{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 3.0, "eval_steps": 500, "global_step": 639, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.004703115814226925, "grad_norm": 1.7139341831207275, "learning_rate": 0.0, "loss": 0.401, "step": 1 }, { "epoch": 0.00940623162845385, "grad_norm": 1.6044167280197144, "learning_rate": 1.875e-06, "loss": 0.3381, "step": 2 }, { "epoch": 0.014109347442680775, "grad_norm": 1.6498277187347412, "learning_rate": 3.75e-06, "loss": 0.3874, "step": 3 }, { "epoch": 0.0188124632569077, "grad_norm": 1.3913252353668213, "learning_rate": 5.625e-06, "loss": 0.3506, "step": 4 }, { "epoch": 0.023515579071134628, "grad_norm": 1.0696426630020142, "learning_rate": 7.5e-06, "loss": 0.3439, "step": 5 }, { "epoch": 0.02821869488536155, "grad_norm": 1.4961087703704834, "learning_rate": 9.375000000000001e-06, "loss": 0.3652, "step": 6 }, { "epoch": 0.03292181069958848, "grad_norm": 1.0645338296890259, "learning_rate": 1.125e-05, "loss": 0.3038, "step": 7 }, { "epoch": 0.0376249265138154, "grad_norm": 1.5855575799942017, "learning_rate": 1.3125e-05, "loss": 0.3353, "step": 8 }, { "epoch": 0.042328042328042326, "grad_norm": 1.6040740013122559, "learning_rate": 1.5e-05, "loss": 0.331, "step": 9 }, { "epoch": 0.047031158142269255, "grad_norm": 1.0025311708450317, "learning_rate": 1.6875e-05, "loss": 0.2458, "step": 10 }, { "epoch": 0.05173427395649618, "grad_norm": 1.1023650169372559, "learning_rate": 1.8750000000000002e-05, "loss": 0.2681, "step": 11 }, { "epoch": 0.0564373897707231, "grad_norm": 1.0352964401245117, "learning_rate": 2.0625e-05, "loss": 0.2878, "step": 12 }, { "epoch": 0.06114050558495003, "grad_norm": 0.8171945214271545, "learning_rate": 2.25e-05, "loss": 0.2736, "step": 13 }, { "epoch": 0.06584362139917696, "grad_norm": 0.7170441150665283, "learning_rate": 2.4375e-05, "loss": 0.2651, "step": 14 }, { "epoch": 0.07054673721340388, "grad_norm": 0.8581724166870117, "learning_rate": 2.625e-05, "loss": 0.3056, "step": 15 }, { "epoch": 0.0752498530276308, "grad_norm": 0.5182654857635498, "learning_rate": 2.8125e-05, "loss": 0.1967, "step": 16 }, { "epoch": 0.07995296884185774, "grad_norm": 0.64597487449646, "learning_rate": 3e-05, "loss": 0.2539, "step": 17 }, { "epoch": 0.08465608465608465, "grad_norm": 0.5166177749633789, "learning_rate": 3.1875e-05, "loss": 0.2162, "step": 18 }, { "epoch": 0.08935920047031158, "grad_norm": 0.5524162650108337, "learning_rate": 3.375e-05, "loss": 0.2359, "step": 19 }, { "epoch": 0.09406231628453851, "grad_norm": 0.5533215403556824, "learning_rate": 3.5625e-05, "loss": 0.2417, "step": 20 }, { "epoch": 0.09876543209876543, "grad_norm": 0.5417770743370056, "learning_rate": 3.7500000000000003e-05, "loss": 0.2351, "step": 21 }, { "epoch": 0.10346854791299236, "grad_norm": 0.45951998233795166, "learning_rate": 3.9375e-05, "loss": 0.2345, "step": 22 }, { "epoch": 0.10817166372721929, "grad_norm": 0.388340562582016, "learning_rate": 4.125e-05, "loss": 0.1917, "step": 23 }, { "epoch": 0.1128747795414462, "grad_norm": 0.3089149594306946, "learning_rate": 4.3125e-05, "loss": 0.1573, "step": 24 }, { "epoch": 0.11757789535567313, "grad_norm": 0.45874661207199097, "learning_rate": 4.5e-05, "loss": 0.2188, "step": 25 }, { "epoch": 0.12228101116990006, "grad_norm": 0.4180874228477478, "learning_rate": 4.6875e-05, "loss": 0.2167, "step": 26 }, { "epoch": 0.12698412698412698, "grad_norm": 0.41246965527534485, "learning_rate": 4.875e-05, "loss": 0.2287, "step": 27 }, { "epoch": 0.13168724279835392, "grad_norm": 0.6864482760429382, "learning_rate": 5.0625000000000004e-05, "loss": 0.1939, "step": 28 }, { "epoch": 0.13639035861258084, "grad_norm": 0.41121217608451843, "learning_rate": 5.25e-05, "loss": 0.1995, "step": 29 }, { "epoch": 0.14109347442680775, "grad_norm": 0.3991910219192505, "learning_rate": 5.4375e-05, "loss": 0.2103, "step": 30 }, { "epoch": 0.1457965902410347, "grad_norm": 0.43401339650154114, "learning_rate": 5.625e-05, "loss": 0.2178, "step": 31 }, { "epoch": 0.1504997060552616, "grad_norm": 0.40365228056907654, "learning_rate": 5.8125e-05, "loss": 0.2312, "step": 32 }, { "epoch": 0.15520282186948853, "grad_norm": 0.38736215233802795, "learning_rate": 6e-05, "loss": 0.1915, "step": 33 }, { "epoch": 0.15990593768371547, "grad_norm": 0.38350024819374084, "learning_rate": 5.999959819748311e-05, "loss": 0.1916, "step": 34 }, { "epoch": 0.1646090534979424, "grad_norm": 0.3522005081176758, "learning_rate": 5.999839280069545e-05, "loss": 0.1903, "step": 35 }, { "epoch": 0.1693121693121693, "grad_norm": 0.34010905027389526, "learning_rate": 5.9996383841925786e-05, "loss": 0.1593, "step": 36 }, { "epoch": 0.17401528512639625, "grad_norm": 0.3255314826965332, "learning_rate": 5.999357137498776e-05, "loss": 0.176, "step": 37 }, { "epoch": 0.17871840094062316, "grad_norm": 0.33202558755874634, "learning_rate": 5.9989955475218474e-05, "loss": 0.1761, "step": 38 }, { "epoch": 0.18342151675485008, "grad_norm": 0.3300604820251465, "learning_rate": 5.9985536239476416e-05, "loss": 0.1773, "step": 39 }, { "epoch": 0.18812463256907702, "grad_norm": 0.3195001780986786, "learning_rate": 5.998031378613893e-05, "loss": 0.1674, "step": 40 }, { "epoch": 0.19282774838330394, "grad_norm": 0.31502053141593933, "learning_rate": 5.997428825509902e-05, "loss": 0.1643, "step": 41 }, { "epoch": 0.19753086419753085, "grad_norm": 0.3568972945213318, "learning_rate": 5.996745980776157e-05, "loss": 0.1686, "step": 42 }, { "epoch": 0.2022339800117578, "grad_norm": 0.31470999121665955, "learning_rate": 5.995982862703908e-05, "loss": 0.1642, "step": 43 }, { "epoch": 0.2069370958259847, "grad_norm": 0.3714190125465393, "learning_rate": 5.9951394917346725e-05, "loss": 0.1976, "step": 44 }, { "epoch": 0.21164021164021163, "grad_norm": 0.28128358721733093, "learning_rate": 5.994215890459689e-05, "loss": 0.1561, "step": 45 }, { "epoch": 0.21634332745443857, "grad_norm": 0.3534548580646515, "learning_rate": 5.993212083619311e-05, "loss": 0.1585, "step": 46 }, { "epoch": 0.2210464432686655, "grad_norm": 0.3488255739212036, "learning_rate": 5.9921280981023473e-05, "loss": 0.1631, "step": 47 }, { "epoch": 0.2257495590828924, "grad_norm": 0.318351149559021, "learning_rate": 5.990963962945338e-05, "loss": 0.1617, "step": 48 }, { "epoch": 0.23045267489711935, "grad_norm": 0.34794872999191284, "learning_rate": 5.9897197093317794e-05, "loss": 0.1808, "step": 49 }, { "epoch": 0.23515579071134626, "grad_norm": 0.326033353805542, "learning_rate": 5.9883953705912856e-05, "loss": 0.184, "step": 50 }, { "epoch": 0.23985890652557318, "grad_norm": 0.3891427218914032, "learning_rate": 5.9869909821987015e-05, "loss": 0.1726, "step": 51 }, { "epoch": 0.24456202233980012, "grad_norm": 0.32868900895118713, "learning_rate": 5.9855065817731435e-05, "loss": 0.1766, "step": 52 }, { "epoch": 0.24926513815402704, "grad_norm": 0.40032389760017395, "learning_rate": 5.983942209077003e-05, "loss": 0.1883, "step": 53 }, { "epoch": 0.25396825396825395, "grad_norm": 0.31055593490600586, "learning_rate": 5.9822979060148706e-05, "loss": 0.1822, "step": 54 }, { "epoch": 0.2586713697824809, "grad_norm": 0.32182222604751587, "learning_rate": 5.980573716632421e-05, "loss": 0.1649, "step": 55 }, { "epoch": 0.26337448559670784, "grad_norm": 0.33574873208999634, "learning_rate": 5.9787696871152305e-05, "loss": 0.1715, "step": 56 }, { "epoch": 0.26807760141093473, "grad_norm": 0.32601475715637207, "learning_rate": 5.9768858657875374e-05, "loss": 0.156, "step": 57 }, { "epoch": 0.2727807172251617, "grad_norm": 0.33685413002967834, "learning_rate": 5.9749223031109525e-05, "loss": 0.1588, "step": 58 }, { "epoch": 0.2774838330393886, "grad_norm": 0.34670382738113403, "learning_rate": 5.972879051683104e-05, "loss": 0.177, "step": 59 }, { "epoch": 0.2821869488536155, "grad_norm": 0.2763045132160187, "learning_rate": 5.970756166236231e-05, "loss": 0.1452, "step": 60 }, { "epoch": 0.28689006466784245, "grad_norm": 0.3145194947719574, "learning_rate": 5.9685537036357125e-05, "loss": 0.1567, "step": 61 }, { "epoch": 0.2915931804820694, "grad_norm": 0.33798298239707947, "learning_rate": 5.966271722878551e-05, "loss": 0.172, "step": 62 }, { "epoch": 0.2962962962962963, "grad_norm": 0.34769999980926514, "learning_rate": 5.963910285091787e-05, "loss": 0.1687, "step": 63 }, { "epoch": 0.3009994121105232, "grad_norm": 0.3211643099784851, "learning_rate": 5.961469453530863e-05, "loss": 0.185, "step": 64 }, { "epoch": 0.30570252792475017, "grad_norm": 0.35740965604782104, "learning_rate": 5.95894929357793e-05, "loss": 0.1685, "step": 65 }, { "epoch": 0.31040564373897706, "grad_norm": 0.3395691215991974, "learning_rate": 5.956349872740097e-05, "loss": 0.1622, "step": 66 }, { "epoch": 0.315108759553204, "grad_norm": 0.2797919511795044, "learning_rate": 5.9536712606476175e-05, "loss": 0.1488, "step": 67 }, { "epoch": 0.31981187536743094, "grad_norm": 0.30878129601478577, "learning_rate": 5.950913529052032e-05, "loss": 0.1516, "step": 68 }, { "epoch": 0.32451499118165783, "grad_norm": 0.26671308279037476, "learning_rate": 5.9480767518242395e-05, "loss": 0.1527, "step": 69 }, { "epoch": 0.3292181069958848, "grad_norm": 0.3521859347820282, "learning_rate": 5.945161004952521e-05, "loss": 0.1624, "step": 70 }, { "epoch": 0.3339212228101117, "grad_norm": 0.307954341173172, "learning_rate": 5.942166366540506e-05, "loss": 0.1641, "step": 71 }, { "epoch": 0.3386243386243386, "grad_norm": 0.2892126142978668, "learning_rate": 5.9390929168050795e-05, "loss": 0.1409, "step": 72 }, { "epoch": 0.34332745443856555, "grad_norm": 0.29247185587882996, "learning_rate": 5.935940738074229e-05, "loss": 0.1639, "step": 73 }, { "epoch": 0.3480305702527925, "grad_norm": 0.3237907588481903, "learning_rate": 5.932709914784845e-05, "loss": 0.172, "step": 74 }, { "epoch": 0.3527336860670194, "grad_norm": 0.2725215256214142, "learning_rate": 5.929400533480456e-05, "loss": 0.1579, "step": 75 }, { "epoch": 0.3574368018812463, "grad_norm": 0.30695515871047974, "learning_rate": 5.92601268280891e-05, "loss": 0.1891, "step": 76 }, { "epoch": 0.36213991769547327, "grad_norm": 0.2982679307460785, "learning_rate": 5.9225464535200043e-05, "loss": 0.159, "step": 77 }, { "epoch": 0.36684303350970016, "grad_norm": 0.25991085171699524, "learning_rate": 5.919001938463047e-05, "loss": 0.1648, "step": 78 }, { "epoch": 0.3715461493239271, "grad_norm": 0.29866698384284973, "learning_rate": 5.915379232584377e-05, "loss": 0.166, "step": 79 }, { "epoch": 0.37624926513815404, "grad_norm": 0.32100582122802734, "learning_rate": 5.9116784329248184e-05, "loss": 0.1763, "step": 80 }, { "epoch": 0.38095238095238093, "grad_norm": 0.3161866366863251, "learning_rate": 5.907899638617077e-05, "loss": 0.1619, "step": 81 }, { "epoch": 0.3856554967666079, "grad_norm": 0.30643048882484436, "learning_rate": 5.90404295088309e-05, "loss": 0.1708, "step": 82 }, { "epoch": 0.3903586125808348, "grad_norm": 0.29074278473854065, "learning_rate": 5.900108473031316e-05, "loss": 0.1613, "step": 83 }, { "epoch": 0.3950617283950617, "grad_norm": 0.28390827775001526, "learning_rate": 5.89609631045396e-05, "loss": 0.16, "step": 84 }, { "epoch": 0.39976484420928865, "grad_norm": 0.2939464747905731, "learning_rate": 5.892006570624156e-05, "loss": 0.1504, "step": 85 }, { "epoch": 0.4044679600235156, "grad_norm": 0.30450060963630676, "learning_rate": 5.88783936309309e-05, "loss": 0.1617, "step": 86 }, { "epoch": 0.4091710758377425, "grad_norm": 0.2854366600513458, "learning_rate": 5.883594799487058e-05, "loss": 0.1655, "step": 87 }, { "epoch": 0.4138741916519694, "grad_norm": 0.2901574969291687, "learning_rate": 5.879272993504485e-05, "loss": 0.1575, "step": 88 }, { "epoch": 0.41857730746619637, "grad_norm": 0.310835599899292, "learning_rate": 5.874874060912871e-05, "loss": 0.1517, "step": 89 }, { "epoch": 0.42328042328042326, "grad_norm": 0.27328577637672424, "learning_rate": 5.870398119545695e-05, "loss": 0.1347, "step": 90 }, { "epoch": 0.4279835390946502, "grad_norm": 0.31220313906669617, "learning_rate": 5.8658452892992585e-05, "loss": 0.1696, "step": 91 }, { "epoch": 0.43268665490887714, "grad_norm": 0.2818368971347809, "learning_rate": 5.8612156921294705e-05, "loss": 0.1529, "step": 92 }, { "epoch": 0.43738977072310403, "grad_norm": 0.299360066652298, "learning_rate": 5.8565094520485845e-05, "loss": 0.1796, "step": 93 }, { "epoch": 0.442092886537331, "grad_norm": 0.3882884979248047, "learning_rate": 5.851726695121874e-05, "loss": 0.1578, "step": 94 }, { "epoch": 0.4467960023515579, "grad_norm": 0.30085819959640503, "learning_rate": 5.8468675494642585e-05, "loss": 0.1582, "step": 95 }, { "epoch": 0.4514991181657848, "grad_norm": 0.3947671949863434, "learning_rate": 5.841932145236867e-05, "loss": 0.172, "step": 96 }, { "epoch": 0.45620223398001175, "grad_norm": 0.2917030155658722, "learning_rate": 5.8369206146435564e-05, "loss": 0.1452, "step": 97 }, { "epoch": 0.4609053497942387, "grad_norm": 0.3343453109264374, "learning_rate": 5.831833091927365e-05, "loss": 0.171, "step": 98 }, { "epoch": 0.4656084656084656, "grad_norm": 0.3141520321369171, "learning_rate": 5.826669713366925e-05, "loss": 0.1455, "step": 99 }, { "epoch": 0.4703115814226925, "grad_norm": 0.2607101500034332, "learning_rate": 5.8214306172727994e-05, "loss": 0.1441, "step": 100 }, { "epoch": 0.47501469723691947, "grad_norm": 0.3105863034725189, "learning_rate": 5.8161159439837913e-05, "loss": 0.1728, "step": 101 }, { "epoch": 0.47971781305114636, "grad_norm": 0.2401721328496933, "learning_rate": 5.8107258358631734e-05, "loss": 0.1223, "step": 102 }, { "epoch": 0.4844209288653733, "grad_norm": 0.28111881017684937, "learning_rate": 5.805260437294878e-05, "loss": 0.1458, "step": 103 }, { "epoch": 0.48912404467960025, "grad_norm": 0.33055195212364197, "learning_rate": 5.7997198946796334e-05, "loss": 0.1768, "step": 104 }, { "epoch": 0.49382716049382713, "grad_norm": 0.29289400577545166, "learning_rate": 5.794104356431037e-05, "loss": 0.1427, "step": 105 }, { "epoch": 0.4985302763080541, "grad_norm": 0.2940140664577484, "learning_rate": 5.788413972971582e-05, "loss": 0.1401, "step": 106 }, { "epoch": 0.503233392122281, "grad_norm": 0.3078160583972931, "learning_rate": 5.782648896728629e-05, "loss": 0.12, "step": 107 }, { "epoch": 0.5079365079365079, "grad_norm": 0.3209651708602905, "learning_rate": 5.7768092821303195e-05, "loss": 0.161, "step": 108 }, { "epoch": 0.5126396237507349, "grad_norm": 0.27314016222953796, "learning_rate": 5.770895285601445e-05, "loss": 0.137, "step": 109 }, { "epoch": 0.5173427395649618, "grad_norm": 0.34741535782814026, "learning_rate": 5.76490706555925e-05, "loss": 0.1858, "step": 110 }, { "epoch": 0.5220458553791887, "grad_norm": 0.30166077613830566, "learning_rate": 5.758844782409194e-05, "loss": 0.1729, "step": 111 }, { "epoch": 0.5267489711934157, "grad_norm": 0.2782808542251587, "learning_rate": 5.752708598540652e-05, "loss": 0.1316, "step": 112 }, { "epoch": 0.5314520870076426, "grad_norm": 0.2750331163406372, "learning_rate": 5.746498678322565e-05, "loss": 0.1468, "step": 113 }, { "epoch": 0.5361552028218695, "grad_norm": 0.30965185165405273, "learning_rate": 5.74021518809904e-05, "loss": 0.1597, "step": 114 }, { "epoch": 0.5408583186360965, "grad_norm": 0.3168213367462158, "learning_rate": 5.733858296184888e-05, "loss": 0.1752, "step": 115 }, { "epoch": 0.5455614344503233, "grad_norm": 0.2981097400188446, "learning_rate": 5.7274281728611185e-05, "loss": 0.151, "step": 116 }, { "epoch": 0.5502645502645502, "grad_norm": 0.3007696568965912, "learning_rate": 5.720924990370383e-05, "loss": 0.1687, "step": 117 }, { "epoch": 0.5549676660787772, "grad_norm": 0.2643842101097107, "learning_rate": 5.7143489229123546e-05, "loss": 0.129, "step": 118 }, { "epoch": 0.5596707818930041, "grad_norm": 0.2749280333518982, "learning_rate": 5.707700146639062e-05, "loss": 0.1568, "step": 119 }, { "epoch": 0.564373897707231, "grad_norm": 0.30500879883766174, "learning_rate": 5.700978839650176e-05, "loss": 0.1693, "step": 120 }, { "epoch": 0.569077013521458, "grad_norm": 0.3124525249004364, "learning_rate": 5.694185181988233e-05, "loss": 0.1519, "step": 121 }, { "epoch": 0.5737801293356849, "grad_norm": 0.28386813402175903, "learning_rate": 5.6873193556338176e-05, "loss": 0.153, "step": 122 }, { "epoch": 0.5784832451499118, "grad_norm": 0.29530754685401917, "learning_rate": 5.6803815445006825e-05, "loss": 0.1541, "step": 123 }, { "epoch": 0.5831863609641388, "grad_norm": 0.24880526959896088, "learning_rate": 5.673371934430826e-05, "loss": 0.1443, "step": 124 }, { "epoch": 0.5878894767783657, "grad_norm": 0.2877785861492157, "learning_rate": 5.666290713189514e-05, "loss": 0.1617, "step": 125 }, { "epoch": 0.5925925925925926, "grad_norm": 0.25762808322906494, "learning_rate": 5.659138070460247e-05, "loss": 0.1345, "step": 126 }, { "epoch": 0.5972957084068196, "grad_norm": 0.2590971887111664, "learning_rate": 5.651914197839681e-05, "loss": 0.1462, "step": 127 }, { "epoch": 0.6019988242210464, "grad_norm": 0.27619895339012146, "learning_rate": 5.644619288832497e-05, "loss": 0.1543, "step": 128 }, { "epoch": 0.6067019400352733, "grad_norm": 0.25903722643852234, "learning_rate": 5.637253538846214e-05, "loss": 0.1193, "step": 129 }, { "epoch": 0.6114050558495003, "grad_norm": 0.23248697817325592, "learning_rate": 5.6298171451859595e-05, "loss": 0.1199, "step": 130 }, { "epoch": 0.6161081716637272, "grad_norm": 0.25144484639167786, "learning_rate": 5.622310307049177e-05, "loss": 0.1288, "step": 131 }, { "epoch": 0.6208112874779541, "grad_norm": 0.28727683424949646, "learning_rate": 5.614733225520298e-05, "loss": 0.1458, "step": 132 }, { "epoch": 0.6255144032921811, "grad_norm": 0.24887113273143768, "learning_rate": 5.6070861035653526e-05, "loss": 0.1346, "step": 133 }, { "epoch": 0.630217519106408, "grad_norm": 0.3177245557308197, "learning_rate": 5.5993691460265284e-05, "loss": 0.1521, "step": 134 }, { "epoch": 0.6349206349206349, "grad_norm": 0.29727864265441895, "learning_rate": 5.59158255961669e-05, "loss": 0.1638, "step": 135 }, { "epoch": 0.6396237507348619, "grad_norm": 0.29992517828941345, "learning_rate": 5.58372655291384e-05, "loss": 0.149, "step": 136 }, { "epoch": 0.6443268665490888, "grad_norm": 0.2903859317302704, "learning_rate": 5.575801336355527e-05, "loss": 0.1679, "step": 137 }, { "epoch": 0.6490299823633157, "grad_norm": 0.31299668550491333, "learning_rate": 5.5678071222332175e-05, "loss": 0.1498, "step": 138 }, { "epoch": 0.6537330981775427, "grad_norm": 0.26878345012664795, "learning_rate": 5.559744124686601e-05, "loss": 0.1343, "step": 139 }, { "epoch": 0.6584362139917695, "grad_norm": 0.25904175639152527, "learning_rate": 5.5516125596978566e-05, "loss": 0.14, "step": 140 }, { "epoch": 0.6631393298059964, "grad_norm": 0.24799123406410217, "learning_rate": 5.5434126450858714e-05, "loss": 0.1276, "step": 141 }, { "epoch": 0.6678424456202234, "grad_norm": 0.2608186602592468, "learning_rate": 5.535144600500401e-05, "loss": 0.1331, "step": 142 }, { "epoch": 0.6725455614344503, "grad_norm": 0.2676827311515808, "learning_rate": 5.526808647416185e-05, "loss": 0.1429, "step": 143 }, { "epoch": 0.6772486772486772, "grad_norm": 0.31518733501434326, "learning_rate": 5.51840500912702e-05, "loss": 0.1533, "step": 144 }, { "epoch": 0.6819517930629042, "grad_norm": 0.28640490770339966, "learning_rate": 5.5099339107397736e-05, "loss": 0.1519, "step": 145 }, { "epoch": 0.6866549088771311, "grad_norm": 0.2560550570487976, "learning_rate": 5.501395579168356e-05, "loss": 0.1506, "step": 146 }, { "epoch": 0.691358024691358, "grad_norm": 0.29262763261795044, "learning_rate": 5.492790243127642e-05, "loss": 0.1802, "step": 147 }, { "epoch": 0.696061140505585, "grad_norm": 0.2738831639289856, "learning_rate": 5.484118133127343e-05, "loss": 0.1449, "step": 148 }, { "epoch": 0.7007642563198119, "grad_norm": 0.25972846150398254, "learning_rate": 5.4753794814658326e-05, "loss": 0.1507, "step": 149 }, { "epoch": 0.7054673721340388, "grad_norm": 0.27528664469718933, "learning_rate": 5.4665745222239284e-05, "loss": 0.1418, "step": 150 }, { "epoch": 0.7101704879482658, "grad_norm": 0.2458568513393402, "learning_rate": 5.4577034912586164e-05, "loss": 0.1319, "step": 151 }, { "epoch": 0.7148736037624926, "grad_norm": 0.269709974527359, "learning_rate": 5.448766626196732e-05, "loss": 0.1405, "step": 152 }, { "epoch": 0.7195767195767195, "grad_norm": 0.2724015712738037, "learning_rate": 5.4397641664286024e-05, "loss": 0.1538, "step": 153 }, { "epoch": 0.7242798353909465, "grad_norm": 0.30268412828445435, "learning_rate": 5.430696353101627e-05, "loss": 0.144, "step": 154 }, { "epoch": 0.7289829512051734, "grad_norm": 0.2880987226963043, "learning_rate": 5.421563429113819e-05, "loss": 0.1585, "step": 155 }, { "epoch": 0.7336860670194003, "grad_norm": 0.25448480248451233, "learning_rate": 5.412365639107302e-05, "loss": 0.1242, "step": 156 }, { "epoch": 0.7383891828336273, "grad_norm": 0.24491570889949799, "learning_rate": 5.4031032294617553e-05, "loss": 0.1333, "step": 157 }, { "epoch": 0.7430922986478542, "grad_norm": 0.2880731225013733, "learning_rate": 5.393776448287811e-05, "loss": 0.1468, "step": 158 }, { "epoch": 0.7477954144620811, "grad_norm": 0.21545594930648804, "learning_rate": 5.384385545420414e-05, "loss": 0.1109, "step": 159 }, { "epoch": 0.7524985302763081, "grad_norm": 0.313944548368454, "learning_rate": 5.374930772412123e-05, "loss": 0.16, "step": 160 }, { "epoch": 0.757201646090535, "grad_norm": 0.25155460834503174, "learning_rate": 5.3654123825263795e-05, "loss": 0.1468, "step": 161 }, { "epoch": 0.7619047619047619, "grad_norm": 0.24023838341236115, "learning_rate": 5.355830630730717e-05, "loss": 0.1211, "step": 162 }, { "epoch": 0.7666078777189889, "grad_norm": 0.27730172872543335, "learning_rate": 5.3461857736899345e-05, "loss": 0.1668, "step": 163 }, { "epoch": 0.7713109935332157, "grad_norm": 0.26910340785980225, "learning_rate": 5.3364780697592205e-05, "loss": 0.1428, "step": 164 }, { "epoch": 0.7760141093474426, "grad_norm": 0.2331807017326355, "learning_rate": 5.3267077789772335e-05, "loss": 0.1502, "step": 165 }, { "epoch": 0.7807172251616696, "grad_norm": 0.28558218479156494, "learning_rate": 5.316875163059136e-05, "loss": 0.17, "step": 166 }, { "epoch": 0.7854203409758965, "grad_norm": 0.2564701437950134, "learning_rate": 5.306980485389582e-05, "loss": 0.1416, "step": 167 }, { "epoch": 0.7901234567901234, "grad_norm": 0.24135640263557434, "learning_rate": 5.297024011015664e-05, "loss": 0.1476, "step": 168 }, { "epoch": 0.7948265726043504, "grad_norm": 0.26303550601005554, "learning_rate": 5.287006006639814e-05, "loss": 0.1374, "step": 169 }, { "epoch": 0.7995296884185773, "grad_norm": 0.25909844040870667, "learning_rate": 5.276926740612656e-05, "loss": 0.1473, "step": 170 }, { "epoch": 0.8042328042328042, "grad_norm": 0.2502562403678894, "learning_rate": 5.266786482925821e-05, "loss": 0.138, "step": 171 }, { "epoch": 0.8089359200470312, "grad_norm": 0.23371152579784393, "learning_rate": 5.2565855052047127e-05, "loss": 0.1361, "step": 172 }, { "epoch": 0.8136390358612581, "grad_norm": 0.26029762625694275, "learning_rate": 5.2463240807012327e-05, "loss": 0.1435, "step": 173 }, { "epoch": 0.818342151675485, "grad_norm": 0.2468917965888977, "learning_rate": 5.236002484286461e-05, "loss": 0.14, "step": 174 }, { "epoch": 0.823045267489712, "grad_norm": 0.25583571195602417, "learning_rate": 5.225620992443291e-05, "loss": 0.1444, "step": 175 }, { "epoch": 0.8277483833039389, "grad_norm": 0.24892207980155945, "learning_rate": 5.215179883259027e-05, "loss": 0.1215, "step": 176 }, { "epoch": 0.8324514991181657, "grad_norm": 0.2475907951593399, "learning_rate": 5.2046794364179323e-05, "loss": 0.1341, "step": 177 }, { "epoch": 0.8371546149323927, "grad_norm": 0.2650558352470398, "learning_rate": 5.194119933193737e-05, "loss": 0.1356, "step": 178 }, { "epoch": 0.8418577307466196, "grad_norm": 0.288430780172348, "learning_rate": 5.183501656442109e-05, "loss": 0.1561, "step": 179 }, { "epoch": 0.8465608465608465, "grad_norm": 0.27561911940574646, "learning_rate": 5.172824890593066e-05, "loss": 0.1453, "step": 180 }, { "epoch": 0.8512639623750735, "grad_norm": 0.30308693647384644, "learning_rate": 5.16208992164337e-05, "loss": 0.1421, "step": 181 }, { "epoch": 0.8559670781893004, "grad_norm": 0.2184101641178131, "learning_rate": 5.1512970371488557e-05, "loss": 0.1137, "step": 182 }, { "epoch": 0.8606701940035273, "grad_norm": 0.2866552472114563, "learning_rate": 5.1404465262167346e-05, "loss": 0.1432, "step": 183 }, { "epoch": 0.8653733098177543, "grad_norm": 0.2429009974002838, "learning_rate": 5.129538679497847e-05, "loss": 0.1286, "step": 184 }, { "epoch": 0.8700764256319812, "grad_norm": 0.2881879508495331, "learning_rate": 5.1185737891788753e-05, "loss": 0.1456, "step": 185 }, { "epoch": 0.8747795414462081, "grad_norm": 0.2657373547554016, "learning_rate": 5.1075521489745234e-05, "loss": 0.1568, "step": 186 }, { "epoch": 0.8794826572604351, "grad_norm": 0.2691710889339447, "learning_rate": 5.0964740541196414e-05, "loss": 0.1435, "step": 187 }, { "epoch": 0.884185773074662, "grad_norm": 0.28845682740211487, "learning_rate": 5.0853398013613234e-05, "loss": 0.1502, "step": 188 }, { "epoch": 0.8888888888888888, "grad_norm": 0.29487770795822144, "learning_rate": 5.074149688950955e-05, "loss": 0.1589, "step": 189 }, { "epoch": 0.8935920047031158, "grad_norm": 0.2817712426185608, "learning_rate": 5.062904016636224e-05, "loss": 0.145, "step": 190 }, { "epoch": 0.8982951205173427, "grad_norm": 0.2663252651691437, "learning_rate": 5.0516030856530935e-05, "loss": 0.1511, "step": 191 }, { "epoch": 0.9029982363315696, "grad_norm": 0.24159681797027588, "learning_rate": 5.0402471987177304e-05, "loss": 0.136, "step": 192 }, { "epoch": 0.9077013521457966, "grad_norm": 0.2759820520877838, "learning_rate": 5.0288366600184004e-05, "loss": 0.1383, "step": 193 }, { "epoch": 0.9124044679600235, "grad_norm": 0.23883500695228577, "learning_rate": 5.017371775207312e-05, "loss": 0.124, "step": 194 }, { "epoch": 0.9171075837742504, "grad_norm": 0.29086732864379883, "learning_rate": 5.005852851392438e-05, "loss": 0.1481, "step": 195 }, { "epoch": 0.9218106995884774, "grad_norm": 0.2699926495552063, "learning_rate": 4.994280197129283e-05, "loss": 0.1531, "step": 196 }, { "epoch": 0.9265138154027043, "grad_norm": 0.3094712197780609, "learning_rate": 4.9826541224126226e-05, "loss": 0.1501, "step": 197 }, { "epoch": 0.9312169312169312, "grad_norm": 0.26731571555137634, "learning_rate": 4.970974938668193e-05, "loss": 0.1547, "step": 198 }, { "epoch": 0.9359200470311582, "grad_norm": 0.306998074054718, "learning_rate": 4.9592429587443596e-05, "loss": 0.1512, "step": 199 }, { "epoch": 0.940623162845385, "grad_norm": 0.28610551357269287, "learning_rate": 4.9474584969037234e-05, "loss": 0.151, "step": 200 }, { "epoch": 0.9453262786596119, "grad_norm": 0.2830105423927307, "learning_rate": 4.935621868814714e-05, "loss": 0.1401, "step": 201 }, { "epoch": 0.9500293944738389, "grad_norm": 0.28803306818008423, "learning_rate": 4.923733391543128e-05, "loss": 0.1532, "step": 202 }, { "epoch": 0.9547325102880658, "grad_norm": 0.3139764070510864, "learning_rate": 4.911793383543639e-05, "loss": 0.1541, "step": 203 }, { "epoch": 0.9594356261022927, "grad_norm": 0.26436036825180054, "learning_rate": 4.899802164651264e-05, "loss": 0.1357, "step": 204 }, { "epoch": 0.9641387419165197, "grad_norm": 0.3035616874694824, "learning_rate": 4.8877600560727986e-05, "loss": 0.1471, "step": 205 }, { "epoch": 0.9688418577307466, "grad_norm": 0.2397439330816269, "learning_rate": 4.875667380378212e-05, "loss": 0.1184, "step": 206 }, { "epoch": 0.9735449735449735, "grad_norm": 0.2978168725967407, "learning_rate": 4.8635244614920074e-05, "loss": 0.1395, "step": 207 }, { "epoch": 0.9782480893592005, "grad_norm": 0.2939645051956177, "learning_rate": 4.8513316246845397e-05, "loss": 0.138, "step": 208 }, { "epoch": 0.9829512051734274, "grad_norm": 0.27488958835601807, "learning_rate": 4.839089196563313e-05, "loss": 0.1491, "step": 209 }, { "epoch": 0.9876543209876543, "grad_norm": 0.2628893256187439, "learning_rate": 4.826797505064221e-05, "loss": 0.1514, "step": 210 }, { "epoch": 0.9923574368018813, "grad_norm": 0.25922319293022156, "learning_rate": 4.814456879442771e-05, "loss": 0.1464, "step": 211 }, { "epoch": 0.9970605526161082, "grad_norm": 0.2652877867221832, "learning_rate": 4.802067650265255e-05, "loss": 0.1532, "step": 212 }, { "epoch": 1.0, "grad_norm": 0.32179388403892517, "learning_rate": 4.789630149399909e-05, "loss": 0.1394, "step": 213 }, { "epoch": 1.004703115814227, "grad_norm": 0.29971933364868164, "learning_rate": 4.777144710008006e-05, "loss": 0.1165, "step": 214 }, { "epoch": 1.0094062316284538, "grad_norm": 0.27687960863113403, "learning_rate": 4.764611666534946e-05, "loss": 0.1157, "step": 215 }, { "epoch": 1.0141093474426808, "grad_norm": 0.30005425214767456, "learning_rate": 4.752031354701289e-05, "loss": 0.1203, "step": 216 }, { "epoch": 1.0188124632569078, "grad_norm": 0.30502191185951233, "learning_rate": 4.739404111493766e-05, "loss": 0.114, "step": 217 }, { "epoch": 1.0235155790711346, "grad_norm": 0.29296910762786865, "learning_rate": 4.7267302751562494e-05, "loss": 0.1221, "step": 218 }, { "epoch": 1.0282186948853616, "grad_norm": 0.2933799624443054, "learning_rate": 4.714010185180697e-05, "loss": 0.1069, "step": 219 }, { "epoch": 1.0329218106995885, "grad_norm": 0.2723463773727417, "learning_rate": 4.701244182298051e-05, "loss": 0.1122, "step": 220 }, { "epoch": 1.0376249265138153, "grad_norm": 0.2650042474269867, "learning_rate": 4.688432608469119e-05, "loss": 0.0957, "step": 221 }, { "epoch": 1.0423280423280423, "grad_norm": 0.2588678300380707, "learning_rate": 4.675575806875409e-05, "loss": 0.1048, "step": 222 }, { "epoch": 1.0470311581422693, "grad_norm": 0.22973236441612244, "learning_rate": 4.662674121909935e-05, "loss": 0.1014, "step": 223 }, { "epoch": 1.051734273956496, "grad_norm": 0.2776679992675781, "learning_rate": 4.649727899167998e-05, "loss": 0.1188, "step": 224 }, { "epoch": 1.056437389770723, "grad_norm": 0.2559938132762909, "learning_rate": 4.636737485437921e-05, "loss": 0.1132, "step": 225 }, { "epoch": 1.06114050558495, "grad_norm": 0.2852188050746918, "learning_rate": 4.623703228691769e-05, "loss": 0.1201, "step": 226 }, { "epoch": 1.0658436213991769, "grad_norm": 0.2689427137374878, "learning_rate": 4.610625478076019e-05, "loss": 0.1183, "step": 227 }, { "epoch": 1.0705467372134039, "grad_norm": 0.2544887661933899, "learning_rate": 4.5975045839022105e-05, "loss": 0.1123, "step": 228 }, { "epoch": 1.0752498530276309, "grad_norm": 0.2446822226047516, "learning_rate": 4.584340897637566e-05, "loss": 0.1142, "step": 229 }, { "epoch": 1.0799529688418577, "grad_norm": 0.26933106780052185, "learning_rate": 4.571134771895569e-05, "loss": 0.0976, "step": 230 }, { "epoch": 1.0846560846560847, "grad_norm": 0.28689515590667725, "learning_rate": 4.557886560426523e-05, "loss": 0.1276, "step": 231 }, { "epoch": 1.0893592004703117, "grad_norm": 0.2573374807834625, "learning_rate": 4.544596618108076e-05, "loss": 0.0991, "step": 232 }, { "epoch": 1.0940623162845384, "grad_norm": 0.26204389333724976, "learning_rate": 4.531265300935714e-05, "loss": 0.1109, "step": 233 }, { "epoch": 1.0987654320987654, "grad_norm": 0.24312853813171387, "learning_rate": 4.51789296601322e-05, "loss": 0.0957, "step": 234 }, { "epoch": 1.1034685479129924, "grad_norm": 0.2802416980266571, "learning_rate": 4.5044799715431203e-05, "loss": 0.1121, "step": 235 }, { "epoch": 1.1081716637272192, "grad_norm": 0.28977179527282715, "learning_rate": 4.4910266768170754e-05, "loss": 0.1177, "step": 236 }, { "epoch": 1.1128747795414462, "grad_norm": 0.2654818892478943, "learning_rate": 4.4775334422062624e-05, "loss": 0.1096, "step": 237 }, { "epoch": 1.1175778953556732, "grad_norm": 0.27074316143989563, "learning_rate": 4.4640006291517254e-05, "loss": 0.1244, "step": 238 }, { "epoch": 1.1222810111699, "grad_norm": 0.2548133134841919, "learning_rate": 4.450428600154686e-05, "loss": 0.1127, "step": 239 }, { "epoch": 1.126984126984127, "grad_norm": 0.28041163086891174, "learning_rate": 4.43681771876684e-05, "loss": 0.1244, "step": 240 }, { "epoch": 1.131687242798354, "grad_norm": 0.22400139272212982, "learning_rate": 4.423168349580613e-05, "loss": 0.0964, "step": 241 }, { "epoch": 1.1363903586125808, "grad_norm": 0.2535853385925293, "learning_rate": 4.409480858219397e-05, "loss": 0.0969, "step": 242 }, { "epoch": 1.1410934744268078, "grad_norm": 0.28813979029655457, "learning_rate": 4.3957556113277586e-05, "loss": 0.1228, "step": 243 }, { "epoch": 1.1457965902410348, "grad_norm": 0.2692713141441345, "learning_rate": 4.381992976561613e-05, "loss": 0.1106, "step": 244 }, { "epoch": 1.1504997060552615, "grad_norm": 0.24593226611614227, "learning_rate": 4.3681933225783804e-05, "loss": 0.1065, "step": 245 }, { "epoch": 1.1552028218694885, "grad_norm": 0.2607971429824829, "learning_rate": 4.3543570190271077e-05, "loss": 0.1163, "step": 246 }, { "epoch": 1.1599059376837155, "grad_norm": 0.2869904935359955, "learning_rate": 4.340484436538566e-05, "loss": 0.1165, "step": 247 }, { "epoch": 1.1646090534979423, "grad_norm": 0.23155410587787628, "learning_rate": 4.326575946715328e-05, "loss": 0.0909, "step": 248 }, { "epoch": 1.1693121693121693, "grad_norm": 0.2504522502422333, "learning_rate": 4.3126319221218076e-05, "loss": 0.0956, "step": 249 }, { "epoch": 1.1740152851263963, "grad_norm": 0.3867388069629669, "learning_rate": 4.298652736274283e-05, "loss": 0.1087, "step": 250 }, { "epoch": 1.178718400940623, "grad_norm": 0.22451654076576233, "learning_rate": 4.2846387636308905e-05, "loss": 0.0983, "step": 251 }, { "epoch": 1.18342151675485, "grad_norm": 0.23521193861961365, "learning_rate": 4.270590379581598e-05, "loss": 0.1209, "step": 252 }, { "epoch": 1.188124632569077, "grad_norm": 0.23621417582035065, "learning_rate": 4.2565079604381406e-05, "loss": 0.1072, "step": 253 }, { "epoch": 1.1928277483833039, "grad_norm": 0.294721394777298, "learning_rate": 4.2423918834239505e-05, "loss": 0.1163, "step": 254 }, { "epoch": 1.1975308641975309, "grad_norm": 0.26161932945251465, "learning_rate": 4.2282425266640444e-05, "loss": 0.1187, "step": 255 }, { "epoch": 1.2022339800117579, "grad_norm": 0.22928793728351593, "learning_rate": 4.214060269174901e-05, "loss": 0.1078, "step": 256 }, { "epoch": 1.2069370958259846, "grad_norm": 0.26653313636779785, "learning_rate": 4.199845490854303e-05, "loss": 0.1188, "step": 257 }, { "epoch": 1.2116402116402116, "grad_norm": 0.2243010401725769, "learning_rate": 4.185598572471166e-05, "loss": 0.1026, "step": 258 }, { "epoch": 1.2163433274544386, "grad_norm": 0.23219768702983856, "learning_rate": 4.171319895655331e-05, "loss": 0.0998, "step": 259 }, { "epoch": 1.2210464432686654, "grad_norm": 0.3027436435222626, "learning_rate": 4.157009842887352e-05, "loss": 0.1037, "step": 260 }, { "epoch": 1.2257495590828924, "grad_norm": 0.21461142599582672, "learning_rate": 4.1426687974882446e-05, "loss": 0.1047, "step": 261 }, { "epoch": 1.2304526748971194, "grad_norm": 0.26062247157096863, "learning_rate": 4.128297143609217e-05, "loss": 0.1066, "step": 262 }, { "epoch": 1.2351557907113462, "grad_norm": 0.21960760653018951, "learning_rate": 4.1138952662213816e-05, "loss": 0.1075, "step": 263 }, { "epoch": 1.2398589065255732, "grad_norm": 0.238066628575325, "learning_rate": 4.0994635511054453e-05, "loss": 0.0992, "step": 264 }, { "epoch": 1.2445620223398002, "grad_norm": 0.2618398070335388, "learning_rate": 4.0850023848413706e-05, "loss": 0.1146, "step": 265 }, { "epoch": 1.249265138154027, "grad_norm": 0.25921371579170227, "learning_rate": 4.070512154798025e-05, "loss": 0.1106, "step": 266 }, { "epoch": 1.253968253968254, "grad_norm": 0.2489279806613922, "learning_rate": 4.0559932491228015e-05, "loss": 0.0984, "step": 267 }, { "epoch": 1.258671369782481, "grad_norm": 0.21687766909599304, "learning_rate": 4.041446056731225e-05, "loss": 0.0971, "step": 268 }, { "epoch": 1.263374485596708, "grad_norm": 0.22782693803310394, "learning_rate": 4.0268709672965265e-05, "loss": 0.1094, "step": 269 }, { "epoch": 1.2680776014109347, "grad_norm": 0.24425670504570007, "learning_rate": 4.012268371239217e-05, "loss": 0.1075, "step": 270 }, { "epoch": 1.2727807172251617, "grad_norm": 0.24464274942874908, "learning_rate": 3.997638659716618e-05, "loss": 0.1079, "step": 271 }, { "epoch": 1.2774838330393887, "grad_norm": 0.24908937513828278, "learning_rate": 3.982982224612391e-05, "loss": 0.0969, "step": 272 }, { "epoch": 1.2821869488536155, "grad_norm": 0.22951169312000275, "learning_rate": 3.9682994585260366e-05, "loss": 0.097, "step": 273 }, { "epoch": 1.2868900646678425, "grad_norm": 0.26538845896720886, "learning_rate": 3.9535907547623796e-05, "loss": 0.1154, "step": 274 }, { "epoch": 1.2915931804820695, "grad_norm": 0.213767871260643, "learning_rate": 3.938856507321032e-05, "loss": 0.1033, "step": 275 }, { "epoch": 1.2962962962962963, "grad_norm": 0.24028168618679047, "learning_rate": 3.9240971108858425e-05, "loss": 0.0977, "step": 276 }, { "epoch": 1.3009994121105233, "grad_norm": 0.2301046997308731, "learning_rate": 3.909312960814318e-05, "loss": 0.1096, "step": 277 }, { "epoch": 1.3057025279247503, "grad_norm": 0.22162428498268127, "learning_rate": 3.8945044531270416e-05, "loss": 0.0948, "step": 278 }, { "epoch": 1.310405643738977, "grad_norm": 0.2335638701915741, "learning_rate": 3.879671984497055e-05, "loss": 0.1098, "step": 279 }, { "epoch": 1.315108759553204, "grad_norm": 0.21702788770198822, "learning_rate": 3.864815952239241e-05, "loss": 0.095, "step": 280 }, { "epoch": 1.319811875367431, "grad_norm": 0.22150631248950958, "learning_rate": 3.8499367542996775e-05, "loss": 0.1096, "step": 281 }, { "epoch": 1.3245149911816578, "grad_norm": 0.24630430340766907, "learning_rate": 3.835034789244975e-05, "loss": 0.1135, "step": 282 }, { "epoch": 1.3292181069958848, "grad_norm": 0.25556787848472595, "learning_rate": 3.8201104562516044e-05, "loss": 0.1107, "step": 283 }, { "epoch": 1.3339212228101118, "grad_norm": 0.2370753437280655, "learning_rate": 3.8051641550952044e-05, "loss": 0.1007, "step": 284 }, { "epoch": 1.3386243386243386, "grad_norm": 0.2643367648124695, "learning_rate": 3.790196286139868e-05, "loss": 0.114, "step": 285 }, { "epoch": 1.3433274544385656, "grad_norm": 0.22937770187854767, "learning_rate": 3.7752072503274266e-05, "loss": 0.0939, "step": 286 }, { "epoch": 1.3480305702527926, "grad_norm": 0.274593710899353, "learning_rate": 3.760197449166697e-05, "loss": 0.1103, "step": 287 }, { "epoch": 1.3527336860670194, "grad_norm": 0.21618634462356567, "learning_rate": 3.745167284722741e-05, "loss": 0.1062, "step": 288 }, { "epoch": 1.3574368018812464, "grad_norm": 0.28842058777809143, "learning_rate": 3.7301171596060834e-05, "loss": 0.1185, "step": 289 }, { "epoch": 1.3621399176954734, "grad_norm": 0.2460644692182541, "learning_rate": 3.7150474769619365e-05, "loss": 0.1181, "step": 290 }, { "epoch": 1.3668430335097002, "grad_norm": 0.28488343954086304, "learning_rate": 3.6999586404593926e-05, "loss": 0.1044, "step": 291 }, { "epoch": 1.3715461493239272, "grad_norm": 0.22789904475212097, "learning_rate": 3.684851054280618e-05, "loss": 0.1003, "step": 292 }, { "epoch": 1.3762492651381542, "grad_norm": 0.24150682985782623, "learning_rate": 3.669725123110024e-05, "loss": 0.1042, "step": 293 }, { "epoch": 1.380952380952381, "grad_norm": 0.2629856765270233, "learning_rate": 3.654581252123423e-05, "loss": 0.1049, "step": 294 }, { "epoch": 1.385655496766608, "grad_norm": 0.2742895185947418, "learning_rate": 3.639419846977182e-05, "loss": 0.1114, "step": 295 }, { "epoch": 1.390358612580835, "grad_norm": 0.27353450655937195, "learning_rate": 3.6242413137973494e-05, "loss": 0.1198, "step": 296 }, { "epoch": 1.3950617283950617, "grad_norm": 0.2110612839460373, "learning_rate": 3.6090460591687804e-05, "loss": 0.0974, "step": 297 }, { "epoch": 1.3997648442092887, "grad_norm": 0.2536123991012573, "learning_rate": 3.593834490124248e-05, "loss": 0.127, "step": 298 }, { "epoch": 1.4044679600235157, "grad_norm": 0.23568709194660187, "learning_rate": 3.578607014133532e-05, "loss": 0.1038, "step": 299 }, { "epoch": 1.4091710758377425, "grad_norm": 0.269501268863678, "learning_rate": 3.5633640390925106e-05, "loss": 0.1244, "step": 300 }, { "epoch": 1.4138741916519695, "grad_norm": 0.17256565392017365, "learning_rate": 3.548105973312233e-05, "loss": 0.075, "step": 301 }, { "epoch": 1.4185773074661965, "grad_norm": 0.23596809804439545, "learning_rate": 3.532833225507984e-05, "loss": 0.0969, "step": 302 }, { "epoch": 1.4232804232804233, "grad_norm": 0.25930461287498474, "learning_rate": 3.5175462047883265e-05, "loss": 0.1061, "step": 303 }, { "epoch": 1.4279835390946503, "grad_norm": 0.27373206615448, "learning_rate": 3.502245320644157e-05, "loss": 0.1216, "step": 304 }, { "epoch": 1.4326866549088773, "grad_norm": 0.24273473024368286, "learning_rate": 3.486930982937726e-05, "loss": 0.1021, "step": 305 }, { "epoch": 1.437389770723104, "grad_norm": 0.23188744485378265, "learning_rate": 3.4716036018916613e-05, "loss": 0.0949, "step": 306 }, { "epoch": 1.442092886537331, "grad_norm": 0.22889705002307892, "learning_rate": 3.456263588077982e-05, "loss": 0.1015, "step": 307 }, { "epoch": 1.446796002351558, "grad_norm": 0.25674113631248474, "learning_rate": 3.4409113524071e-05, "loss": 0.113, "step": 308 }, { "epoch": 1.4514991181657848, "grad_norm": 0.28295740485191345, "learning_rate": 3.425547306116809e-05, "loss": 0.1125, "step": 309 }, { "epoch": 1.4562022339800118, "grad_norm": 0.223489910364151, "learning_rate": 3.410171860761274e-05, "loss": 0.0988, "step": 310 }, { "epoch": 1.4609053497942388, "grad_norm": 0.24564069509506226, "learning_rate": 3.394785428200005e-05, "loss": 0.0923, "step": 311 }, { "epoch": 1.4656084656084656, "grad_norm": 0.27584192156791687, "learning_rate": 3.379388420586824e-05, "loss": 0.1167, "step": 312 }, { "epoch": 1.4703115814226926, "grad_norm": 0.22047095000743866, "learning_rate": 3.3639812503588255e-05, "loss": 0.1083, "step": 313 }, { "epoch": 1.4750146972369196, "grad_norm": 0.24885299801826477, "learning_rate": 3.3485643302253266e-05, "loss": 0.1005, "step": 314 }, { "epoch": 1.4797178130511464, "grad_norm": 0.24875092506408691, "learning_rate": 3.3331380731568156e-05, "loss": 0.0996, "step": 315 }, { "epoch": 1.4844209288653734, "grad_norm": 0.21699145436286926, "learning_rate": 3.317702892373886e-05, "loss": 0.0982, "step": 316 }, { "epoch": 1.4891240446796004, "grad_norm": 0.24046854674816132, "learning_rate": 3.3022592013361724e-05, "loss": 0.0949, "step": 317 }, { "epoch": 1.4938271604938271, "grad_norm": 0.26729434728622437, "learning_rate": 3.2868074137312674e-05, "loss": 0.1242, "step": 318 }, { "epoch": 1.4985302763080541, "grad_norm": 0.2422710806131363, "learning_rate": 3.27134794346365e-05, "loss": 0.1185, "step": 319 }, { "epoch": 1.5032333921222811, "grad_norm": 0.2061970829963684, "learning_rate": 3.255881204643591e-05, "loss": 0.0788, "step": 320 }, { "epoch": 1.507936507936508, "grad_norm": 0.24345166981220245, "learning_rate": 3.24040761157606e-05, "loss": 0.0909, "step": 321 }, { "epoch": 1.512639623750735, "grad_norm": 0.273099422454834, "learning_rate": 3.224927578749636e-05, "loss": 0.1178, "step": 322 }, { "epoch": 1.517342739564962, "grad_norm": 0.22807250916957855, "learning_rate": 3.209441520825394e-05, "loss": 0.0921, "step": 323 }, { "epoch": 1.5220458553791887, "grad_norm": 0.2253958284854889, "learning_rate": 3.193949852625805e-05, "loss": 0.103, "step": 324 }, { "epoch": 1.5267489711934157, "grad_norm": 0.23763658106327057, "learning_rate": 3.178452989123621e-05, "loss": 0.1153, "step": 325 }, { "epoch": 1.5314520870076427, "grad_norm": 0.24107792973518372, "learning_rate": 3.162951345430757e-05, "loss": 0.0943, "step": 326 }, { "epoch": 1.5361552028218695, "grad_norm": 0.26309165358543396, "learning_rate": 3.147445336787179e-05, "loss": 0.1152, "step": 327 }, { "epoch": 1.5408583186360965, "grad_norm": 0.27157434821128845, "learning_rate": 3.131935378549773e-05, "loss": 0.1122, "step": 328 }, { "epoch": 1.5455614344503235, "grad_norm": 0.21065029501914978, "learning_rate": 3.116421886181221e-05, "loss": 0.1063, "step": 329 }, { "epoch": 1.5502645502645502, "grad_norm": 0.24972011148929596, "learning_rate": 3.1009052752388775e-05, "loss": 0.1158, "step": 330 }, { "epoch": 1.5549676660787772, "grad_norm": 0.2365872859954834, "learning_rate": 3.08538596136363e-05, "loss": 0.1107, "step": 331 }, { "epoch": 1.5596707818930042, "grad_norm": 0.22084331512451172, "learning_rate": 3.069864360268771e-05, "loss": 0.0918, "step": 332 }, { "epoch": 1.564373897707231, "grad_norm": 0.2525952458381653, "learning_rate": 3.054340887728858e-05, "loss": 0.1188, "step": 333 }, { "epoch": 1.569077013521458, "grad_norm": 0.24593819677829742, "learning_rate": 3.0388159595685813e-05, "loss": 0.1027, "step": 334 }, { "epoch": 1.573780129335685, "grad_norm": 0.2355092316865921, "learning_rate": 3.023289991651621e-05, "loss": 0.1123, "step": 335 }, { "epoch": 1.5784832451499118, "grad_norm": 0.25615260004997253, "learning_rate": 3.0077633998695096e-05, "loss": 0.1138, "step": 336 }, { "epoch": 1.5831863609641388, "grad_norm": 0.25977692008018494, "learning_rate": 2.9922366001304912e-05, "loss": 0.0995, "step": 337 }, { "epoch": 1.5878894767783658, "grad_norm": 0.20958293974399567, "learning_rate": 2.9767100083483803e-05, "loss": 0.1053, "step": 338 }, { "epoch": 1.5925925925925926, "grad_norm": 0.254332572221756, "learning_rate": 2.961184040431419e-05, "loss": 0.115, "step": 339 }, { "epoch": 1.5972957084068196, "grad_norm": 0.24442750215530396, "learning_rate": 2.9456591122711422e-05, "loss": 0.1126, "step": 340 }, { "epoch": 1.6019988242210466, "grad_norm": 0.23448610305786133, "learning_rate": 2.9301356397312296e-05, "loss": 0.1048, "step": 341 }, { "epoch": 1.6067019400352733, "grad_norm": 0.23055116832256317, "learning_rate": 2.9146140386363702e-05, "loss": 0.0976, "step": 342 }, { "epoch": 1.6114050558495003, "grad_norm": 0.23804478347301483, "learning_rate": 2.8990947247611223e-05, "loss": 0.1063, "step": 343 }, { "epoch": 1.6161081716637273, "grad_norm": 0.26679643988609314, "learning_rate": 2.8835781138187788e-05, "loss": 0.1144, "step": 344 }, { "epoch": 1.620811287477954, "grad_norm": 0.22137752175331116, "learning_rate": 2.868064621450228e-05, "loss": 0.1038, "step": 345 }, { "epoch": 1.625514403292181, "grad_norm": 0.23607514798641205, "learning_rate": 2.852554663212822e-05, "loss": 0.1041, "step": 346 }, { "epoch": 1.630217519106408, "grad_norm": 0.24644407629966736, "learning_rate": 2.837048654569243e-05, "loss": 0.1058, "step": 347 }, { "epoch": 1.6349206349206349, "grad_norm": 0.22648413479328156, "learning_rate": 2.8215470108763797e-05, "loss": 0.1019, "step": 348 }, { "epoch": 1.6396237507348619, "grad_norm": 0.220939040184021, "learning_rate": 2.8060501473741956e-05, "loss": 0.1108, "step": 349 }, { "epoch": 1.6443268665490889, "grad_norm": 0.24095316231250763, "learning_rate": 2.790558479174607e-05, "loss": 0.1004, "step": 350 }, { "epoch": 1.6490299823633157, "grad_norm": 0.21854864060878754, "learning_rate": 2.7750724212503644e-05, "loss": 0.098, "step": 351 }, { "epoch": 1.6537330981775427, "grad_norm": 0.2552099823951721, "learning_rate": 2.7595923884239402e-05, "loss": 0.1266, "step": 352 }, { "epoch": 1.6584362139917697, "grad_norm": 0.2471349537372589, "learning_rate": 2.7441187953564103e-05, "loss": 0.1034, "step": 353 }, { "epoch": 1.6631393298059964, "grad_norm": 0.21639327704906464, "learning_rate": 2.7286520565363503e-05, "loss": 0.0905, "step": 354 }, { "epoch": 1.6678424456202234, "grad_norm": 0.260152667760849, "learning_rate": 2.7131925862687324e-05, "loss": 0.1149, "step": 355 }, { "epoch": 1.6725455614344504, "grad_norm": 0.22149719297885895, "learning_rate": 2.6977407986638284e-05, "loss": 0.1098, "step": 356 }, { "epoch": 1.6772486772486772, "grad_norm": 0.21370597183704376, "learning_rate": 2.6822971076261142e-05, "loss": 0.1027, "step": 357 }, { "epoch": 1.6819517930629042, "grad_norm": 0.23036998510360718, "learning_rate": 2.666861926843186e-05, "loss": 0.1086, "step": 358 }, { "epoch": 1.6866549088771312, "grad_norm": 0.24688982963562012, "learning_rate": 2.651435669774674e-05, "loss": 0.1073, "step": 359 }, { "epoch": 1.691358024691358, "grad_norm": 0.23335649073123932, "learning_rate": 2.6360187496411753e-05, "loss": 0.1014, "step": 360 }, { "epoch": 1.696061140505585, "grad_norm": 0.21480391919612885, "learning_rate": 2.6206115794131763e-05, "loss": 0.112, "step": 361 }, { "epoch": 1.700764256319812, "grad_norm": 0.2111615091562271, "learning_rate": 2.6052145717999957e-05, "loss": 0.0961, "step": 362 }, { "epoch": 1.7054673721340388, "grad_norm": 0.21552674472332, "learning_rate": 2.5898281392387258e-05, "loss": 0.087, "step": 363 }, { "epoch": 1.7101704879482658, "grad_norm": 0.22968819737434387, "learning_rate": 2.5744526938831913e-05, "loss": 0.1043, "step": 364 }, { "epoch": 1.7148736037624928, "grad_norm": 0.2401447296142578, "learning_rate": 2.559088647592901e-05, "loss": 0.1236, "step": 365 }, { "epoch": 1.7195767195767195, "grad_norm": 0.21172498166561127, "learning_rate": 2.5437364119220185e-05, "loss": 0.1006, "step": 366 }, { "epoch": 1.7242798353909465, "grad_norm": 0.2539319097995758, "learning_rate": 2.528396398108339e-05, "loss": 0.1252, "step": 367 }, { "epoch": 1.7289829512051735, "grad_norm": 0.22244076430797577, "learning_rate": 2.5130690170622745e-05, "loss": 0.1066, "step": 368 }, { "epoch": 1.7336860670194003, "grad_norm": 0.2509514391422272, "learning_rate": 2.4977546793558434e-05, "loss": 0.112, "step": 369 }, { "epoch": 1.7383891828336273, "grad_norm": 0.2561204135417938, "learning_rate": 2.4824537952116746e-05, "loss": 0.1103, "step": 370 }, { "epoch": 1.7430922986478543, "grad_norm": 0.21031582355499268, "learning_rate": 2.4671667744920174e-05, "loss": 0.0994, "step": 371 }, { "epoch": 1.747795414462081, "grad_norm": 0.24004732072353363, "learning_rate": 2.451894026687767e-05, "loss": 0.1134, "step": 372 }, { "epoch": 1.752498530276308, "grad_norm": 0.2273636907339096, "learning_rate": 2.4366359609074906e-05, "loss": 0.0981, "step": 373 }, { "epoch": 1.757201646090535, "grad_norm": 0.23199258744716644, "learning_rate": 2.421392985866469e-05, "loss": 0.0961, "step": 374 }, { "epoch": 1.7619047619047619, "grad_norm": 0.24324755370616913, "learning_rate": 2.4061655098757527e-05, "loss": 0.1091, "step": 375 }, { "epoch": 1.7666078777189889, "grad_norm": 0.2258569449186325, "learning_rate": 2.3909539408312197e-05, "loss": 0.1019, "step": 376 }, { "epoch": 1.7713109935332159, "grad_norm": 0.23349852859973907, "learning_rate": 2.375758686202651e-05, "loss": 0.1037, "step": 377 }, { "epoch": 1.7760141093474426, "grad_norm": 0.17248693108558655, "learning_rate": 2.360580153022818e-05, "loss": 0.0789, "step": 378 }, { "epoch": 1.7807172251616696, "grad_norm": 0.23220425844192505, "learning_rate": 2.345418747876577e-05, "loss": 0.1044, "step": 379 }, { "epoch": 1.7854203409758966, "grad_norm": 0.20680402219295502, "learning_rate": 2.330274876889977e-05, "loss": 0.1055, "step": 380 }, { "epoch": 1.7901234567901234, "grad_norm": 0.20497600734233856, "learning_rate": 2.3151489457193823e-05, "loss": 0.1, "step": 381 }, { "epoch": 1.7948265726043504, "grad_norm": 0.21781094372272491, "learning_rate": 2.3000413595406076e-05, "loss": 0.0979, "step": 382 }, { "epoch": 1.7995296884185774, "grad_norm": 0.23362252116203308, "learning_rate": 2.2849525230380643e-05, "loss": 0.091, "step": 383 }, { "epoch": 1.8042328042328042, "grad_norm": 0.23850637674331665, "learning_rate": 2.269882840393917e-05, "loss": 0.1022, "step": 384 }, { "epoch": 1.8089359200470312, "grad_norm": 0.20775571465492249, "learning_rate": 2.25483271527726e-05, "loss": 0.0841, "step": 385 }, { "epoch": 1.8136390358612582, "grad_norm": 0.20628474652767181, "learning_rate": 2.2398025508333033e-05, "loss": 0.0897, "step": 386 }, { "epoch": 1.818342151675485, "grad_norm": 0.23100906610488892, "learning_rate": 2.2247927496725743e-05, "loss": 0.0957, "step": 387 }, { "epoch": 1.823045267489712, "grad_norm": 0.2351640909910202, "learning_rate": 2.2098037138601318e-05, "loss": 0.1039, "step": 388 }, { "epoch": 1.827748383303939, "grad_norm": 0.25146380066871643, "learning_rate": 2.1948358449047964e-05, "loss": 0.1036, "step": 389 }, { "epoch": 1.8324514991181657, "grad_norm": 0.19981586933135986, "learning_rate": 2.1798895437483954e-05, "loss": 0.1029, "step": 390 }, { "epoch": 1.8371546149323927, "grad_norm": 0.24228838086128235, "learning_rate": 2.1649652107550256e-05, "loss": 0.0895, "step": 391 }, { "epoch": 1.8418577307466197, "grad_norm": 0.22370409965515137, "learning_rate": 2.1500632457003233e-05, "loss": 0.1074, "step": 392 }, { "epoch": 1.8465608465608465, "grad_norm": 0.23530763387680054, "learning_rate": 2.135184047760759e-05, "loss": 0.1104, "step": 393 }, { "epoch": 1.8512639623750735, "grad_norm": 0.20164668560028076, "learning_rate": 2.1203280155029445e-05, "loss": 0.0887, "step": 394 }, { "epoch": 1.8559670781893005, "grad_norm": 0.21399357914924622, "learning_rate": 2.105495546872959e-05, "loss": 0.0957, "step": 395 }, { "epoch": 1.8606701940035273, "grad_norm": 0.27256250381469727, "learning_rate": 2.090687039185682e-05, "loss": 0.104, "step": 396 }, { "epoch": 1.8653733098177543, "grad_norm": 0.22376582026481628, "learning_rate": 2.0759028891141584e-05, "loss": 0.1005, "step": 397 }, { "epoch": 1.8700764256319813, "grad_norm": 0.21237486600875854, "learning_rate": 2.061143492678968e-05, "loss": 0.098, "step": 398 }, { "epoch": 1.874779541446208, "grad_norm": 0.24553731083869934, "learning_rate": 2.0464092452376212e-05, "loss": 0.1096, "step": 399 }, { "epoch": 1.879482657260435, "grad_norm": 0.19243447482585907, "learning_rate": 2.0317005414739646e-05, "loss": 0.0917, "step": 400 }, { "epoch": 1.884185773074662, "grad_norm": 0.22185510396957397, "learning_rate": 2.0170177753876104e-05, "loss": 0.1052, "step": 401 }, { "epoch": 1.8888888888888888, "grad_norm": 0.2508143186569214, "learning_rate": 2.002361340283382e-05, "loss": 0.1197, "step": 402 }, { "epoch": 1.8935920047031158, "grad_norm": 0.20621263980865479, "learning_rate": 1.9877316287607836e-05, "loss": 0.0954, "step": 403 }, { "epoch": 1.8982951205173428, "grad_norm": 0.2721441388130188, "learning_rate": 1.973129032703474e-05, "loss": 0.0961, "step": 404 }, { "epoch": 1.9029982363315696, "grad_norm": 0.243619903922081, "learning_rate": 1.9585539432687768e-05, "loss": 0.1064, "step": 405 }, { "epoch": 1.9077013521457966, "grad_norm": 0.17235860228538513, "learning_rate": 1.9440067508771983e-05, "loss": 0.0745, "step": 406 }, { "epoch": 1.9124044679600236, "grad_norm": 0.22149856388568878, "learning_rate": 1.9294878452019753e-05, "loss": 0.0933, "step": 407 }, { "epoch": 1.9171075837742504, "grad_norm": 0.23720677196979523, "learning_rate": 1.9149976151586306e-05, "loss": 0.0858, "step": 408 }, { "epoch": 1.9218106995884774, "grad_norm": 0.2073083519935608, "learning_rate": 1.900536448894556e-05, "loss": 0.0954, "step": 409 }, { "epoch": 1.9265138154027044, "grad_norm": 0.234296977519989, "learning_rate": 1.8861047337786192e-05, "loss": 0.1075, "step": 410 }, { "epoch": 1.9312169312169312, "grad_norm": 0.24207735061645508, "learning_rate": 1.871702856390784e-05, "loss": 0.0967, "step": 411 }, { "epoch": 1.9359200470311582, "grad_norm": 0.20719723403453827, "learning_rate": 1.8573312025117563e-05, "loss": 0.0966, "step": 412 }, { "epoch": 1.9406231628453852, "grad_norm": 0.20428553223609924, "learning_rate": 1.8429901571126483e-05, "loss": 0.0877, "step": 413 }, { "epoch": 1.945326278659612, "grad_norm": 0.22946356236934662, "learning_rate": 1.8286801043446693e-05, "loss": 0.1019, "step": 414 }, { "epoch": 1.950029394473839, "grad_norm": 0.2179248332977295, "learning_rate": 1.8144014275288353e-05, "loss": 0.09, "step": 415 }, { "epoch": 1.954732510288066, "grad_norm": 0.23784589767456055, "learning_rate": 1.800154509145697e-05, "loss": 0.1132, "step": 416 }, { "epoch": 1.9594356261022927, "grad_norm": 0.20071126520633698, "learning_rate": 1.7859397308251e-05, "loss": 0.0994, "step": 417 }, { "epoch": 1.9641387419165197, "grad_norm": 0.2521038353443146, "learning_rate": 1.771757473335955e-05, "loss": 0.1092, "step": 418 }, { "epoch": 1.9688418577307467, "grad_norm": 0.2522083818912506, "learning_rate": 1.75760811657605e-05, "loss": 0.124, "step": 419 }, { "epoch": 1.9735449735449735, "grad_norm": 0.2524920403957367, "learning_rate": 1.74349203956186e-05, "loss": 0.1057, "step": 420 }, { "epoch": 1.9782480893592005, "grad_norm": 0.2568269371986389, "learning_rate": 1.729409620418403e-05, "loss": 0.1014, "step": 421 }, { "epoch": 1.9829512051734275, "grad_norm": 0.24609288573265076, "learning_rate": 1.7153612363691086e-05, "loss": 0.1098, "step": 422 }, { "epoch": 1.9876543209876543, "grad_norm": 0.23845499753952026, "learning_rate": 1.701347263725717e-05, "loss": 0.117, "step": 423 }, { "epoch": 1.9923574368018813, "grad_norm": 0.2170892059803009, "learning_rate": 1.687368077878193e-05, "loss": 0.0996, "step": 424 }, { "epoch": 1.9970605526161083, "grad_norm": 0.2381209135055542, "learning_rate": 1.6734240532846722e-05, "loss": 0.1076, "step": 425 }, { "epoch": 2.0, "grad_norm": 0.25441399216651917, "learning_rate": 1.6595155634614343e-05, "loss": 0.0938, "step": 426 }, { "epoch": 2.0047031158142268, "grad_norm": 0.32570019364356995, "learning_rate": 1.645642980972894e-05, "loss": 0.0798, "step": 427 }, { "epoch": 2.009406231628454, "grad_norm": 0.2428978681564331, "learning_rate": 1.6318066774216207e-05, "loss": 0.076, "step": 428 }, { "epoch": 2.0141093474426808, "grad_norm": 0.2431434541940689, "learning_rate": 1.6180070234383885e-05, "loss": 0.0685, "step": 429 }, { "epoch": 2.0188124632569076, "grad_norm": 0.3919472098350525, "learning_rate": 1.6042443886722423e-05, "loss": 0.0769, "step": 430 }, { "epoch": 2.0235155790711348, "grad_norm": 0.29864704608917236, "learning_rate": 1.5905191417806035e-05, "loss": 0.0697, "step": 431 }, { "epoch": 2.0282186948853616, "grad_norm": 0.21277965605258942, "learning_rate": 1.576831650419388e-05, "loss": 0.0613, "step": 432 }, { "epoch": 2.0329218106995883, "grad_norm": 0.2263723462820053, "learning_rate": 1.563182281233161e-05, "loss": 0.0644, "step": 433 }, { "epoch": 2.0376249265138155, "grad_norm": 0.23350580036640167, "learning_rate": 1.5495713998453135e-05, "loss": 0.07, "step": 434 }, { "epoch": 2.0423280423280423, "grad_norm": 0.25206705927848816, "learning_rate": 1.535999370848275e-05, "loss": 0.0707, "step": 435 }, { "epoch": 2.047031158142269, "grad_norm": 0.22276893258094788, "learning_rate": 1.5224665577937383e-05, "loss": 0.0688, "step": 436 }, { "epoch": 2.0517342739564963, "grad_norm": 0.24506792426109314, "learning_rate": 1.5089733231829264e-05, "loss": 0.0678, "step": 437 }, { "epoch": 2.056437389770723, "grad_norm": 0.23243868350982666, "learning_rate": 1.4955200284568795e-05, "loss": 0.076, "step": 438 }, { "epoch": 2.06114050558495, "grad_norm": 0.2618112564086914, "learning_rate": 1.4821070339867797e-05, "loss": 0.0752, "step": 439 }, { "epoch": 2.065843621399177, "grad_norm": 0.24187178909778595, "learning_rate": 1.4687346990642874e-05, "loss": 0.0705, "step": 440 }, { "epoch": 2.070546737213404, "grad_norm": 0.2358836531639099, "learning_rate": 1.4554033818919238e-05, "loss": 0.0719, "step": 441 }, { "epoch": 2.0752498530276307, "grad_norm": 0.24052295088768005, "learning_rate": 1.4421134395734772e-05, "loss": 0.0751, "step": 442 }, { "epoch": 2.079952968841858, "grad_norm": 0.21751539409160614, "learning_rate": 1.4288652281044317e-05, "loss": 0.0645, "step": 443 }, { "epoch": 2.0846560846560847, "grad_norm": 0.24449367821216583, "learning_rate": 1.4156591023624345e-05, "loss": 0.0779, "step": 444 }, { "epoch": 2.0893592004703114, "grad_norm": 0.22946541011333466, "learning_rate": 1.4024954160977883e-05, "loss": 0.0692, "step": 445 }, { "epoch": 2.0940623162845386, "grad_norm": 0.21861298382282257, "learning_rate": 1.389374521923981e-05, "loss": 0.0693, "step": 446 }, { "epoch": 2.0987654320987654, "grad_norm": 0.22534681856632233, "learning_rate": 1.3762967713082306e-05, "loss": 0.0719, "step": 447 }, { "epoch": 2.103468547912992, "grad_norm": 0.22906312346458435, "learning_rate": 1.363262514562079e-05, "loss": 0.0702, "step": 448 }, { "epoch": 2.1081716637272194, "grad_norm": 0.2390565425157547, "learning_rate": 1.3502721008320033e-05, "loss": 0.067, "step": 449 }, { "epoch": 2.112874779541446, "grad_norm": 0.242502361536026, "learning_rate": 1.3373258780900661e-05, "loss": 0.0781, "step": 450 }, { "epoch": 2.117577895355673, "grad_norm": 0.2245815247297287, "learning_rate": 1.3244241931245923e-05, "loss": 0.0717, "step": 451 }, { "epoch": 2.1222810111699, "grad_norm": 0.2660517990589142, "learning_rate": 1.3115673915308819e-05, "loss": 0.0879, "step": 452 }, { "epoch": 2.126984126984127, "grad_norm": 0.2333550900220871, "learning_rate": 1.2987558177019494e-05, "loss": 0.0682, "step": 453 }, { "epoch": 2.1316872427983538, "grad_norm": 0.2599058449268341, "learning_rate": 1.2859898148193044e-05, "loss": 0.0724, "step": 454 }, { "epoch": 2.136390358612581, "grad_norm": 0.23258008062839508, "learning_rate": 1.2732697248437517e-05, "loss": 0.0754, "step": 455 }, { "epoch": 2.1410934744268078, "grad_norm": 0.2433544546365738, "learning_rate": 1.2605958885062356e-05, "loss": 0.0797, "step": 456 }, { "epoch": 2.1457965902410345, "grad_norm": 0.279856413602829, "learning_rate": 1.2479686452987118e-05, "loss": 0.0677, "step": 457 }, { "epoch": 2.1504997060552618, "grad_norm": 0.19199180603027344, "learning_rate": 1.2353883334650548e-05, "loss": 0.0605, "step": 458 }, { "epoch": 2.1552028218694885, "grad_norm": 0.23078687489032745, "learning_rate": 1.2228552899919947e-05, "loss": 0.0764, "step": 459 }, { "epoch": 2.1599059376837153, "grad_norm": 0.2297143042087555, "learning_rate": 1.2103698506000923e-05, "loss": 0.0715, "step": 460 }, { "epoch": 2.1646090534979425, "grad_norm": 0.2373790144920349, "learning_rate": 1.1979323497347447e-05, "loss": 0.0689, "step": 461 }, { "epoch": 2.1693121693121693, "grad_norm": 0.24250781536102295, "learning_rate": 1.1855431205572303e-05, "loss": 0.0776, "step": 462 }, { "epoch": 2.174015285126396, "grad_norm": 0.22349432110786438, "learning_rate": 1.1732024949357796e-05, "loss": 0.0667, "step": 463 }, { "epoch": 2.1787184009406233, "grad_norm": 0.24029043316841125, "learning_rate": 1.160910803436688e-05, "loss": 0.0694, "step": 464 }, { "epoch": 2.18342151675485, "grad_norm": 0.24622848629951477, "learning_rate": 1.14866837531546e-05, "loss": 0.0831, "step": 465 }, { "epoch": 2.188124632569077, "grad_norm": 0.18277762830257416, "learning_rate": 1.1364755385079935e-05, "loss": 0.0597, "step": 466 }, { "epoch": 2.192827748383304, "grad_norm": 0.2516407072544098, "learning_rate": 1.1243326196217878e-05, "loss": 0.0745, "step": 467 }, { "epoch": 2.197530864197531, "grad_norm": 0.21791240572929382, "learning_rate": 1.1122399439272013e-05, "loss": 0.0605, "step": 468 }, { "epoch": 2.2022339800117576, "grad_norm": 0.24293601512908936, "learning_rate": 1.1001978353487356e-05, "loss": 0.0674, "step": 469 }, { "epoch": 2.206937095825985, "grad_norm": 0.25094592571258545, "learning_rate": 1.0882066164563608e-05, "loss": 0.0747, "step": 470 }, { "epoch": 2.2116402116402116, "grad_norm": 0.22727538645267487, "learning_rate": 1.0762666084568718e-05, "loss": 0.0682, "step": 471 }, { "epoch": 2.2163433274544384, "grad_norm": 0.2640625238418579, "learning_rate": 1.0643781311852867e-05, "loss": 0.0813, "step": 472 }, { "epoch": 2.2210464432686656, "grad_norm": 0.2240592986345291, "learning_rate": 1.0525415030962771e-05, "loss": 0.0656, "step": 473 }, { "epoch": 2.2257495590828924, "grad_norm": 0.23659418523311615, "learning_rate": 1.0407570412556412e-05, "loss": 0.069, "step": 474 }, { "epoch": 2.230452674897119, "grad_norm": 0.23898428678512573, "learning_rate": 1.029025061331807e-05, "loss": 0.0696, "step": 475 }, { "epoch": 2.2351557907113464, "grad_norm": 0.2337837666273117, "learning_rate": 1.017345877587379e-05, "loss": 0.0713, "step": 476 }, { "epoch": 2.239858906525573, "grad_norm": 0.2324306219816208, "learning_rate": 1.0057198028707173e-05, "loss": 0.0696, "step": 477 }, { "epoch": 2.2445620223398, "grad_norm": 0.24400180578231812, "learning_rate": 9.941471486075632e-06, "loss": 0.0691, "step": 478 }, { "epoch": 2.249265138154027, "grad_norm": 0.24171234667301178, "learning_rate": 9.826282247926895e-06, "loss": 0.0716, "step": 479 }, { "epoch": 2.253968253968254, "grad_norm": 0.22459232807159424, "learning_rate": 9.711633399816013e-06, "loss": 0.0586, "step": 480 }, { "epoch": 2.2586713697824807, "grad_norm": 0.2683708965778351, "learning_rate": 9.597528012822694e-06, "loss": 0.0794, "step": 481 }, { "epoch": 2.263374485596708, "grad_norm": 0.22851063311100006, "learning_rate": 9.483969143469071e-06, "loss": 0.0621, "step": 482 }, { "epoch": 2.2680776014109347, "grad_norm": 0.21968196332454681, "learning_rate": 9.370959833637768e-06, "loss": 0.0669, "step": 483 }, { "epoch": 2.2727807172251615, "grad_norm": 0.2192542552947998, "learning_rate": 9.258503110490462e-06, "loss": 0.0714, "step": 484 }, { "epoch": 2.2774838330393887, "grad_norm": 0.21319252252578735, "learning_rate": 9.146601986386765e-06, "loss": 0.0624, "step": 485 }, { "epoch": 2.2821869488536155, "grad_norm": 0.2305806577205658, "learning_rate": 9.035259458803586e-06, "loss": 0.0659, "step": 486 }, { "epoch": 2.2868900646678423, "grad_norm": 0.24348193407058716, "learning_rate": 8.924478510254774e-06, "loss": 0.0705, "step": 487 }, { "epoch": 2.2915931804820695, "grad_norm": 0.2252054214477539, "learning_rate": 8.814262108211253e-06, "loss": 0.0679, "step": 488 }, { "epoch": 2.2962962962962963, "grad_norm": 0.26006028056144714, "learning_rate": 8.704613205021535e-06, "loss": 0.0773, "step": 489 }, { "epoch": 2.300999412110523, "grad_norm": 0.22696566581726074, "learning_rate": 8.595534737832654e-06, "loss": 0.0748, "step": 490 }, { "epoch": 2.3057025279247503, "grad_norm": 0.23085075616836548, "learning_rate": 8.487029628511442e-06, "loss": 0.071, "step": 491 }, { "epoch": 2.310405643738977, "grad_norm": 0.24782857298851013, "learning_rate": 8.379100783566306e-06, "loss": 0.0762, "step": 492 }, { "epoch": 2.315108759553204, "grad_norm": 0.2269497960805893, "learning_rate": 8.271751094069345e-06, "loss": 0.0683, "step": 493 }, { "epoch": 2.319811875367431, "grad_norm": 0.23065273463726044, "learning_rate": 8.164983435578925e-06, "loss": 0.0689, "step": 494 }, { "epoch": 2.324514991181658, "grad_norm": 0.231636643409729, "learning_rate": 8.058800668062632e-06, "loss": 0.0682, "step": 495 }, { "epoch": 2.3292181069958846, "grad_norm": 0.2084759771823883, "learning_rate": 7.953205635820681e-06, "loss": 0.0628, "step": 496 }, { "epoch": 2.333921222810112, "grad_norm": 0.23873017728328705, "learning_rate": 7.848201167409735e-06, "loss": 0.0785, "step": 497 }, { "epoch": 2.3386243386243386, "grad_norm": 0.21174301207065582, "learning_rate": 7.743790075567097e-06, "loss": 0.0602, "step": 498 }, { "epoch": 2.3433274544385654, "grad_norm": 0.26984986662864685, "learning_rate": 7.639975157135403e-06, "loss": 0.072, "step": 499 }, { "epoch": 2.3480305702527926, "grad_norm": 0.27114883065223694, "learning_rate": 7.5367591929876825e-06, "loss": 0.0788, "step": 500 }, { "epoch": 2.3527336860670194, "grad_norm": 0.22701899707317352, "learning_rate": 7.4341449479528775e-06, "loss": 0.0721, "step": 501 }, { "epoch": 2.357436801881246, "grad_norm": 0.214376300573349, "learning_rate": 7.332135170741795e-06, "loss": 0.0682, "step": 502 }, { "epoch": 2.3621399176954734, "grad_norm": 0.3009589910507202, "learning_rate": 7.230732593873445e-06, "loss": 0.0584, "step": 503 }, { "epoch": 2.3668430335097, "grad_norm": 0.2075635939836502, "learning_rate": 7.129939933601869e-06, "loss": 0.0632, "step": 504 }, { "epoch": 2.371546149323927, "grad_norm": 0.23966585099697113, "learning_rate": 7.029759889843358e-06, "loss": 0.0691, "step": 505 }, { "epoch": 2.376249265138154, "grad_norm": 0.21880073845386505, "learning_rate": 6.930195146104186e-06, "loss": 0.0714, "step": 506 }, { "epoch": 2.380952380952381, "grad_norm": 0.22032232582569122, "learning_rate": 6.831248369408647e-06, "loss": 0.0708, "step": 507 }, { "epoch": 2.3856554967666077, "grad_norm": 0.18172289431095123, "learning_rate": 6.732922210227661e-06, "loss": 0.0635, "step": 508 }, { "epoch": 2.390358612580835, "grad_norm": 0.2099859118461609, "learning_rate": 6.635219302407796e-06, "loss": 0.0682, "step": 509 }, { "epoch": 2.3950617283950617, "grad_norm": 0.2302139550447464, "learning_rate": 6.538142263100656e-06, "loss": 0.0666, "step": 510 }, { "epoch": 2.3997648442092885, "grad_norm": 0.1997382491827011, "learning_rate": 6.4416936926928315e-06, "loss": 0.0591, "step": 511 }, { "epoch": 2.4044679600235157, "grad_norm": 0.23313842713832855, "learning_rate": 6.3458761747361985e-06, "loss": 0.0665, "step": 512 }, { "epoch": 2.4091710758377425, "grad_norm": 0.22455184161663055, "learning_rate": 6.250692275878763e-06, "loss": 0.0707, "step": 513 }, { "epoch": 2.4138741916519693, "grad_norm": 0.23126228153705597, "learning_rate": 6.156144545795864e-06, "loss": 0.0778, "step": 514 }, { "epoch": 2.4185773074661965, "grad_norm": 0.20600196719169617, "learning_rate": 6.06223551712189e-06, "loss": 0.0607, "step": 515 }, { "epoch": 2.4232804232804233, "grad_norm": 0.24002297222614288, "learning_rate": 5.968967705382452e-06, "loss": 0.0767, "step": 516 }, { "epoch": 2.42798353909465, "grad_norm": 0.18777860701084137, "learning_rate": 5.876343608926984e-06, "loss": 0.0609, "step": 517 }, { "epoch": 2.4326866549088773, "grad_norm": 0.21755680441856384, "learning_rate": 5.784365708861816e-06, "loss": 0.0655, "step": 518 }, { "epoch": 2.437389770723104, "grad_norm": 0.20052874088287354, "learning_rate": 5.693036468983739e-06, "loss": 0.0562, "step": 519 }, { "epoch": 2.442092886537331, "grad_norm": 0.23969148099422455, "learning_rate": 5.602358335713974e-06, "loss": 0.0736, "step": 520 }, { "epoch": 2.446796002351558, "grad_norm": 0.21396146714687347, "learning_rate": 5.5123337380326785e-06, "loss": 0.0647, "step": 521 }, { "epoch": 2.451499118165785, "grad_norm": 0.22914955019950867, "learning_rate": 5.422965087413844e-06, "loss": 0.0634, "step": 522 }, { "epoch": 2.4562022339800116, "grad_norm": 0.22646230459213257, "learning_rate": 5.334254777760717e-06, "loss": 0.0671, "step": 523 }, { "epoch": 2.460905349794239, "grad_norm": 0.23329733312129974, "learning_rate": 5.246205185341672e-06, "loss": 0.0664, "step": 524 }, { "epoch": 2.4656084656084656, "grad_norm": 0.2292928695678711, "learning_rate": 5.1588186687265815e-06, "loss": 0.0723, "step": 525 }, { "epoch": 2.4703115814226924, "grad_norm": 0.26244285702705383, "learning_rate": 5.072097568723585e-06, "loss": 0.0718, "step": 526 }, { "epoch": 2.4750146972369196, "grad_norm": 0.166345477104187, "learning_rate": 4.986044208316442e-06, "loss": 0.0601, "step": 527 }, { "epoch": 2.4797178130511464, "grad_norm": 0.24680264294147491, "learning_rate": 4.900660892602261e-06, "loss": 0.0668, "step": 528 }, { "epoch": 2.484420928865373, "grad_norm": 0.22012190520763397, "learning_rate": 4.815949908729798e-06, "loss": 0.0767, "step": 529 }, { "epoch": 2.4891240446796004, "grad_norm": 0.22690841555595398, "learning_rate": 4.73191352583815e-06, "loss": 0.0683, "step": 530 }, { "epoch": 2.493827160493827, "grad_norm": 0.20190899074077606, "learning_rate": 4.648553994995995e-06, "loss": 0.0635, "step": 531 }, { "epoch": 2.498530276308054, "grad_norm": 0.2297000139951706, "learning_rate": 4.5658735491412794e-06, "loss": 0.0686, "step": 532 }, { "epoch": 2.503233392122281, "grad_norm": 0.2161605954170227, "learning_rate": 4.483874403021432e-06, "loss": 0.0715, "step": 533 }, { "epoch": 2.507936507936508, "grad_norm": 0.206724151968956, "learning_rate": 4.402558753133996e-06, "loss": 0.0683, "step": 534 }, { "epoch": 2.5126396237507347, "grad_norm": 0.2074771523475647, "learning_rate": 4.3219287776678285e-06, "loss": 0.0648, "step": 535 }, { "epoch": 2.517342739564962, "grad_norm": 0.22342519462108612, "learning_rate": 4.241986636444727e-06, "loss": 0.0668, "step": 536 }, { "epoch": 2.5220458553791887, "grad_norm": 0.22877030074596405, "learning_rate": 4.162734470861604e-06, "loss": 0.0645, "step": 537 }, { "epoch": 2.526748971193416, "grad_norm": 0.21734531223773956, "learning_rate": 4.084174403833102e-06, "loss": 0.067, "step": 538 }, { "epoch": 2.5314520870076427, "grad_norm": 0.1927523910999298, "learning_rate": 4.006308539734723e-06, "loss": 0.0631, "step": 539 }, { "epoch": 2.5361552028218695, "grad_norm": 0.19919046759605408, "learning_rate": 3.92913896434648e-06, "loss": 0.0606, "step": 540 }, { "epoch": 2.5408583186360962, "grad_norm": 0.22096918523311615, "learning_rate": 3.8526677447970185e-06, "loss": 0.0645, "step": 541 }, { "epoch": 2.5455614344503235, "grad_norm": 0.18752585351467133, "learning_rate": 3.7768969295082354e-06, "loss": 0.0537, "step": 542 }, { "epoch": 2.5502645502645502, "grad_norm": 0.2204677313566208, "learning_rate": 3.7018285481404157e-06, "loss": 0.0712, "step": 543 }, { "epoch": 2.5549676660787775, "grad_norm": 0.21374481916427612, "learning_rate": 3.6274646115378562e-06, "loss": 0.0637, "step": 544 }, { "epoch": 2.5596707818930042, "grad_norm": 0.2232723981142044, "learning_rate": 3.5538071116750326e-06, "loss": 0.0702, "step": 545 }, { "epoch": 2.564373897707231, "grad_norm": 0.22076444327831268, "learning_rate": 3.480858021603194e-06, "loss": 0.0712, "step": 546 }, { "epoch": 2.569077013521458, "grad_norm": 0.20655864477157593, "learning_rate": 3.408619295397538e-06, "loss": 0.0624, "step": 547 }, { "epoch": 2.573780129335685, "grad_norm": 0.20781254768371582, "learning_rate": 3.3370928681048586e-06, "loss": 0.0622, "step": 548 }, { "epoch": 2.578483245149912, "grad_norm": 0.20648232102394104, "learning_rate": 3.2662806556917402e-06, "loss": 0.0679, "step": 549 }, { "epoch": 2.583186360964139, "grad_norm": 0.2140021026134491, "learning_rate": 3.196184554993182e-06, "loss": 0.0649, "step": 550 }, { "epoch": 2.587889476778366, "grad_norm": 0.18609030544757843, "learning_rate": 3.1268064436618314e-06, "loss": 0.0575, "step": 551 }, { "epoch": 2.5925925925925926, "grad_norm": 0.20522786676883698, "learning_rate": 3.0581481801176692e-06, "loss": 0.0686, "step": 552 }, { "epoch": 2.5972957084068193, "grad_norm": 0.19409161806106567, "learning_rate": 2.990211603498244e-06, "loss": 0.0665, "step": 553 }, { "epoch": 2.6019988242210466, "grad_norm": 0.20299561321735382, "learning_rate": 2.9229985336093825e-06, "loss": 0.0615, "step": 554 }, { "epoch": 2.6067019400352733, "grad_norm": 0.2129613161087036, "learning_rate": 2.8565107708764593e-06, "loss": 0.0639, "step": 555 }, { "epoch": 2.6114050558495006, "grad_norm": 0.22230957448482513, "learning_rate": 2.7907500962961653e-06, "loss": 0.0667, "step": 556 }, { "epoch": 2.6161081716637273, "grad_norm": 0.20212505757808685, "learning_rate": 2.7257182713888164e-06, "loss": 0.0605, "step": 557 }, { "epoch": 2.620811287477954, "grad_norm": 0.17893598973751068, "learning_rate": 2.6614170381511325e-06, "loss": 0.0534, "step": 558 }, { "epoch": 2.625514403292181, "grad_norm": 0.2134314775466919, "learning_rate": 2.5978481190096025e-06, "loss": 0.0683, "step": 559 }, { "epoch": 2.630217519106408, "grad_norm": 0.1998036503791809, "learning_rate": 2.535013216774349e-06, "loss": 0.0539, "step": 560 }, { "epoch": 2.634920634920635, "grad_norm": 0.20523333549499512, "learning_rate": 2.472914014593479e-06, "loss": 0.0679, "step": 561 }, { "epoch": 2.639623750734862, "grad_norm": 0.24482150375843048, "learning_rate": 2.411552175908062e-06, "loss": 0.0693, "step": 562 }, { "epoch": 2.644326866549089, "grad_norm": 0.2093353122472763, "learning_rate": 2.3509293444075007e-06, "loss": 0.0628, "step": 563 }, { "epoch": 2.6490299823633157, "grad_norm": 0.2260051816701889, "learning_rate": 2.291047143985553e-06, "loss": 0.0714, "step": 564 }, { "epoch": 2.6537330981775424, "grad_norm": 0.20605359971523285, "learning_rate": 2.2319071786968038e-06, "loss": 0.0604, "step": 565 }, { "epoch": 2.6584362139917697, "grad_norm": 0.22026947140693665, "learning_rate": 2.1735110327137165e-06, "loss": 0.0648, "step": 566 }, { "epoch": 2.6631393298059964, "grad_norm": 0.2127152532339096, "learning_rate": 2.1158602702841855e-06, "loss": 0.0668, "step": 567 }, { "epoch": 2.6678424456202237, "grad_norm": 0.21803465485572815, "learning_rate": 2.058956435689634e-06, "loss": 0.0712, "step": 568 }, { "epoch": 2.6725455614344504, "grad_norm": 0.21160848438739777, "learning_rate": 2.002801053203672e-06, "loss": 0.0644, "step": 569 }, { "epoch": 2.677248677248677, "grad_norm": 0.2484295517206192, "learning_rate": 1.947395627051225e-06, "loss": 0.0761, "step": 570 }, { "epoch": 2.681951793062904, "grad_norm": 0.2674879729747772, "learning_rate": 1.8927416413682762e-06, "loss": 0.0626, "step": 571 }, { "epoch": 2.686654908877131, "grad_norm": 0.20065443217754364, "learning_rate": 1.838840560162085e-06, "loss": 0.0657, "step": 572 }, { "epoch": 2.691358024691358, "grad_norm": 0.19854646921157837, "learning_rate": 1.7856938272720025e-06, "loss": 0.0574, "step": 573 }, { "epoch": 2.696061140505585, "grad_norm": 0.32806870341300964, "learning_rate": 1.733302866330757e-06, "loss": 0.0662, "step": 574 }, { "epoch": 2.700764256319812, "grad_norm": 0.21149712800979614, "learning_rate": 1.6816690807263447e-06, "loss": 0.059, "step": 575 }, { "epoch": 2.7054673721340388, "grad_norm": 0.1935122013092041, "learning_rate": 1.6307938535644417e-06, "loss": 0.0563, "step": 576 }, { "epoch": 2.7101704879482655, "grad_norm": 0.2256065309047699, "learning_rate": 1.5806785476313324e-06, "loss": 0.0755, "step": 577 }, { "epoch": 2.7148736037624928, "grad_norm": 0.23243260383605957, "learning_rate": 1.5313245053574165e-06, "loss": 0.0639, "step": 578 }, { "epoch": 2.7195767195767195, "grad_norm": 0.2159624993801117, "learning_rate": 1.4827330487812528e-06, "loss": 0.0638, "step": 579 }, { "epoch": 2.7242798353909468, "grad_norm": 0.207381010055542, "learning_rate": 1.4349054795141535e-06, "loss": 0.0623, "step": 580 }, { "epoch": 2.7289829512051735, "grad_norm": 0.193582221865654, "learning_rate": 1.3878430787052954e-06, "loss": 0.0586, "step": 581 }, { "epoch": 2.7336860670194003, "grad_norm": 0.19909608364105225, "learning_rate": 1.341547107007417e-06, "loss": 0.0601, "step": 582 }, { "epoch": 2.738389182833627, "grad_norm": 0.2190837413072586, "learning_rate": 1.29601880454305e-06, "loss": 0.0722, "step": 583 }, { "epoch": 2.7430922986478543, "grad_norm": 0.23968404531478882, "learning_rate": 1.2512593908712944e-06, "loss": 0.0627, "step": 584 }, { "epoch": 2.747795414462081, "grad_norm": 0.22253671288490295, "learning_rate": 1.2072700649551528e-06, "loss": 0.0649, "step": 585 }, { "epoch": 2.7524985302763083, "grad_norm": 0.23740307986736298, "learning_rate": 1.1640520051294212e-06, "loss": 0.0756, "step": 586 }, { "epoch": 2.757201646090535, "grad_norm": 0.22015875577926636, "learning_rate": 1.121606369069106e-06, "loss": 0.0712, "step": 587 }, { "epoch": 2.761904761904762, "grad_norm": 0.21934981644153595, "learning_rate": 1.0799342937584433e-06, "loss": 0.062, "step": 588 }, { "epoch": 2.7666078777189886, "grad_norm": 0.20875823497772217, "learning_rate": 1.0390368954604124e-06, "loss": 0.0722, "step": 589 }, { "epoch": 2.771310993533216, "grad_norm": 0.19888935983181, "learning_rate": 9.989152696868475e-07, "loss": 0.0554, "step": 590 }, { "epoch": 2.7760141093474426, "grad_norm": 0.2003571093082428, "learning_rate": 9.595704911690994e-07, "loss": 0.067, "step": 591 }, { "epoch": 2.78071722516167, "grad_norm": 0.20960742235183716, "learning_rate": 9.21003613829241e-07, "loss": 0.0762, "step": 592 }, { "epoch": 2.7854203409758966, "grad_norm": 0.19166284799575806, "learning_rate": 8.832156707518268e-07, "loss": 0.0623, "step": 593 }, { "epoch": 2.7901234567901234, "grad_norm": 0.1826678365468979, "learning_rate": 8.462076741562319e-07, "loss": 0.0599, "step": 594 }, { "epoch": 2.79482657260435, "grad_norm": 0.23774580657482147, "learning_rate": 8.099806153695332e-07, "loss": 0.0711, "step": 595 }, { "epoch": 2.7995296884185774, "grad_norm": 0.20436201989650726, "learning_rate": 7.745354647999648e-07, "loss": 0.0613, "step": 596 }, { "epoch": 2.804232804232804, "grad_norm": 0.18979007005691528, "learning_rate": 7.398731719109042e-07, "loss": 0.0603, "step": 597 }, { "epoch": 2.8089359200470314, "grad_norm": 0.2165534943342209, "learning_rate": 7.059946651954508e-07, "loss": 0.0714, "step": 598 }, { "epoch": 2.813639035861258, "grad_norm": 0.2155015915632248, "learning_rate": 6.729008521515545e-07, "loss": 0.0762, "step": 599 }, { "epoch": 2.818342151675485, "grad_norm": 0.21946902573108673, "learning_rate": 6.405926192577094e-07, "loss": 0.0764, "step": 600 }, { "epoch": 2.8230452674897117, "grad_norm": 0.19192436337471008, "learning_rate": 6.090708319492055e-07, "loss": 0.0655, "step": 601 }, { "epoch": 2.827748383303939, "grad_norm": 0.21605895459651947, "learning_rate": 5.783363345949344e-07, "loss": 0.0583, "step": 602 }, { "epoch": 2.8324514991181657, "grad_norm": 0.2169600874185562, "learning_rate": 5.483899504747902e-07, "loss": 0.0687, "step": 603 }, { "epoch": 2.837154614932393, "grad_norm": 0.22245965898036957, "learning_rate": 5.192324817576111e-07, "loss": 0.0685, "step": 604 }, { "epoch": 2.8418577307466197, "grad_norm": 0.19889821112155914, "learning_rate": 4.908647094796825e-07, "loss": 0.0687, "step": 605 }, { "epoch": 2.8465608465608465, "grad_norm": 0.19336895644664764, "learning_rate": 4.6328739352382464e-07, "loss": 0.0654, "step": 606 }, { "epoch": 2.8512639623750733, "grad_norm": 0.22919213771820068, "learning_rate": 4.3650127259903137e-07, "loss": 0.0695, "step": 607 }, { "epoch": 2.8559670781893005, "grad_norm": 0.2187366634607315, "learning_rate": 4.1050706422069653e-07, "loss": 0.0707, "step": 608 }, { "epoch": 2.8606701940035273, "grad_norm": 0.22111642360687256, "learning_rate": 3.853054646913723e-07, "loss": 0.0715, "step": 609 }, { "epoch": 2.8653733098177545, "grad_norm": 0.2176741063594818, "learning_rate": 3.6089714908213445e-07, "loss": 0.0771, "step": 610 }, { "epoch": 2.8700764256319813, "grad_norm": 0.2191702127456665, "learning_rate": 3.372827712144899e-07, "loss": 0.0697, "step": 611 }, { "epoch": 2.874779541446208, "grad_norm": 0.22539176046848297, "learning_rate": 3.144629636428742e-07, "loss": 0.0714, "step": 612 }, { "epoch": 2.879482657260435, "grad_norm": 0.18655090034008026, "learning_rate": 2.924383376376949e-07, "loss": 0.061, "step": 613 }, { "epoch": 2.884185773074662, "grad_norm": 0.21486076712608337, "learning_rate": 2.712094831689582e-07, "loss": 0.0666, "step": 614 }, { "epoch": 2.888888888888889, "grad_norm": 0.21621838212013245, "learning_rate": 2.5077696889047487e-07, "loss": 0.0641, "step": 615 }, { "epoch": 2.893592004703116, "grad_norm": 0.1847686767578125, "learning_rate": 2.311413421246289e-07, "loss": 0.0579, "step": 616 }, { "epoch": 2.898295120517343, "grad_norm": 0.2058878093957901, "learning_rate": 2.1230312884769954e-07, "loss": 0.0673, "step": 617 }, { "epoch": 2.9029982363315696, "grad_norm": 0.1946004331111908, "learning_rate": 1.94262833675789e-07, "loss": 0.0639, "step": 618 }, { "epoch": 2.9077013521457964, "grad_norm": 0.23575949668884277, "learning_rate": 1.7702093985129341e-07, "loss": 0.076, "step": 619 }, { "epoch": 2.9124044679600236, "grad_norm": 0.17332737147808075, "learning_rate": 1.6057790922997306e-07, "loss": 0.0506, "step": 620 }, { "epoch": 2.9171075837742504, "grad_norm": 0.3159274160861969, "learning_rate": 1.4493418226856568e-07, "loss": 0.0729, "step": 621 }, { "epoch": 2.9218106995884776, "grad_norm": 0.25181010365486145, "learning_rate": 1.3009017801299262e-07, "loss": 0.0778, "step": 622 }, { "epoch": 2.9265138154027044, "grad_norm": 0.20591221749782562, "learning_rate": 1.1604629408714428e-07, "loss": 0.0637, "step": 623 }, { "epoch": 2.931216931216931, "grad_norm": 0.2154921144247055, "learning_rate": 1.0280290668221226e-07, "loss": 0.0787, "step": 624 }, { "epoch": 2.935920047031158, "grad_norm": 0.23178526759147644, "learning_rate": 9.03603705466205e-08, "loss": 0.0669, "step": 625 }, { "epoch": 2.940623162845385, "grad_norm": 0.2173140048980713, "learning_rate": 7.871901897652966e-08, "loss": 0.067, "step": 626 }, { "epoch": 2.945326278659612, "grad_norm": 0.21959051489830017, "learning_rate": 6.787916380689096e-08, "loss": 0.0686, "step": 627 }, { "epoch": 2.950029394473839, "grad_norm": 0.18698427081108093, "learning_rate": 5.7841095403112775e-08, "loss": 0.0648, "step": 628 }, { "epoch": 2.954732510288066, "grad_norm": 0.2005276381969452, "learning_rate": 4.86050826532769e-08, "loss": 0.0655, "step": 629 }, { "epoch": 2.9594356261022927, "grad_norm": 0.21265257894992828, "learning_rate": 4.017137296091766e-08, "loss": 0.0653, "step": 630 }, { "epoch": 2.9641387419165195, "grad_norm": 0.2376765012741089, "learning_rate": 3.2540192238430524e-08, "loss": 0.0759, "step": 631 }, { "epoch": 2.9688418577307467, "grad_norm": 0.18806982040405273, "learning_rate": 2.5711744900983602e-08, "loss": 0.06, "step": 632 }, { "epoch": 2.9735449735449735, "grad_norm": 0.23710228502750397, "learning_rate": 1.9686213861068723e-08, "loss": 0.0739, "step": 633 }, { "epoch": 2.9782480893592007, "grad_norm": 0.21858985722064972, "learning_rate": 1.4463760523588664e-08, "loss": 0.057, "step": 634 }, { "epoch": 2.9829512051734275, "grad_norm": 0.2170712947845459, "learning_rate": 1.0044524781530618e-08, "loss": 0.0712, "step": 635 }, { "epoch": 2.9876543209876543, "grad_norm": 0.19599014520645142, "learning_rate": 6.428625012239176e-09, "loss": 0.066, "step": 636 }, { "epoch": 2.992357436801881, "grad_norm": 0.20459137856960297, "learning_rate": 3.616158074215559e-09, "loss": 0.0671, "step": 637 }, { "epoch": 2.9970605526161083, "grad_norm": 0.22584471106529236, "learning_rate": 1.6071993045529975e-09, "loss": 0.0616, "step": 638 }, { "epoch": 3.0, "grad_norm": 0.2316618114709854, "learning_rate": 4.018025168917028e-10, "loss": 0.0671, "step": 639 }, { "epoch": 3.0, "step": 639, "total_flos": 1.0649557350303662e+19, "train_loss": 0.11448299087852193, "train_runtime": 32500.2706, "train_samples_per_second": 1.257, "train_steps_per_second": 0.02 } ], "logging_steps": 1.0, "max_steps": 639, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 300, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 1.0649557350303662e+19, "train_batch_size": 1, "trial_name": null, "trial_params": null }