866e-06, "loss": 0.453, "step": 407 }, { "epoch": 0.7654784240150094, "grad_norm": 0.38521793484687805, "learning_rate": 3.2246450270158425e-06, "loss": 0.4959, "step": 408 }, { "epoch": 0.7673545966228893, "grad_norm": 0.38005560636520386, "learning_rate": 3.1765528871368946e-06, "loss": 0.426, "step": 409 }, { "epoch": 0.7692307692307693, "grad_norm": 0.42967918515205383, "learning_rate": 3.128754262724879e-06, "loss": 0.4792, "step": 410 }, { "epoch": 0.7711069418386491, "grad_norm": 0.3669396638870239, "learning_rate": 3.0812512098718717e-06, "loss": 0.4602, "step": 411 }, { "epoch": 0.7729831144465291, "grad_norm": 0.3635663092136383, "learning_rate": 3.034045771955736e-06, "loss": 0.4546, "step": 412 }, { "epoch": 0.774859287054409, "grad_norm": 0.3650107979774475, "learning_rate": 2.9871399795522062e-06, "loss": 0.4647, "step": 413 }, { "epoch": 0.776735459662289, "grad_norm": 0.36175158619880676, "learning_rate": 2.9405358503475536e-06, "loss": 0.4506, "step": 414 }, { "epoch": 0.7786116322701688, "grad_norm": 0.3650931417942047, "learning_rate": 2.8942353890517894e-06, "loss": 0.4521, "step": 415 }, { "epoch": 0.7804878048780488, "grad_norm": 0.3675496578216553, "learning_rate": 2.848240587312433e-06, "loss": 0.4655, "step": 416 }, { "epoch": 0.7823639774859287, "grad_norm": 0.35920068621635437, "learning_rate": 2.80255342362884e-06, "loss": 0.4606, "step": 417 }, { "epoch": 0.7842401500938087, "grad_norm": 0.3604222238063812, "learning_rate": 2.7571758632670897e-06, "loss": 0.464, "step": 418 }, { "epoch": 0.7861163227016885, "grad_norm": 0.36000943183898926, "learning_rate": 2.7121098581754635e-06, "loss": 0.4562, "step": 419 }, { "epoch": 0.7879924953095685, "grad_norm": 0.3869664669036865, "learning_rate": 2.667357346900459e-06, "loss": 0.4606, "step": 420 }, { "epoch": 0.7898686679174484, "grad_norm": 0.35324493050575256, "learning_rate": 2.622920254503416e-06, "loss": 0.4647, "step": 421 }, { "epoch": 0.7917448405253283, "grad_norm": 0.3965626060962677, "learning_rate": 2.5788004924777065e-06, "loss": 0.4719, "step": 422 }, { "epoch": 0.7936210131332082, "grad_norm": 0.35837239027023315, "learning_rate": 2.5349999586665077e-06, "loss": 0.4597, "step": 423 }, { "epoch": 0.7954971857410882, "grad_norm": 0.3734018802642822, "learning_rate": 2.491520537181167e-06, "loss": 0.4627, "step": 424 }, { "epoch": 0.797373358348968, "grad_norm": 0.38226038217544556, "learning_rate": 2.448364098320154e-06, "loss": 0.4462, "step": 425 }, { "epoch": 0.799249530956848, "grad_norm": 0.34819310903549194, "learning_rate": 2.405532498488612e-06, "loss": 0.4405, "step": 426 }, { "epoch": 0.801125703564728, "grad_norm": 0.3812004625797272, "learning_rate": 2.3630275801184975e-06, "loss": 0.4623, "step": 427 }, { "epoch": 0.8030018761726079, "grad_norm": 0.33405259251594543, "learning_rate": 2.3208511715893334e-06, "loss": 0.4702, "step": 428 }, { "epoch": 0.8048780487804879, "grad_norm": 0.3457287847995758, "learning_rate": 2.2790050871495518e-06, "loss": 0.4543, "step": 429 }, { "epoch": 0.8067542213883677, "grad_norm": 0.37848466634750366, "learning_rate": 2.2374911268384614e-06, "loss": 0.4747, "step": 430 }, { "epoch": 0.8086303939962477, "grad_norm": 0.37516096234321594, "learning_rate": 2.196311076408808e-06, "loss": 0.4499, "step": 431 }, { "epoch": 0.8105065666041276, "grad_norm": 0.35740143060684204, "learning_rate": 2.1554667072499747e-06, "loss": 0.448, "step": 432 }, { "epoch": 0.8123827392120075, "grad_norm": 0.37683647871017456, "learning_rate": 2.114959776311767e-06, "loss": 0.4595, "step": 433 }, { "epoch": 0.8142589118198874, "grad_norm": 0.36013343930244446, "learning_rate": 2.074792026028841e-06, "loss": 0.457, "step": 434 }, { "epoch": 0.8161350844277674, "grad_norm": 0.37009820342063904, "learning_rate": 2.0349651842457606e-06, "loss": 0.4739, "step": 435 }, { "epoch": 0.8180112570356473, "grad_norm": 0.3644636571407318, "learning_rate": 1.995480964142663e-06, "loss": 0.4551, "step": 436 }, { "epoch": 0.8198874296435272, "grad_norm": 0.3416192829608917, "learning_rate": 1.9563410641615666e-06, "loss": 0.4597, "step": 437 }, { "epoch": 0.8217636022514071, "grad_norm": 0.3656933009624481, "learning_rate": 1.9175471679333146e-06, "loss": 0.4195, "step": 438 }, { "epoch": 0.8236397748592871, "grad_norm": 0.4020621180534363, "learning_rate": 1.8791009442051545e-06, "loss": 0.4751, "step": 439 }, { "epoch": 0.8255159474671669, "grad_norm": 0.3509070873260498, "learning_rate": 1.8410040467689472e-06, "loss": 0.4418, "step": 440 }, { "epoch": 0.8273921200750469, "grad_norm": 0.4642477333545685, "learning_rate": 1.8032581143900342e-06, "loss": 0.4648, "step": 441 }, { "epoch": 0.8292682926829268, "grad_norm": 0.3921687602996826, "learning_rate": 1.7658647707367438e-06, "loss": 0.4616, "step": 442 }, { "epoch": 0.8311444652908068, "grad_norm": 0.33472052216529846, "learning_rate": 1.7288256243105484e-06, "loss": 0.449, "step": 443 }, { "epoch": 0.8330206378986866, "grad_norm": 0.3562254011631012, "learning_rate": 1.6921422683768707e-06, "loss": 0.4402, "step": 444 }, { "epoch": 0.8348968105065666, "grad_norm": 0.38186293840408325, "learning_rate": 1.6558162808965495e-06, "loss": 0.454, "step": 445 }, { "epoch": 0.8367729831144465, "grad_norm": 0.35252490639686584, "learning_rate": 1.6198492244579723e-06, "loss": 0.4611, "step": 446 }, { "epoch": 0.8386491557223265, "grad_norm": 0.3606928288936615, "learning_rate": 1.5842426462098392e-06, "loss": 0.4572, "step": 447 }, { "epoch": 0.8405253283302064, "grad_norm": 0.3576737940311432, "learning_rate": 1.54899807779463e-06, "loss": 0.4785, "step": 448 }, { "epoch": 0.8424015009380863, "grad_norm": 0.35132601857185364, "learning_rate": 1.5141170352827094e-06, "loss": 0.4481, "step": 449 }, { "epoch": 0.8442776735459663, "grad_norm": 0.3655112683773041, "learning_rate": 1.479601019107113e-06, "loss": 0.4668, "step": 450 }, { "epoch": 0.8461538461538461, "grad_norm": 0.3495786190032959, "learning_rate": 1.4454515139990122e-06, "loss": 0.4671, "step": 451 }, { "epoch": 0.8480300187617261, "grad_norm": 0.36569535732269287, "learning_rate": 1.4116699889238372e-06, "loss": 0.4635, "step": 452 }, { "epoch": 0.849906191369606, "grad_norm": 0.34859490394592285, "learning_rate": 1.378257897018096e-06, "loss": 0.4679, "step": 453 }, { "epoch": 0.851782363977486, "grad_norm": 0.3567720055580139, "learning_rate": 1.3452166755268637e-06, "loss": 0.454, "step": 454 }, { "epoch": 0.8536585365853658, "grad_norm": 0.3588789999485016, "learning_rate": 1.312547745741959e-06, "loss": 0.4466, "step": 455 }, { "epoch": 0.8555347091932458, "grad_norm": 0.35184621810913086, "learning_rate": 1.2802525129408039e-06, "loss": 0.4478, "step": 456 }, { "epoch": 0.8574108818011257, "grad_norm": 0.3764590620994568, "learning_rate": 1.2483323663259805e-06, "loss": 0.4599, "step": 457 }, { "epoch": 0.8592870544090057, "grad_norm": 0.36193057894706726, "learning_rate": 1.2167886789654659e-06, "loss": 0.4555, "step": 458 }, { "epoch": 0.8611632270168855, "grad_norm": 0.35677453875541687, "learning_rate": 1.1856228077335775e-06, "loss": 0.4716, "step": 459 }, { "epoch": 0.8630393996247655, "grad_norm": 0.33563223481178284, "learning_rate": 1.154836093252597e-06, "loss": 0.4664, "step": 460 }, { "epoch": 0.8649155722326454, "grad_norm": 0.3576035499572754, "learning_rate": 1.1244298598351078e-06, "loss": 0.467, "step": 461 }, { "epoch": 0.8667917448405253, "grad_norm": 0.3751625120639801, "learning_rate": 1.094405415427029e-06, "loss": 0.447, "step": 462 }, { "epoch": 0.8686679174484052, "grad_norm": 0.348402202129364, "learning_rate": 1.064764051551349e-06, "loss": 0.4653, "step": 463 }, { "epoch": 0.8705440900562852, "grad_norm": 0.3535415530204773, "learning_rate": 1.035507043252577e-06, "loss": 0.4627, "step": 464 }, { "epoch": 0.8724202626641651, "grad_norm": 0.35580676794052124, "learning_rate": 1.0066356490418871e-06, "loss": 0.4415, "step": 465 }, { "epoch": 0.874296435272045, "grad_norm": 0.36892953515052795, "learning_rate": 9.781511108429908e-07, "loss": 0.4596, "step": 466 }, { "epoch": 0.8761726078799249, "grad_norm": 0.388686865568161, "learning_rate": 9.500546539387101e-07, "loss": 0.4672, "step": 467 }, { "epoch": 0.8780487804878049, "grad_norm": 0.3477744162082672, "learning_rate": 9.223474869182691e-07, "loss": 0.4467, "step": 468 }, { "epoch": 0.8799249530956847, "grad_norm": 0.5885300040245056, "learning_rate": 8.950308016253129e-07, "loss": 0.4668, "step": 469 }, { "epoch": 0.8818011257035647, "grad_norm": 0.3635028600692749, "learning_rate": 8.681057731066322e-07, "loss": 0.4509, "step": 470 }, { "epoch": 0.8836772983114447, "grad_norm": 0.34183740615844727, "learning_rate": 8.415735595616204e-07, "loss": 0.4445, "step": 471 }, { "epoch": 0.8855534709193246, "grad_norm": 0.38252541422843933, "learning_rate": 8.154353022924577e-07, "loss": 0.4486, "step": 472 }, { "epoch": 0.8874296435272045, "grad_norm": 0.3649146854877472, "learning_rate": 7.896921256550094e-07, "loss": 0.4594, "step": 473 }, { "epoch": 0.8893058161350844, "grad_norm": 0.3455508053302765, "learning_rate": 7.643451370104649e-07, "loss": 0.47, "step": 474 }, { "epoch": 0.8911819887429644, "grad_norm": 0.34994518756866455, "learning_rate": 7.393954266777048e-07, "loss": 0.4577, "step": 475 }, { "epoch": 0.8930581613508443, "grad_norm": 0.3708822429180145, "learning_rate": 7.148440678863921e-07, "loss": 0.4603, "step": 476 }, { "epoch": 0.8949343339587242, "grad_norm": 0.34789973497390747, "learning_rate": 6.906921167308212e-07, "loss": 0.4649, "step": 477 }, { "epoch": 0.8968105065666041, "grad_norm": 0.34732475876808167, "learning_rate": 6.669406121244748e-07, "loss": 0.4563, "step": 478 }, { "epoch": 0.8986866791744841, "grad_norm": 0.34246909618377686, "learning_rate": 6.435905757553463e-07, "loss": 0.4637, "step": 479 }, { "epoch": 0.900562851782364, "grad_norm": 0.35301247239112854, "learning_rate": 6.206430120419804e-07, "loss": 0.4415, "step": 480 }, { "epoch": 0.9024390243902439, "grad_norm": 0.34336552023887634, "learning_rate": 5.980989080902721e-07, "loss": 0.4515, "step": 481 }, { "epoch": 0.9043151969981238, "grad_norm": 0.34129807353019714, "learning_rate": 5.759592336510078e-07, "loss": 0.4414, "step": 482 }, { "epoch": 0.9061913696060038, "grad_norm": 0.34144312143325806, "learning_rate": 5.542249410781486e-07, "loss": 0.4503, "step": 483 }, { "epoch": 0.9080675422138836, "grad_norm": 0.3457910120487213, "learning_rate": 5.328969652878624e-07, "loss": 0.4474, "step": 484 }, { "epoch": 0.9099437148217636, "grad_norm": 0.35740694403648376, "learning_rate": 5.119762237183079e-07, "loss": 0.4555, "step": 485 }, { "epoch": 0.9118198874296435, "grad_norm": 0.3321978747844696, "learning_rate": 4.914636162901799e-07, "loss": 0.4427, "step": 486 }, { "epoch": 0.9136960600375235, "grad_norm": 0.3253515064716339, "learning_rate": 4.7136002536798176e-07, "loss": 0.4599, "step": 487 }, { "epoch": 0.9155722326454033, "grad_norm": 0.36756089329719543, "learning_rate": 4.516663157220846e-07, "loss": 0.4788, "step": 488 }, { "epoch": 0.9174484052532833, "grad_norm": 0.33447879552841187, "learning_rate": 4.323833344915185e-07, "loss": 0.4578, "step": 489 }, { "epoch": 0.9193245778611632, "grad_norm": 0.3380565047264099, "learning_rate": 4.135119111475383e-07, "loss": 0.4426, "step": 490 }, { "epoch": 0.9212007504690432, "grad_norm": 0.3644172251224518, "learning_rate": 3.9505285745794155e-07, "loss": 0.4602, "step": 491 }, { "epoch": 0.9230769230769231, "grad_norm": 0.358119398355484, "learning_rate": 3.770069674521515e-07, "loss": 0.445, "step": 492 }, { "epoch": 0.924953095684803, "grad_norm": 0.34130486845970154, "learning_rate": 3.5937501738705584e-07, "loss": 0.4582, "step": 493 }, { "epoch": 0.926829268292683, "grad_norm": 0.33966928720474243, "learning_rate": 3.421577657136221e-07, "loss": 0.4442, "step": 494 }, { "epoch": 0.9287054409005628, "grad_norm": 0.360805869102478, "learning_rate": 3.2535595304426735e-07, "loss": 0.467, "step": 495 }, { "epoch": 0.9305816135084428, "grad_norm": 0.33938154578208923, "learning_rate": 3.089703021210033e-07, "loss": 0.4574, "step": 496 }, { "epoch": 0.9324577861163227, "grad_norm": 0.3522200882434845, "learning_rate": 2.9300151778434593e-07, "loss": 0.4374, "step": 497 }, { "epoch": 0.9343339587242027, "grad_norm": 0.34403195977211, "learning_rate": 2.7745028694299513e-07, "loss": 0.4428, "step": 498 }, { "epoch": 0.9362101313320825, "grad_norm": 0.33853229880332947, "learning_rate": 2.6231727854428845e-07, "loss": 0.4576, "step": 499 }, { "epoch": 0.9380863039399625, "grad_norm": 0.34455257654190063, "learning_rate": 2.4760314354542737e-07, "loss": 0.444, "step": 500 }, { "epoch": 0.9399624765478424, "grad_norm": 0.3327702283859253, "learning_rate": 2.333085148854708e-07, "loss": 0.459, "step": 501 }, { "epoch": 0.9418386491557224, "grad_norm": 0.3427714407444, "learning_rate": 2.1943400745811473e-07, "loss": 0.4542, "step": 502 }, { "epoch": 0.9437148217636022, "grad_norm": 0.3703705966472626, "learning_rate": 2.059802180852377e-07, "loss": 0.4494, "step": 503 }, { "epoch": 0.9455909943714822, "grad_norm": 0.3655228018760681, "learning_rate": 1.9294772549122932e-07, "loss": 0.4553, "step": 504 }, { "epoch": 0.9474671669793621, "grad_norm": 0.34462401270866394, "learning_rate": 1.8033709027809655e-07, "loss": 0.4447, "step": 505 }, { "epoch": 0.949343339587242, "grad_norm": 0.3382973372936249, "learning_rate": 1.6814885490135103e-07, "loss": 0.4528, "step": 506 }, { "epoch": 0.9512195121951219, "grad_norm": 0.34772956371307373, "learning_rate": 1.5638354364666986e-07, "loss": 0.4587, "step": 507 }, { "epoch": 0.9530956848030019, "grad_norm": 0.34169095754623413, "learning_rate": 1.4504166260734698e-07, "loss": 0.4675, "step": 508 }, { "epoch": 0.9549718574108818, "grad_norm": 0.3375537395477295, "learning_rate": 1.3412369966252393e-07, "loss": 0.4462, "step": 509 }, { "epoch": 0.9568480300187617, "grad_norm": 0.3615083694458008, "learning_rate": 1.236301244561977e-07, "loss": 0.4585, "step": 510 }, { "epoch": 0.9587242026266416, "grad_norm": 0.3645174205303192, "learning_rate": 1.1356138837702702e-07, "loss": 0.4589, "step": 511 }, { "epoch": 0.9606003752345216, "grad_norm": 0.34688958525657654, "learning_rate": 1.039179245389077e-07, "loss": 0.4526, "step": 512 }, { "epoch": 0.9624765478424016, "grad_norm": 0.36116132140159607, "learning_rate": 9.470014776234881e-08, "loss": 0.4696, "step": 513 }, { "epoch": 0.9643527204502814, "grad_norm": 0.3596712052822113, "learning_rate": 8.590845455662133e-08, "loss": 0.4604, "step": 514 }, { "epoch": 0.9662288930581614, "grad_norm": 0.33651649951934814, "learning_rate": 7.754322310270846e-08, "loss": 0.477, "step": 515 }, { "epoch": 0.9681050656660413, "grad_norm": 0.3588255047798157, "learning_rate": 6.960481323703639e-08, "loss": 0.4392, "step": 516 }, { "epoch": 0.9699812382739212, "grad_norm": 0.37312379479408264, "learning_rate": 6.20935664359934e-08, "loss": 0.4527, "step": 517 }, { "epoch": 0.9718574108818011, "grad_norm": 0.4521438181400299, "learning_rate": 5.500980580124271e-08, "loss": 0.4626, "step": 518 }, { "epoch": 0.9737335834896811, "grad_norm": 0.34084129333496094, "learning_rate": 4.8353836045824666e-08, "loss": 0.4549, "step": 519 }, { "epoch": 0.975609756097561, "grad_norm": 0.3634425103664398, "learning_rate": 4.212594348104615e-08, "loss": 0.4578, "step": 520 }, { "epoch": 0.9774859287054409, "grad_norm": 0.3438330590724945, "learning_rate": 3.632639600416932e-08, "loss": 0.4671, "step": 521 }, { "epoch": 0.9793621013133208, "grad_norm": 0.3470819294452667, "learning_rate": 3.095544308688414e-08, "loss": 0.4696, "step": 522 }, { "epoch": 0.9812382739212008, "grad_norm": 0.37453538179397583, "learning_rate": 2.6013315764580326e-08, "loss": 0.4515, "step": 523 }, { "epoch": 0.9831144465290806, "grad_norm": 0.34173503518104553, "learning_rate": 2.1500226626404164e-08, "loss": 0.4752, "step": 524 }, { "epoch": 0.9849906191369606, "grad_norm": 0.3387591242790222, "learning_rate": 1.741636980612027e-08, "loss": 0.4478, "step": 525 }, { "epoch": 0.9868667917448405, "grad_norm": 0.3569246530532837, "learning_rate": 1.376192097375495e-08, "loss": 0.4673, "step": 526 }, { "epoch": 0.9887429643527205, "grad_norm": 0.3663165867328644, "learning_rate": 1.0537037328044453e-08, "loss": 0.457, "step": 527 }, { "epoch": 0.9906191369606003, "grad_norm": 0.34201619029045105, "learning_rate": 7.741857589668167e-09, "loss": 0.47, "step": 528 }, { "epoch": 0.9924953095684803, "grad_norm": 0.354859858751297, "learning_rate": 5.376501995286721e-09, "loss": 0.458, "step": 529 }, { "epoch": 0.9943714821763602, "grad_norm": 0.3580581247806549, "learning_rate": 3.4410722923650108e-09, "loss": 0.4543, "step": 530 }, { "epoch": 0.9962476547842402, "grad_norm": 0.351889431476593, "learning_rate": 1.9356517347990377e-09, "loss": 0.462, "step": 531 }, { "epoch": 0.99812382739212, "grad_norm": 0.35378509759902954, "learning_rate": 8.603050793332124e-10, "loss": 0.4505, "step": 532 }, { "epoch": 1.0, "grad_norm": 0.35387977957725525, "learning_rate": 2.1507858277258764e-10, "loss": 0.4469, "step": 533 } ], "logging_steps": 1, "max_steps": 533, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 50, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 2.465935052576391e+19, "train_batch_size": 2, "trial_name": null, "trial_params": null }