{ "best_metric": 0.018521126359701157, "best_model_checkpoint": "/home/paperspace/Data/models/Goavanto/llm3br256-v/checkpoint-400", "epoch": 5.198019801980198, "eval_steps": 25, "global_step": 525, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.009900990099009901, "grad_norm": 0.2780945897102356, "learning_rate": 3.952569169960474e-07, "loss": 0.1412, "step": 1 }, { "epoch": 0.019801980198019802, "grad_norm": 0.2978728413581848, "learning_rate": 7.905138339920948e-07, "loss": 0.1399, "step": 2 }, { "epoch": 0.0297029702970297, "grad_norm": 0.30333277583122253, "learning_rate": 1.1857707509881422e-06, "loss": 0.14, "step": 3 }, { "epoch": 0.039603960396039604, "grad_norm": 0.2764367461204529, "learning_rate": 1.5810276679841897e-06, "loss": 0.1333, "step": 4 }, { "epoch": 0.04950495049504951, "grad_norm": 0.31314605474472046, "learning_rate": 1.9762845849802374e-06, "loss": 0.1377, "step": 5 }, { "epoch": 0.0594059405940594, "grad_norm": 0.2985245883464813, "learning_rate": 2.3715415019762844e-06, "loss": 0.1872, "step": 6 }, { "epoch": 0.06930693069306931, "grad_norm": 0.314704567193985, "learning_rate": 2.7667984189723323e-06, "loss": 0.1336, "step": 7 }, { "epoch": 0.07920792079207921, "grad_norm": 0.31308513879776, "learning_rate": 3.1620553359683794e-06, "loss": 0.156, "step": 8 }, { "epoch": 0.0891089108910891, "grad_norm": 0.29465916752815247, "learning_rate": 3.5573122529644273e-06, "loss": 0.1615, "step": 9 }, { "epoch": 0.09900990099009901, "grad_norm": 0.258452445268631, "learning_rate": 3.952569169960475e-06, "loss": 0.1277, "step": 10 }, { "epoch": 0.10891089108910891, "grad_norm": 0.27227145433425903, "learning_rate": 4.347826086956522e-06, "loss": 0.156, "step": 11 }, { "epoch": 0.1188118811881188, "grad_norm": 0.256413072347641, "learning_rate": 4.743083003952569e-06, "loss": 0.1454, "step": 12 }, { "epoch": 0.12871287128712872, "grad_norm": 0.18560951948165894, "learning_rate": 5.138339920948617e-06, "loss": 0.1014, "step": 13 }, { "epoch": 0.13861386138613863, "grad_norm": 0.21946443617343903, "learning_rate": 5.533596837944665e-06, "loss": 0.1573, "step": 14 }, { "epoch": 0.1485148514851485, "grad_norm": 0.20054368674755096, "learning_rate": 5.928853754940711e-06, "loss": 0.1043, "step": 15 }, { "epoch": 0.15841584158415842, "grad_norm": 0.17403173446655273, "learning_rate": 6.324110671936759e-06, "loss": 0.1517, "step": 16 }, { "epoch": 0.16831683168316833, "grad_norm": 0.1680103838443756, "learning_rate": 6.719367588932807e-06, "loss": 0.1285, "step": 17 }, { "epoch": 0.1782178217821782, "grad_norm": 0.16556352376937866, "learning_rate": 7.1146245059288545e-06, "loss": 0.1036, "step": 18 }, { "epoch": 0.18811881188118812, "grad_norm": 0.1210479736328125, "learning_rate": 7.509881422924901e-06, "loss": 0.1052, "step": 19 }, { "epoch": 0.19801980198019803, "grad_norm": 0.14721368253231049, "learning_rate": 7.90513833992095e-06, "loss": 0.0883, "step": 20 }, { "epoch": 0.2079207920792079, "grad_norm": 0.14860320091247559, "learning_rate": 8.300395256916998e-06, "loss": 0.1041, "step": 21 }, { "epoch": 0.21782178217821782, "grad_norm": 0.14374814927577972, "learning_rate": 8.695652173913044e-06, "loss": 0.0877, "step": 22 }, { "epoch": 0.22772277227722773, "grad_norm": 0.13484112918376923, "learning_rate": 9.090909090909091e-06, "loss": 0.1186, "step": 23 }, { "epoch": 0.2376237623762376, "grad_norm": 0.13147170841693878, "learning_rate": 9.486166007905138e-06, "loss": 0.1149, "step": 24 }, { "epoch": 0.24752475247524752, "grad_norm": 0.12901976704597473, "learning_rate": 9.881422924901186e-06, "loss": 0.1227, "step": 25 }, { "epoch": 0.24752475247524752, "eval_loss": 0.10737022757530212, "eval_runtime": 22.0248, "eval_samples_per_second": 4.54, "eval_steps_per_second": 0.136, "step": 25 }, { "epoch": 0.25742574257425743, "grad_norm": 0.12279005348682404, "learning_rate": 1.0276679841897234e-05, "loss": 0.0986, "step": 26 }, { "epoch": 0.26732673267326734, "grad_norm": 0.11221862584352493, "learning_rate": 1.0671936758893281e-05, "loss": 0.0932, "step": 27 }, { "epoch": 0.27722772277227725, "grad_norm": 0.11220777034759521, "learning_rate": 1.106719367588933e-05, "loss": 0.091, "step": 28 }, { "epoch": 0.2871287128712871, "grad_norm": 0.1216827854514122, "learning_rate": 1.1462450592885376e-05, "loss": 0.095, "step": 29 }, { "epoch": 0.297029702970297, "grad_norm": 0.0984376072883606, "learning_rate": 1.1857707509881423e-05, "loss": 0.0587, "step": 30 }, { "epoch": 0.3069306930693069, "grad_norm": 0.09776771813631058, "learning_rate": 1.225296442687747e-05, "loss": 0.0788, "step": 31 }, { "epoch": 0.31683168316831684, "grad_norm": 0.10127560794353485, "learning_rate": 1.2648221343873517e-05, "loss": 0.0967, "step": 32 }, { "epoch": 0.32673267326732675, "grad_norm": 0.10297820717096329, "learning_rate": 1.3043478260869566e-05, "loss": 0.0857, "step": 33 }, { "epoch": 0.33663366336633666, "grad_norm": 0.10922635346651077, "learning_rate": 1.3438735177865614e-05, "loss": 0.1421, "step": 34 }, { "epoch": 0.3465346534653465, "grad_norm": 0.09746473282575607, "learning_rate": 1.383399209486166e-05, "loss": 0.0773, "step": 35 }, { "epoch": 0.3564356435643564, "grad_norm": 0.0974055677652359, "learning_rate": 1.4229249011857709e-05, "loss": 0.0613, "step": 36 }, { "epoch": 0.36633663366336633, "grad_norm": 0.092307910323143, "learning_rate": 1.4624505928853754e-05, "loss": 0.0902, "step": 37 }, { "epoch": 0.37623762376237624, "grad_norm": 0.1032821536064148, "learning_rate": 1.5019762845849802e-05, "loss": 0.0907, "step": 38 }, { "epoch": 0.38613861386138615, "grad_norm": 0.08956699073314667, "learning_rate": 1.541501976284585e-05, "loss": 0.0667, "step": 39 }, { "epoch": 0.39603960396039606, "grad_norm": 0.08857525885105133, "learning_rate": 1.58102766798419e-05, "loss": 0.0501, "step": 40 }, { "epoch": 0.40594059405940597, "grad_norm": 0.0948619470000267, "learning_rate": 1.6205533596837947e-05, "loss": 0.074, "step": 41 }, { "epoch": 0.4158415841584158, "grad_norm": 0.09170933812856674, "learning_rate": 1.6600790513833996e-05, "loss": 0.0791, "step": 42 }, { "epoch": 0.42574257425742573, "grad_norm": 0.0803118497133255, "learning_rate": 1.699604743083004e-05, "loss": 0.075, "step": 43 }, { "epoch": 0.43564356435643564, "grad_norm": 0.08512408286333084, "learning_rate": 1.739130434782609e-05, "loss": 0.0611, "step": 44 }, { "epoch": 0.44554455445544555, "grad_norm": 0.08622541278600693, "learning_rate": 1.7786561264822134e-05, "loss": 0.0449, "step": 45 }, { "epoch": 0.45544554455445546, "grad_norm": 0.08092786371707916, "learning_rate": 1.8181818181818182e-05, "loss": 0.038, "step": 46 }, { "epoch": 0.46534653465346537, "grad_norm": 0.09300900250673294, "learning_rate": 1.857707509881423e-05, "loss": 0.1017, "step": 47 }, { "epoch": 0.4752475247524752, "grad_norm": 0.10565974563360214, "learning_rate": 1.8972332015810275e-05, "loss": 0.0709, "step": 48 }, { "epoch": 0.48514851485148514, "grad_norm": 0.09708713740110397, "learning_rate": 1.9367588932806324e-05, "loss": 0.0581, "step": 49 }, { "epoch": 0.49504950495049505, "grad_norm": 0.07682275772094727, "learning_rate": 1.9762845849802372e-05, "loss": 0.0553, "step": 50 }, { "epoch": 0.49504950495049505, "eval_loss": 0.055061474442481995, "eval_runtime": 20.9273, "eval_samples_per_second": 4.778, "eval_steps_per_second": 0.143, "step": 50 }, { "epoch": 0.504950495049505, "grad_norm": 0.08843517303466797, "learning_rate": 2.015810276679842e-05, "loss": 0.085, "step": 51 }, { "epoch": 0.5148514851485149, "grad_norm": 0.07925857603549957, "learning_rate": 2.055335968379447e-05, "loss": 0.0466, "step": 52 }, { "epoch": 0.5247524752475248, "grad_norm": 0.07153014093637466, "learning_rate": 2.0948616600790517e-05, "loss": 0.037, "step": 53 }, { "epoch": 0.5346534653465347, "grad_norm": 0.07946132123470306, "learning_rate": 2.1343873517786562e-05, "loss": 0.0542, "step": 54 }, { "epoch": 0.5445544554455446, "grad_norm": 0.08954454213380814, "learning_rate": 2.173913043478261e-05, "loss": 0.0335, "step": 55 }, { "epoch": 0.5544554455445545, "grad_norm": 0.07380135357379913, "learning_rate": 2.213438735177866e-05, "loss": 0.0348, "step": 56 }, { "epoch": 0.5643564356435643, "grad_norm": 0.0993795096874237, "learning_rate": 2.2529644268774703e-05, "loss": 0.0568, "step": 57 }, { "epoch": 0.5742574257425742, "grad_norm": 0.07377209514379501, "learning_rate": 2.2924901185770752e-05, "loss": 0.0365, "step": 58 }, { "epoch": 0.5841584158415841, "grad_norm": 0.06827972829341888, "learning_rate": 2.33201581027668e-05, "loss": 0.0464, "step": 59 }, { "epoch": 0.594059405940594, "grad_norm": 0.06968732923269272, "learning_rate": 2.3715415019762845e-05, "loss": 0.0548, "step": 60 }, { "epoch": 0.6039603960396039, "grad_norm": 0.07616455107927322, "learning_rate": 2.4110671936758893e-05, "loss": 0.0431, "step": 61 }, { "epoch": 0.6138613861386139, "grad_norm": 0.06691834330558777, "learning_rate": 2.450592885375494e-05, "loss": 0.0459, "step": 62 }, { "epoch": 0.6237623762376238, "grad_norm": 0.07361909747123718, "learning_rate": 2.490118577075099e-05, "loss": 0.0364, "step": 63 }, { "epoch": 0.6336633663366337, "grad_norm": 0.07976940274238586, "learning_rate": 2.5296442687747035e-05, "loss": 0.0618, "step": 64 }, { "epoch": 0.6435643564356436, "grad_norm": 0.08242682367563248, "learning_rate": 2.5691699604743087e-05, "loss": 0.0401, "step": 65 }, { "epoch": 0.6534653465346535, "grad_norm": 0.05510717257857323, "learning_rate": 2.608695652173913e-05, "loss": 0.0238, "step": 66 }, { "epoch": 0.6633663366336634, "grad_norm": 0.08613371849060059, "learning_rate": 2.6482213438735183e-05, "loss": 0.0494, "step": 67 }, { "epoch": 0.6732673267326733, "grad_norm": 0.07181484997272491, "learning_rate": 2.6877470355731228e-05, "loss": 0.0373, "step": 68 }, { "epoch": 0.6831683168316832, "grad_norm": 0.07495307922363281, "learning_rate": 2.7272727272727273e-05, "loss": 0.0346, "step": 69 }, { "epoch": 0.693069306930693, "grad_norm": 0.08683991432189941, "learning_rate": 2.766798418972332e-05, "loss": 0.0278, "step": 70 }, { "epoch": 0.7029702970297029, "grad_norm": 0.08579660952091217, "learning_rate": 2.8063241106719366e-05, "loss": 0.0383, "step": 71 }, { "epoch": 0.7128712871287128, "grad_norm": 0.10032771527767181, "learning_rate": 2.8458498023715418e-05, "loss": 0.0565, "step": 72 }, { "epoch": 0.7227722772277227, "grad_norm": 0.09024665504693985, "learning_rate": 2.8853754940711463e-05, "loss": 0.0449, "step": 73 }, { "epoch": 0.7326732673267327, "grad_norm": 0.09194691479206085, "learning_rate": 2.9249011857707508e-05, "loss": 0.0378, "step": 74 }, { "epoch": 0.7425742574257426, "grad_norm": 0.07428496330976486, "learning_rate": 2.964426877470356e-05, "loss": 0.0338, "step": 75 }, { "epoch": 0.7425742574257426, "eval_loss": 0.03502385690808296, "eval_runtime": 20.9125, "eval_samples_per_second": 4.782, "eval_steps_per_second": 0.143, "step": 75 }, { "epoch": 0.7524752475247525, "grad_norm": 0.06667866557836533, "learning_rate": 3.0039525691699605e-05, "loss": 0.0317, "step": 76 }, { "epoch": 0.7623762376237624, "grad_norm": 0.07727614790201187, "learning_rate": 3.0434782608695656e-05, "loss": 0.0396, "step": 77 }, { "epoch": 0.7722772277227723, "grad_norm": 0.10815678536891937, "learning_rate": 3.08300395256917e-05, "loss": 0.0297, "step": 78 }, { "epoch": 0.7821782178217822, "grad_norm": 0.07847210019826889, "learning_rate": 3.1225296442687746e-05, "loss": 0.0414, "step": 79 }, { "epoch": 0.7920792079207921, "grad_norm": 0.09983616322278976, "learning_rate": 3.16205533596838e-05, "loss": 0.0453, "step": 80 }, { "epoch": 0.801980198019802, "grad_norm": 0.06763055920600891, "learning_rate": 3.201581027667984e-05, "loss": 0.0269, "step": 81 }, { "epoch": 0.8118811881188119, "grad_norm": 0.07611255347728729, "learning_rate": 3.2411067193675894e-05, "loss": 0.0364, "step": 82 }, { "epoch": 0.8217821782178217, "grad_norm": 0.06326984614133835, "learning_rate": 3.280632411067194e-05, "loss": 0.0285, "step": 83 }, { "epoch": 0.8316831683168316, "grad_norm": 0.06751732528209686, "learning_rate": 3.320158102766799e-05, "loss": 0.0244, "step": 84 }, { "epoch": 0.8415841584158416, "grad_norm": 0.06836965680122375, "learning_rate": 3.3596837944664036e-05, "loss": 0.0293, "step": 85 }, { "epoch": 0.8514851485148515, "grad_norm": 0.06516125798225403, "learning_rate": 3.399209486166008e-05, "loss": 0.0378, "step": 86 }, { "epoch": 0.8613861386138614, "grad_norm": 0.06571876257658005, "learning_rate": 3.438735177865613e-05, "loss": 0.0265, "step": 87 }, { "epoch": 0.8712871287128713, "grad_norm": 0.06418901681900024, "learning_rate": 3.478260869565218e-05, "loss": 0.0363, "step": 88 }, { "epoch": 0.8811881188118812, "grad_norm": 0.09142803400754929, "learning_rate": 3.517786561264822e-05, "loss": 0.0351, "step": 89 }, { "epoch": 0.8910891089108911, "grad_norm": 0.09272617101669312, "learning_rate": 3.557312252964427e-05, "loss": 0.0314, "step": 90 }, { "epoch": 0.900990099009901, "grad_norm": 0.08047693967819214, "learning_rate": 3.596837944664031e-05, "loss": 0.0277, "step": 91 }, { "epoch": 0.9108910891089109, "grad_norm": 0.07349320501089096, "learning_rate": 3.6363636363636364e-05, "loss": 0.025, "step": 92 }, { "epoch": 0.9207920792079208, "grad_norm": 0.08519802987575531, "learning_rate": 3.675889328063241e-05, "loss": 0.0406, "step": 93 }, { "epoch": 0.9306930693069307, "grad_norm": 0.06724913418292999, "learning_rate": 3.715415019762846e-05, "loss": 0.0317, "step": 94 }, { "epoch": 0.9405940594059405, "grad_norm": 0.06739809364080429, "learning_rate": 3.7549407114624506e-05, "loss": 0.0363, "step": 95 }, { "epoch": 0.9504950495049505, "grad_norm": 0.07618068903684616, "learning_rate": 3.794466403162055e-05, "loss": 0.0181, "step": 96 }, { "epoch": 0.9603960396039604, "grad_norm": 0.061489593237638474, "learning_rate": 3.83399209486166e-05, "loss": 0.0296, "step": 97 }, { "epoch": 0.9702970297029703, "grad_norm": 0.0637054592370987, "learning_rate": 3.873517786561265e-05, "loss": 0.0213, "step": 98 }, { "epoch": 0.9801980198019802, "grad_norm": 0.0836983397603035, "learning_rate": 3.91304347826087e-05, "loss": 0.0294, "step": 99 }, { "epoch": 0.9900990099009901, "grad_norm": 0.06744949519634247, "learning_rate": 3.9525691699604744e-05, "loss": 0.0302, "step": 100 }, { "epoch": 0.9900990099009901, "eval_loss": 0.027701813727617264, "eval_runtime": 20.9769, "eval_samples_per_second": 4.767, "eval_steps_per_second": 0.143, "step": 100 }, { "epoch": 1.0, "grad_norm": 0.11184727400541306, "learning_rate": 3.9920948616600796e-05, "loss": 0.0226, "step": 101 }, { "epoch": 1.00990099009901, "grad_norm": 0.056078869849443436, "learning_rate": 4.031620553359684e-05, "loss": 0.023, "step": 102 }, { "epoch": 1.0198019801980198, "grad_norm": 0.06441275775432587, "learning_rate": 4.0711462450592886e-05, "loss": 0.0296, "step": 103 }, { "epoch": 1.0297029702970297, "grad_norm": 0.07957013696432114, "learning_rate": 4.110671936758894e-05, "loss": 0.0203, "step": 104 }, { "epoch": 1.0396039603960396, "grad_norm": 0.05331544578075409, "learning_rate": 4.150197628458498e-05, "loss": 0.0235, "step": 105 }, { "epoch": 1.0495049504950495, "grad_norm": 0.06107131764292717, "learning_rate": 4.1897233201581034e-05, "loss": 0.0296, "step": 106 }, { "epoch": 1.0594059405940595, "grad_norm": 0.05904534086585045, "learning_rate": 4.229249011857708e-05, "loss": 0.0272, "step": 107 }, { "epoch": 1.0693069306930694, "grad_norm": 0.07586849480867386, "learning_rate": 4.2687747035573124e-05, "loss": 0.0341, "step": 108 }, { "epoch": 1.0792079207920793, "grad_norm": 0.08533436059951782, "learning_rate": 4.3083003952569175e-05, "loss": 0.0355, "step": 109 }, { "epoch": 1.0891089108910892, "grad_norm": 0.05731397494673729, "learning_rate": 4.347826086956522e-05, "loss": 0.03, "step": 110 }, { "epoch": 1.099009900990099, "grad_norm": 0.048471707850694656, "learning_rate": 4.387351778656127e-05, "loss": 0.0196, "step": 111 }, { "epoch": 1.108910891089109, "grad_norm": 0.053837962448596954, "learning_rate": 4.426877470355732e-05, "loss": 0.0168, "step": 112 }, { "epoch": 1.118811881188119, "grad_norm": 0.06376203894615173, "learning_rate": 4.466403162055336e-05, "loss": 0.0251, "step": 113 }, { "epoch": 1.1287128712871288, "grad_norm": 0.06253273785114288, "learning_rate": 4.505928853754941e-05, "loss": 0.0244, "step": 114 }, { "epoch": 1.1386138613861387, "grad_norm": 0.05787895992398262, "learning_rate": 4.545454545454546e-05, "loss": 0.0213, "step": 115 }, { "epoch": 1.1485148514851484, "grad_norm": 0.07152873277664185, "learning_rate": 4.5849802371541504e-05, "loss": 0.0206, "step": 116 }, { "epoch": 1.1584158415841583, "grad_norm": 0.07703561335802078, "learning_rate": 4.624505928853755e-05, "loss": 0.0346, "step": 117 }, { "epoch": 1.1683168316831682, "grad_norm": 0.05837339907884598, "learning_rate": 4.66403162055336e-05, "loss": 0.0259, "step": 118 }, { "epoch": 1.1782178217821782, "grad_norm": 0.07039913535118103, "learning_rate": 4.7035573122529645e-05, "loss": 0.0248, "step": 119 }, { "epoch": 1.188118811881188, "grad_norm": 0.06346864998340607, "learning_rate": 4.743083003952569e-05, "loss": 0.0243, "step": 120 }, { "epoch": 1.198019801980198, "grad_norm": 0.07102694362401962, "learning_rate": 4.782608695652174e-05, "loss": 0.0211, "step": 121 }, { "epoch": 1.2079207920792079, "grad_norm": 0.08494184911251068, "learning_rate": 4.822134387351779e-05, "loss": 0.0395, "step": 122 }, { "epoch": 1.2178217821782178, "grad_norm": 0.07663221657276154, "learning_rate": 4.861660079051384e-05, "loss": 0.0343, "step": 123 }, { "epoch": 1.2277227722772277, "grad_norm": 0.0614091195166111, "learning_rate": 4.901185770750988e-05, "loss": 0.0269, "step": 124 }, { "epoch": 1.2376237623762376, "grad_norm": 0.08366970717906952, "learning_rate": 4.940711462450593e-05, "loss": 0.0373, "step": 125 }, { "epoch": 1.2376237623762376, "eval_loss": 0.025583934038877487, "eval_runtime": 20.9445, "eval_samples_per_second": 4.775, "eval_steps_per_second": 0.143, "step": 125 }, { "epoch": 1.2475247524752475, "grad_norm": 0.07697997242212296, "learning_rate": 4.980237154150198e-05, "loss": 0.0305, "step": 126 }, { "epoch": 1.2574257425742574, "grad_norm": 0.05984925106167793, "learning_rate": 5.0197628458498025e-05, "loss": 0.0171, "step": 127 }, { "epoch": 1.2673267326732673, "grad_norm": 0.08026100695133209, "learning_rate": 5.059288537549407e-05, "loss": 0.0238, "step": 128 }, { "epoch": 1.2772277227722773, "grad_norm": 0.05464643985033035, "learning_rate": 5.098814229249013e-05, "loss": 0.0296, "step": 129 }, { "epoch": 1.2871287128712872, "grad_norm": 0.07287590205669403, "learning_rate": 5.138339920948617e-05, "loss": 0.0246, "step": 130 }, { "epoch": 1.297029702970297, "grad_norm": 0.08635013550519943, "learning_rate": 5.177865612648222e-05, "loss": 0.0339, "step": 131 }, { "epoch": 1.306930693069307, "grad_norm": 0.06489317864179611, "learning_rate": 5.217391304347826e-05, "loss": 0.0181, "step": 132 }, { "epoch": 1.316831683168317, "grad_norm": 0.37230196595191956, "learning_rate": 5.256916996047431e-05, "loss": 0.0307, "step": 133 }, { "epoch": 1.3267326732673268, "grad_norm": 0.06730218231678009, "learning_rate": 5.2964426877470366e-05, "loss": 0.0215, "step": 134 }, { "epoch": 1.3366336633663367, "grad_norm": 0.09615404158830643, "learning_rate": 5.335968379446641e-05, "loss": 0.0252, "step": 135 }, { "epoch": 1.3465346534653464, "grad_norm": 0.08481566607952118, "learning_rate": 5.3754940711462456e-05, "loss": 0.0284, "step": 136 }, { "epoch": 1.3564356435643563, "grad_norm": 0.11659260839223862, "learning_rate": 5.41501976284585e-05, "loss": 0.0336, "step": 137 }, { "epoch": 1.3663366336633662, "grad_norm": 0.0634186789393425, "learning_rate": 5.4545454545454546e-05, "loss": 0.0241, "step": 138 }, { "epoch": 1.3762376237623761, "grad_norm": 0.08782602101564407, "learning_rate": 5.49407114624506e-05, "loss": 0.0239, "step": 139 }, { "epoch": 1.386138613861386, "grad_norm": 0.10084912180900574, "learning_rate": 5.533596837944664e-05, "loss": 0.0342, "step": 140 }, { "epoch": 1.396039603960396, "grad_norm": 0.07874171435832977, "learning_rate": 5.573122529644269e-05, "loss": 0.0186, "step": 141 }, { "epoch": 1.4059405940594059, "grad_norm": 0.06874096393585205, "learning_rate": 5.612648221343873e-05, "loss": 0.0244, "step": 142 }, { "epoch": 1.4158415841584158, "grad_norm": 0.060906875878572464, "learning_rate": 5.652173913043478e-05, "loss": 0.0179, "step": 143 }, { "epoch": 1.4257425742574257, "grad_norm": 0.061183176934719086, "learning_rate": 5.6916996047430836e-05, "loss": 0.0216, "step": 144 }, { "epoch": 1.4356435643564356, "grad_norm": 0.055084019899368286, "learning_rate": 5.731225296442688e-05, "loss": 0.0171, "step": 145 }, { "epoch": 1.4455445544554455, "grad_norm": 0.05983046442270279, "learning_rate": 5.7707509881422926e-05, "loss": 0.0231, "step": 146 }, { "epoch": 1.4554455445544554, "grad_norm": 0.060153719037771225, "learning_rate": 5.810276679841897e-05, "loss": 0.0147, "step": 147 }, { "epoch": 1.4653465346534653, "grad_norm": 0.046402279287576675, "learning_rate": 5.8498023715415016e-05, "loss": 0.0273, "step": 148 }, { "epoch": 1.4752475247524752, "grad_norm": 0.06791272014379501, "learning_rate": 5.8893280632411074e-05, "loss": 0.0185, "step": 149 }, { "epoch": 1.4851485148514851, "grad_norm": 0.06259552389383316, "learning_rate": 5.928853754940712e-05, "loss": 0.0321, "step": 150 }, { "epoch": 1.4851485148514851, "eval_loss": 0.025141000747680664, "eval_runtime": 20.9532, "eval_samples_per_second": 4.773, "eval_steps_per_second": 0.143, "step": 150 }, { "epoch": 1.495049504950495, "grad_norm": 0.05741759389638901, "learning_rate": 5.9683794466403164e-05, "loss": 0.0227, "step": 151 }, { "epoch": 1.504950495049505, "grad_norm": 0.07616166770458221, "learning_rate": 6.007905138339921e-05, "loss": 0.0175, "step": 152 }, { "epoch": 1.5148514851485149, "grad_norm": 0.05826897919178009, "learning_rate": 6.0474308300395254e-05, "loss": 0.0227, "step": 153 }, { "epoch": 1.5247524752475248, "grad_norm": 0.055770143866539, "learning_rate": 6.086956521739131e-05, "loss": 0.0183, "step": 154 }, { "epoch": 1.5346534653465347, "grad_norm": 0.055019546300172806, "learning_rate": 6.126482213438736e-05, "loss": 0.02, "step": 155 }, { "epoch": 1.5445544554455446, "grad_norm": 0.053829967975616455, "learning_rate": 6.16600790513834e-05, "loss": 0.0157, "step": 156 }, { "epoch": 1.5544554455445545, "grad_norm": 0.051947206258773804, "learning_rate": 6.205533596837945e-05, "loss": 0.0265, "step": 157 }, { "epoch": 1.5643564356435644, "grad_norm": 0.0410446897149086, "learning_rate": 6.245059288537549e-05, "loss": 0.014, "step": 158 }, { "epoch": 1.5742574257425743, "grad_norm": 0.06168140098452568, "learning_rate": 6.284584980237155e-05, "loss": 0.0264, "step": 159 }, { "epoch": 1.5841584158415842, "grad_norm": 0.045245859771966934, "learning_rate": 6.32411067193676e-05, "loss": 0.0153, "step": 160 }, { "epoch": 1.5940594059405941, "grad_norm": 0.0567997582256794, "learning_rate": 6.363636363636364e-05, "loss": 0.0172, "step": 161 }, { "epoch": 1.603960396039604, "grad_norm": 0.04940714314579964, "learning_rate": 6.403162055335969e-05, "loss": 0.023, "step": 162 }, { "epoch": 1.613861386138614, "grad_norm": 0.05434204638004303, "learning_rate": 6.442687747035574e-05, "loss": 0.0388, "step": 163 }, { "epoch": 1.6237623762376239, "grad_norm": 0.056556135416030884, "learning_rate": 6.482213438735179e-05, "loss": 0.0198, "step": 164 }, { "epoch": 1.6336633663366338, "grad_norm": 0.048558373004198074, "learning_rate": 6.521739130434783e-05, "loss": 0.0303, "step": 165 }, { "epoch": 1.6435643564356437, "grad_norm": 0.05275854095816612, "learning_rate": 6.561264822134388e-05, "loss": 0.0157, "step": 166 }, { "epoch": 1.6534653465346536, "grad_norm": 0.04988724738359451, "learning_rate": 6.600790513833992e-05, "loss": 0.0157, "step": 167 }, { "epoch": 1.6633663366336635, "grad_norm": 0.04950392246246338, "learning_rate": 6.640316205533598e-05, "loss": 0.0288, "step": 168 }, { "epoch": 1.6732673267326734, "grad_norm": 0.06501295417547226, "learning_rate": 6.679841897233203e-05, "loss": 0.0344, "step": 169 }, { "epoch": 1.6831683168316833, "grad_norm": 0.05085508152842522, "learning_rate": 6.719367588932807e-05, "loss": 0.0315, "step": 170 }, { "epoch": 1.693069306930693, "grad_norm": 0.055841974914073944, "learning_rate": 6.758893280632412e-05, "loss": 0.0219, "step": 171 }, { "epoch": 1.702970297029703, "grad_norm": 0.050552286207675934, "learning_rate": 6.798418972332016e-05, "loss": 0.0309, "step": 172 }, { "epoch": 1.7128712871287128, "grad_norm": 0.052804503589868546, "learning_rate": 6.837944664031622e-05, "loss": 0.0303, "step": 173 }, { "epoch": 1.7227722772277227, "grad_norm": 0.055684514343738556, "learning_rate": 6.877470355731227e-05, "loss": 0.0289, "step": 174 }, { "epoch": 1.7326732673267327, "grad_norm": 0.04727136716246605, "learning_rate": 6.916996047430831e-05, "loss": 0.026, "step": 175 }, { "epoch": 1.7326732673267327, "eval_loss": 0.022802595049142838, "eval_runtime": 20.961, "eval_samples_per_second": 4.771, "eval_steps_per_second": 0.143, "step": 175 }, { "epoch": 1.7425742574257426, "grad_norm": 0.05808348208665848, "learning_rate": 6.956521739130436e-05, "loss": 0.0296, "step": 176 }, { "epoch": 1.7524752475247525, "grad_norm": 0.047991879284381866, "learning_rate": 6.99604743083004e-05, "loss": 0.0203, "step": 177 }, { "epoch": 1.7623762376237624, "grad_norm": 0.04677740857005119, "learning_rate": 7.035573122529645e-05, "loss": 0.016, "step": 178 }, { "epoch": 1.7722772277227723, "grad_norm": 0.0436997190117836, "learning_rate": 7.075098814229249e-05, "loss": 0.0161, "step": 179 }, { "epoch": 1.7821782178217822, "grad_norm": 0.05496394634246826, "learning_rate": 7.114624505928854e-05, "loss": 0.0351, "step": 180 }, { "epoch": 1.7920792079207921, "grad_norm": 0.044135309755802155, "learning_rate": 7.154150197628458e-05, "loss": 0.0198, "step": 181 }, { "epoch": 1.801980198019802, "grad_norm": 0.04966725409030914, "learning_rate": 7.193675889328062e-05, "loss": 0.0214, "step": 182 }, { "epoch": 1.811881188118812, "grad_norm": 0.04237734153866768, "learning_rate": 7.233201581027668e-05, "loss": 0.0211, "step": 183 }, { "epoch": 1.8217821782178216, "grad_norm": 0.04926709085702896, "learning_rate": 7.272727272727273e-05, "loss": 0.0291, "step": 184 }, { "epoch": 1.8316831683168315, "grad_norm": 0.053725503385066986, "learning_rate": 7.312252964426877e-05, "loss": 0.0151, "step": 185 }, { "epoch": 1.8415841584158414, "grad_norm": 0.039645515382289886, "learning_rate": 7.351778656126482e-05, "loss": 0.0227, "step": 186 }, { "epoch": 1.8514851485148514, "grad_norm": 0.0530475378036499, "learning_rate": 7.391304347826086e-05, "loss": 0.0335, "step": 187 }, { "epoch": 1.8613861386138613, "grad_norm": 0.04808201268315315, "learning_rate": 7.430830039525692e-05, "loss": 0.0272, "step": 188 }, { "epoch": 1.8712871287128712, "grad_norm": 0.05676993727684021, "learning_rate": 7.470355731225297e-05, "loss": 0.0244, "step": 189 }, { "epoch": 1.881188118811881, "grad_norm": 0.04248756170272827, "learning_rate": 7.509881422924901e-05, "loss": 0.0139, "step": 190 }, { "epoch": 1.891089108910891, "grad_norm": 0.04386115446686745, "learning_rate": 7.549407114624506e-05, "loss": 0.0161, "step": 191 }, { "epoch": 1.900990099009901, "grad_norm": 0.04502849653363228, "learning_rate": 7.58893280632411e-05, "loss": 0.0246, "step": 192 }, { "epoch": 1.9108910891089108, "grad_norm": 0.053589943796396255, "learning_rate": 7.628458498023716e-05, "loss": 0.0207, "step": 193 }, { "epoch": 1.9207920792079207, "grad_norm": 0.04484814032912254, "learning_rate": 7.66798418972332e-05, "loss": 0.0219, "step": 194 }, { "epoch": 1.9306930693069306, "grad_norm": 0.06994163244962692, "learning_rate": 7.707509881422925e-05, "loss": 0.0279, "step": 195 }, { "epoch": 1.9405940594059405, "grad_norm": 0.044320590794086456, "learning_rate": 7.74703557312253e-05, "loss": 0.0284, "step": 196 }, { "epoch": 1.9504950495049505, "grad_norm": 0.04095998406410217, "learning_rate": 7.786561264822134e-05, "loss": 0.022, "step": 197 }, { "epoch": 1.9603960396039604, "grad_norm": 0.043975040316581726, "learning_rate": 7.82608695652174e-05, "loss": 0.0189, "step": 198 }, { "epoch": 1.9702970297029703, "grad_norm": 0.048833929002285004, "learning_rate": 7.865612648221344e-05, "loss": 0.0279, "step": 199 }, { "epoch": 1.9801980198019802, "grad_norm": 0.05329909175634384, "learning_rate": 7.905138339920949e-05, "loss": 0.029, "step": 200 }, { "epoch": 1.9801980198019802, "eval_loss": 0.021168576553463936, "eval_runtime": 20.9649, "eval_samples_per_second": 4.77, "eval_steps_per_second": 0.143, "step": 200 }, { "epoch": 1.99009900990099, "grad_norm": 0.04758258908987045, "learning_rate": 7.944664031620553e-05, "loss": 0.0174, "step": 201 }, { "epoch": 2.0, "grad_norm": 0.07869398593902588, "learning_rate": 7.984189723320159e-05, "loss": 0.0162, "step": 202 }, { "epoch": 2.00990099009901, "grad_norm": 0.0439910814166069, "learning_rate": 8.023715415019764e-05, "loss": 0.017, "step": 203 }, { "epoch": 2.01980198019802, "grad_norm": 0.04175785556435585, "learning_rate": 8.063241106719368e-05, "loss": 0.0108, "step": 204 }, { "epoch": 2.0297029702970297, "grad_norm": 0.037400927394628525, "learning_rate": 8.102766798418973e-05, "loss": 0.0129, "step": 205 }, { "epoch": 2.0396039603960396, "grad_norm": 0.09054706990718842, "learning_rate": 8.142292490118577e-05, "loss": 0.0497, "step": 206 }, { "epoch": 2.0495049504950495, "grad_norm": 0.032963309437036514, "learning_rate": 8.181818181818183e-05, "loss": 0.0132, "step": 207 }, { "epoch": 2.0594059405940595, "grad_norm": 0.045048072934150696, "learning_rate": 8.221343873517787e-05, "loss": 0.0139, "step": 208 }, { "epoch": 2.0693069306930694, "grad_norm": 0.04151559993624687, "learning_rate": 8.260869565217392e-05, "loss": 0.0186, "step": 209 }, { "epoch": 2.0792079207920793, "grad_norm": 0.04299120604991913, "learning_rate": 8.300395256916996e-05, "loss": 0.0146, "step": 210 }, { "epoch": 2.089108910891089, "grad_norm": 0.05108791962265968, "learning_rate": 8.339920948616601e-05, "loss": 0.0234, "step": 211 }, { "epoch": 2.099009900990099, "grad_norm": 0.044956084340810776, "learning_rate": 8.379446640316207e-05, "loss": 0.0266, "step": 212 }, { "epoch": 2.108910891089109, "grad_norm": 0.04504725709557533, "learning_rate": 8.418972332015811e-05, "loss": 0.0201, "step": 213 }, { "epoch": 2.118811881188119, "grad_norm": 0.06300884485244751, "learning_rate": 8.458498023715416e-05, "loss": 0.0464, "step": 214 }, { "epoch": 2.128712871287129, "grad_norm": 0.04494632035493851, "learning_rate": 8.49802371541502e-05, "loss": 0.0117, "step": 215 }, { "epoch": 2.1386138613861387, "grad_norm": 0.0645475760102272, "learning_rate": 8.537549407114625e-05, "loss": 0.0311, "step": 216 }, { "epoch": 2.1485148514851486, "grad_norm": 0.03961382433772087, "learning_rate": 8.57707509881423e-05, "loss": 0.01, "step": 217 }, { "epoch": 2.1584158415841586, "grad_norm": 0.04515567421913147, "learning_rate": 8.616600790513835e-05, "loss": 0.0141, "step": 218 }, { "epoch": 2.1683168316831685, "grad_norm": 0.06631825864315033, "learning_rate": 8.65612648221344e-05, "loss": 0.0175, "step": 219 }, { "epoch": 2.1782178217821784, "grad_norm": 0.04718014970421791, "learning_rate": 8.695652173913044e-05, "loss": 0.0201, "step": 220 }, { "epoch": 2.1881188118811883, "grad_norm": 0.06612230092287064, "learning_rate": 8.735177865612649e-05, "loss": 0.0317, "step": 221 }, { "epoch": 2.198019801980198, "grad_norm": 0.05043951794505119, "learning_rate": 8.774703557312254e-05, "loss": 0.02, "step": 222 }, { "epoch": 2.207920792079208, "grad_norm": 0.03858309984207153, "learning_rate": 8.814229249011859e-05, "loss": 0.0142, "step": 223 }, { "epoch": 2.217821782178218, "grad_norm": 0.06211186945438385, "learning_rate": 8.853754940711463e-05, "loss": 0.0398, "step": 224 }, { "epoch": 2.227722772277228, "grad_norm": 0.04007279500365257, "learning_rate": 8.893280632411068e-05, "loss": 0.0152, "step": 225 }, { "epoch": 2.227722772277228, "eval_loss": 0.021625498309731483, "eval_runtime": 21.7529, "eval_samples_per_second": 4.597, "eval_steps_per_second": 0.138, "step": 225 }, { "epoch": 2.237623762376238, "grad_norm": 0.042071305215358734, "learning_rate": 8.932806324110672e-05, "loss": 0.0153, "step": 226 }, { "epoch": 2.2475247524752477, "grad_norm": 0.04820103570818901, "learning_rate": 8.972332015810277e-05, "loss": 0.0143, "step": 227 }, { "epoch": 2.2574257425742577, "grad_norm": 0.047800008207559586, "learning_rate": 9.011857707509881e-05, "loss": 0.0144, "step": 228 }, { "epoch": 2.2673267326732676, "grad_norm": 0.03672846406698227, "learning_rate": 9.051383399209486e-05, "loss": 0.0204, "step": 229 }, { "epoch": 2.2772277227722775, "grad_norm": 0.044539038091897964, "learning_rate": 9.090909090909092e-05, "loss": 0.0241, "step": 230 }, { "epoch": 2.287128712871287, "grad_norm": 0.03706245496869087, "learning_rate": 9.130434782608696e-05, "loss": 0.0189, "step": 231 }, { "epoch": 2.297029702970297, "grad_norm": 0.038041867315769196, "learning_rate": 9.169960474308301e-05, "loss": 0.0168, "step": 232 }, { "epoch": 2.3069306930693068, "grad_norm": 0.05145088583230972, "learning_rate": 9.209486166007905e-05, "loss": 0.0173, "step": 233 }, { "epoch": 2.3168316831683167, "grad_norm": 0.03916524723172188, "learning_rate": 9.24901185770751e-05, "loss": 0.0186, "step": 234 }, { "epoch": 2.3267326732673266, "grad_norm": 0.03896910697221756, "learning_rate": 9.288537549407114e-05, "loss": 0.0166, "step": 235 }, { "epoch": 2.3366336633663365, "grad_norm": 0.04472080245614052, "learning_rate": 9.32806324110672e-05, "loss": 0.0258, "step": 236 }, { "epoch": 2.3465346534653464, "grad_norm": 0.0344708114862442, "learning_rate": 9.367588932806325e-05, "loss": 0.0165, "step": 237 }, { "epoch": 2.3564356435643563, "grad_norm": 0.03994801267981529, "learning_rate": 9.407114624505929e-05, "loss": 0.0288, "step": 238 }, { "epoch": 2.366336633663366, "grad_norm": 0.03858465701341629, "learning_rate": 9.446640316205534e-05, "loss": 0.0216, "step": 239 }, { "epoch": 2.376237623762376, "grad_norm": 0.0324896015226841, "learning_rate": 9.486166007905138e-05, "loss": 0.0133, "step": 240 }, { "epoch": 2.386138613861386, "grad_norm": 0.04445994645357132, "learning_rate": 9.525691699604744e-05, "loss": 0.026, "step": 241 }, { "epoch": 2.396039603960396, "grad_norm": 0.046353645622730255, "learning_rate": 9.565217391304348e-05, "loss": 0.0218, "step": 242 }, { "epoch": 2.405940594059406, "grad_norm": 0.03423113003373146, "learning_rate": 9.604743083003953e-05, "loss": 0.0099, "step": 243 }, { "epoch": 2.4158415841584158, "grad_norm": 0.04123309999704361, "learning_rate": 9.644268774703557e-05, "loss": 0.0202, "step": 244 }, { "epoch": 2.4257425742574257, "grad_norm": 0.039391182363033295, "learning_rate": 9.683794466403162e-05, "loss": 0.0203, "step": 245 }, { "epoch": 2.4356435643564356, "grad_norm": 0.045452989637851715, "learning_rate": 9.723320158102768e-05, "loss": 0.0299, "step": 246 }, { "epoch": 2.4455445544554455, "grad_norm": 0.04196856915950775, "learning_rate": 9.762845849802372e-05, "loss": 0.0209, "step": 247 }, { "epoch": 2.4554455445544554, "grad_norm": 0.0465984083712101, "learning_rate": 9.802371541501977e-05, "loss": 0.0264, "step": 248 }, { "epoch": 2.4653465346534653, "grad_norm": 0.036751143634319305, "learning_rate": 9.841897233201581e-05, "loss": 0.0132, "step": 249 }, { "epoch": 2.4752475247524752, "grad_norm": 0.03972426801919937, "learning_rate": 9.881422924901186e-05, "loss": 0.011, "step": 250 }, { "epoch": 2.4752475247524752, "eval_loss": 0.02048182487487793, "eval_runtime": 20.9235, "eval_samples_per_second": 4.779, "eval_steps_per_second": 0.143, "step": 250 }, { "epoch": 2.485148514851485, "grad_norm": 0.03993945196270943, "learning_rate": 9.920948616600791e-05, "loss": 0.0112, "step": 251 }, { "epoch": 2.495049504950495, "grad_norm": 0.03752398490905762, "learning_rate": 9.960474308300396e-05, "loss": 0.0172, "step": 252 }, { "epoch": 2.504950495049505, "grad_norm": 0.031341757625341415, "learning_rate": 0.0001, "loss": 0.0135, "step": 253 }, { "epoch": 2.514851485148515, "grad_norm": 0.04680801182985306, "learning_rate": 9.999995220053555e-05, "loss": 0.0175, "step": 254 }, { "epoch": 2.5247524752475248, "grad_norm": 0.04588630795478821, "learning_rate": 9.999980880223359e-05, "loss": 0.0305, "step": 255 }, { "epoch": 2.5346534653465347, "grad_norm": 0.035120490938425064, "learning_rate": 9.999956980536828e-05, "loss": 0.0246, "step": 256 }, { "epoch": 2.5445544554455446, "grad_norm": 0.041602976620197296, "learning_rate": 9.999923521039659e-05, "loss": 0.0109, "step": 257 }, { "epoch": 2.5544554455445545, "grad_norm": 0.04591014236211777, "learning_rate": 9.999880501795826e-05, "loss": 0.0138, "step": 258 }, { "epoch": 2.5643564356435644, "grad_norm": 0.030721504241228104, "learning_rate": 9.99982792288758e-05, "loss": 0.0099, "step": 259 }, { "epoch": 2.5742574257425743, "grad_norm": 0.047804564237594604, "learning_rate": 9.999765784415451e-05, "loss": 0.0192, "step": 260 }, { "epoch": 2.5841584158415842, "grad_norm": 0.04211296886205673, "learning_rate": 9.999694086498248e-05, "loss": 0.0211, "step": 261 }, { "epoch": 2.594059405940594, "grad_norm": 0.05463152006268501, "learning_rate": 9.999612829273053e-05, "loss": 0.0125, "step": 262 }, { "epoch": 2.603960396039604, "grad_norm": 0.03957533463835716, "learning_rate": 9.99952201289523e-05, "loss": 0.0237, "step": 263 }, { "epoch": 2.613861386138614, "grad_norm": 0.04941708594560623, "learning_rate": 9.999421637538418e-05, "loss": 0.0156, "step": 264 }, { "epoch": 2.623762376237624, "grad_norm": 0.035674627870321274, "learning_rate": 9.999311703394532e-05, "loss": 0.0175, "step": 265 }, { "epoch": 2.633663366336634, "grad_norm": 0.04425996169447899, "learning_rate": 9.999192210673762e-05, "loss": 0.0301, "step": 266 }, { "epoch": 2.6435643564356437, "grad_norm": 0.03343842178583145, "learning_rate": 9.999063159604579e-05, "loss": 0.0178, "step": 267 }, { "epoch": 2.6534653465346536, "grad_norm": 0.028746318072080612, "learning_rate": 9.998924550433723e-05, "loss": 0.0161, "step": 268 }, { "epoch": 2.6633663366336635, "grad_norm": 0.03598029911518097, "learning_rate": 9.998776383426216e-05, "loss": 0.024, "step": 269 }, { "epoch": 2.6732673267326734, "grad_norm": 0.03354136273264885, "learning_rate": 9.998618658865344e-05, "loss": 0.0125, "step": 270 }, { "epoch": 2.6831683168316833, "grad_norm": 0.03313228860497475, "learning_rate": 9.998451377052678e-05, "loss": 0.0214, "step": 271 }, { "epoch": 2.693069306930693, "grad_norm": 0.04074874147772789, "learning_rate": 9.998274538308054e-05, "loss": 0.0182, "step": 272 }, { "epoch": 2.7029702970297027, "grad_norm": 0.03895655646920204, "learning_rate": 9.998088142969586e-05, "loss": 0.0268, "step": 273 }, { "epoch": 2.7128712871287126, "grad_norm": 0.029414329677820206, "learning_rate": 9.997892191393657e-05, "loss": 0.0088, "step": 274 }, { "epoch": 2.7227722772277225, "grad_norm": 0.0380302369594574, "learning_rate": 9.997686683954923e-05, "loss": 0.0154, "step": 275 }, { "epoch": 2.7227722772277225, "eval_loss": 0.019408825784921646, "eval_runtime": 20.9386, "eval_samples_per_second": 4.776, "eval_steps_per_second": 0.143, "step": 275 }, { "epoch": 2.7326732673267324, "grad_norm": 0.04297591373324394, "learning_rate": 9.997471621046308e-05, "loss": 0.0172, "step": 276 }, { "epoch": 2.7425742574257423, "grad_norm": 0.043008070439100266, "learning_rate": 9.997247003079008e-05, "loss": 0.0317, "step": 277 }, { "epoch": 2.7524752475247523, "grad_norm": 0.03837353363633156, "learning_rate": 9.997012830482491e-05, "loss": 0.0246, "step": 278 }, { "epoch": 2.762376237623762, "grad_norm": 0.03948510065674782, "learning_rate": 9.996769103704486e-05, "loss": 0.0183, "step": 279 }, { "epoch": 2.772277227722772, "grad_norm": 0.029715241864323616, "learning_rate": 9.996515823210997e-05, "loss": 0.0219, "step": 280 }, { "epoch": 2.782178217821782, "grad_norm": 0.031051289290189743, "learning_rate": 9.996252989486287e-05, "loss": 0.0143, "step": 281 }, { "epoch": 2.792079207920792, "grad_norm": 0.03561589494347572, "learning_rate": 9.99598060303289e-05, "loss": 0.0178, "step": 282 }, { "epoch": 2.801980198019802, "grad_norm": 0.03417595103383064, "learning_rate": 9.995698664371604e-05, "loss": 0.0114, "step": 283 }, { "epoch": 2.8118811881188117, "grad_norm": 0.03924238681793213, "learning_rate": 9.995407174041489e-05, "loss": 0.019, "step": 284 }, { "epoch": 2.8217821782178216, "grad_norm": 0.03989838808774948, "learning_rate": 9.995106132599869e-05, "loss": 0.0114, "step": 285 }, { "epoch": 2.8316831683168315, "grad_norm": 0.030943676829338074, "learning_rate": 9.994795540622328e-05, "loss": 0.0121, "step": 286 }, { "epoch": 2.8415841584158414, "grad_norm": 0.03534318134188652, "learning_rate": 9.99447539870271e-05, "loss": 0.0133, "step": 287 }, { "epoch": 2.8514851485148514, "grad_norm": 0.03818822652101517, "learning_rate": 9.99414570745312e-05, "loss": 0.0198, "step": 288 }, { "epoch": 2.8613861386138613, "grad_norm": 0.04481323063373566, "learning_rate": 9.993806467503923e-05, "loss": 0.0169, "step": 289 }, { "epoch": 2.871287128712871, "grad_norm": 0.03227623179554939, "learning_rate": 9.993457679503737e-05, "loss": 0.0214, "step": 290 }, { "epoch": 2.881188118811881, "grad_norm": 0.033491671085357666, "learning_rate": 9.993099344119437e-05, "loss": 0.0104, "step": 291 }, { "epoch": 2.891089108910891, "grad_norm": 0.03478483110666275, "learning_rate": 9.992731462036152e-05, "loss": 0.0183, "step": 292 }, { "epoch": 2.900990099009901, "grad_norm": 0.0348794087767601, "learning_rate": 9.992354033957266e-05, "loss": 0.0095, "step": 293 }, { "epoch": 2.910891089108911, "grad_norm": 0.058163851499557495, "learning_rate": 9.991967060604413e-05, "loss": 0.0197, "step": 294 }, { "epoch": 2.9207920792079207, "grad_norm": 0.05041566491127014, "learning_rate": 9.991570542717477e-05, "loss": 0.0219, "step": 295 }, { "epoch": 2.9306930693069306, "grad_norm": 0.031357474625110626, "learning_rate": 9.991164481054591e-05, "loss": 0.0127, "step": 296 }, { "epoch": 2.9405940594059405, "grad_norm": 0.052746862173080444, "learning_rate": 9.99074887639214e-05, "loss": 0.0161, "step": 297 }, { "epoch": 2.9504950495049505, "grad_norm": 0.04254617169499397, "learning_rate": 9.990323729524747e-05, "loss": 0.019, "step": 298 }, { "epoch": 2.9603960396039604, "grad_norm": 0.05648938938975334, "learning_rate": 9.989889041265286e-05, "loss": 0.0149, "step": 299 }, { "epoch": 2.9702970297029703, "grad_norm": 0.0423521064221859, "learning_rate": 9.98944481244487e-05, "loss": 0.021, "step": 300 }, { "epoch": 2.9702970297029703, "eval_loss": 0.019180113449692726, "eval_runtime": 20.9272, "eval_samples_per_second": 4.778, "eval_steps_per_second": 0.143, "step": 300 }, { "epoch": 2.98019801980198, "grad_norm": 0.0332060270011425, "learning_rate": 9.988991043912857e-05, "loss": 0.01, "step": 301 }, { "epoch": 2.99009900990099, "grad_norm": 0.05181276798248291, "learning_rate": 9.988527736536841e-05, "loss": 0.0326, "step": 302 }, { "epoch": 3.0, "grad_norm": 0.037442926317453384, "learning_rate": 9.988054891202656e-05, "loss": 0.0052, "step": 303 }, { "epoch": 3.00990099009901, "grad_norm": 0.032612621784210205, "learning_rate": 9.987572508814372e-05, "loss": 0.0093, "step": 304 }, { "epoch": 3.01980198019802, "grad_norm": 0.040106579661369324, "learning_rate": 9.987080590294295e-05, "loss": 0.0293, "step": 305 }, { "epoch": 3.0297029702970297, "grad_norm": 0.059703320264816284, "learning_rate": 9.986579136582963e-05, "loss": 0.0273, "step": 306 }, { "epoch": 3.0396039603960396, "grad_norm": 0.045052703469991684, "learning_rate": 9.986068148639143e-05, "loss": 0.0079, "step": 307 }, { "epoch": 3.0495049504950495, "grad_norm": 0.035572804510593414, "learning_rate": 9.985547627439835e-05, "loss": 0.0139, "step": 308 }, { "epoch": 3.0594059405940595, "grad_norm": 0.04415634274482727, "learning_rate": 9.985017573980262e-05, "loss": 0.0094, "step": 309 }, { "epoch": 3.0693069306930694, "grad_norm": 0.0477583073079586, "learning_rate": 9.984477989273876e-05, "loss": 0.0156, "step": 310 }, { "epoch": 3.0792079207920793, "grad_norm": 0.03828883171081543, "learning_rate": 9.983928874352352e-05, "loss": 0.0069, "step": 311 }, { "epoch": 3.089108910891089, "grad_norm": 0.04859181493520737, "learning_rate": 9.983370230265585e-05, "loss": 0.0234, "step": 312 }, { "epoch": 3.099009900990099, "grad_norm": 0.03425335884094238, "learning_rate": 9.982802058081691e-05, "loss": 0.0133, "step": 313 }, { "epoch": 3.108910891089109, "grad_norm": 0.03466329351067543, "learning_rate": 9.982224358887003e-05, "loss": 0.0225, "step": 314 }, { "epoch": 3.118811881188119, "grad_norm": 0.040790338069200516, "learning_rate": 9.981637133786071e-05, "loss": 0.01, "step": 315 }, { "epoch": 3.128712871287129, "grad_norm": 0.028947383165359497, "learning_rate": 9.981040383901652e-05, "loss": 0.0071, "step": 316 }, { "epoch": 3.1386138613861387, "grad_norm": 0.03497043997049332, "learning_rate": 9.980434110374724e-05, "loss": 0.023, "step": 317 }, { "epoch": 3.1485148514851486, "grad_norm": 0.03491488844156265, "learning_rate": 9.979818314364468e-05, "loss": 0.0118, "step": 318 }, { "epoch": 3.1584158415841586, "grad_norm": 0.027231434360146523, "learning_rate": 9.979192997048271e-05, "loss": 0.0089, "step": 319 }, { "epoch": 3.1683168316831685, "grad_norm": 0.030446205288171768, "learning_rate": 9.978558159621728e-05, "loss": 0.0135, "step": 320 }, { "epoch": 3.1782178217821784, "grad_norm": 0.03138475492596626, "learning_rate": 9.977913803298633e-05, "loss": 0.012, "step": 321 }, { "epoch": 3.1881188118811883, "grad_norm": 0.03834952786564827, "learning_rate": 9.977259929310985e-05, "loss": 0.0089, "step": 322 }, { "epoch": 3.198019801980198, "grad_norm": 0.035104572772979736, "learning_rate": 9.97659653890897e-05, "loss": 0.0088, "step": 323 }, { "epoch": 3.207920792079208, "grad_norm": 0.035660646855831146, "learning_rate": 9.975923633360985e-05, "loss": 0.022, "step": 324 }, { "epoch": 3.217821782178218, "grad_norm": 0.04493353143334389, "learning_rate": 9.975241213953606e-05, "loss": 0.0282, "step": 325 }, { "epoch": 3.217821782178218, "eval_loss": 0.018639273941516876, "eval_runtime": 20.9758, "eval_samples_per_second": 4.767, "eval_steps_per_second": 0.143, "step": 325 }, { "epoch": 3.227722772277228, "grad_norm": 0.042079996317625046, "learning_rate": 9.974549281991603e-05, "loss": 0.0072, "step": 326 }, { "epoch": 3.237623762376238, "grad_norm": 0.04238072782754898, "learning_rate": 9.973847838797939e-05, "loss": 0.0199, "step": 327 }, { "epoch": 3.2475247524752477, "grad_norm": 0.03974232077598572, "learning_rate": 9.973136885713754e-05, "loss": 0.0132, "step": 328 }, { "epoch": 3.2574257425742577, "grad_norm": 0.03601127117872238, "learning_rate": 9.972416424098379e-05, "loss": 0.0157, "step": 329 }, { "epoch": 3.2673267326732676, "grad_norm": 0.03373201563954353, "learning_rate": 9.971686455329319e-05, "loss": 0.0165, "step": 330 }, { "epoch": 3.2772277227722775, "grad_norm": 0.03458605706691742, "learning_rate": 9.970946980802261e-05, "loss": 0.0147, "step": 331 }, { "epoch": 3.287128712871287, "grad_norm": 0.02960544265806675, "learning_rate": 9.970198001931062e-05, "loss": 0.0088, "step": 332 }, { "epoch": 3.297029702970297, "grad_norm": 0.03317386284470558, "learning_rate": 9.969439520147754e-05, "loss": 0.0169, "step": 333 }, { "epoch": 3.3069306930693068, "grad_norm": 0.037376001477241516, "learning_rate": 9.968671536902539e-05, "loss": 0.0176, "step": 334 }, { "epoch": 3.3168316831683167, "grad_norm": 0.03728969767689705, "learning_rate": 9.967894053663782e-05, "loss": 0.0128, "step": 335 }, { "epoch": 3.3267326732673266, "grad_norm": 0.033844251185655594, "learning_rate": 9.967107071918019e-05, "loss": 0.0124, "step": 336 }, { "epoch": 3.3366336633663365, "grad_norm": 0.04100586473941803, "learning_rate": 9.966310593169936e-05, "loss": 0.0266, "step": 337 }, { "epoch": 3.3465346534653464, "grad_norm": 0.03216198459267616, "learning_rate": 9.965504618942389e-05, "loss": 0.0078, "step": 338 }, { "epoch": 3.3564356435643563, "grad_norm": 0.03028401918709278, "learning_rate": 9.96468915077638e-05, "loss": 0.0163, "step": 339 }, { "epoch": 3.366336633663366, "grad_norm": 0.0313386544585228, "learning_rate": 9.963864190231067e-05, "loss": 0.0212, "step": 340 }, { "epoch": 3.376237623762376, "grad_norm": 0.04166916385293007, "learning_rate": 9.96302973888376e-05, "loss": 0.0315, "step": 341 }, { "epoch": 3.386138613861386, "grad_norm": 0.028147250413894653, "learning_rate": 9.962185798329909e-05, "loss": 0.0111, "step": 342 }, { "epoch": 3.396039603960396, "grad_norm": 0.028218761086463928, "learning_rate": 9.96133237018311e-05, "loss": 0.0107, "step": 343 }, { "epoch": 3.405940594059406, "grad_norm": 0.03172610327601433, "learning_rate": 9.960469456075099e-05, "loss": 0.0166, "step": 344 }, { "epoch": 3.4158415841584158, "grad_norm": 0.0334465391933918, "learning_rate": 9.959597057655753e-05, "loss": 0.0215, "step": 345 }, { "epoch": 3.4257425742574257, "grad_norm": 0.036227963864803314, "learning_rate": 9.958715176593076e-05, "loss": 0.0139, "step": 346 }, { "epoch": 3.4356435643564356, "grad_norm": 0.03319300711154938, "learning_rate": 9.957823814573206e-05, "loss": 0.0096, "step": 347 }, { "epoch": 3.4455445544554455, "grad_norm": 0.02689778245985508, "learning_rate": 9.956922973300409e-05, "loss": 0.0129, "step": 348 }, { "epoch": 3.4554455445544554, "grad_norm": 0.030777866020798683, "learning_rate": 9.956012654497074e-05, "loss": 0.016, "step": 349 }, { "epoch": 3.4653465346534653, "grad_norm": 0.03275037929415703, "learning_rate": 9.95509285990371e-05, "loss": 0.007, "step": 350 }, { "epoch": 3.4653465346534653, "eval_loss": 0.018103841692209244, "eval_runtime": 20.9432, "eval_samples_per_second": 4.775, "eval_steps_per_second": 0.143, "step": 350 }, { "epoch": 3.4752475247524752, "grad_norm": 0.0414116345345974, "learning_rate": 9.954163591278945e-05, "loss": 0.0322, "step": 351 }, { "epoch": 3.485148514851485, "grad_norm": 0.039487581700086594, "learning_rate": 9.953224850399524e-05, "loss": 0.0091, "step": 352 }, { "epoch": 3.495049504950495, "grad_norm": 0.04589547961950302, "learning_rate": 9.952276639060292e-05, "loss": 0.0298, "step": 353 }, { "epoch": 3.504950495049505, "grad_norm": 0.038935884833335876, "learning_rate": 9.951318959074216e-05, "loss": 0.009, "step": 354 }, { "epoch": 3.514851485148515, "grad_norm": 0.035445939749479294, "learning_rate": 9.950351812272356e-05, "loss": 0.0081, "step": 355 }, { "epoch": 3.5247524752475248, "grad_norm": 0.04069902002811432, "learning_rate": 9.949375200503877e-05, "loss": 0.0086, "step": 356 }, { "epoch": 3.5346534653465347, "grad_norm": 0.046185996383428574, "learning_rate": 9.948389125636039e-05, "loss": 0.0201, "step": 357 }, { "epoch": 3.5445544554455446, "grad_norm": 0.02967759221792221, "learning_rate": 9.947393589554197e-05, "loss": 0.015, "step": 358 }, { "epoch": 3.5544554455445545, "grad_norm": 0.02880985476076603, "learning_rate": 9.946388594161795e-05, "loss": 0.0081, "step": 359 }, { "epoch": 3.5643564356435644, "grad_norm": 0.03159020096063614, "learning_rate": 9.945374141380361e-05, "loss": 0.0153, "step": 360 }, { "epoch": 3.5742574257425743, "grad_norm": 0.034859638661146164, "learning_rate": 9.944350233149509e-05, "loss": 0.0128, "step": 361 }, { "epoch": 3.5841584158415842, "grad_norm": 0.04179144650697708, "learning_rate": 9.943316871426929e-05, "loss": 0.0368, "step": 362 }, { "epoch": 3.594059405940594, "grad_norm": 0.03368615359067917, "learning_rate": 9.942274058188383e-05, "loss": 0.0245, "step": 363 }, { "epoch": 3.603960396039604, "grad_norm": 0.03103993646800518, "learning_rate": 9.941221795427713e-05, "loss": 0.0119, "step": 364 }, { "epoch": 3.613861386138614, "grad_norm": 0.024007977917790413, "learning_rate": 9.94016008515682e-05, "loss": 0.007, "step": 365 }, { "epoch": 3.623762376237624, "grad_norm": 0.031901855021715164, "learning_rate": 9.939088929405674e-05, "loss": 0.0124, "step": 366 }, { "epoch": 3.633663366336634, "grad_norm": 0.026758648455142975, "learning_rate": 9.938008330222296e-05, "loss": 0.0089, "step": 367 }, { "epoch": 3.6435643564356437, "grad_norm": 0.0313340462744236, "learning_rate": 9.936918289672774e-05, "loss": 0.0101, "step": 368 }, { "epoch": 3.6534653465346536, "grad_norm": 0.028882941231131554, "learning_rate": 9.93581880984124e-05, "loss": 0.0093, "step": 369 }, { "epoch": 3.6633663366336635, "grad_norm": 0.033211950212717056, "learning_rate": 9.934709892829875e-05, "loss": 0.0143, "step": 370 }, { "epoch": 3.6732673267326734, "grad_norm": 0.04559667780995369, "learning_rate": 9.933591540758907e-05, "loss": 0.0403, "step": 371 }, { "epoch": 3.6831683168316833, "grad_norm": 0.0350009985268116, "learning_rate": 9.932463755766599e-05, "loss": 0.0297, "step": 372 }, { "epoch": 3.693069306930693, "grad_norm": 0.03305431827902794, "learning_rate": 9.931326540009253e-05, "loss": 0.0228, "step": 373 }, { "epoch": 3.7029702970297027, "grad_norm": 0.025855455547571182, "learning_rate": 9.930179895661201e-05, "loss": 0.007, "step": 374 }, { "epoch": 3.7128712871287126, "grad_norm": 0.03375259414315224, "learning_rate": 9.929023824914802e-05, "loss": 0.017, "step": 375 }, { "epoch": 3.7128712871287126, "eval_loss": 0.018772218376398087, "eval_runtime": 20.9276, "eval_samples_per_second": 4.778, "eval_steps_per_second": 0.143, "step": 375 }, { "epoch": 3.7227722772277225, "grad_norm": 0.031592901796102524, "learning_rate": 9.927858329980439e-05, "loss": 0.0177, "step": 376 }, { "epoch": 3.7326732673267324, "grad_norm": 0.03559165447950363, "learning_rate": 9.926683413086514e-05, "loss": 0.0229, "step": 377 }, { "epoch": 3.7425742574257423, "grad_norm": 0.03730347007513046, "learning_rate": 9.925499076479441e-05, "loss": 0.0169, "step": 378 }, { "epoch": 3.7524752475247523, "grad_norm": 0.04660610854625702, "learning_rate": 9.924305322423649e-05, "loss": 0.034, "step": 379 }, { "epoch": 3.762376237623762, "grad_norm": 0.023445578292012215, "learning_rate": 9.923102153201566e-05, "loss": 0.0098, "step": 380 }, { "epoch": 3.772277227722772, "grad_norm": 0.026974381878972054, "learning_rate": 9.921889571113628e-05, "loss": 0.0123, "step": 381 }, { "epoch": 3.782178217821782, "grad_norm": 0.029063357040286064, "learning_rate": 9.920667578478268e-05, "loss": 0.0202, "step": 382 }, { "epoch": 3.792079207920792, "grad_norm": 0.04441928118467331, "learning_rate": 9.919436177631907e-05, "loss": 0.0096, "step": 383 }, { "epoch": 3.801980198019802, "grad_norm": 0.03253911808133125, "learning_rate": 9.918195370928957e-05, "loss": 0.017, "step": 384 }, { "epoch": 3.8118811881188117, "grad_norm": 0.0321219228208065, "learning_rate": 9.916945160741817e-05, "loss": 0.007, "step": 385 }, { "epoch": 3.8217821782178216, "grad_norm": 0.029211685061454773, "learning_rate": 9.915685549460861e-05, "loss": 0.0091, "step": 386 }, { "epoch": 3.8316831683168315, "grad_norm": 0.028232336044311523, "learning_rate": 9.914416539494435e-05, "loss": 0.009, "step": 387 }, { "epoch": 3.8415841584158414, "grad_norm": 0.03041473776102066, "learning_rate": 9.913138133268862e-05, "loss": 0.0082, "step": 388 }, { "epoch": 3.8514851485148514, "grad_norm": 0.026392994448542595, "learning_rate": 9.911850333228427e-05, "loss": 0.0159, "step": 389 }, { "epoch": 3.8613861386138613, "grad_norm": 0.027819879353046417, "learning_rate": 9.910553141835376e-05, "loss": 0.0179, "step": 390 }, { "epoch": 3.871287128712871, "grad_norm": 0.032292746007442474, "learning_rate": 9.909246561569912e-05, "loss": 0.0192, "step": 391 }, { "epoch": 3.881188118811881, "grad_norm": 0.02765706181526184, "learning_rate": 9.907930594930185e-05, "loss": 0.0233, "step": 392 }, { "epoch": 3.891089108910891, "grad_norm": 0.027257481589913368, "learning_rate": 9.9066052444323e-05, "loss": 0.012, "step": 393 }, { "epoch": 3.900990099009901, "grad_norm": 0.03747186064720154, "learning_rate": 9.905270512610296e-05, "loss": 0.0279, "step": 394 }, { "epoch": 3.910891089108911, "grad_norm": 0.022682279348373413, "learning_rate": 9.903926402016153e-05, "loss": 0.0069, "step": 395 }, { "epoch": 3.9207920792079207, "grad_norm": 0.02796732820570469, "learning_rate": 9.902572915219779e-05, "loss": 0.0073, "step": 396 }, { "epoch": 3.9306930693069306, "grad_norm": 0.034723684191703796, "learning_rate": 9.901210054809015e-05, "loss": 0.0181, "step": 397 }, { "epoch": 3.9405940594059405, "grad_norm": 0.033110056072473526, "learning_rate": 9.899837823389618e-05, "loss": 0.0078, "step": 398 }, { "epoch": 3.9504950495049505, "grad_norm": 0.03528871014714241, "learning_rate": 9.898456223585267e-05, "loss": 0.0132, "step": 399 }, { "epoch": 3.9603960396039604, "grad_norm": 0.056491754949092865, "learning_rate": 9.897065258037552e-05, "loss": 0.0315, "step": 400 }, { "epoch": 3.9603960396039604, "eval_loss": 0.018521126359701157, "eval_runtime": 20.9582, "eval_samples_per_second": 4.771, "eval_steps_per_second": 0.143, "step": 400 }, { "epoch": 3.9702970297029703, "grad_norm": 0.03693537786602974, "learning_rate": 9.895664929405966e-05, "loss": 0.0164, "step": 401 }, { "epoch": 3.98019801980198, "grad_norm": 0.034034907817840576, "learning_rate": 9.89425524036791e-05, "loss": 0.015, "step": 402 }, { "epoch": 3.99009900990099, "grad_norm": 0.03214896842837334, "learning_rate": 9.892836193618679e-05, "loss": 0.012, "step": 403 }, { "epoch": 4.0, "grad_norm": 0.049190979450941086, "learning_rate": 9.89140779187146e-05, "loss": 0.009, "step": 404 }, { "epoch": 4.00990099009901, "grad_norm": 0.02638743631541729, "learning_rate": 9.889970037857324e-05, "loss": 0.0169, "step": 405 }, { "epoch": 4.01980198019802, "grad_norm": 0.02798108384013176, "learning_rate": 9.88852293432523e-05, "loss": 0.0201, "step": 406 }, { "epoch": 4.02970297029703, "grad_norm": 0.02562817744910717, "learning_rate": 9.887066484042007e-05, "loss": 0.0134, "step": 407 }, { "epoch": 4.03960396039604, "grad_norm": 0.025396671146154404, "learning_rate": 9.885600689792356e-05, "loss": 0.0063, "step": 408 }, { "epoch": 4.0495049504950495, "grad_norm": 0.024238383397459984, "learning_rate": 9.884125554378845e-05, "loss": 0.0112, "step": 409 }, { "epoch": 4.0594059405940595, "grad_norm": 0.035111505538225174, "learning_rate": 9.882641080621902e-05, "loss": 0.0265, "step": 410 }, { "epoch": 4.069306930693069, "grad_norm": 0.03213327378034592, "learning_rate": 9.881147271359807e-05, "loss": 0.0141, "step": 411 }, { "epoch": 4.079207920792079, "grad_norm": 0.03519801050424576, "learning_rate": 9.879644129448694e-05, "loss": 0.0072, "step": 412 }, { "epoch": 4.089108910891089, "grad_norm": 0.03529242426156998, "learning_rate": 9.878131657762535e-05, "loss": 0.0112, "step": 413 }, { "epoch": 4.099009900990099, "grad_norm": 0.023639151826500893, "learning_rate": 9.876609859193145e-05, "loss": 0.0057, "step": 414 }, { "epoch": 4.108910891089109, "grad_norm": 0.02800002135336399, "learning_rate": 9.875078736650172e-05, "loss": 0.0183, "step": 415 }, { "epoch": 4.118811881188119, "grad_norm": 0.02918158285319805, "learning_rate": 9.873538293061087e-05, "loss": 0.0148, "step": 416 }, { "epoch": 4.128712871287129, "grad_norm": 0.03694870322942734, "learning_rate": 9.871988531371185e-05, "loss": 0.006, "step": 417 }, { "epoch": 4.138613861386139, "grad_norm": 0.03968213126063347, "learning_rate": 9.870429454543582e-05, "loss": 0.0083, "step": 418 }, { "epoch": 4.148514851485149, "grad_norm": 0.036222394555807114, "learning_rate": 9.868861065559192e-05, "loss": 0.0157, "step": 419 }, { "epoch": 4.158415841584159, "grad_norm": 0.03854987397789955, "learning_rate": 9.867283367416747e-05, "loss": 0.0066, "step": 420 }, { "epoch": 4.1683168316831685, "grad_norm": 0.03001275099813938, "learning_rate": 9.865696363132769e-05, "loss": 0.0144, "step": 421 }, { "epoch": 4.178217821782178, "grad_norm": 0.023233724758028984, "learning_rate": 9.864100055741576e-05, "loss": 0.005, "step": 422 }, { "epoch": 4.188118811881188, "grad_norm": 0.027578100562095642, "learning_rate": 9.862494448295277e-05, "loss": 0.0066, "step": 423 }, { "epoch": 4.198019801980198, "grad_norm": 0.03242870792746544, "learning_rate": 9.860879543863755e-05, "loss": 0.0182, "step": 424 }, { "epoch": 4.207920792079208, "grad_norm": 0.02438744716346264, "learning_rate": 9.859255345534675e-05, "loss": 0.0156, "step": 425 }, { "epoch": 4.207920792079208, "eval_loss": 0.019263744354248047, "eval_runtime": 20.9857, "eval_samples_per_second": 4.765, "eval_steps_per_second": 0.143, "step": 425 }, { "epoch": 4.217821782178218, "grad_norm": 0.027921592816710472, "learning_rate": 9.857621856413469e-05, "loss": 0.0052, "step": 426 }, { "epoch": 4.227722772277228, "grad_norm": 0.031431883573532104, "learning_rate": 9.855979079623332e-05, "loss": 0.0118, "step": 427 }, { "epoch": 4.237623762376238, "grad_norm": 0.03149943798780441, "learning_rate": 9.85432701830522e-05, "loss": 0.0093, "step": 428 }, { "epoch": 4.247524752475248, "grad_norm": 0.029634475708007812, "learning_rate": 9.852665675617837e-05, "loss": 0.0174, "step": 429 }, { "epoch": 4.257425742574258, "grad_norm": 0.03414541855454445, "learning_rate": 9.850995054737637e-05, "loss": 0.0062, "step": 430 }, { "epoch": 4.267326732673268, "grad_norm": 0.0337190143764019, "learning_rate": 9.849315158858807e-05, "loss": 0.0067, "step": 431 }, { "epoch": 4.2772277227722775, "grad_norm": 0.050311364233493805, "learning_rate": 9.847625991193277e-05, "loss": 0.019, "step": 432 }, { "epoch": 4.287128712871287, "grad_norm": 0.03678404539823532, "learning_rate": 9.845927554970698e-05, "loss": 0.0275, "step": 433 }, { "epoch": 4.297029702970297, "grad_norm": 0.03602934628725052, "learning_rate": 9.84421985343844e-05, "loss": 0.0263, "step": 434 }, { "epoch": 4.306930693069307, "grad_norm": 0.0423722043633461, "learning_rate": 9.842502889861596e-05, "loss": 0.0063, "step": 435 }, { "epoch": 4.316831683168317, "grad_norm": 0.026815395802259445, "learning_rate": 9.840776667522962e-05, "loss": 0.0104, "step": 436 }, { "epoch": 4.326732673267327, "grad_norm": 0.04021260514855385, "learning_rate": 9.839041189723039e-05, "loss": 0.0113, "step": 437 }, { "epoch": 4.336633663366337, "grad_norm": 0.03357745334506035, "learning_rate": 9.837296459780022e-05, "loss": 0.0277, "step": 438 }, { "epoch": 4.346534653465347, "grad_norm": 0.03575926274061203, "learning_rate": 9.835542481029798e-05, "loss": 0.014, "step": 439 }, { "epoch": 4.356435643564357, "grad_norm": 0.03378582373261452, "learning_rate": 9.833779256825937e-05, "loss": 0.014, "step": 440 }, { "epoch": 4.366336633663367, "grad_norm": 0.029247019439935684, "learning_rate": 9.832006790539685e-05, "loss": 0.0075, "step": 441 }, { "epoch": 4.376237623762377, "grad_norm": 0.0354682132601738, "learning_rate": 9.830225085559961e-05, "loss": 0.0106, "step": 442 }, { "epoch": 4.3861386138613865, "grad_norm": 0.04129399359226227, "learning_rate": 9.828434145293346e-05, "loss": 0.02, "step": 443 }, { "epoch": 4.396039603960396, "grad_norm": 0.026085088029503822, "learning_rate": 9.826633973164079e-05, "loss": 0.0122, "step": 444 }, { "epoch": 4.405940594059406, "grad_norm": 0.038606371730566025, "learning_rate": 9.824824572614051e-05, "loss": 0.0134, "step": 445 }, { "epoch": 4.415841584158416, "grad_norm": 0.03461376577615738, "learning_rate": 9.823005947102797e-05, "loss": 0.0056, "step": 446 }, { "epoch": 4.425742574257426, "grad_norm": 0.029777944087982178, "learning_rate": 9.821178100107489e-05, "loss": 0.0211, "step": 447 }, { "epoch": 4.435643564356436, "grad_norm": 0.025174397975206375, "learning_rate": 9.819341035122933e-05, "loss": 0.0065, "step": 448 }, { "epoch": 4.445544554455446, "grad_norm": 0.02835717424750328, "learning_rate": 9.817494755661558e-05, "loss": 0.0164, "step": 449 }, { "epoch": 4.455445544554456, "grad_norm": 0.02822643145918846, "learning_rate": 9.815639265253409e-05, "loss": 0.0059, "step": 450 }, { "epoch": 4.455445544554456, "eval_loss": 0.01967804692685604, "eval_runtime": 20.9324, "eval_samples_per_second": 4.777, "eval_steps_per_second": 0.143, "step": 450 }, { "epoch": 4.465346534653466, "grad_norm": 0.03281950205564499, "learning_rate": 9.813774567446145e-05, "loss": 0.0064, "step": 451 }, { "epoch": 4.475247524752476, "grad_norm": 0.027459366247057915, "learning_rate": 9.811900665805029e-05, "loss": 0.0167, "step": 452 }, { "epoch": 4.485148514851485, "grad_norm": 0.03079644776880741, "learning_rate": 9.81001756391292e-05, "loss": 0.0062, "step": 453 }, { "epoch": 4.4950495049504955, "grad_norm": 0.02574409544467926, "learning_rate": 9.808125265370269e-05, "loss": 0.0082, "step": 454 }, { "epoch": 4.5049504950495045, "grad_norm": 0.04239686205983162, "learning_rate": 9.806223773795108e-05, "loss": 0.0083, "step": 455 }, { "epoch": 4.514851485148515, "grad_norm": 0.027789965271949768, "learning_rate": 9.804313092823049e-05, "loss": 0.0131, "step": 456 }, { "epoch": 4.524752475247524, "grad_norm": 0.024712661281228065, "learning_rate": 9.802393226107278e-05, "loss": 0.0086, "step": 457 }, { "epoch": 4.534653465346535, "grad_norm": 0.028639836236834526, "learning_rate": 9.800464177318531e-05, "loss": 0.0131, "step": 458 }, { "epoch": 4.544554455445544, "grad_norm": 0.023141171783208847, "learning_rate": 9.798525950145115e-05, "loss": 0.0056, "step": 459 }, { "epoch": 4.554455445544555, "grad_norm": 0.029834497720003128, "learning_rate": 9.796578548292874e-05, "loss": 0.0113, "step": 460 }, { "epoch": 4.564356435643564, "grad_norm": 0.029348380863666534, "learning_rate": 9.794621975485201e-05, "loss": 0.0081, "step": 461 }, { "epoch": 4.574257425742574, "grad_norm": 0.029745472595095634, "learning_rate": 9.79265623546302e-05, "loss": 0.0091, "step": 462 }, { "epoch": 4.584158415841584, "grad_norm": 0.04096932336688042, "learning_rate": 9.790681331984785e-05, "loss": 0.0217, "step": 463 }, { "epoch": 4.594059405940594, "grad_norm": 0.037326063960790634, "learning_rate": 9.78869726882647e-05, "loss": 0.0067, "step": 464 }, { "epoch": 4.603960396039604, "grad_norm": 0.029236366972327232, "learning_rate": 9.786704049781558e-05, "loss": 0.017, "step": 465 }, { "epoch": 4.6138613861386135, "grad_norm": 0.027106214314699173, "learning_rate": 9.784701678661045e-05, "loss": 0.006, "step": 466 }, { "epoch": 4.623762376237623, "grad_norm": 0.041205085813999176, "learning_rate": 9.782690159293419e-05, "loss": 0.0214, "step": 467 }, { "epoch": 4.633663366336633, "grad_norm": 0.02912343665957451, "learning_rate": 9.780669495524661e-05, "loss": 0.0068, "step": 468 }, { "epoch": 4.643564356435643, "grad_norm": 0.02972271479666233, "learning_rate": 9.77863969121824e-05, "loss": 0.0132, "step": 469 }, { "epoch": 4.653465346534653, "grad_norm": 0.03316974267363548, "learning_rate": 9.776600750255099e-05, "loss": 0.0104, "step": 470 }, { "epoch": 4.663366336633663, "grad_norm": 0.025208162143826485, "learning_rate": 9.774552676533644e-05, "loss": 0.019, "step": 471 }, { "epoch": 4.673267326732673, "grad_norm": 0.029168223962187767, "learning_rate": 9.772495473969751e-05, "loss": 0.0185, "step": 472 }, { "epoch": 4.683168316831683, "grad_norm": 0.027234015986323357, "learning_rate": 9.77042914649675e-05, "loss": 0.013, "step": 473 }, { "epoch": 4.693069306930693, "grad_norm": 0.030596833676099777, "learning_rate": 9.768353698065412e-05, "loss": 0.0111, "step": 474 }, { "epoch": 4.702970297029703, "grad_norm": 0.027127567678689957, "learning_rate": 9.766269132643951e-05, "loss": 0.0136, "step": 475 }, { "epoch": 4.702970297029703, "eval_loss": 0.019799688830971718, "eval_runtime": 20.9596, "eval_samples_per_second": 4.771, "eval_steps_per_second": 0.143, "step": 475 }, { "epoch": 4.712871287128713, "grad_norm": 0.031133603304624557, "learning_rate": 9.76417545421801e-05, "loss": 0.0163, "step": 476 }, { "epoch": 4.7227722772277225, "grad_norm": 0.034247223287820816, "learning_rate": 9.762072666790658e-05, "loss": 0.0245, "step": 477 }, { "epoch": 4.732673267326732, "grad_norm": 0.0344618484377861, "learning_rate": 9.75996077438238e-05, "loss": 0.0142, "step": 478 }, { "epoch": 4.742574257425742, "grad_norm": 0.03324158489704132, "learning_rate": 9.757839781031069e-05, "loss": 0.0114, "step": 479 }, { "epoch": 4.752475247524752, "grad_norm": 0.025920778512954712, "learning_rate": 9.755709690792017e-05, "loss": 0.0095, "step": 480 }, { "epoch": 4.762376237623762, "grad_norm": 0.03353674337267876, "learning_rate": 9.753570507737914e-05, "loss": 0.0223, "step": 481 }, { "epoch": 4.772277227722772, "grad_norm": 0.035666413605213165, "learning_rate": 9.751422235958829e-05, "loss": 0.0196, "step": 482 }, { "epoch": 4.782178217821782, "grad_norm": 0.03323884680867195, "learning_rate": 9.749264879562216e-05, "loss": 0.0275, "step": 483 }, { "epoch": 4.792079207920792, "grad_norm": 0.024832090362906456, "learning_rate": 9.74709844267289e-05, "loss": 0.0197, "step": 484 }, { "epoch": 4.801980198019802, "grad_norm": 0.025249451398849487, "learning_rate": 9.744922929433033e-05, "loss": 0.018, "step": 485 }, { "epoch": 4.811881188118812, "grad_norm": 0.027032941579818726, "learning_rate": 9.74273834400218e-05, "loss": 0.0185, "step": 486 }, { "epoch": 4.821782178217822, "grad_norm": 0.03405793011188507, "learning_rate": 9.740544690557213e-05, "loss": 0.0284, "step": 487 }, { "epoch": 4.8316831683168315, "grad_norm": 0.033517688512802124, "learning_rate": 9.738341973292349e-05, "loss": 0.0319, "step": 488 }, { "epoch": 4.841584158415841, "grad_norm": 0.027846721932291985, "learning_rate": 9.736130196419135e-05, "loss": 0.0139, "step": 489 }, { "epoch": 4.851485148514851, "grad_norm": 0.027481894940137863, "learning_rate": 9.733909364166442e-05, "loss": 0.0078, "step": 490 }, { "epoch": 4.861386138613861, "grad_norm": 0.02963847480714321, "learning_rate": 9.731679480780456e-05, "loss": 0.0175, "step": 491 }, { "epoch": 4.871287128712871, "grad_norm": 0.022556889802217484, "learning_rate": 9.729440550524664e-05, "loss": 0.0065, "step": 492 }, { "epoch": 4.881188118811881, "grad_norm": 0.030938800424337387, "learning_rate": 9.727192577679851e-05, "loss": 0.0126, "step": 493 }, { "epoch": 4.891089108910891, "grad_norm": 0.05100259929895401, "learning_rate": 9.724935566544098e-05, "loss": 0.0365, "step": 494 }, { "epoch": 4.900990099009901, "grad_norm": 0.03517129644751549, "learning_rate": 9.722669521432757e-05, "loss": 0.0219, "step": 495 }, { "epoch": 4.910891089108911, "grad_norm": 0.02679610438644886, "learning_rate": 9.720394446678458e-05, "loss": 0.0147, "step": 496 }, { "epoch": 4.920792079207921, "grad_norm": 0.027280865237116814, "learning_rate": 9.718110346631099e-05, "loss": 0.0152, "step": 497 }, { "epoch": 4.930693069306931, "grad_norm": 0.029038678854703903, "learning_rate": 9.715817225657827e-05, "loss": 0.0117, "step": 498 }, { "epoch": 4.9405940594059405, "grad_norm": 0.02707214094698429, "learning_rate": 9.713515088143042e-05, "loss": 0.0099, "step": 499 }, { "epoch": 4.9504950495049505, "grad_norm": 0.028160203248262405, "learning_rate": 9.71120393848838e-05, "loss": 0.0092, "step": 500 }, { "epoch": 4.9504950495049505, "eval_loss": 0.021699432283639908, "eval_runtime": 20.9339, "eval_samples_per_second": 4.777, "eval_steps_per_second": 0.143, "step": 500 }, { "epoch": 4.96039603960396, "grad_norm": 0.028015898540616035, "learning_rate": 9.70888378111271e-05, "loss": 0.0138, "step": 501 }, { "epoch": 4.97029702970297, "grad_norm": 0.02438513934612274, "learning_rate": 9.706554620452125e-05, "loss": 0.0065, "step": 502 }, { "epoch": 4.98019801980198, "grad_norm": 0.03049881011247635, "learning_rate": 9.704216460959929e-05, "loss": 0.013, "step": 503 }, { "epoch": 4.99009900990099, "grad_norm": 0.02331537939608097, "learning_rate": 9.701869307106633e-05, "loss": 0.0208, "step": 504 }, { "epoch": 5.0, "grad_norm": 0.11598920822143555, "learning_rate": 9.699513163379943e-05, "loss": 0.0146, "step": 505 }, { "epoch": 5.00990099009901, "grad_norm": 0.019882583990693092, "learning_rate": 9.697148034284759e-05, "loss": 0.0117, "step": 506 }, { "epoch": 5.01980198019802, "grad_norm": 0.03078438714146614, "learning_rate": 9.694773924343154e-05, "loss": 0.0052, "step": 507 }, { "epoch": 5.02970297029703, "grad_norm": 0.02752445451915264, "learning_rate": 9.692390838094377e-05, "loss": 0.0121, "step": 508 }, { "epoch": 5.03960396039604, "grad_norm": 0.027121013030409813, "learning_rate": 9.689998780094837e-05, "loss": 0.0261, "step": 509 }, { "epoch": 5.0495049504950495, "grad_norm": 0.0361727774143219, "learning_rate": 9.687597754918099e-05, "loss": 0.006, "step": 510 }, { "epoch": 5.0594059405940595, "grad_norm": 0.03587155416607857, "learning_rate": 9.68518776715487e-05, "loss": 0.0067, "step": 511 }, { "epoch": 5.069306930693069, "grad_norm": 0.032527755945920944, "learning_rate": 9.682768821412997e-05, "loss": 0.0067, "step": 512 }, { "epoch": 5.079207920792079, "grad_norm": 0.03142087161540985, "learning_rate": 9.68034092231745e-05, "loss": 0.0079, "step": 513 }, { "epoch": 5.089108910891089, "grad_norm": 0.03114234283566475, "learning_rate": 9.677904074510322e-05, "loss": 0.0199, "step": 514 }, { "epoch": 5.099009900990099, "grad_norm": 0.026284724473953247, "learning_rate": 9.675458282650813e-05, "loss": 0.0121, "step": 515 }, { "epoch": 5.108910891089109, "grad_norm": 0.0318143405020237, "learning_rate": 9.673003551415224e-05, "loss": 0.0063, "step": 516 }, { "epoch": 5.118811881188119, "grad_norm": 0.035465918481349945, "learning_rate": 9.67053988549695e-05, "loss": 0.0207, "step": 517 }, { "epoch": 5.128712871287129, "grad_norm": 0.0312662236392498, "learning_rate": 9.668067289606466e-05, "loss": 0.012, "step": 518 }, { "epoch": 5.138613861386139, "grad_norm": 0.03460320085287094, "learning_rate": 9.665585768471324e-05, "loss": 0.0052, "step": 519 }, { "epoch": 5.148514851485149, "grad_norm": 0.03635144233703613, "learning_rate": 9.663095326836138e-05, "loss": 0.0226, "step": 520 }, { "epoch": 5.158415841584159, "grad_norm": 0.03495261073112488, "learning_rate": 9.660595969462578e-05, "loss": 0.0157, "step": 521 }, { "epoch": 5.1683168316831685, "grad_norm": 0.029816031455993652, "learning_rate": 9.658087701129365e-05, "loss": 0.0052, "step": 522 }, { "epoch": 5.178217821782178, "grad_norm": 0.027445781975984573, "learning_rate": 9.655570526632252e-05, "loss": 0.0129, "step": 523 }, { "epoch": 5.188118811881188, "grad_norm": 0.03341228514909744, "learning_rate": 9.653044450784023e-05, "loss": 0.0177, "step": 524 }, { "epoch": 5.198019801980198, "grad_norm": 0.036780472844839096, "learning_rate": 9.650509478414482e-05, "loss": 0.008, "step": 525 }, { "epoch": 5.198019801980198, "eval_loss": 0.01887640729546547, "eval_runtime": 20.9336, "eval_samples_per_second": 4.777, "eval_steps_per_second": 0.143, "step": 525 }, { "epoch": 5.198019801980198, "step": 525, "total_flos": 1.9740066929914675e+18, "train_loss": 0.027972995166977245, "train_runtime": 14286.9421, "train_samples_per_second": 8.427, "train_steps_per_second": 0.177 } ], "logging_steps": 1, "max_steps": 2525, "num_input_tokens_seen": 0, "num_train_epochs": 25, "save_steps": 100, "stateful_callbacks": { "EarlyStoppingCallback": { "args": { "early_stopping_patience": 5, "early_stopping_threshold": 0.0 }, "attributes": { "early_stopping_patience_counter": 4 } }, "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 1.9740066929914675e+18, "train_batch_size": 48, "trial_name": null, "trial_params": null }