| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 5.0, |
| "eval_steps": 500, |
| "global_step": 785, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "entropy": 1.1603021323680878, |
| "epoch": 0.0064, |
| "grad_norm": 0.22975344955921173, |
| "learning_rate": 0.0002, |
| "loss": 2.6077966690063477, |
| "mean_token_accuracy": 0.4999677650630474, |
| "num_tokens": 37716.0, |
| "step": 1 |
| }, |
| { |
| "entropy": 1.2748871892690659, |
| "epoch": 0.0128, |
| "grad_norm": 0.2017921358346939, |
| "learning_rate": 0.0002, |
| "loss": 2.2619409561157227, |
| "mean_token_accuracy": 0.5358003973960876, |
| "num_tokens": 75123.0, |
| "step": 2 |
| }, |
| { |
| "entropy": 1.4657676070928574, |
| "epoch": 0.0192, |
| "grad_norm": 0.13960610330104828, |
| "learning_rate": 0.0002, |
| "loss": 1.8277919292449951, |
| "mean_token_accuracy": 0.5620946511626244, |
| "num_tokens": 112455.0, |
| "step": 3 |
| }, |
| { |
| "entropy": 1.4639433324337006, |
| "epoch": 0.0256, |
| "grad_norm": 0.1115739569067955, |
| "learning_rate": 0.0002, |
| "loss": 1.5044896602630615, |
| "mean_token_accuracy": 0.6032674387097359, |
| "num_tokens": 150168.0, |
| "step": 4 |
| }, |
| { |
| "entropy": 1.4306974858045578, |
| "epoch": 0.032, |
| "grad_norm": 0.1513909250497818, |
| "learning_rate": 0.0002, |
| "loss": 1.3954216241836548, |
| "mean_token_accuracy": 0.607626736164093, |
| "num_tokens": 187390.0, |
| "step": 5 |
| }, |
| { |
| "entropy": 1.3751554787158966, |
| "epoch": 0.0384, |
| "grad_norm": 0.07965348660945892, |
| "learning_rate": 0.0002, |
| "loss": 1.2835979461669922, |
| "mean_token_accuracy": 0.6308266744017601, |
| "num_tokens": 224660.0, |
| "step": 6 |
| }, |
| { |
| "entropy": 1.3173644244670868, |
| "epoch": 0.0448, |
| "grad_norm": 0.049434103071689606, |
| "learning_rate": 0.0002, |
| "loss": 1.2139647006988525, |
| "mean_token_accuracy": 0.6277531310915947, |
| "num_tokens": 262611.0, |
| "step": 7 |
| }, |
| { |
| "entropy": 1.2547403424978256, |
| "epoch": 0.0512, |
| "grad_norm": 0.0511409156024456, |
| "learning_rate": 0.0002, |
| "loss": 1.1280027627944946, |
| "mean_token_accuracy": 0.6461542472243309, |
| "num_tokens": 300183.0, |
| "step": 8 |
| }, |
| { |
| "entropy": 1.1726891100406647, |
| "epoch": 0.0576, |
| "grad_norm": 0.05379360541701317, |
| "learning_rate": 0.0002, |
| "loss": 1.0599746704101562, |
| "mean_token_accuracy": 0.6579638719558716, |
| "num_tokens": 338051.0, |
| "step": 9 |
| }, |
| { |
| "entropy": 1.0671324282884598, |
| "epoch": 0.064, |
| "grad_norm": 0.060306161642074585, |
| "learning_rate": 0.0002, |
| "loss": 0.9810148477554321, |
| "mean_token_accuracy": 0.6758092492818832, |
| "num_tokens": 375360.0, |
| "step": 10 |
| }, |
| { |
| "entropy": 1.0067108944058418, |
| "epoch": 0.0704, |
| "grad_norm": 0.051368217915296555, |
| "learning_rate": 0.0002, |
| "loss": 0.9359661340713501, |
| "mean_token_accuracy": 0.6835062801837921, |
| "num_tokens": 412957.0, |
| "step": 11 |
| }, |
| { |
| "entropy": 0.9524737820029259, |
| "epoch": 0.0768, |
| "grad_norm": 0.5623471140861511, |
| "learning_rate": 0.0002, |
| "loss": 0.8969950675964355, |
| "mean_token_accuracy": 0.6872275173664093, |
| "num_tokens": 450706.0, |
| "step": 12 |
| }, |
| { |
| "entropy": 0.9274985566735268, |
| "epoch": 0.0832, |
| "grad_norm": 0.05319288372993469, |
| "learning_rate": 0.0002, |
| "loss": 0.8793208599090576, |
| "mean_token_accuracy": 0.6885223314166069, |
| "num_tokens": 487960.0, |
| "step": 13 |
| }, |
| { |
| "entropy": 0.8979481309652328, |
| "epoch": 0.0896, |
| "grad_norm": 0.21191297471523285, |
| "learning_rate": 0.0002, |
| "loss": 0.8658405542373657, |
| "mean_token_accuracy": 0.6915783286094666, |
| "num_tokens": 525195.0, |
| "step": 14 |
| }, |
| { |
| "entropy": 0.8346997126936913, |
| "epoch": 0.096, |
| "grad_norm": 0.05889149382710457, |
| "learning_rate": 0.0002, |
| "loss": 0.8389202356338501, |
| "mean_token_accuracy": 0.6947608664631844, |
| "num_tokens": 562338.0, |
| "step": 15 |
| }, |
| { |
| "entropy": 0.8163095191121101, |
| "epoch": 0.1024, |
| "grad_norm": 0.04048901051282883, |
| "learning_rate": 0.0002, |
| "loss": 0.8089202642440796, |
| "mean_token_accuracy": 0.7007258981466293, |
| "num_tokens": 600135.0, |
| "step": 16 |
| }, |
| { |
| "entropy": 0.7877696678042412, |
| "epoch": 0.1088, |
| "grad_norm": 0.039190541952848434, |
| "learning_rate": 0.0002, |
| "loss": 0.7770611047744751, |
| "mean_token_accuracy": 0.7096988186240196, |
| "num_tokens": 637693.0, |
| "step": 17 |
| }, |
| { |
| "entropy": 0.7828011736273766, |
| "epoch": 0.1152, |
| "grad_norm": 0.04370075836777687, |
| "learning_rate": 0.0002, |
| "loss": 0.7714797258377075, |
| "mean_token_accuracy": 0.7088576778769493, |
| "num_tokens": 675327.0, |
| "step": 18 |
| }, |
| { |
| "entropy": 0.7552840113639832, |
| "epoch": 0.1216, |
| "grad_norm": 0.04059312492609024, |
| "learning_rate": 0.0002, |
| "loss": 0.7444543838500977, |
| "mean_token_accuracy": 0.7163014858961105, |
| "num_tokens": 712985.0, |
| "step": 19 |
| }, |
| { |
| "entropy": 0.7549928575754166, |
| "epoch": 0.128, |
| "grad_norm": 0.03694331273436546, |
| "learning_rate": 0.0002, |
| "loss": 0.7338740229606628, |
| "mean_token_accuracy": 0.7175227254629135, |
| "num_tokens": 750710.0, |
| "step": 20 |
| }, |
| { |
| "entropy": 0.7592482566833496, |
| "epoch": 0.1344, |
| "grad_norm": 0.04042579606175423, |
| "learning_rate": 0.0002, |
| "loss": 0.7357518076896667, |
| "mean_token_accuracy": 0.7131277471780777, |
| "num_tokens": 788255.0, |
| "step": 21 |
| }, |
| { |
| "entropy": 0.7549540996551514, |
| "epoch": 0.1408, |
| "grad_norm": 0.03494592010974884, |
| "learning_rate": 0.0002, |
| "loss": 0.7316156625747681, |
| "mean_token_accuracy": 0.7107274830341339, |
| "num_tokens": 826086.0, |
| "step": 22 |
| }, |
| { |
| "entropy": 0.722670815885067, |
| "epoch": 0.1472, |
| "grad_norm": 0.031072545796632767, |
| "learning_rate": 0.0002, |
| "loss": 0.7062587738037109, |
| "mean_token_accuracy": 0.7226787135004997, |
| "num_tokens": 864023.0, |
| "step": 23 |
| }, |
| { |
| "entropy": 0.7071146741509438, |
| "epoch": 0.1536, |
| "grad_norm": 0.03113628178834915, |
| "learning_rate": 0.0002, |
| "loss": 0.7100369334220886, |
| "mean_token_accuracy": 0.7202128395438194, |
| "num_tokens": 901749.0, |
| "step": 24 |
| }, |
| { |
| "entropy": 0.6773204877972603, |
| "epoch": 0.16, |
| "grad_norm": 0.03384184464812279, |
| "learning_rate": 0.0002, |
| "loss": 0.6899121999740601, |
| "mean_token_accuracy": 0.7300205677747726, |
| "num_tokens": 939298.0, |
| "step": 25 |
| }, |
| { |
| "entropy": 0.6714279726147652, |
| "epoch": 0.1664, |
| "grad_norm": 0.03193815425038338, |
| "learning_rate": 0.0002, |
| "loss": 0.6869939565658569, |
| "mean_token_accuracy": 0.7289758324623108, |
| "num_tokens": 976724.0, |
| "step": 26 |
| }, |
| { |
| "entropy": 0.6800564154982567, |
| "epoch": 0.1728, |
| "grad_norm": 0.02955479919910431, |
| "learning_rate": 0.0002, |
| "loss": 0.68382728099823, |
| "mean_token_accuracy": 0.729714535176754, |
| "num_tokens": 1013951.0, |
| "step": 27 |
| }, |
| { |
| "entropy": 0.6879034861922264, |
| "epoch": 0.1792, |
| "grad_norm": 0.025940844789147377, |
| "learning_rate": 0.0002, |
| "loss": 0.6867204904556274, |
| "mean_token_accuracy": 0.7293097972869873, |
| "num_tokens": 1051525.0, |
| "step": 28 |
| }, |
| { |
| "entropy": 0.6878452003002167, |
| "epoch": 0.1856, |
| "grad_norm": 0.02489350363612175, |
| "learning_rate": 0.0002, |
| "loss": 0.6796096563339233, |
| "mean_token_accuracy": 0.7287048920989037, |
| "num_tokens": 1089369.0, |
| "step": 29 |
| }, |
| { |
| "entropy": 0.6869403198361397, |
| "epoch": 0.192, |
| "grad_norm": 0.025337131693959236, |
| "learning_rate": 0.0002, |
| "loss": 0.678722620010376, |
| "mean_token_accuracy": 0.7302690520882607, |
| "num_tokens": 1126844.0, |
| "step": 30 |
| }, |
| { |
| "entropy": 0.6806962639093399, |
| "epoch": 0.1984, |
| "grad_norm": 0.02659286931157112, |
| "learning_rate": 0.0002, |
| "loss": 0.6713651418685913, |
| "mean_token_accuracy": 0.7335517108440399, |
| "num_tokens": 1164699.0, |
| "step": 31 |
| }, |
| { |
| "entropy": 0.676600731909275, |
| "epoch": 0.2048, |
| "grad_norm": 0.024583281949162483, |
| "learning_rate": 0.0002, |
| "loss": 0.674942135810852, |
| "mean_token_accuracy": 0.7303079515695572, |
| "num_tokens": 1201884.0, |
| "step": 32 |
| }, |
| { |
| "entropy": 0.6764877885580063, |
| "epoch": 0.2112, |
| "grad_norm": 0.019307173788547516, |
| "learning_rate": 0.0002, |
| "loss": 0.6733279228210449, |
| "mean_token_accuracy": 0.732945054769516, |
| "num_tokens": 1239141.0, |
| "step": 33 |
| }, |
| { |
| "entropy": 0.6605517789721489, |
| "epoch": 0.2176, |
| "grad_norm": 0.020387521013617516, |
| "learning_rate": 0.0002, |
| "loss": 0.6627103090286255, |
| "mean_token_accuracy": 0.737023763358593, |
| "num_tokens": 1276671.0, |
| "step": 34 |
| }, |
| { |
| "entropy": 0.6582437306642532, |
| "epoch": 0.224, |
| "grad_norm": 0.020866557955741882, |
| "learning_rate": 0.0002, |
| "loss": 0.666618824005127, |
| "mean_token_accuracy": 0.7362421080470085, |
| "num_tokens": 1314330.0, |
| "step": 35 |
| }, |
| { |
| "entropy": 0.6579794958233833, |
| "epoch": 0.2304, |
| "grad_norm": 0.01998458243906498, |
| "learning_rate": 0.0002, |
| "loss": 0.6648584008216858, |
| "mean_token_accuracy": 0.7348862290382385, |
| "num_tokens": 1351870.0, |
| "step": 36 |
| }, |
| { |
| "entropy": 0.6570402011275291, |
| "epoch": 0.2368, |
| "grad_norm": 0.021064545959234238, |
| "learning_rate": 0.0002, |
| "loss": 0.666895866394043, |
| "mean_token_accuracy": 0.7330928146839142, |
| "num_tokens": 1389586.0, |
| "step": 37 |
| }, |
| { |
| "entropy": 0.6450310498476028, |
| "epoch": 0.2432, |
| "grad_norm": 0.02274121530354023, |
| "learning_rate": 0.0002, |
| "loss": 0.6487395763397217, |
| "mean_token_accuracy": 0.7399148046970367, |
| "num_tokens": 1427289.0, |
| "step": 38 |
| }, |
| { |
| "entropy": 0.6655421927571297, |
| "epoch": 0.2496, |
| "grad_norm": 0.019761748611927032, |
| "learning_rate": 0.0002, |
| "loss": 0.6655306816101074, |
| "mean_token_accuracy": 0.7331964820623398, |
| "num_tokens": 1464754.0, |
| "step": 39 |
| }, |
| { |
| "entropy": 0.6678934022784233, |
| "epoch": 0.256, |
| "grad_norm": 0.020196782425045967, |
| "learning_rate": 0.0002, |
| "loss": 0.6606800556182861, |
| "mean_token_accuracy": 0.7348242327570915, |
| "num_tokens": 1502466.0, |
| "step": 40 |
| }, |
| { |
| "entropy": 0.6633569970726967, |
| "epoch": 0.2624, |
| "grad_norm": 0.01856420934200287, |
| "learning_rate": 0.0002, |
| "loss": 0.6598410606384277, |
| "mean_token_accuracy": 0.7345370575785637, |
| "num_tokens": 1539911.0, |
| "step": 41 |
| }, |
| { |
| "entropy": 0.6672858148813248, |
| "epoch": 0.2688, |
| "grad_norm": 0.019625825807452202, |
| "learning_rate": 0.0002, |
| "loss": 0.6584136486053467, |
| "mean_token_accuracy": 0.7353677749633789, |
| "num_tokens": 1577459.0, |
| "step": 42 |
| }, |
| { |
| "entropy": 0.6759661063551903, |
| "epoch": 0.2752, |
| "grad_norm": 0.019913548603653908, |
| "learning_rate": 0.0002, |
| "loss": 0.6726773977279663, |
| "mean_token_accuracy": 0.729034997522831, |
| "num_tokens": 1615462.0, |
| "step": 43 |
| }, |
| { |
| "entropy": 0.6660498529672623, |
| "epoch": 0.2816, |
| "grad_norm": 0.014487133361399174, |
| "learning_rate": 0.0002, |
| "loss": 0.6681607961654663, |
| "mean_token_accuracy": 0.7323712110519409, |
| "num_tokens": 1652949.0, |
| "step": 44 |
| }, |
| { |
| "entropy": 0.6481832191348076, |
| "epoch": 0.288, |
| "grad_norm": 0.01776648312807083, |
| "learning_rate": 0.0002, |
| "loss": 0.6530840396881104, |
| "mean_token_accuracy": 0.7379923015832901, |
| "num_tokens": 1690313.0, |
| "step": 45 |
| }, |
| { |
| "entropy": 0.6430671736598015, |
| "epoch": 0.2944, |
| "grad_norm": 0.018955176696181297, |
| "learning_rate": 0.0002, |
| "loss": 0.6464742422103882, |
| "mean_token_accuracy": 0.7409427240490913, |
| "num_tokens": 1727486.0, |
| "step": 46 |
| }, |
| { |
| "entropy": 0.6565458923578262, |
| "epoch": 0.3008, |
| "grad_norm": 0.015031078830361366, |
| "learning_rate": 0.0002, |
| "loss": 0.6587884426116943, |
| "mean_token_accuracy": 0.7355991005897522, |
| "num_tokens": 1765413.0, |
| "step": 47 |
| }, |
| { |
| "entropy": 0.6365433260798454, |
| "epoch": 0.3072, |
| "grad_norm": 0.017183614894747734, |
| "learning_rate": 0.0002, |
| "loss": 0.6374931335449219, |
| "mean_token_accuracy": 0.7455704137682915, |
| "num_tokens": 1803010.0, |
| "step": 48 |
| }, |
| { |
| "entropy": 0.6563282832503319, |
| "epoch": 0.3136, |
| "grad_norm": 0.01428211573511362, |
| "learning_rate": 0.0002, |
| "loss": 0.6553747057914734, |
| "mean_token_accuracy": 0.7369147315621376, |
| "num_tokens": 1840622.0, |
| "step": 49 |
| }, |
| { |
| "entropy": 0.6499469205737114, |
| "epoch": 0.32, |
| "grad_norm": 0.01203683577477932, |
| "learning_rate": 0.0002, |
| "loss": 0.6548190116882324, |
| "mean_token_accuracy": 0.736673392355442, |
| "num_tokens": 1877938.0, |
| "step": 50 |
| }, |
| { |
| "entropy": 0.6385157108306885, |
| "epoch": 0.3264, |
| "grad_norm": 0.013347586616873741, |
| "learning_rate": 0.0002, |
| "loss": 0.6381226778030396, |
| "mean_token_accuracy": 0.7450113892555237, |
| "num_tokens": 1915406.0, |
| "step": 51 |
| }, |
| { |
| "entropy": 0.6538697853684425, |
| "epoch": 0.3328, |
| "grad_norm": 0.012674320489168167, |
| "learning_rate": 0.0002, |
| "loss": 0.6501171588897705, |
| "mean_token_accuracy": 0.739890843629837, |
| "num_tokens": 1952912.0, |
| "step": 52 |
| }, |
| { |
| "entropy": 0.6603258103132248, |
| "epoch": 0.3392, |
| "grad_norm": 0.01250320952385664, |
| "learning_rate": 0.0002, |
| "loss": 0.6589174270629883, |
| "mean_token_accuracy": 0.7365714758634567, |
| "num_tokens": 1990472.0, |
| "step": 53 |
| }, |
| { |
| "entropy": 0.656892940402031, |
| "epoch": 0.3456, |
| "grad_norm": 0.01285612117499113, |
| "learning_rate": 0.0002, |
| "loss": 0.6544902324676514, |
| "mean_token_accuracy": 0.7372777089476585, |
| "num_tokens": 2028004.0, |
| "step": 54 |
| }, |
| { |
| "entropy": 0.6557554453611374, |
| "epoch": 0.352, |
| "grad_norm": 0.013015029951930046, |
| "learning_rate": 0.0002, |
| "loss": 0.6539305448532104, |
| "mean_token_accuracy": 0.7372152432799339, |
| "num_tokens": 2065450.0, |
| "step": 55 |
| }, |
| { |
| "entropy": 0.6432914957404137, |
| "epoch": 0.3584, |
| "grad_norm": 0.01194705069065094, |
| "learning_rate": 0.0002, |
| "loss": 0.6476873755455017, |
| "mean_token_accuracy": 0.7385553196072578, |
| "num_tokens": 2103001.0, |
| "step": 56 |
| }, |
| { |
| "entropy": 0.665123961865902, |
| "epoch": 0.3648, |
| "grad_norm": 0.014306853525340557, |
| "learning_rate": 0.0002, |
| "loss": 0.6692231893539429, |
| "mean_token_accuracy": 0.7308292016386986, |
| "num_tokens": 2140766.0, |
| "step": 57 |
| }, |
| { |
| "entropy": 0.6395360752940178, |
| "epoch": 0.3712, |
| "grad_norm": 0.012413417920470238, |
| "learning_rate": 0.0002, |
| "loss": 0.6425060033798218, |
| "mean_token_accuracy": 0.7416690960526466, |
| "num_tokens": 2178215.0, |
| "step": 58 |
| }, |
| { |
| "entropy": 0.6377176344394684, |
| "epoch": 0.3776, |
| "grad_norm": 0.011347637511789799, |
| "learning_rate": 0.0002, |
| "loss": 0.6416236162185669, |
| "mean_token_accuracy": 0.7413541078567505, |
| "num_tokens": 2215834.0, |
| "step": 59 |
| }, |
| { |
| "entropy": 0.6470205709338188, |
| "epoch": 0.384, |
| "grad_norm": 0.013059594668447971, |
| "learning_rate": 0.0002, |
| "loss": 0.6504924297332764, |
| "mean_token_accuracy": 0.7374131381511688, |
| "num_tokens": 2253236.0, |
| "step": 60 |
| }, |
| { |
| "entropy": 0.6510438621044159, |
| "epoch": 0.3904, |
| "grad_norm": 0.010343637317419052, |
| "learning_rate": 0.0002, |
| "loss": 0.6483369469642639, |
| "mean_token_accuracy": 0.7396193742752075, |
| "num_tokens": 2290556.0, |
| "step": 61 |
| }, |
| { |
| "entropy": 0.6448361873626709, |
| "epoch": 0.3968, |
| "grad_norm": 0.01215020939707756, |
| "learning_rate": 0.0002, |
| "loss": 0.6442714929580688, |
| "mean_token_accuracy": 0.7406364679336548, |
| "num_tokens": 2327838.0, |
| "step": 62 |
| }, |
| { |
| "entropy": 0.6578632816672325, |
| "epoch": 0.4032, |
| "grad_norm": 0.013611266389489174, |
| "learning_rate": 0.0002, |
| "loss": 0.650489330291748, |
| "mean_token_accuracy": 0.737756036221981, |
| "num_tokens": 2365216.0, |
| "step": 63 |
| }, |
| { |
| "entropy": 0.6599203571677208, |
| "epoch": 0.4096, |
| "grad_norm": 0.013333442620933056, |
| "learning_rate": 0.0002, |
| "loss": 0.6547380089759827, |
| "mean_token_accuracy": 0.7386084869503975, |
| "num_tokens": 2403044.0, |
| "step": 64 |
| }, |
| { |
| "entropy": 0.6421995609998703, |
| "epoch": 0.416, |
| "grad_norm": 0.013022989965975285, |
| "learning_rate": 0.0002, |
| "loss": 0.6451696157455444, |
| "mean_token_accuracy": 0.7419813498854637, |
| "num_tokens": 2440509.0, |
| "step": 65 |
| }, |
| { |
| "entropy": 0.6482381522655487, |
| "epoch": 0.4224, |
| "grad_norm": 0.011019188910722733, |
| "learning_rate": 0.0002, |
| "loss": 0.6525042057037354, |
| "mean_token_accuracy": 0.7360658198595047, |
| "num_tokens": 2477977.0, |
| "step": 66 |
| }, |
| { |
| "entropy": 0.6513727456331253, |
| "epoch": 0.4288, |
| "grad_norm": 0.011377367191016674, |
| "learning_rate": 0.0002, |
| "loss": 0.6533432006835938, |
| "mean_token_accuracy": 0.7368385717272758, |
| "num_tokens": 2515504.0, |
| "step": 67 |
| }, |
| { |
| "entropy": 0.6338299661874771, |
| "epoch": 0.4352, |
| "grad_norm": 0.012209996581077576, |
| "learning_rate": 0.0002, |
| "loss": 0.6345840692520142, |
| "mean_token_accuracy": 0.7449672818183899, |
| "num_tokens": 2552725.0, |
| "step": 68 |
| }, |
| { |
| "entropy": 0.6595024093985558, |
| "epoch": 0.4416, |
| "grad_norm": 0.011869995854794979, |
| "learning_rate": 0.0002, |
| "loss": 0.6633318066596985, |
| "mean_token_accuracy": 0.7312925457954407, |
| "num_tokens": 2590334.0, |
| "step": 69 |
| }, |
| { |
| "entropy": 0.6419216245412827, |
| "epoch": 0.448, |
| "grad_norm": 0.011688044294714928, |
| "learning_rate": 0.0002, |
| "loss": 0.6422508955001831, |
| "mean_token_accuracy": 0.7409501895308495, |
| "num_tokens": 2628114.0, |
| "step": 70 |
| }, |
| { |
| "entropy": 0.6486918181180954, |
| "epoch": 0.4544, |
| "grad_norm": 0.012189529836177826, |
| "learning_rate": 0.0002, |
| "loss": 0.6435794830322266, |
| "mean_token_accuracy": 0.7398836389183998, |
| "num_tokens": 2665938.0, |
| "step": 71 |
| }, |
| { |
| "entropy": 0.6421536579728127, |
| "epoch": 0.4608, |
| "grad_norm": 0.01274161972105503, |
| "learning_rate": 0.0002, |
| "loss": 0.639503538608551, |
| "mean_token_accuracy": 0.7419992312788963, |
| "num_tokens": 2703327.0, |
| "step": 72 |
| }, |
| { |
| "entropy": 0.6552243158221245, |
| "epoch": 0.4672, |
| "grad_norm": 0.011226268485188484, |
| "learning_rate": 0.0002, |
| "loss": 0.6587808132171631, |
| "mean_token_accuracy": 0.7335348948836327, |
| "num_tokens": 2740612.0, |
| "step": 73 |
| }, |
| { |
| "entropy": 0.6495375782251358, |
| "epoch": 0.4736, |
| "grad_norm": 0.01099670771509409, |
| "learning_rate": 0.0002, |
| "loss": 0.6522738933563232, |
| "mean_token_accuracy": 0.7379574105143547, |
| "num_tokens": 2778351.0, |
| "step": 74 |
| }, |
| { |
| "entropy": 0.6299872100353241, |
| "epoch": 0.48, |
| "grad_norm": 0.011653655208647251, |
| "learning_rate": 0.0002, |
| "loss": 0.635120153427124, |
| "mean_token_accuracy": 0.7442547604441643, |
| "num_tokens": 2815733.0, |
| "step": 75 |
| }, |
| { |
| "entropy": 0.646803118288517, |
| "epoch": 0.4864, |
| "grad_norm": 0.011539405211806297, |
| "learning_rate": 0.0002, |
| "loss": 0.6486905813217163, |
| "mean_token_accuracy": 0.7385760024189949, |
| "num_tokens": 2853606.0, |
| "step": 76 |
| }, |
| { |
| "entropy": 0.6475054696202278, |
| "epoch": 0.4928, |
| "grad_norm": 0.011377925053238869, |
| "learning_rate": 0.0002, |
| "loss": 0.6478685140609741, |
| "mean_token_accuracy": 0.7385416328907013, |
| "num_tokens": 2891146.0, |
| "step": 77 |
| }, |
| { |
| "entropy": 0.6380101665854454, |
| "epoch": 0.4992, |
| "grad_norm": 0.011224031448364258, |
| "learning_rate": 0.0002, |
| "loss": 0.6410291194915771, |
| "mean_token_accuracy": 0.7412817031145096, |
| "num_tokens": 2928562.0, |
| "step": 78 |
| }, |
| { |
| "entropy": 0.6493655145168304, |
| "epoch": 0.5056, |
| "grad_norm": 0.010403023101389408, |
| "learning_rate": 0.0002, |
| "loss": 0.6491314768791199, |
| "mean_token_accuracy": 0.7371294796466827, |
| "num_tokens": 2966281.0, |
| "step": 79 |
| }, |
| { |
| "entropy": 0.6337103247642517, |
| "epoch": 0.512, |
| "grad_norm": 0.012346550822257996, |
| "learning_rate": 0.0002, |
| "loss": 0.6318129301071167, |
| "mean_token_accuracy": 0.7457293793559074, |
| "num_tokens": 3003719.0, |
| "step": 80 |
| }, |
| { |
| "entropy": 0.6503832414746284, |
| "epoch": 0.5184, |
| "grad_norm": 0.012706570327281952, |
| "learning_rate": 0.0002, |
| "loss": 0.6492017507553101, |
| "mean_token_accuracy": 0.7375014126300812, |
| "num_tokens": 3041261.0, |
| "step": 81 |
| }, |
| { |
| "entropy": 0.6609693467617035, |
| "epoch": 0.5248, |
| "grad_norm": 0.010637188330292702, |
| "learning_rate": 0.0002, |
| "loss": 0.6600979566574097, |
| "mean_token_accuracy": 0.7335498854517937, |
| "num_tokens": 3078968.0, |
| "step": 82 |
| }, |
| { |
| "entropy": 0.6473255082964897, |
| "epoch": 0.5312, |
| "grad_norm": 0.01124926470220089, |
| "learning_rate": 0.0002, |
| "loss": 0.6503981351852417, |
| "mean_token_accuracy": 0.7380518168210983, |
| "num_tokens": 3116811.0, |
| "step": 83 |
| }, |
| { |
| "entropy": 0.6533865705132484, |
| "epoch": 0.5376, |
| "grad_norm": 0.012132731266319752, |
| "learning_rate": 0.0002, |
| "loss": 0.6592696309089661, |
| "mean_token_accuracy": 0.733529195189476, |
| "num_tokens": 3154474.0, |
| "step": 84 |
| }, |
| { |
| "entropy": 0.639193020761013, |
| "epoch": 0.544, |
| "grad_norm": 0.011734750121831894, |
| "learning_rate": 0.0002, |
| "loss": 0.6403356790542603, |
| "mean_token_accuracy": 0.7433002889156342, |
| "num_tokens": 3192006.0, |
| "step": 85 |
| }, |
| { |
| "entropy": 0.6401269435882568, |
| "epoch": 0.5504, |
| "grad_norm": 0.010875481180846691, |
| "learning_rate": 0.0002, |
| "loss": 0.6439944505691528, |
| "mean_token_accuracy": 0.7402178049087524, |
| "num_tokens": 3229461.0, |
| "step": 86 |
| }, |
| { |
| "entropy": 0.6467242240905762, |
| "epoch": 0.5568, |
| "grad_norm": 0.01122159045189619, |
| "learning_rate": 0.0002, |
| "loss": 0.65086829662323, |
| "mean_token_accuracy": 0.7366317883133888, |
| "num_tokens": 3266854.0, |
| "step": 87 |
| }, |
| { |
| "entropy": 0.6459343954920769, |
| "epoch": 0.5632, |
| "grad_norm": 0.01132342778146267, |
| "learning_rate": 0.0002, |
| "loss": 0.6473137140274048, |
| "mean_token_accuracy": 0.7397668585181236, |
| "num_tokens": 3304594.0, |
| "step": 88 |
| }, |
| { |
| "entropy": 0.6517693251371384, |
| "epoch": 0.5696, |
| "grad_norm": 0.01150190457701683, |
| "learning_rate": 0.0002, |
| "loss": 0.647284746170044, |
| "mean_token_accuracy": 0.7392672076821327, |
| "num_tokens": 3341878.0, |
| "step": 89 |
| }, |
| { |
| "entropy": 0.6644957289099693, |
| "epoch": 0.576, |
| "grad_norm": 0.011668134480714798, |
| "learning_rate": 0.0002, |
| "loss": 0.6594465970993042, |
| "mean_token_accuracy": 0.7339938580989838, |
| "num_tokens": 3379626.0, |
| "step": 90 |
| }, |
| { |
| "entropy": 0.6448649242520332, |
| "epoch": 0.5824, |
| "grad_norm": 0.012058609165251255, |
| "learning_rate": 0.0002, |
| "loss": 0.6404842734336853, |
| "mean_token_accuracy": 0.7406293153762817, |
| "num_tokens": 3417230.0, |
| "step": 91 |
| }, |
| { |
| "entropy": 0.6402811780571938, |
| "epoch": 0.5888, |
| "grad_norm": 0.011592954397201538, |
| "learning_rate": 0.0002, |
| "loss": 0.6447786092758179, |
| "mean_token_accuracy": 0.7402076348662376, |
| "num_tokens": 3454690.0, |
| "step": 92 |
| }, |
| { |
| "entropy": 0.6428509131073952, |
| "epoch": 0.5952, |
| "grad_norm": 0.012272155843675137, |
| "learning_rate": 0.0002, |
| "loss": 0.6479693651199341, |
| "mean_token_accuracy": 0.7390052601695061, |
| "num_tokens": 3492182.0, |
| "step": 93 |
| }, |
| { |
| "entropy": 0.6426275372505188, |
| "epoch": 0.6016, |
| "grad_norm": 0.01083293091505766, |
| "learning_rate": 0.0002, |
| "loss": 0.644639253616333, |
| "mean_token_accuracy": 0.740093432366848, |
| "num_tokens": 3530068.0, |
| "step": 94 |
| }, |
| { |
| "entropy": 0.626714438199997, |
| "epoch": 0.608, |
| "grad_norm": 0.010761498473584652, |
| "learning_rate": 0.0002, |
| "loss": 0.628358006477356, |
| "mean_token_accuracy": 0.746553897857666, |
| "num_tokens": 3567305.0, |
| "step": 95 |
| }, |
| { |
| "entropy": 0.6431040018796921, |
| "epoch": 0.6144, |
| "grad_norm": 0.012162288650870323, |
| "learning_rate": 0.0002, |
| "loss": 0.6470193862915039, |
| "mean_token_accuracy": 0.7389233484864235, |
| "num_tokens": 3604807.0, |
| "step": 96 |
| }, |
| { |
| "entropy": 0.645052507519722, |
| "epoch": 0.6208, |
| "grad_norm": 0.010187218897044659, |
| "learning_rate": 0.0002, |
| "loss": 0.6489447951316833, |
| "mean_token_accuracy": 0.738676629960537, |
| "num_tokens": 3642594.0, |
| "step": 97 |
| }, |
| { |
| "entropy": 0.6390751749277115, |
| "epoch": 0.6272, |
| "grad_norm": 0.01165873184800148, |
| "learning_rate": 0.0002, |
| "loss": 0.643662691116333, |
| "mean_token_accuracy": 0.7390685454010963, |
| "num_tokens": 3680543.0, |
| "step": 98 |
| }, |
| { |
| "entropy": 0.6514940857887268, |
| "epoch": 0.6336, |
| "grad_norm": 0.010981060564517975, |
| "learning_rate": 0.0002, |
| "loss": 0.6510151624679565, |
| "mean_token_accuracy": 0.7382907196879387, |
| "num_tokens": 3717970.0, |
| "step": 99 |
| }, |
| { |
| "entropy": 0.6472062841057777, |
| "epoch": 0.64, |
| "grad_norm": 0.012016931548714638, |
| "learning_rate": 0.0002, |
| "loss": 0.6510175466537476, |
| "mean_token_accuracy": 0.7374041378498077, |
| "num_tokens": 3755566.0, |
| "step": 100 |
| }, |
| { |
| "entropy": 0.6526609882712364, |
| "epoch": 0.6464, |
| "grad_norm": 0.010779659263789654, |
| "learning_rate": 0.0002, |
| "loss": 0.6495513916015625, |
| "mean_token_accuracy": 0.7356445118784904, |
| "num_tokens": 3793159.0, |
| "step": 101 |
| }, |
| { |
| "entropy": 0.6481966897845268, |
| "epoch": 0.6528, |
| "grad_norm": 0.010695680044591427, |
| "learning_rate": 0.0002, |
| "loss": 0.6442012786865234, |
| "mean_token_accuracy": 0.7392323464155197, |
| "num_tokens": 3830925.0, |
| "step": 102 |
| }, |
| { |
| "entropy": 0.6423428729176521, |
| "epoch": 0.6592, |
| "grad_norm": 0.009773760102689266, |
| "learning_rate": 0.0002, |
| "loss": 0.6454004049301147, |
| "mean_token_accuracy": 0.7405061349272728, |
| "num_tokens": 3868672.0, |
| "step": 103 |
| }, |
| { |
| "entropy": 0.6281508877873421, |
| "epoch": 0.6656, |
| "grad_norm": 0.01067226193845272, |
| "learning_rate": 0.0002, |
| "loss": 0.6323127150535583, |
| "mean_token_accuracy": 0.743611678481102, |
| "num_tokens": 3905993.0, |
| "step": 104 |
| }, |
| { |
| "entropy": 0.6415385156869888, |
| "epoch": 0.672, |
| "grad_norm": 0.01100232359021902, |
| "learning_rate": 0.0002, |
| "loss": 0.6450967192649841, |
| "mean_token_accuracy": 0.741372749209404, |
| "num_tokens": 3943387.0, |
| "step": 105 |
| }, |
| { |
| "entropy": 0.6479355171322823, |
| "epoch": 0.6784, |
| "grad_norm": 0.011068901047110558, |
| "learning_rate": 0.0002, |
| "loss": 0.6533315777778625, |
| "mean_token_accuracy": 0.7338352426886559, |
| "num_tokens": 3981143.0, |
| "step": 106 |
| }, |
| { |
| "entropy": 0.6498983204364777, |
| "epoch": 0.6848, |
| "grad_norm": 0.010501043871045113, |
| "learning_rate": 0.0002, |
| "loss": 0.6492184400558472, |
| "mean_token_accuracy": 0.7377433255314827, |
| "num_tokens": 4018874.0, |
| "step": 107 |
| }, |
| { |
| "entropy": 0.6513847932219505, |
| "epoch": 0.6912, |
| "grad_norm": 0.012076501734554768, |
| "learning_rate": 0.0002, |
| "loss": 0.6527359485626221, |
| "mean_token_accuracy": 0.7364412918686867, |
| "num_tokens": 4056434.0, |
| "step": 108 |
| }, |
| { |
| "entropy": 0.6415090262889862, |
| "epoch": 0.6976, |
| "grad_norm": 0.01073481049388647, |
| "learning_rate": 0.0002, |
| "loss": 0.6410619020462036, |
| "mean_token_accuracy": 0.740181528031826, |
| "num_tokens": 4094245.0, |
| "step": 109 |
| }, |
| { |
| "entropy": 0.6442006528377533, |
| "epoch": 0.704, |
| "grad_norm": 0.011465134099125862, |
| "learning_rate": 0.0002, |
| "loss": 0.6447471380233765, |
| "mean_token_accuracy": 0.7409348115324974, |
| "num_tokens": 4131358.0, |
| "step": 110 |
| }, |
| { |
| "entropy": 0.6425353735685349, |
| "epoch": 0.7104, |
| "grad_norm": 0.011008083820343018, |
| "learning_rate": 0.0002, |
| "loss": 0.6414906978607178, |
| "mean_token_accuracy": 0.7418420538306236, |
| "num_tokens": 4169051.0, |
| "step": 111 |
| }, |
| { |
| "entropy": 0.65395537763834, |
| "epoch": 0.7168, |
| "grad_norm": 0.010419737547636032, |
| "learning_rate": 0.0002, |
| "loss": 0.6524069309234619, |
| "mean_token_accuracy": 0.736035592854023, |
| "num_tokens": 4206785.0, |
| "step": 112 |
| }, |
| { |
| "entropy": 0.6436598747968674, |
| "epoch": 0.7232, |
| "grad_norm": 0.01072368398308754, |
| "learning_rate": 0.0002, |
| "loss": 0.646194338798523, |
| "mean_token_accuracy": 0.7391205802559853, |
| "num_tokens": 4243952.0, |
| "step": 113 |
| }, |
| { |
| "entropy": 0.6517779007554054, |
| "epoch": 0.7296, |
| "grad_norm": 0.010077660903334618, |
| "learning_rate": 0.0002, |
| "loss": 0.6503125429153442, |
| "mean_token_accuracy": 0.7375629469752312, |
| "num_tokens": 4281302.0, |
| "step": 114 |
| }, |
| { |
| "entropy": 0.6431594043970108, |
| "epoch": 0.736, |
| "grad_norm": 0.009454594925045967, |
| "learning_rate": 0.0002, |
| "loss": 0.647723913192749, |
| "mean_token_accuracy": 0.7380199134349823, |
| "num_tokens": 4318445.0, |
| "step": 115 |
| }, |
| { |
| "entropy": 0.6490769982337952, |
| "epoch": 0.7424, |
| "grad_norm": 0.010790850967168808, |
| "learning_rate": 0.0002, |
| "loss": 0.6519957780838013, |
| "mean_token_accuracy": 0.7370847165584564, |
| "num_tokens": 4356069.0, |
| "step": 116 |
| }, |
| { |
| "entropy": 0.6421378776431084, |
| "epoch": 0.7488, |
| "grad_norm": 0.011676953174173832, |
| "learning_rate": 0.0002, |
| "loss": 0.6456701755523682, |
| "mean_token_accuracy": 0.7384574711322784, |
| "num_tokens": 4393886.0, |
| "step": 117 |
| }, |
| { |
| "entropy": 0.6397042796015739, |
| "epoch": 0.7552, |
| "grad_norm": 0.009942916221916676, |
| "learning_rate": 0.0002, |
| "loss": 0.6421793699264526, |
| "mean_token_accuracy": 0.7401494830846786, |
| "num_tokens": 4431050.0, |
| "step": 118 |
| }, |
| { |
| "entropy": 0.6442151814699173, |
| "epoch": 0.7616, |
| "grad_norm": 0.010225712321698666, |
| "learning_rate": 0.0002, |
| "loss": 0.6509747505187988, |
| "mean_token_accuracy": 0.7365128919482231, |
| "num_tokens": 4468708.0, |
| "step": 119 |
| }, |
| { |
| "entropy": 0.6483751237392426, |
| "epoch": 0.768, |
| "grad_norm": 0.010288415476679802, |
| "learning_rate": 0.0002, |
| "loss": 0.6510953903198242, |
| "mean_token_accuracy": 0.7370466068387032, |
| "num_tokens": 4506387.0, |
| "step": 120 |
| }, |
| { |
| "entropy": 0.6402674838900566, |
| "epoch": 0.7744, |
| "grad_norm": 0.011825313791632652, |
| "learning_rate": 0.0002, |
| "loss": 0.6385786533355713, |
| "mean_token_accuracy": 0.7403052300214767, |
| "num_tokens": 4544227.0, |
| "step": 121 |
| }, |
| { |
| "entropy": 0.6531669348478317, |
| "epoch": 0.7808, |
| "grad_norm": 0.009835828095674515, |
| "learning_rate": 0.0002, |
| "loss": 0.6538360118865967, |
| "mean_token_accuracy": 0.73631202429533, |
| "num_tokens": 4581868.0, |
| "step": 122 |
| }, |
| { |
| "entropy": 0.6490024328231812, |
| "epoch": 0.7872, |
| "grad_norm": 0.01063550915569067, |
| "learning_rate": 0.0002, |
| "loss": 0.6501119136810303, |
| "mean_token_accuracy": 0.7366527765989304, |
| "num_tokens": 4619257.0, |
| "step": 123 |
| }, |
| { |
| "entropy": 0.6489348411560059, |
| "epoch": 0.7936, |
| "grad_norm": 0.009436458349227905, |
| "learning_rate": 0.0002, |
| "loss": 0.6502528786659241, |
| "mean_token_accuracy": 0.7353222295641899, |
| "num_tokens": 4656790.0, |
| "step": 124 |
| }, |
| { |
| "entropy": 0.6380393132567406, |
| "epoch": 0.8, |
| "grad_norm": 0.009827700443565845, |
| "learning_rate": 0.0002, |
| "loss": 0.640160322189331, |
| "mean_token_accuracy": 0.7403444275259972, |
| "num_tokens": 4694256.0, |
| "step": 125 |
| }, |
| { |
| "entropy": 0.6383800283074379, |
| "epoch": 0.8064, |
| "grad_norm": 0.009908480569720268, |
| "learning_rate": 0.0002, |
| "loss": 0.6422752737998962, |
| "mean_token_accuracy": 0.7412146180868149, |
| "num_tokens": 4731993.0, |
| "step": 126 |
| }, |
| { |
| "entropy": 0.6368249654769897, |
| "epoch": 0.8128, |
| "grad_norm": 0.011256285011768341, |
| "learning_rate": 0.0002, |
| "loss": 0.6375234723091125, |
| "mean_token_accuracy": 0.7389892339706421, |
| "num_tokens": 4769564.0, |
| "step": 127 |
| }, |
| { |
| "entropy": 0.6328444108366966, |
| "epoch": 0.8192, |
| "grad_norm": 0.009496535174548626, |
| "learning_rate": 0.0002, |
| "loss": 0.6372179985046387, |
| "mean_token_accuracy": 0.7419247180223465, |
| "num_tokens": 4807156.0, |
| "step": 128 |
| }, |
| { |
| "entropy": 0.6487380862236023, |
| "epoch": 0.8256, |
| "grad_norm": 0.010182644240558147, |
| "learning_rate": 0.0002, |
| "loss": 0.651898980140686, |
| "mean_token_accuracy": 0.7349159717559814, |
| "num_tokens": 4844688.0, |
| "step": 129 |
| }, |
| { |
| "entropy": 0.637291207909584, |
| "epoch": 0.832, |
| "grad_norm": 0.009813020937144756, |
| "learning_rate": 0.0002, |
| "loss": 0.6357983350753784, |
| "mean_token_accuracy": 0.7435917556285858, |
| "num_tokens": 4882067.0, |
| "step": 130 |
| }, |
| { |
| "entropy": 0.6475042626261711, |
| "epoch": 0.8384, |
| "grad_norm": 0.009938180446624756, |
| "learning_rate": 0.0002, |
| "loss": 0.6457779407501221, |
| "mean_token_accuracy": 0.7377768382430077, |
| "num_tokens": 4919683.0, |
| "step": 131 |
| }, |
| { |
| "entropy": 0.6361658647656441, |
| "epoch": 0.8448, |
| "grad_norm": 0.01157945767045021, |
| "learning_rate": 0.0002, |
| "loss": 0.6357731819152832, |
| "mean_token_accuracy": 0.7428592145442963, |
| "num_tokens": 4957344.0, |
| "step": 132 |
| }, |
| { |
| "entropy": 0.6509395390748978, |
| "epoch": 0.8512, |
| "grad_norm": 0.010125997476279736, |
| "learning_rate": 0.0002, |
| "loss": 0.6515601873397827, |
| "mean_token_accuracy": 0.7356820181012154, |
| "num_tokens": 4994764.0, |
| "step": 133 |
| }, |
| { |
| "entropy": 0.6364396661520004, |
| "epoch": 0.8576, |
| "grad_norm": 0.01021180022507906, |
| "learning_rate": 0.0002, |
| "loss": 0.6399521827697754, |
| "mean_token_accuracy": 0.7389387339353561, |
| "num_tokens": 5032302.0, |
| "step": 134 |
| }, |
| { |
| "entropy": 0.6350365057587624, |
| "epoch": 0.864, |
| "grad_norm": 0.010611058212816715, |
| "learning_rate": 0.0002, |
| "loss": 0.6368668675422668, |
| "mean_token_accuracy": 0.7429890111088753, |
| "num_tokens": 5069759.0, |
| "step": 135 |
| }, |
| { |
| "entropy": 0.6327914297580719, |
| "epoch": 0.8704, |
| "grad_norm": 0.009575539268553257, |
| "learning_rate": 0.0002, |
| "loss": 0.6354016065597534, |
| "mean_token_accuracy": 0.7427869364619255, |
| "num_tokens": 5107295.0, |
| "step": 136 |
| }, |
| { |
| "entropy": 0.6594432219862938, |
| "epoch": 0.8768, |
| "grad_norm": 0.00979944784194231, |
| "learning_rate": 0.0002, |
| "loss": 0.6595268249511719, |
| "mean_token_accuracy": 0.7346527501940727, |
| "num_tokens": 5145124.0, |
| "step": 137 |
| }, |
| { |
| "entropy": 0.6408862993121147, |
| "epoch": 0.8832, |
| "grad_norm": 0.011191108264029026, |
| "learning_rate": 0.0002, |
| "loss": 0.6428693532943726, |
| "mean_token_accuracy": 0.7407258599996567, |
| "num_tokens": 5182599.0, |
| "step": 138 |
| }, |
| { |
| "entropy": 0.6376849785447121, |
| "epoch": 0.8896, |
| "grad_norm": 0.010853955522179604, |
| "learning_rate": 0.0002, |
| "loss": 0.6410936713218689, |
| "mean_token_accuracy": 0.7405535206198692, |
| "num_tokens": 5220168.0, |
| "step": 139 |
| }, |
| { |
| "entropy": 0.6452121436595917, |
| "epoch": 0.896, |
| "grad_norm": 0.010287974961102009, |
| "learning_rate": 0.0002, |
| "loss": 0.6451249122619629, |
| "mean_token_accuracy": 0.7396348267793655, |
| "num_tokens": 5257986.0, |
| "step": 140 |
| }, |
| { |
| "entropy": 0.6390210688114166, |
| "epoch": 0.9024, |
| "grad_norm": 0.011026793159544468, |
| "learning_rate": 0.0002, |
| "loss": 0.644250750541687, |
| "mean_token_accuracy": 0.7396276742219925, |
| "num_tokens": 5295673.0, |
| "step": 141 |
| }, |
| { |
| "entropy": 0.6457666233181953, |
| "epoch": 0.9088, |
| "grad_norm": 0.00994186196476221, |
| "learning_rate": 0.0002, |
| "loss": 0.6455720663070679, |
| "mean_token_accuracy": 0.7386891022324562, |
| "num_tokens": 5333647.0, |
| "step": 142 |
| }, |
| { |
| "entropy": 0.6408794969320297, |
| "epoch": 0.9152, |
| "grad_norm": 0.011928732506930828, |
| "learning_rate": 0.0002, |
| "loss": 0.6402020454406738, |
| "mean_token_accuracy": 0.742262989282608, |
| "num_tokens": 5371718.0, |
| "step": 143 |
| }, |
| { |
| "entropy": 0.6543991938233376, |
| "epoch": 0.9216, |
| "grad_norm": 0.010643723420798779, |
| "learning_rate": 0.0002, |
| "loss": 0.6522170305252075, |
| "mean_token_accuracy": 0.735626682639122, |
| "num_tokens": 5409417.0, |
| "step": 144 |
| }, |
| { |
| "entropy": 0.6360428184270859, |
| "epoch": 0.928, |
| "grad_norm": 0.010354955680668354, |
| "learning_rate": 0.0002, |
| "loss": 0.633360743522644, |
| "mean_token_accuracy": 0.7439651861786842, |
| "num_tokens": 5447224.0, |
| "step": 145 |
| }, |
| { |
| "entropy": 0.6295241191983223, |
| "epoch": 0.9344, |
| "grad_norm": 0.009584055282175541, |
| "learning_rate": 0.0002, |
| "loss": 0.6330816745758057, |
| "mean_token_accuracy": 0.743884801864624, |
| "num_tokens": 5484456.0, |
| "step": 146 |
| }, |
| { |
| "entropy": 0.6305922344326973, |
| "epoch": 0.9408, |
| "grad_norm": 0.012600995600223541, |
| "learning_rate": 0.0002, |
| "loss": 0.6410214900970459, |
| "mean_token_accuracy": 0.7401221916079521, |
| "num_tokens": 5521974.0, |
| "step": 147 |
| }, |
| { |
| "entropy": 0.6405795589089394, |
| "epoch": 0.9472, |
| "grad_norm": 0.012624030001461506, |
| "learning_rate": 0.0002, |
| "loss": 0.6476458311080933, |
| "mean_token_accuracy": 0.7366938292980194, |
| "num_tokens": 5559577.0, |
| "step": 148 |
| }, |
| { |
| "entropy": 0.6548889800906181, |
| "epoch": 0.9536, |
| "grad_norm": 0.009168867953121662, |
| "learning_rate": 0.0002, |
| "loss": 0.6527200937271118, |
| "mean_token_accuracy": 0.7344470545649529, |
| "num_tokens": 5597209.0, |
| "step": 149 |
| }, |
| { |
| "entropy": 0.6553688123822212, |
| "epoch": 0.96, |
| "grad_norm": 0.011672625318169594, |
| "learning_rate": 0.0002, |
| "loss": 0.6522246599197388, |
| "mean_token_accuracy": 0.735475592315197, |
| "num_tokens": 5634927.0, |
| "step": 150 |
| }, |
| { |
| "entropy": 0.6557204276323318, |
| "epoch": 0.9664, |
| "grad_norm": 0.010263725183904171, |
| "learning_rate": 0.0002, |
| "loss": 0.6540011167526245, |
| "mean_token_accuracy": 0.7331173792481422, |
| "num_tokens": 5672469.0, |
| "step": 151 |
| }, |
| { |
| "entropy": 0.6292876526713371, |
| "epoch": 0.9728, |
| "grad_norm": 0.009562517516314983, |
| "learning_rate": 0.0002, |
| "loss": 0.6356937289237976, |
| "mean_token_accuracy": 0.7415798529982567, |
| "num_tokens": 5709851.0, |
| "step": 152 |
| }, |
| { |
| "entropy": 0.6344784423708916, |
| "epoch": 0.9792, |
| "grad_norm": 0.010696685872972012, |
| "learning_rate": 0.0002, |
| "loss": 0.6421383023262024, |
| "mean_token_accuracy": 0.7404361814260483, |
| "num_tokens": 5747183.0, |
| "step": 153 |
| }, |
| { |
| "entropy": 0.6344292610883713, |
| "epoch": 0.9856, |
| "grad_norm": 0.01072372030466795, |
| "learning_rate": 0.0002, |
| "loss": 0.6366742253303528, |
| "mean_token_accuracy": 0.7436658665537834, |
| "num_tokens": 5785030.0, |
| "step": 154 |
| }, |
| { |
| "entropy": 0.64640112221241, |
| "epoch": 0.992, |
| "grad_norm": 0.009201000444591045, |
| "learning_rate": 0.0002, |
| "loss": 0.6510665416717529, |
| "mean_token_accuracy": 0.7334160059690475, |
| "num_tokens": 5822675.0, |
| "step": 155 |
| }, |
| { |
| "entropy": 0.6349588707089424, |
| "epoch": 0.9984, |
| "grad_norm": 0.009053889662027359, |
| "learning_rate": 0.0002, |
| "loss": 0.6340664625167847, |
| "mean_token_accuracy": 0.743820808827877, |
| "num_tokens": 5860056.0, |
| "step": 156 |
| }, |
| { |
| "entropy": 0.6518890261650085, |
| "epoch": 1.0, |
| "grad_norm": 0.01602179929614067, |
| "learning_rate": 0.0002, |
| "loss": 0.6524105072021484, |
| "mean_token_accuracy": 0.7354754209518433, |
| "num_tokens": 5869314.0, |
| "step": 157 |
| }, |
| { |
| "entropy": 0.6527635008096695, |
| "epoch": 1.0064, |
| "grad_norm": 0.011629520915448666, |
| "learning_rate": 0.0002, |
| "loss": 0.648344099521637, |
| "mean_token_accuracy": 0.7363307550549507, |
| "num_tokens": 5907492.0, |
| "step": 158 |
| }, |
| { |
| "entropy": 0.6342032626271248, |
| "epoch": 1.0128, |
| "grad_norm": 0.009327917359769344, |
| "learning_rate": 0.0002, |
| "loss": 0.6365879774093628, |
| "mean_token_accuracy": 0.7422033324837685, |
| "num_tokens": 5945150.0, |
| "step": 159 |
| }, |
| { |
| "entropy": 0.6452426686882973, |
| "epoch": 1.0192, |
| "grad_norm": 0.009940714575350285, |
| "learning_rate": 0.0002, |
| "loss": 0.6485167741775513, |
| "mean_token_accuracy": 0.7388251274824142, |
| "num_tokens": 5983293.0, |
| "step": 160 |
| }, |
| { |
| "entropy": 0.6330019310116768, |
| "epoch": 1.0256, |
| "grad_norm": 0.010047292336821556, |
| "learning_rate": 0.0002, |
| "loss": 0.6353905200958252, |
| "mean_token_accuracy": 0.7421540543437004, |
| "num_tokens": 6020861.0, |
| "step": 161 |
| }, |
| { |
| "entropy": 0.6366018727421761, |
| "epoch": 1.032, |
| "grad_norm": 0.010758111253380775, |
| "learning_rate": 0.0002, |
| "loss": 0.6427363157272339, |
| "mean_token_accuracy": 0.7399178668856621, |
| "num_tokens": 6058895.0, |
| "step": 162 |
| }, |
| { |
| "entropy": 0.6386806666851044, |
| "epoch": 1.0384, |
| "grad_norm": 0.010479118674993515, |
| "learning_rate": 0.0002, |
| "loss": 0.6465561389923096, |
| "mean_token_accuracy": 0.7374918833374977, |
| "num_tokens": 6096481.0, |
| "step": 163 |
| }, |
| { |
| "entropy": 0.6303133890032768, |
| "epoch": 1.0448, |
| "grad_norm": 0.009492664597928524, |
| "learning_rate": 0.0002, |
| "loss": 0.6275724172592163, |
| "mean_token_accuracy": 0.7442837283015251, |
| "num_tokens": 6133720.0, |
| "step": 164 |
| }, |
| { |
| "entropy": 0.641479380428791, |
| "epoch": 1.0512, |
| "grad_norm": 0.011456873267889023, |
| "learning_rate": 0.0002, |
| "loss": 0.6362390518188477, |
| "mean_token_accuracy": 0.741039365530014, |
| "num_tokens": 6171551.0, |
| "step": 165 |
| }, |
| { |
| "entropy": 0.635175496339798, |
| "epoch": 1.0576, |
| "grad_norm": 0.009045133367180824, |
| "learning_rate": 0.0002, |
| "loss": 0.636081874370575, |
| "mean_token_accuracy": 0.7414724603295326, |
| "num_tokens": 6209178.0, |
| "step": 166 |
| }, |
| { |
| "entropy": 0.6251291632652283, |
| "epoch": 1.064, |
| "grad_norm": 0.013078802265226841, |
| "learning_rate": 0.0002, |
| "loss": 0.6349364519119263, |
| "mean_token_accuracy": 0.7421944439411163, |
| "num_tokens": 6246417.0, |
| "step": 167 |
| }, |
| { |
| "entropy": 0.6297666281461716, |
| "epoch": 1.0704, |
| "grad_norm": 0.011462744325399399, |
| "learning_rate": 0.0002, |
| "loss": 0.6320569515228271, |
| "mean_token_accuracy": 0.7444151639938354, |
| "num_tokens": 6284425.0, |
| "step": 168 |
| }, |
| { |
| "entropy": 0.6380733549594879, |
| "epoch": 1.0768, |
| "grad_norm": 0.009066379629075527, |
| "learning_rate": 0.0002, |
| "loss": 0.6397888660430908, |
| "mean_token_accuracy": 0.7402750551700592, |
| "num_tokens": 6321885.0, |
| "step": 169 |
| }, |
| { |
| "entropy": 0.6488857790827751, |
| "epoch": 1.0832, |
| "grad_norm": 0.010398726910352707, |
| "learning_rate": 0.0002, |
| "loss": 0.6441566944122314, |
| "mean_token_accuracy": 0.7384657263755798, |
| "num_tokens": 6359780.0, |
| "step": 170 |
| }, |
| { |
| "entropy": 0.6515408530831337, |
| "epoch": 1.0896, |
| "grad_norm": 0.011355352587997913, |
| "learning_rate": 0.0002, |
| "loss": 0.6486490964889526, |
| "mean_token_accuracy": 0.7374377101659775, |
| "num_tokens": 6397361.0, |
| "step": 171 |
| }, |
| { |
| "entropy": 0.6507275626063347, |
| "epoch": 1.096, |
| "grad_norm": 0.008314304985105991, |
| "learning_rate": 0.0002, |
| "loss": 0.6553799510002136, |
| "mean_token_accuracy": 0.7341008260846138, |
| "num_tokens": 6434762.0, |
| "step": 172 |
| }, |
| { |
| "entropy": 0.6377227902412415, |
| "epoch": 1.1024, |
| "grad_norm": 0.010710292495787144, |
| "learning_rate": 0.0002, |
| "loss": 0.647055983543396, |
| "mean_token_accuracy": 0.7381266057491302, |
| "num_tokens": 6472429.0, |
| "step": 173 |
| }, |
| { |
| "entropy": 0.6286719441413879, |
| "epoch": 1.1088, |
| "grad_norm": 0.010212961584329605, |
| "learning_rate": 0.0002, |
| "loss": 0.6336620450019836, |
| "mean_token_accuracy": 0.7432440966367722, |
| "num_tokens": 6509562.0, |
| "step": 174 |
| }, |
| { |
| "entropy": 0.633246898651123, |
| "epoch": 1.1152, |
| "grad_norm": 0.008904446847736835, |
| "learning_rate": 0.0002, |
| "loss": 0.634044885635376, |
| "mean_token_accuracy": 0.7444055899977684, |
| "num_tokens": 6547088.0, |
| "step": 175 |
| }, |
| { |
| "entropy": 0.6382523626089096, |
| "epoch": 1.1216, |
| "grad_norm": 0.010376264341175556, |
| "learning_rate": 0.0002, |
| "loss": 0.6372156143188477, |
| "mean_token_accuracy": 0.7388828843832016, |
| "num_tokens": 6584424.0, |
| "step": 176 |
| }, |
| { |
| "entropy": 0.6464436203241348, |
| "epoch": 1.1280000000000001, |
| "grad_norm": 0.011439846828579903, |
| "learning_rate": 0.0002, |
| "loss": 0.6371127963066101, |
| "mean_token_accuracy": 0.7424579933285713, |
| "num_tokens": 6622393.0, |
| "step": 177 |
| }, |
| { |
| "entropy": 0.6296398118138313, |
| "epoch": 1.1344, |
| "grad_norm": 0.009771931916475296, |
| "learning_rate": 0.0002, |
| "loss": 0.6298056840896606, |
| "mean_token_accuracy": 0.7466778457164764, |
| "num_tokens": 6660099.0, |
| "step": 178 |
| }, |
| { |
| "entropy": 0.637910395860672, |
| "epoch": 1.1408, |
| "grad_norm": 0.010232111439108849, |
| "learning_rate": 0.0002, |
| "loss": 0.6460920572280884, |
| "mean_token_accuracy": 0.738376684486866, |
| "num_tokens": 6697941.0, |
| "step": 179 |
| }, |
| { |
| "entropy": 0.634870246052742, |
| "epoch": 1.1472, |
| "grad_norm": 0.010192861780524254, |
| "learning_rate": 0.0002, |
| "loss": 0.6416190266609192, |
| "mean_token_accuracy": 0.7403257936239243, |
| "num_tokens": 6735661.0, |
| "step": 180 |
| }, |
| { |
| "entropy": 0.6310748159885406, |
| "epoch": 1.1536, |
| "grad_norm": 0.01060323603451252, |
| "learning_rate": 0.0002, |
| "loss": 0.6375827193260193, |
| "mean_token_accuracy": 0.7393625825643539, |
| "num_tokens": 6772921.0, |
| "step": 181 |
| }, |
| { |
| "entropy": 0.6480697020888329, |
| "epoch": 1.16, |
| "grad_norm": 0.01187078095972538, |
| "learning_rate": 0.0002, |
| "loss": 0.6427325010299683, |
| "mean_token_accuracy": 0.7374937310814857, |
| "num_tokens": 6810167.0, |
| "step": 182 |
| }, |
| { |
| "entropy": 0.64576156437397, |
| "epoch": 1.1663999999999999, |
| "grad_norm": 0.009763217531144619, |
| "learning_rate": 0.0002, |
| "loss": 0.6441277861595154, |
| "mean_token_accuracy": 0.7376614883542061, |
| "num_tokens": 6848110.0, |
| "step": 183 |
| }, |
| { |
| "entropy": 0.6370326280593872, |
| "epoch": 1.1728, |
| "grad_norm": 0.009325532242655754, |
| "learning_rate": 0.0002, |
| "loss": 0.6410567760467529, |
| "mean_token_accuracy": 0.7398818284273148, |
| "num_tokens": 6885422.0, |
| "step": 184 |
| }, |
| { |
| "entropy": 0.6284242644906044, |
| "epoch": 1.1792, |
| "grad_norm": 0.010027528740465641, |
| "learning_rate": 0.0002, |
| "loss": 0.6299871206283569, |
| "mean_token_accuracy": 0.7442184612154961, |
| "num_tokens": 6922828.0, |
| "step": 185 |
| }, |
| { |
| "entropy": 0.6239589303731918, |
| "epoch": 1.1856, |
| "grad_norm": 0.012052655220031738, |
| "learning_rate": 0.0002, |
| "loss": 0.632190465927124, |
| "mean_token_accuracy": 0.7433017045259476, |
| "num_tokens": 6959969.0, |
| "step": 186 |
| }, |
| { |
| "entropy": 0.6507940962910652, |
| "epoch": 1.192, |
| "grad_norm": 0.010141950100660324, |
| "learning_rate": 0.0002, |
| "loss": 0.6531009078025818, |
| "mean_token_accuracy": 0.7333656772971153, |
| "num_tokens": 6997337.0, |
| "step": 187 |
| }, |
| { |
| "entropy": 0.6532803177833557, |
| "epoch": 1.1984, |
| "grad_norm": 0.010835838504135609, |
| "learning_rate": 0.0002, |
| "loss": 0.6479194164276123, |
| "mean_token_accuracy": 0.7359819039702415, |
| "num_tokens": 7034795.0, |
| "step": 188 |
| }, |
| { |
| "entropy": 0.6465721130371094, |
| "epoch": 1.2048, |
| "grad_norm": 0.011012948118150234, |
| "learning_rate": 0.0002, |
| "loss": 0.6399669051170349, |
| "mean_token_accuracy": 0.743029810488224, |
| "num_tokens": 7072227.0, |
| "step": 189 |
| }, |
| { |
| "entropy": 0.643355593085289, |
| "epoch": 1.2112, |
| "grad_norm": 0.0094833392649889, |
| "learning_rate": 0.0002, |
| "loss": 0.6482529640197754, |
| "mean_token_accuracy": 0.7374711334705353, |
| "num_tokens": 7110108.0, |
| "step": 190 |
| }, |
| { |
| "entropy": 0.6375522390007973, |
| "epoch": 1.2176, |
| "grad_norm": 0.010187760926783085, |
| "learning_rate": 0.0002, |
| "loss": 0.6461261510848999, |
| "mean_token_accuracy": 0.7388442009687424, |
| "num_tokens": 7147610.0, |
| "step": 191 |
| }, |
| { |
| "entropy": 0.6215626671910286, |
| "epoch": 1.224, |
| "grad_norm": 0.009307745844125748, |
| "learning_rate": 0.0002, |
| "loss": 0.6269906163215637, |
| "mean_token_accuracy": 0.7465217709541321, |
| "num_tokens": 7184782.0, |
| "step": 192 |
| }, |
| { |
| "entropy": 0.6429780498147011, |
| "epoch": 1.2304, |
| "grad_norm": 0.009042990393936634, |
| "learning_rate": 0.0002, |
| "loss": 0.648235559463501, |
| "mean_token_accuracy": 0.7354854270815849, |
| "num_tokens": 7222549.0, |
| "step": 193 |
| }, |
| { |
| "entropy": 0.6526690945029259, |
| "epoch": 1.2368000000000001, |
| "grad_norm": 0.010063275694847107, |
| "learning_rate": 0.0002, |
| "loss": 0.6548038721084595, |
| "mean_token_accuracy": 0.7341009303927422, |
| "num_tokens": 7260409.0, |
| "step": 194 |
| }, |
| { |
| "entropy": 0.6345907151699066, |
| "epoch": 1.2432, |
| "grad_norm": 0.010623205453157425, |
| "learning_rate": 0.0002, |
| "loss": 0.6308838129043579, |
| "mean_token_accuracy": 0.7419967949390411, |
| "num_tokens": 7297937.0, |
| "step": 195 |
| }, |
| { |
| "entropy": 0.6445695832371712, |
| "epoch": 1.2496, |
| "grad_norm": 0.010199649259448051, |
| "learning_rate": 0.0002, |
| "loss": 0.6364445686340332, |
| "mean_token_accuracy": 0.7410052716732025, |
| "num_tokens": 7335147.0, |
| "step": 196 |
| }, |
| { |
| "entropy": 0.6346744820475578, |
| "epoch": 1.256, |
| "grad_norm": 0.009105252102017403, |
| "learning_rate": 0.0002, |
| "loss": 0.6322548985481262, |
| "mean_token_accuracy": 0.7424812093377113, |
| "num_tokens": 7372946.0, |
| "step": 197 |
| }, |
| { |
| "entropy": 0.619812473654747, |
| "epoch": 1.2624, |
| "grad_norm": 0.009648271836340427, |
| "learning_rate": 0.0002, |
| "loss": 0.626278817653656, |
| "mean_token_accuracy": 0.7455899342894554, |
| "num_tokens": 7410415.0, |
| "step": 198 |
| }, |
| { |
| "entropy": 0.6315840631723404, |
| "epoch": 1.2688, |
| "grad_norm": 0.009451290592551231, |
| "learning_rate": 0.0002, |
| "loss": 0.6375157833099365, |
| "mean_token_accuracy": 0.7421969324350357, |
| "num_tokens": 7448206.0, |
| "step": 199 |
| }, |
| { |
| "entropy": 0.6275417804718018, |
| "epoch": 1.2752, |
| "grad_norm": 0.009674392640590668, |
| "learning_rate": 0.0002, |
| "loss": 0.6342942714691162, |
| "mean_token_accuracy": 0.74417594820261, |
| "num_tokens": 7485553.0, |
| "step": 200 |
| }, |
| { |
| "entropy": 0.6313388273119926, |
| "epoch": 1.2816, |
| "grad_norm": 0.008578372187912464, |
| "learning_rate": 0.0002, |
| "loss": 0.6364251375198364, |
| "mean_token_accuracy": 0.7415003478527069, |
| "num_tokens": 7523107.0, |
| "step": 201 |
| }, |
| { |
| "entropy": 0.6285647079348564, |
| "epoch": 1.288, |
| "grad_norm": 0.007911495864391327, |
| "learning_rate": 0.0002, |
| "loss": 0.6274697780609131, |
| "mean_token_accuracy": 0.7439461648464203, |
| "num_tokens": 7560637.0, |
| "step": 202 |
| }, |
| { |
| "entropy": 0.6555930450558662, |
| "epoch": 1.2944, |
| "grad_norm": 0.00908783357590437, |
| "learning_rate": 0.0002, |
| "loss": 0.6531112194061279, |
| "mean_token_accuracy": 0.7365255653858185, |
| "num_tokens": 7598202.0, |
| "step": 203 |
| }, |
| { |
| "entropy": 0.6405614539980888, |
| "epoch": 1.3008, |
| "grad_norm": 0.008850960060954094, |
| "learning_rate": 0.0002, |
| "loss": 0.6386165022850037, |
| "mean_token_accuracy": 0.7407704368233681, |
| "num_tokens": 7635602.0, |
| "step": 204 |
| }, |
| { |
| "entropy": 0.6183491796255112, |
| "epoch": 1.3072, |
| "grad_norm": 0.009933196939527988, |
| "learning_rate": 0.0002, |
| "loss": 0.6215780973434448, |
| "mean_token_accuracy": 0.7468694671988487, |
| "num_tokens": 7672796.0, |
| "step": 205 |
| }, |
| { |
| "entropy": 0.6282857060432434, |
| "epoch": 1.3136, |
| "grad_norm": 0.009941700845956802, |
| "learning_rate": 0.0002, |
| "loss": 0.6309329271316528, |
| "mean_token_accuracy": 0.7419614642858505, |
| "num_tokens": 7710123.0, |
| "step": 206 |
| }, |
| { |
| "entropy": 0.6409614756703377, |
| "epoch": 1.32, |
| "grad_norm": 0.009079815819859505, |
| "learning_rate": 0.0002, |
| "loss": 0.6415680050849915, |
| "mean_token_accuracy": 0.7399025559425354, |
| "num_tokens": 7747853.0, |
| "step": 207 |
| }, |
| { |
| "entropy": 0.6362860053777695, |
| "epoch": 1.3264, |
| "grad_norm": 0.009475532919168472, |
| "learning_rate": 0.0002, |
| "loss": 0.639657735824585, |
| "mean_token_accuracy": 0.740733340382576, |
| "num_tokens": 7785809.0, |
| "step": 208 |
| }, |
| { |
| "entropy": 0.648863323032856, |
| "epoch": 1.3328, |
| "grad_norm": 0.00897946022450924, |
| "learning_rate": 0.0002, |
| "loss": 0.6453667879104614, |
| "mean_token_accuracy": 0.7376150414347649, |
| "num_tokens": 7823564.0, |
| "step": 209 |
| }, |
| { |
| "entropy": 0.6473242938518524, |
| "epoch": 1.3392, |
| "grad_norm": 0.00988426897674799, |
| "learning_rate": 0.0002, |
| "loss": 0.6461673974990845, |
| "mean_token_accuracy": 0.7394340336322784, |
| "num_tokens": 7861487.0, |
| "step": 210 |
| }, |
| { |
| "entropy": 0.6313100084662437, |
| "epoch": 1.3456000000000001, |
| "grad_norm": 0.011011740192770958, |
| "learning_rate": 0.0002, |
| "loss": 0.6353209614753723, |
| "mean_token_accuracy": 0.7412855923175812, |
| "num_tokens": 7898738.0, |
| "step": 211 |
| }, |
| { |
| "entropy": 0.6332249045372009, |
| "epoch": 1.3519999999999999, |
| "grad_norm": 0.009350410662591457, |
| "learning_rate": 0.0002, |
| "loss": 0.6443768739700317, |
| "mean_token_accuracy": 0.7384829372167587, |
| "num_tokens": 7936394.0, |
| "step": 212 |
| }, |
| { |
| "entropy": 0.6210881397128105, |
| "epoch": 1.3584, |
| "grad_norm": 0.010020367801189423, |
| "learning_rate": 0.0002, |
| "loss": 0.6294596195220947, |
| "mean_token_accuracy": 0.7448422238230705, |
| "num_tokens": 7974219.0, |
| "step": 213 |
| }, |
| { |
| "entropy": 0.6376784816384315, |
| "epoch": 1.3648, |
| "grad_norm": 0.00982749741524458, |
| "learning_rate": 0.0002, |
| "loss": 0.6414127945899963, |
| "mean_token_accuracy": 0.7404457107186317, |
| "num_tokens": 8011498.0, |
| "step": 214 |
| }, |
| { |
| "entropy": 0.6365342438220978, |
| "epoch": 1.3712, |
| "grad_norm": 0.007822374813258648, |
| "learning_rate": 0.0002, |
| "loss": 0.6363272666931152, |
| "mean_token_accuracy": 0.7404549047350883, |
| "num_tokens": 8048792.0, |
| "step": 215 |
| }, |
| { |
| "entropy": 0.6440632939338684, |
| "epoch": 1.3776, |
| "grad_norm": 0.009724266827106476, |
| "learning_rate": 0.0002, |
| "loss": 0.6365130543708801, |
| "mean_token_accuracy": 0.7415405437350273, |
| "num_tokens": 8086606.0, |
| "step": 216 |
| }, |
| { |
| "entropy": 0.6494074836373329, |
| "epoch": 1.384, |
| "grad_norm": 0.009119455702602863, |
| "learning_rate": 0.0002, |
| "loss": 0.645447850227356, |
| "mean_token_accuracy": 0.7357565984129906, |
| "num_tokens": 8124114.0, |
| "step": 217 |
| }, |
| { |
| "entropy": 0.6484241932630539, |
| "epoch": 1.3904, |
| "grad_norm": 0.009591936133801937, |
| "learning_rate": 0.0002, |
| "loss": 0.6502270698547363, |
| "mean_token_accuracy": 0.7375201731920242, |
| "num_tokens": 8162048.0, |
| "step": 218 |
| }, |
| { |
| "entropy": 0.6512304544448853, |
| "epoch": 1.3968, |
| "grad_norm": 0.008009335026144981, |
| "learning_rate": 0.0002, |
| "loss": 0.6536368131637573, |
| "mean_token_accuracy": 0.735274650156498, |
| "num_tokens": 8199794.0, |
| "step": 219 |
| }, |
| { |
| "entropy": 0.6484591439366341, |
| "epoch": 1.4032, |
| "grad_norm": 0.0092353206127882, |
| "learning_rate": 0.0002, |
| "loss": 0.6539183259010315, |
| "mean_token_accuracy": 0.7346156910061836, |
| "num_tokens": 8237281.0, |
| "step": 220 |
| }, |
| { |
| "entropy": 0.6388984844088554, |
| "epoch": 1.4096, |
| "grad_norm": 0.009845041669905186, |
| "learning_rate": 0.0002, |
| "loss": 0.6434773206710815, |
| "mean_token_accuracy": 0.7382834777235985, |
| "num_tokens": 8274814.0, |
| "step": 221 |
| }, |
| { |
| "entropy": 0.6463811621069908, |
| "epoch": 1.416, |
| "grad_norm": 0.008870167657732964, |
| "learning_rate": 0.0002, |
| "loss": 0.6482495665550232, |
| "mean_token_accuracy": 0.7370684891939163, |
| "num_tokens": 8312525.0, |
| "step": 222 |
| }, |
| { |
| "entropy": 0.6367313861846924, |
| "epoch": 1.4224, |
| "grad_norm": 0.008752333000302315, |
| "learning_rate": 0.0002, |
| "loss": 0.6363902688026428, |
| "mean_token_accuracy": 0.7398954927921295, |
| "num_tokens": 8350434.0, |
| "step": 223 |
| }, |
| { |
| "entropy": 0.6389205679297447, |
| "epoch": 1.4288, |
| "grad_norm": 0.009939228184521198, |
| "learning_rate": 0.0002, |
| "loss": 0.6399004459381104, |
| "mean_token_accuracy": 0.739352636039257, |
| "num_tokens": 8387935.0, |
| "step": 224 |
| }, |
| { |
| "entropy": 0.6301346495747566, |
| "epoch": 1.4352, |
| "grad_norm": 0.01083251554518938, |
| "learning_rate": 0.0002, |
| "loss": 0.6333423256874084, |
| "mean_token_accuracy": 0.7439003512263298, |
| "num_tokens": 8425350.0, |
| "step": 225 |
| }, |
| { |
| "entropy": 0.6417813748121262, |
| "epoch": 1.4416, |
| "grad_norm": 0.008651083335280418, |
| "learning_rate": 0.0002, |
| "loss": 0.6453697681427002, |
| "mean_token_accuracy": 0.7393379509449005, |
| "num_tokens": 8462747.0, |
| "step": 226 |
| }, |
| { |
| "entropy": 0.6465223357081413, |
| "epoch": 1.448, |
| "grad_norm": 0.010395637713372707, |
| "learning_rate": 0.0002, |
| "loss": 0.6427249908447266, |
| "mean_token_accuracy": 0.7377897799015045, |
| "num_tokens": 8500639.0, |
| "step": 227 |
| }, |
| { |
| "entropy": 0.637003168463707, |
| "epoch": 1.4544000000000001, |
| "grad_norm": 0.00956573337316513, |
| "learning_rate": 0.0002, |
| "loss": 0.6341052055358887, |
| "mean_token_accuracy": 0.7431980520486832, |
| "num_tokens": 8538277.0, |
| "step": 228 |
| }, |
| { |
| "entropy": 0.6219193041324615, |
| "epoch": 1.4607999999999999, |
| "grad_norm": 0.009173355996608734, |
| "learning_rate": 0.0002, |
| "loss": 0.6226502060890198, |
| "mean_token_accuracy": 0.7491968795657158, |
| "num_tokens": 8576252.0, |
| "step": 229 |
| }, |
| { |
| "entropy": 0.6295832619071007, |
| "epoch": 1.4672, |
| "grad_norm": 0.009499134495854378, |
| "learning_rate": 0.0002, |
| "loss": 0.6385797262191772, |
| "mean_token_accuracy": 0.740376353263855, |
| "num_tokens": 8613847.0, |
| "step": 230 |
| }, |
| { |
| "entropy": 0.6238328814506531, |
| "epoch": 1.4736, |
| "grad_norm": 0.009796243160963058, |
| "learning_rate": 0.0002, |
| "loss": 0.633277177810669, |
| "mean_token_accuracy": 0.7418293952941895, |
| "num_tokens": 8651305.0, |
| "step": 231 |
| }, |
| { |
| "entropy": 0.6379890963435173, |
| "epoch": 1.48, |
| "grad_norm": 0.00879639107733965, |
| "learning_rate": 0.0002, |
| "loss": 0.6392139196395874, |
| "mean_token_accuracy": 0.7400495782494545, |
| "num_tokens": 8688955.0, |
| "step": 232 |
| }, |
| { |
| "entropy": 0.639459103345871, |
| "epoch": 1.4864, |
| "grad_norm": 0.00866638869047165, |
| "learning_rate": 0.0002, |
| "loss": 0.6354138255119324, |
| "mean_token_accuracy": 0.7424653545022011, |
| "num_tokens": 8726561.0, |
| "step": 233 |
| }, |
| { |
| "entropy": 0.6338846683502197, |
| "epoch": 1.4928, |
| "grad_norm": 0.008886488154530525, |
| "learning_rate": 0.0002, |
| "loss": 0.6311143636703491, |
| "mean_token_accuracy": 0.7435080260038376, |
| "num_tokens": 8763633.0, |
| "step": 234 |
| }, |
| { |
| "entropy": 0.6329428404569626, |
| "epoch": 1.4992, |
| "grad_norm": 0.008422540500760078, |
| "learning_rate": 0.0002, |
| "loss": 0.6340688467025757, |
| "mean_token_accuracy": 0.7437330037355423, |
| "num_tokens": 8801223.0, |
| "step": 235 |
| }, |
| { |
| "entropy": 0.6404994279146194, |
| "epoch": 1.5056, |
| "grad_norm": 0.008861835114657879, |
| "learning_rate": 0.0002, |
| "loss": 0.6435329914093018, |
| "mean_token_accuracy": 0.7402794137597084, |
| "num_tokens": 8838852.0, |
| "step": 236 |
| }, |
| { |
| "entropy": 0.6229164972901344, |
| "epoch": 1.512, |
| "grad_norm": 0.01079252827912569, |
| "learning_rate": 0.0002, |
| "loss": 0.6297635436058044, |
| "mean_token_accuracy": 0.7451627627015114, |
| "num_tokens": 8876215.0, |
| "step": 237 |
| }, |
| { |
| "entropy": 0.645681232213974, |
| "epoch": 1.5184, |
| "grad_norm": 0.00952441431581974, |
| "learning_rate": 0.0002, |
| "loss": 0.6496944427490234, |
| "mean_token_accuracy": 0.7374964207410812, |
| "num_tokens": 8913833.0, |
| "step": 238 |
| }, |
| { |
| "entropy": 0.6374045237898827, |
| "epoch": 1.5248, |
| "grad_norm": 0.010180641897022724, |
| "learning_rate": 0.0002, |
| "loss": 0.631719172000885, |
| "mean_token_accuracy": 0.7413778752088547, |
| "num_tokens": 8951296.0, |
| "step": 239 |
| }, |
| { |
| "entropy": 0.6539132967591286, |
| "epoch": 1.5312000000000001, |
| "grad_norm": 0.011931417509913445, |
| "learning_rate": 0.0002, |
| "loss": 0.6448370218276978, |
| "mean_token_accuracy": 0.7378397807478905, |
| "num_tokens": 8988896.0, |
| "step": 240 |
| }, |
| { |
| "entropy": 0.6414381936192513, |
| "epoch": 1.5375999999999999, |
| "grad_norm": 0.00920459907501936, |
| "learning_rate": 0.0002, |
| "loss": 0.6397557258605957, |
| "mean_token_accuracy": 0.7399087175726891, |
| "num_tokens": 9026747.0, |
| "step": 241 |
| }, |
| { |
| "entropy": 0.6196104139089584, |
| "epoch": 1.544, |
| "grad_norm": 0.011374457739293575, |
| "learning_rate": 0.0002, |
| "loss": 0.6309009194374084, |
| "mean_token_accuracy": 0.743213526904583, |
| "num_tokens": 9064429.0, |
| "step": 242 |
| }, |
| { |
| "entropy": 0.6261283829808235, |
| "epoch": 1.5504, |
| "grad_norm": 0.011355147697031498, |
| "learning_rate": 0.0002, |
| "loss": 0.6374455690383911, |
| "mean_token_accuracy": 0.7419503480195999, |
| "num_tokens": 9102195.0, |
| "step": 243 |
| }, |
| { |
| "entropy": 0.6445719599723816, |
| "epoch": 1.5568, |
| "grad_norm": 0.009919662959873676, |
| "learning_rate": 0.0002, |
| "loss": 0.6474390029907227, |
| "mean_token_accuracy": 0.7369806244969368, |
| "num_tokens": 9139609.0, |
| "step": 244 |
| }, |
| { |
| "entropy": 0.6413188800215721, |
| "epoch": 1.5632000000000001, |
| "grad_norm": 0.00855494849383831, |
| "learning_rate": 0.0002, |
| "loss": 0.641474187374115, |
| "mean_token_accuracy": 0.7400150150060654, |
| "num_tokens": 9177293.0, |
| "step": 245 |
| }, |
| { |
| "entropy": 0.637481302022934, |
| "epoch": 1.5695999999999999, |
| "grad_norm": 0.00973748043179512, |
| "learning_rate": 0.0002, |
| "loss": 0.6346510648727417, |
| "mean_token_accuracy": 0.7417012825608253, |
| "num_tokens": 9214895.0, |
| "step": 246 |
| }, |
| { |
| "entropy": 0.6503799557685852, |
| "epoch": 1.576, |
| "grad_norm": 0.007979532703757286, |
| "learning_rate": 0.0002, |
| "loss": 0.6497414112091064, |
| "mean_token_accuracy": 0.7372497469186783, |
| "num_tokens": 9252813.0, |
| "step": 247 |
| }, |
| { |
| "entropy": 0.6455269455909729, |
| "epoch": 1.5824, |
| "grad_norm": 0.008097643963992596, |
| "learning_rate": 0.0002, |
| "loss": 0.6451165676116943, |
| "mean_token_accuracy": 0.7385182455182076, |
| "num_tokens": 9290181.0, |
| "step": 248 |
| }, |
| { |
| "entropy": 0.644989550113678, |
| "epoch": 1.5888, |
| "grad_norm": 0.010681331157684326, |
| "learning_rate": 0.0002, |
| "loss": 0.6487670540809631, |
| "mean_token_accuracy": 0.7362834960222244, |
| "num_tokens": 9327721.0, |
| "step": 249 |
| }, |
| { |
| "entropy": 0.6285341307520866, |
| "epoch": 1.5952, |
| "grad_norm": 0.008401221595704556, |
| "learning_rate": 0.0002, |
| "loss": 0.6307709217071533, |
| "mean_token_accuracy": 0.7442108020186424, |
| "num_tokens": 9365266.0, |
| "step": 250 |
| }, |
| { |
| "entropy": 0.6323808878660202, |
| "epoch": 1.6016, |
| "grad_norm": 0.008853926323354244, |
| "learning_rate": 0.0002, |
| "loss": 0.6337858438491821, |
| "mean_token_accuracy": 0.7412157282233238, |
| "num_tokens": 9403484.0, |
| "step": 251 |
| }, |
| { |
| "entropy": 0.6329245269298553, |
| "epoch": 1.608, |
| "grad_norm": 0.009235359728336334, |
| "learning_rate": 0.0002, |
| "loss": 0.6332880258560181, |
| "mean_token_accuracy": 0.743882454931736, |
| "num_tokens": 9441086.0, |
| "step": 252 |
| }, |
| { |
| "entropy": 0.6339508295059204, |
| "epoch": 1.6143999999999998, |
| "grad_norm": 0.008013821206986904, |
| "learning_rate": 0.0002, |
| "loss": 0.63725346326828, |
| "mean_token_accuracy": 0.7408271208405495, |
| "num_tokens": 9478771.0, |
| "step": 253 |
| }, |
| { |
| "entropy": 0.6374928578734398, |
| "epoch": 1.6208, |
| "grad_norm": 0.009221353568136692, |
| "learning_rate": 0.0002, |
| "loss": 0.6384063959121704, |
| "mean_token_accuracy": 0.7406769022345543, |
| "num_tokens": 9516166.0, |
| "step": 254 |
| }, |
| { |
| "entropy": 0.6367692276835442, |
| "epoch": 1.6272, |
| "grad_norm": 0.00975379254668951, |
| "learning_rate": 0.0002, |
| "loss": 0.6376797556877136, |
| "mean_token_accuracy": 0.7408984154462814, |
| "num_tokens": 9553885.0, |
| "step": 255 |
| }, |
| { |
| "entropy": 0.6397164911031723, |
| "epoch": 1.6336, |
| "grad_norm": 0.009269645437598228, |
| "learning_rate": 0.0002, |
| "loss": 0.6477100849151611, |
| "mean_token_accuracy": 0.7368867322802544, |
| "num_tokens": 9591274.0, |
| "step": 256 |
| }, |
| { |
| "entropy": 0.6350990980863571, |
| "epoch": 1.6400000000000001, |
| "grad_norm": 0.007825898006558418, |
| "learning_rate": 0.0002, |
| "loss": 0.6354209184646606, |
| "mean_token_accuracy": 0.7403729483485222, |
| "num_tokens": 9628921.0, |
| "step": 257 |
| }, |
| { |
| "entropy": 0.6429452896118164, |
| "epoch": 1.6463999999999999, |
| "grad_norm": 0.009811664931476116, |
| "learning_rate": 0.0002, |
| "loss": 0.6441528797149658, |
| "mean_token_accuracy": 0.7374731153249741, |
| "num_tokens": 9666769.0, |
| "step": 258 |
| }, |
| { |
| "entropy": 0.6346355751156807, |
| "epoch": 1.6528, |
| "grad_norm": 0.010059292428195477, |
| "learning_rate": 0.0002, |
| "loss": 0.6366721391677856, |
| "mean_token_accuracy": 0.7407139092683792, |
| "num_tokens": 9704033.0, |
| "step": 259 |
| }, |
| { |
| "entropy": 0.6290543302893639, |
| "epoch": 1.6592, |
| "grad_norm": 0.008349488489329815, |
| "learning_rate": 0.0002, |
| "loss": 0.6278114914894104, |
| "mean_token_accuracy": 0.7450250014662743, |
| "num_tokens": 9741540.0, |
| "step": 260 |
| }, |
| { |
| "entropy": 0.6501712873578072, |
| "epoch": 1.6656, |
| "grad_norm": 0.009427984245121479, |
| "learning_rate": 0.0002, |
| "loss": 0.6549891829490662, |
| "mean_token_accuracy": 0.7353075668215752, |
| "num_tokens": 9779201.0, |
| "step": 261 |
| }, |
| { |
| "entropy": 0.6343263909220695, |
| "epoch": 1.6720000000000002, |
| "grad_norm": 0.008428818546235561, |
| "learning_rate": 0.0002, |
| "loss": 0.6368517875671387, |
| "mean_token_accuracy": 0.7391695827245712, |
| "num_tokens": 9816683.0, |
| "step": 262 |
| }, |
| { |
| "entropy": 0.649608425796032, |
| "epoch": 1.6784, |
| "grad_norm": 0.008335414342582226, |
| "learning_rate": 0.0002, |
| "loss": 0.6505298614501953, |
| "mean_token_accuracy": 0.7356899008154869, |
| "num_tokens": 9854491.0, |
| "step": 263 |
| }, |
| { |
| "entropy": 0.6355179324746132, |
| "epoch": 1.6848, |
| "grad_norm": 0.009246018715202808, |
| "learning_rate": 0.0002, |
| "loss": 0.6331362128257751, |
| "mean_token_accuracy": 0.741562083363533, |
| "num_tokens": 9891893.0, |
| "step": 264 |
| }, |
| { |
| "entropy": 0.6557022258639336, |
| "epoch": 1.6912, |
| "grad_norm": 0.008260353468358517, |
| "learning_rate": 0.0002, |
| "loss": 0.6587477922439575, |
| "mean_token_accuracy": 0.7323677465319633, |
| "num_tokens": 9929548.0, |
| "step": 265 |
| }, |
| { |
| "entropy": 0.6404315456748009, |
| "epoch": 1.6976, |
| "grad_norm": 0.009794406592845917, |
| "learning_rate": 0.0002, |
| "loss": 0.6475528478622437, |
| "mean_token_accuracy": 0.7362662330269814, |
| "num_tokens": 9967059.0, |
| "step": 266 |
| }, |
| { |
| "entropy": 0.63386220484972, |
| "epoch": 1.704, |
| "grad_norm": 0.008251597173511982, |
| "learning_rate": 0.0002, |
| "loss": 0.6386945247650146, |
| "mean_token_accuracy": 0.7404668778181076, |
| "num_tokens": 10004660.0, |
| "step": 267 |
| }, |
| { |
| "entropy": 0.6313491612672806, |
| "epoch": 1.7104, |
| "grad_norm": 0.00842359196394682, |
| "learning_rate": 0.0002, |
| "loss": 0.6330629587173462, |
| "mean_token_accuracy": 0.7405205965042114, |
| "num_tokens": 10042002.0, |
| "step": 268 |
| }, |
| { |
| "entropy": 0.6439215540885925, |
| "epoch": 1.7168, |
| "grad_norm": 0.008792798034846783, |
| "learning_rate": 0.0002, |
| "loss": 0.64313805103302, |
| "mean_token_accuracy": 0.7380542382597923, |
| "num_tokens": 10079455.0, |
| "step": 269 |
| }, |
| { |
| "entropy": 0.6456866934895515, |
| "epoch": 1.7231999999999998, |
| "grad_norm": 0.008770551532506943, |
| "learning_rate": 0.0002, |
| "loss": 0.6415017247200012, |
| "mean_token_accuracy": 0.7395961955189705, |
| "num_tokens": 10117042.0, |
| "step": 270 |
| }, |
| { |
| "entropy": 0.6421365886926651, |
| "epoch": 1.7296, |
| "grad_norm": 0.008746870793402195, |
| "learning_rate": 0.0002, |
| "loss": 0.6441514492034912, |
| "mean_token_accuracy": 0.7391441687941551, |
| "num_tokens": 10154684.0, |
| "step": 271 |
| }, |
| { |
| "entropy": 0.6459959074854851, |
| "epoch": 1.736, |
| "grad_norm": 0.008375383913516998, |
| "learning_rate": 0.0002, |
| "loss": 0.6512868404388428, |
| "mean_token_accuracy": 0.7382498681545258, |
| "num_tokens": 10192405.0, |
| "step": 272 |
| }, |
| { |
| "entropy": 0.6390120834112167, |
| "epoch": 1.7424, |
| "grad_norm": 0.009461523965001106, |
| "learning_rate": 0.0002, |
| "loss": 0.6469432711601257, |
| "mean_token_accuracy": 0.7358321473002434, |
| "num_tokens": 10230330.0, |
| "step": 273 |
| }, |
| { |
| "entropy": 0.6369089707732201, |
| "epoch": 1.7488000000000001, |
| "grad_norm": 0.008092108182609081, |
| "learning_rate": 0.0002, |
| "loss": 0.6383406519889832, |
| "mean_token_accuracy": 0.7406154125928879, |
| "num_tokens": 10267525.0, |
| "step": 274 |
| }, |
| { |
| "entropy": 0.6338964253664017, |
| "epoch": 1.7551999999999999, |
| "grad_norm": 0.008980642072856426, |
| "learning_rate": 0.0002, |
| "loss": 0.633415937423706, |
| "mean_token_accuracy": 0.7437249273061752, |
| "num_tokens": 10304863.0, |
| "step": 275 |
| }, |
| { |
| "entropy": 0.6264254227280617, |
| "epoch": 1.7616, |
| "grad_norm": 0.008377771824598312, |
| "learning_rate": 0.0002, |
| "loss": 0.6282482743263245, |
| "mean_token_accuracy": 0.7431060671806335, |
| "num_tokens": 10342202.0, |
| "step": 276 |
| }, |
| { |
| "entropy": 0.6434390917420387, |
| "epoch": 1.768, |
| "grad_norm": 0.008159980177879333, |
| "learning_rate": 0.0002, |
| "loss": 0.646558403968811, |
| "mean_token_accuracy": 0.7382596433162689, |
| "num_tokens": 10379740.0, |
| "step": 277 |
| }, |
| { |
| "entropy": 0.6326303333044052, |
| "epoch": 1.7744, |
| "grad_norm": 0.008124861866235733, |
| "learning_rate": 0.0002, |
| "loss": 0.6332470178604126, |
| "mean_token_accuracy": 0.7423404455184937, |
| "num_tokens": 10417746.0, |
| "step": 278 |
| }, |
| { |
| "entropy": 0.6520350500941277, |
| "epoch": 1.7808000000000002, |
| "grad_norm": 0.009632322005927563, |
| "learning_rate": 0.0002, |
| "loss": 0.6571191549301147, |
| "mean_token_accuracy": 0.7318461984395981, |
| "num_tokens": 10455758.0, |
| "step": 279 |
| }, |
| { |
| "entropy": 0.6354654431343079, |
| "epoch": 1.7872, |
| "grad_norm": 0.008794812485575676, |
| "learning_rate": 0.0002, |
| "loss": 0.6319587230682373, |
| "mean_token_accuracy": 0.7421321347355843, |
| "num_tokens": 10493098.0, |
| "step": 280 |
| }, |
| { |
| "entropy": 0.6494236141443253, |
| "epoch": 1.7936, |
| "grad_norm": 0.00833588931709528, |
| "learning_rate": 0.0002, |
| "loss": 0.6512980461120605, |
| "mean_token_accuracy": 0.7350147068500519, |
| "num_tokens": 10530840.0, |
| "step": 281 |
| }, |
| { |
| "entropy": 0.6404789388179779, |
| "epoch": 1.8, |
| "grad_norm": 0.009666857309639454, |
| "learning_rate": 0.0002, |
| "loss": 0.6438995599746704, |
| "mean_token_accuracy": 0.7382337227463722, |
| "num_tokens": 10568316.0, |
| "step": 282 |
| }, |
| { |
| "entropy": 0.628923237323761, |
| "epoch": 1.8064, |
| "grad_norm": 0.010019267909228802, |
| "learning_rate": 0.0002, |
| "loss": 0.6307887434959412, |
| "mean_token_accuracy": 0.7422001957893372, |
| "num_tokens": 10605621.0, |
| "step": 283 |
| }, |
| { |
| "entropy": 0.6334665641188622, |
| "epoch": 1.8128, |
| "grad_norm": 0.00908628199249506, |
| "learning_rate": 0.0002, |
| "loss": 0.6341119408607483, |
| "mean_token_accuracy": 0.7430456355214119, |
| "num_tokens": 10642983.0, |
| "step": 284 |
| }, |
| { |
| "entropy": 0.6285069659352303, |
| "epoch": 1.8192, |
| "grad_norm": 0.008308637887239456, |
| "learning_rate": 0.0002, |
| "loss": 0.6301131248474121, |
| "mean_token_accuracy": 0.7429656311869621, |
| "num_tokens": 10680597.0, |
| "step": 285 |
| }, |
| { |
| "entropy": 0.6323676705360413, |
| "epoch": 1.8256000000000001, |
| "grad_norm": 0.008813594467937946, |
| "learning_rate": 0.0002, |
| "loss": 0.6346842050552368, |
| "mean_token_accuracy": 0.7398638725280762, |
| "num_tokens": 10718004.0, |
| "step": 286 |
| }, |
| { |
| "entropy": 0.6334202289581299, |
| "epoch": 1.8319999999999999, |
| "grad_norm": 0.009448044933378696, |
| "learning_rate": 0.0002, |
| "loss": 0.640605092048645, |
| "mean_token_accuracy": 0.7379657998681068, |
| "num_tokens": 10755392.0, |
| "step": 287 |
| }, |
| { |
| "entropy": 0.6541434079408646, |
| "epoch": 1.8384, |
| "grad_norm": 0.00910591334104538, |
| "learning_rate": 0.0002, |
| "loss": 0.6537045240402222, |
| "mean_token_accuracy": 0.7336858883500099, |
| "num_tokens": 10792841.0, |
| "step": 288 |
| }, |
| { |
| "entropy": 0.6449815109372139, |
| "epoch": 1.8448, |
| "grad_norm": 0.010256773792207241, |
| "learning_rate": 0.0002, |
| "loss": 0.6409913301467896, |
| "mean_token_accuracy": 0.739972397685051, |
| "num_tokens": 10830422.0, |
| "step": 289 |
| }, |
| { |
| "entropy": 0.6341065391898155, |
| "epoch": 1.8512, |
| "grad_norm": 0.007780797313898802, |
| "learning_rate": 0.0002, |
| "loss": 0.6369997262954712, |
| "mean_token_accuracy": 0.7405647411942482, |
| "num_tokens": 10867712.0, |
| "step": 290 |
| }, |
| { |
| "entropy": 0.6363702341914177, |
| "epoch": 1.8576000000000001, |
| "grad_norm": 0.008313016034662724, |
| "learning_rate": 0.0002, |
| "loss": 0.6386253833770752, |
| "mean_token_accuracy": 0.7408165112137794, |
| "num_tokens": 10905152.0, |
| "step": 291 |
| }, |
| { |
| "entropy": 0.6477962657809258, |
| "epoch": 1.8639999999999999, |
| "grad_norm": 0.007996824570000172, |
| "learning_rate": 0.0002, |
| "loss": 0.649878740310669, |
| "mean_token_accuracy": 0.7363680452108383, |
| "num_tokens": 10942566.0, |
| "step": 292 |
| }, |
| { |
| "entropy": 0.6444478929042816, |
| "epoch": 1.8704, |
| "grad_norm": 0.009034682996571064, |
| "learning_rate": 0.0002, |
| "loss": 0.64991295337677, |
| "mean_token_accuracy": 0.7348211482167244, |
| "num_tokens": 10979522.0, |
| "step": 293 |
| }, |
| { |
| "entropy": 0.6329373270273209, |
| "epoch": 1.8768, |
| "grad_norm": 0.009291103109717369, |
| "learning_rate": 0.0002, |
| "loss": 0.6315436363220215, |
| "mean_token_accuracy": 0.7441153600811958, |
| "num_tokens": 11016799.0, |
| "step": 294 |
| }, |
| { |
| "entropy": 0.6502094119787216, |
| "epoch": 1.8832, |
| "grad_norm": 0.0096050426363945, |
| "learning_rate": 0.0002, |
| "loss": 0.6489418148994446, |
| "mean_token_accuracy": 0.7356565669178963, |
| "num_tokens": 11054518.0, |
| "step": 295 |
| }, |
| { |
| "entropy": 0.6323768645524979, |
| "epoch": 1.8896, |
| "grad_norm": 0.008002777583897114, |
| "learning_rate": 0.0002, |
| "loss": 0.635691225528717, |
| "mean_token_accuracy": 0.7405551075935364, |
| "num_tokens": 11091967.0, |
| "step": 296 |
| }, |
| { |
| "entropy": 0.6422302722930908, |
| "epoch": 1.896, |
| "grad_norm": 0.008403711952269077, |
| "learning_rate": 0.0002, |
| "loss": 0.6455032825469971, |
| "mean_token_accuracy": 0.7383149340748787, |
| "num_tokens": 11129384.0, |
| "step": 297 |
| }, |
| { |
| "entropy": 0.6316574737429619, |
| "epoch": 1.9024, |
| "grad_norm": 0.00967500451952219, |
| "learning_rate": 0.0002, |
| "loss": 0.6350202560424805, |
| "mean_token_accuracy": 0.7421634197235107, |
| "num_tokens": 11166669.0, |
| "step": 298 |
| }, |
| { |
| "entropy": 0.6459977030754089, |
| "epoch": 1.9088, |
| "grad_norm": 0.00876573659479618, |
| "learning_rate": 0.0002, |
| "loss": 0.6403264999389648, |
| "mean_token_accuracy": 0.7382558658719063, |
| "num_tokens": 11204332.0, |
| "step": 299 |
| }, |
| { |
| "entropy": 0.6415895000100136, |
| "epoch": 1.9152, |
| "grad_norm": 0.009217560291290283, |
| "learning_rate": 0.0002, |
| "loss": 0.6415034532546997, |
| "mean_token_accuracy": 0.7386994808912277, |
| "num_tokens": 11241726.0, |
| "step": 300 |
| }, |
| { |
| "entropy": 0.6311015710234642, |
| "epoch": 1.9216, |
| "grad_norm": 0.00828156340867281, |
| "learning_rate": 0.0002, |
| "loss": 0.630814790725708, |
| "mean_token_accuracy": 0.7444434463977814, |
| "num_tokens": 11279304.0, |
| "step": 301 |
| }, |
| { |
| "entropy": 0.6455347687005997, |
| "epoch": 1.928, |
| "grad_norm": 0.00847472995519638, |
| "learning_rate": 0.0002, |
| "loss": 0.6488364934921265, |
| "mean_token_accuracy": 0.7379944175481796, |
| "num_tokens": 11316642.0, |
| "step": 302 |
| }, |
| { |
| "entropy": 0.6381795853376389, |
| "epoch": 1.9344000000000001, |
| "grad_norm": 0.010508674196898937, |
| "learning_rate": 0.0002, |
| "loss": 0.6469117403030396, |
| "mean_token_accuracy": 0.7371617555618286, |
| "num_tokens": 11354142.0, |
| "step": 303 |
| }, |
| { |
| "entropy": 0.6340028718113899, |
| "epoch": 1.9407999999999999, |
| "grad_norm": 0.008417687378823757, |
| "learning_rate": 0.0002, |
| "loss": 0.638616681098938, |
| "mean_token_accuracy": 0.7400232255458832, |
| "num_tokens": 11391584.0, |
| "step": 304 |
| }, |
| { |
| "entropy": 0.641148068010807, |
| "epoch": 1.9472, |
| "grad_norm": 0.009189863689243793, |
| "learning_rate": 0.0002, |
| "loss": 0.6417672038078308, |
| "mean_token_accuracy": 0.7394173890352249, |
| "num_tokens": 11429141.0, |
| "step": 305 |
| }, |
| { |
| "entropy": 0.6361806094646454, |
| "epoch": 1.9536, |
| "grad_norm": 0.009170212782919407, |
| "learning_rate": 0.0002, |
| "loss": 0.6348021626472473, |
| "mean_token_accuracy": 0.741854839026928, |
| "num_tokens": 11466566.0, |
| "step": 306 |
| }, |
| { |
| "entropy": 0.6448198854923248, |
| "epoch": 1.96, |
| "grad_norm": 0.008513331413269043, |
| "learning_rate": 0.0002, |
| "loss": 0.6473972797393799, |
| "mean_token_accuracy": 0.7364873364567757, |
| "num_tokens": 11503681.0, |
| "step": 307 |
| }, |
| { |
| "entropy": 0.6346408724784851, |
| "epoch": 1.9664000000000001, |
| "grad_norm": 0.010691906325519085, |
| "learning_rate": 0.0002, |
| "loss": 0.6393898725509644, |
| "mean_token_accuracy": 0.7428330779075623, |
| "num_tokens": 11541361.0, |
| "step": 308 |
| }, |
| { |
| "entropy": 0.6447126045823097, |
| "epoch": 1.9727999999999999, |
| "grad_norm": 0.009089854545891285, |
| "learning_rate": 0.0002, |
| "loss": 0.6462785601615906, |
| "mean_token_accuracy": 0.7361640483140945, |
| "num_tokens": 11578943.0, |
| "step": 309 |
| }, |
| { |
| "entropy": 0.6443200558423996, |
| "epoch": 1.9792, |
| "grad_norm": 0.007877051830291748, |
| "learning_rate": 0.0002, |
| "loss": 0.6410749554634094, |
| "mean_token_accuracy": 0.7393750101327896, |
| "num_tokens": 11616900.0, |
| "step": 310 |
| }, |
| { |
| "entropy": 0.6526265293359756, |
| "epoch": 1.9856, |
| "grad_norm": 0.007553855888545513, |
| "learning_rate": 0.0002, |
| "loss": 0.6491004824638367, |
| "mean_token_accuracy": 0.7368245124816895, |
| "num_tokens": 11654118.0, |
| "step": 311 |
| }, |
| { |
| "entropy": 0.6361679136753082, |
| "epoch": 1.992, |
| "grad_norm": 0.0077677839435637, |
| "learning_rate": 0.0002, |
| "loss": 0.6400581002235413, |
| "mean_token_accuracy": 0.7392396479845047, |
| "num_tokens": 11691819.0, |
| "step": 312 |
| }, |
| { |
| "entropy": 0.6478787511587143, |
| "epoch": 1.9984, |
| "grad_norm": 0.008330225013196468, |
| "learning_rate": 0.0002, |
| "loss": 0.6550832390785217, |
| "mean_token_accuracy": 0.7333075851202011, |
| "num_tokens": 11729371.0, |
| "step": 313 |
| }, |
| { |
| "entropy": 0.647148609161377, |
| "epoch": 2.0, |
| "grad_norm": 0.014249460771679878, |
| "learning_rate": 0.0002, |
| "loss": 0.6511927843093872, |
| "mean_token_accuracy": 0.7351100444793701, |
| "num_tokens": 11738913.0, |
| "step": 314 |
| }, |
| { |
| "entropy": 0.6428509056568146, |
| "epoch": 2.0064, |
| "grad_norm": 0.012224607169628143, |
| "learning_rate": 0.0002, |
| "loss": 0.6413295865058899, |
| "mean_token_accuracy": 0.7383991628885269, |
| "num_tokens": 11776564.0, |
| "step": 315 |
| }, |
| { |
| "entropy": 0.6307617798447609, |
| "epoch": 2.0128, |
| "grad_norm": 0.00805046409368515, |
| "learning_rate": 0.0002, |
| "loss": 0.6318984031677246, |
| "mean_token_accuracy": 0.7424051091074944, |
| "num_tokens": 11813755.0, |
| "step": 316 |
| }, |
| { |
| "entropy": 0.6430513709783554, |
| "epoch": 2.0192, |
| "grad_norm": 0.007973214611411095, |
| "learning_rate": 0.0002, |
| "loss": 0.6426272392272949, |
| "mean_token_accuracy": 0.7385435774922371, |
| "num_tokens": 11851558.0, |
| "step": 317 |
| }, |
| { |
| "entropy": 0.6318764910101891, |
| "epoch": 2.0256, |
| "grad_norm": 0.012760069221258163, |
| "learning_rate": 0.0002, |
| "loss": 0.6337249875068665, |
| "mean_token_accuracy": 0.7423495799303055, |
| "num_tokens": 11889166.0, |
| "step": 318 |
| }, |
| { |
| "entropy": 0.655825637280941, |
| "epoch": 2.032, |
| "grad_norm": 0.008295831270515919, |
| "learning_rate": 0.0002, |
| "loss": 0.6574875712394714, |
| "mean_token_accuracy": 0.7304191887378693, |
| "num_tokens": 11926828.0, |
| "step": 319 |
| }, |
| { |
| "entropy": 0.646898128092289, |
| "epoch": 2.0384, |
| "grad_norm": 0.0076156072318553925, |
| "learning_rate": 0.0002, |
| "loss": 0.6442586183547974, |
| "mean_token_accuracy": 0.7376453951001167, |
| "num_tokens": 11964281.0, |
| "step": 320 |
| }, |
| { |
| "entropy": 0.6386341005563736, |
| "epoch": 2.0448, |
| "grad_norm": 0.008703756146132946, |
| "learning_rate": 0.0002, |
| "loss": 0.6401532888412476, |
| "mean_token_accuracy": 0.7430068925023079, |
| "num_tokens": 12001686.0, |
| "step": 321 |
| }, |
| { |
| "entropy": 0.6369054093956947, |
| "epoch": 2.0512, |
| "grad_norm": 0.008225949481129646, |
| "learning_rate": 0.0002, |
| "loss": 0.6394542455673218, |
| "mean_token_accuracy": 0.7397433742880821, |
| "num_tokens": 12039411.0, |
| "step": 322 |
| }, |
| { |
| "entropy": 0.6331326514482498, |
| "epoch": 2.0576, |
| "grad_norm": 0.009685281664133072, |
| "learning_rate": 0.0002, |
| "loss": 0.6398283839225769, |
| "mean_token_accuracy": 0.7404422760009766, |
| "num_tokens": 12076768.0, |
| "step": 323 |
| }, |
| { |
| "entropy": 0.6296347230672836, |
| "epoch": 2.064, |
| "grad_norm": 0.008879579603672028, |
| "learning_rate": 0.0002, |
| "loss": 0.632715106010437, |
| "mean_token_accuracy": 0.7417664974927902, |
| "num_tokens": 12114584.0, |
| "step": 324 |
| }, |
| { |
| "entropy": 0.6318413317203522, |
| "epoch": 2.0704, |
| "grad_norm": 0.008431381545960903, |
| "learning_rate": 0.0002, |
| "loss": 0.6331377029418945, |
| "mean_token_accuracy": 0.7394522577524185, |
| "num_tokens": 12152129.0, |
| "step": 325 |
| }, |
| { |
| "entropy": 0.6365228146314621, |
| "epoch": 2.0768, |
| "grad_norm": 0.008421050384640694, |
| "learning_rate": 0.0002, |
| "loss": 0.6375148296356201, |
| "mean_token_accuracy": 0.7391103804111481, |
| "num_tokens": 12189530.0, |
| "step": 326 |
| }, |
| { |
| "entropy": 0.6343080475926399, |
| "epoch": 2.0832, |
| "grad_norm": 0.008700543083250523, |
| "learning_rate": 0.0002, |
| "loss": 0.640760600566864, |
| "mean_token_accuracy": 0.737753376364708, |
| "num_tokens": 12227254.0, |
| "step": 327 |
| }, |
| { |
| "entropy": 0.6292807161808014, |
| "epoch": 2.0896, |
| "grad_norm": 0.008493369445204735, |
| "learning_rate": 0.0002, |
| "loss": 0.6337940692901611, |
| "mean_token_accuracy": 0.7432547584176064, |
| "num_tokens": 12264717.0, |
| "step": 328 |
| }, |
| { |
| "entropy": 0.6373203322291374, |
| "epoch": 2.096, |
| "grad_norm": 0.008298007771372795, |
| "learning_rate": 0.0002, |
| "loss": 0.6361969709396362, |
| "mean_token_accuracy": 0.7403373941779137, |
| "num_tokens": 12301926.0, |
| "step": 329 |
| }, |
| { |
| "entropy": 0.645341120660305, |
| "epoch": 2.1024, |
| "grad_norm": 0.009415465407073498, |
| "learning_rate": 0.0002, |
| "loss": 0.6422229409217834, |
| "mean_token_accuracy": 0.7388109862804413, |
| "num_tokens": 12339358.0, |
| "step": 330 |
| }, |
| { |
| "entropy": 0.6284746676683426, |
| "epoch": 2.1088, |
| "grad_norm": 0.00816258043050766, |
| "learning_rate": 0.0002, |
| "loss": 0.6270098090171814, |
| "mean_token_accuracy": 0.7465712875127792, |
| "num_tokens": 12376845.0, |
| "step": 331 |
| }, |
| { |
| "entropy": 0.618787370622158, |
| "epoch": 2.1152, |
| "grad_norm": 0.010069424286484718, |
| "learning_rate": 0.0002, |
| "loss": 0.6233252286911011, |
| "mean_token_accuracy": 0.7466351315379143, |
| "num_tokens": 12414270.0, |
| "step": 332 |
| }, |
| { |
| "entropy": 0.6204424351453781, |
| "epoch": 2.1216, |
| "grad_norm": 0.011632254347205162, |
| "learning_rate": 0.0002, |
| "loss": 0.6273159384727478, |
| "mean_token_accuracy": 0.7449653670191765, |
| "num_tokens": 12451814.0, |
| "step": 333 |
| }, |
| { |
| "entropy": 0.6244671940803528, |
| "epoch": 2.128, |
| "grad_norm": 0.007731855846941471, |
| "learning_rate": 0.0002, |
| "loss": 0.6259894371032715, |
| "mean_token_accuracy": 0.7442785128951073, |
| "num_tokens": 12489174.0, |
| "step": 334 |
| }, |
| { |
| "entropy": 0.6379582434892654, |
| "epoch": 2.1344, |
| "grad_norm": 0.009793682023882866, |
| "learning_rate": 0.0002, |
| "loss": 0.6348966360092163, |
| "mean_token_accuracy": 0.740781731903553, |
| "num_tokens": 12526495.0, |
| "step": 335 |
| }, |
| { |
| "entropy": 0.6337939351797104, |
| "epoch": 2.1408, |
| "grad_norm": 0.00962368305772543, |
| "learning_rate": 0.0002, |
| "loss": 0.6337376832962036, |
| "mean_token_accuracy": 0.741876944899559, |
| "num_tokens": 12563862.0, |
| "step": 336 |
| }, |
| { |
| "entropy": 0.6327385306358337, |
| "epoch": 2.1471999999999998, |
| "grad_norm": 0.008747846819460392, |
| "learning_rate": 0.0002, |
| "loss": 0.6306090354919434, |
| "mean_token_accuracy": 0.7432660833001137, |
| "num_tokens": 12601147.0, |
| "step": 337 |
| }, |
| { |
| "entropy": 0.6386691257357597, |
| "epoch": 2.1536, |
| "grad_norm": 0.008939294144511223, |
| "learning_rate": 0.0002, |
| "loss": 0.6422123908996582, |
| "mean_token_accuracy": 0.7385012805461884, |
| "num_tokens": 12638941.0, |
| "step": 338 |
| }, |
| { |
| "entropy": 0.6356615126132965, |
| "epoch": 2.16, |
| "grad_norm": 0.008577845059335232, |
| "learning_rate": 0.0002, |
| "loss": 0.6377971768379211, |
| "mean_token_accuracy": 0.7411153167486191, |
| "num_tokens": 12676252.0, |
| "step": 339 |
| }, |
| { |
| "entropy": 0.6395266354084015, |
| "epoch": 2.1664, |
| "grad_norm": 0.009049834683537483, |
| "learning_rate": 0.0002, |
| "loss": 0.6420882344245911, |
| "mean_token_accuracy": 0.7383701205253601, |
| "num_tokens": 12713835.0, |
| "step": 340 |
| }, |
| { |
| "entropy": 0.6292238682508469, |
| "epoch": 2.1728, |
| "grad_norm": 0.008495191112160683, |
| "learning_rate": 0.0002, |
| "loss": 0.6327275037765503, |
| "mean_token_accuracy": 0.7408149838447571, |
| "num_tokens": 12751620.0, |
| "step": 341 |
| }, |
| { |
| "entropy": 0.639611691236496, |
| "epoch": 2.1792, |
| "grad_norm": 0.009403538890182972, |
| "learning_rate": 0.0002, |
| "loss": 0.6445578336715698, |
| "mean_token_accuracy": 0.7371161133050919, |
| "num_tokens": 12789311.0, |
| "step": 342 |
| }, |
| { |
| "entropy": 0.6382555812597275, |
| "epoch": 2.1856, |
| "grad_norm": 0.008258577436208725, |
| "learning_rate": 0.0002, |
| "loss": 0.6395673751831055, |
| "mean_token_accuracy": 0.7395190820097923, |
| "num_tokens": 12826828.0, |
| "step": 343 |
| }, |
| { |
| "entropy": 0.6255771890282631, |
| "epoch": 2.192, |
| "grad_norm": 0.008409053087234497, |
| "learning_rate": 0.0002, |
| "loss": 0.6285756826400757, |
| "mean_token_accuracy": 0.7443142682313919, |
| "num_tokens": 12864340.0, |
| "step": 344 |
| }, |
| { |
| "entropy": 0.6310818865895271, |
| "epoch": 2.1984, |
| "grad_norm": 0.009435487911105156, |
| "learning_rate": 0.0002, |
| "loss": 0.6294571161270142, |
| "mean_token_accuracy": 0.7434982731938362, |
| "num_tokens": 12902046.0, |
| "step": 345 |
| }, |
| { |
| "entropy": 0.6311678513884544, |
| "epoch": 2.2048, |
| "grad_norm": 0.008755765855312347, |
| "learning_rate": 0.0002, |
| "loss": 0.6339205503463745, |
| "mean_token_accuracy": 0.740614227950573, |
| "num_tokens": 12939744.0, |
| "step": 346 |
| }, |
| { |
| "entropy": 0.6452009528875351, |
| "epoch": 2.2112, |
| "grad_norm": 0.008575056679546833, |
| "learning_rate": 0.0002, |
| "loss": 0.644209623336792, |
| "mean_token_accuracy": 0.7392476424574852, |
| "num_tokens": 12977341.0, |
| "step": 347 |
| }, |
| { |
| "entropy": 0.6338612660765648, |
| "epoch": 2.2176, |
| "grad_norm": 0.007798387669026852, |
| "learning_rate": 0.0002, |
| "loss": 0.6330971121788025, |
| "mean_token_accuracy": 0.7440877333283424, |
| "num_tokens": 13015002.0, |
| "step": 348 |
| }, |
| { |
| "entropy": 0.6385946869850159, |
| "epoch": 2.224, |
| "grad_norm": 0.009336304850876331, |
| "learning_rate": 0.0002, |
| "loss": 0.6359999179840088, |
| "mean_token_accuracy": 0.741933673620224, |
| "num_tokens": 13052683.0, |
| "step": 349 |
| }, |
| { |
| "entropy": 0.6185505017638206, |
| "epoch": 2.2304, |
| "grad_norm": 0.009118903428316116, |
| "learning_rate": 0.0002, |
| "loss": 0.6220842599868774, |
| "mean_token_accuracy": 0.7472022995352745, |
| "num_tokens": 13089828.0, |
| "step": 350 |
| }, |
| { |
| "entropy": 0.6268252283334732, |
| "epoch": 2.2368, |
| "grad_norm": 0.0092701381072402, |
| "learning_rate": 0.0002, |
| "loss": 0.6330834627151489, |
| "mean_token_accuracy": 0.7435643449425697, |
| "num_tokens": 13127264.0, |
| "step": 351 |
| }, |
| { |
| "entropy": 0.6323676556348801, |
| "epoch": 2.2432, |
| "grad_norm": 0.010936826467514038, |
| "learning_rate": 0.0002, |
| "loss": 0.6385864615440369, |
| "mean_token_accuracy": 0.7403518706560135, |
| "num_tokens": 13164850.0, |
| "step": 352 |
| }, |
| { |
| "entropy": 0.6403925344347954, |
| "epoch": 2.2496, |
| "grad_norm": 0.009062140248715878, |
| "learning_rate": 0.0002, |
| "loss": 0.6446559429168701, |
| "mean_token_accuracy": 0.737325981259346, |
| "num_tokens": 13202818.0, |
| "step": 353 |
| }, |
| { |
| "entropy": 0.6653745025396347, |
| "epoch": 2.2560000000000002, |
| "grad_norm": 0.008989578112959862, |
| "learning_rate": 0.0002, |
| "loss": 0.6635587215423584, |
| "mean_token_accuracy": 0.7302659377455711, |
| "num_tokens": 13240741.0, |
| "step": 354 |
| }, |
| { |
| "entropy": 0.6176604405045509, |
| "epoch": 2.2624, |
| "grad_norm": 0.011122855357825756, |
| "learning_rate": 0.0002, |
| "loss": 0.6100451350212097, |
| "mean_token_accuracy": 0.7515672147274017, |
| "num_tokens": 13278017.0, |
| "step": 355 |
| }, |
| { |
| "entropy": 0.6418539881706238, |
| "epoch": 2.2688, |
| "grad_norm": 0.009430945850908756, |
| "learning_rate": 0.0002, |
| "loss": 0.6456764340400696, |
| "mean_token_accuracy": 0.7369844615459442, |
| "num_tokens": 13315575.0, |
| "step": 356 |
| }, |
| { |
| "entropy": 0.6377789452672005, |
| "epoch": 2.2752, |
| "grad_norm": 0.01120819989591837, |
| "learning_rate": 0.0002, |
| "loss": 0.6447769999504089, |
| "mean_token_accuracy": 0.7389207035303116, |
| "num_tokens": 13353349.0, |
| "step": 357 |
| }, |
| { |
| "entropy": 0.6309510096907616, |
| "epoch": 2.2816, |
| "grad_norm": 0.01070281770080328, |
| "learning_rate": 0.0002, |
| "loss": 0.639892578125, |
| "mean_token_accuracy": 0.7402263358235359, |
| "num_tokens": 13390831.0, |
| "step": 358 |
| }, |
| { |
| "entropy": 0.6376594752073288, |
| "epoch": 2.288, |
| "grad_norm": 0.008750580251216888, |
| "learning_rate": 0.0002, |
| "loss": 0.6361696720123291, |
| "mean_token_accuracy": 0.7411545366048813, |
| "num_tokens": 13428400.0, |
| "step": 359 |
| }, |
| { |
| "entropy": 0.6379339694976807, |
| "epoch": 2.2944, |
| "grad_norm": 0.01135624572634697, |
| "learning_rate": 0.0002, |
| "loss": 0.6322520971298218, |
| "mean_token_accuracy": 0.7416113168001175, |
| "num_tokens": 13465745.0, |
| "step": 360 |
| }, |
| { |
| "entropy": 0.6344308853149414, |
| "epoch": 2.3008, |
| "grad_norm": 0.008200406096875668, |
| "learning_rate": 0.0002, |
| "loss": 0.6279163360595703, |
| "mean_token_accuracy": 0.7453168705105782, |
| "num_tokens": 13503838.0, |
| "step": 361 |
| }, |
| { |
| "entropy": 0.6380530670285225, |
| "epoch": 2.3072, |
| "grad_norm": 0.011549552902579308, |
| "learning_rate": 0.0002, |
| "loss": 0.6419570446014404, |
| "mean_token_accuracy": 0.7404475137591362, |
| "num_tokens": 13541929.0, |
| "step": 362 |
| }, |
| { |
| "entropy": 0.6338977962732315, |
| "epoch": 2.3136, |
| "grad_norm": 0.009041829034686089, |
| "learning_rate": 0.0002, |
| "loss": 0.6397197842597961, |
| "mean_token_accuracy": 0.7420290112495422, |
| "num_tokens": 13579161.0, |
| "step": 363 |
| }, |
| { |
| "entropy": 0.6449583545327187, |
| "epoch": 2.32, |
| "grad_norm": 0.009089567698538303, |
| "learning_rate": 0.0002, |
| "loss": 0.6466807126998901, |
| "mean_token_accuracy": 0.7365088015794754, |
| "num_tokens": 13616744.0, |
| "step": 364 |
| }, |
| { |
| "entropy": 0.642234593629837, |
| "epoch": 2.3264, |
| "grad_norm": 0.009368225000798702, |
| "learning_rate": 0.0002, |
| "loss": 0.6429442167282104, |
| "mean_token_accuracy": 0.7369751259684563, |
| "num_tokens": 13654392.0, |
| "step": 365 |
| }, |
| { |
| "entropy": 0.6480699181556702, |
| "epoch": 2.3327999999999998, |
| "grad_norm": 0.008836016058921814, |
| "learning_rate": 0.0002, |
| "loss": 0.6484840512275696, |
| "mean_token_accuracy": 0.7375075444579124, |
| "num_tokens": 13691824.0, |
| "step": 366 |
| }, |
| { |
| "entropy": 0.6319603100419044, |
| "epoch": 2.3392, |
| "grad_norm": 0.008661167696118355, |
| "learning_rate": 0.0002, |
| "loss": 0.6352815628051758, |
| "mean_token_accuracy": 0.7423906549811363, |
| "num_tokens": 13729838.0, |
| "step": 367 |
| }, |
| { |
| "entropy": 0.6437906175851822, |
| "epoch": 2.3456, |
| "grad_norm": 0.009302763268351555, |
| "learning_rate": 0.0002, |
| "loss": 0.6494675874710083, |
| "mean_token_accuracy": 0.7354337424039841, |
| "num_tokens": 13767404.0, |
| "step": 368 |
| }, |
| { |
| "entropy": 0.6363216936588287, |
| "epoch": 2.352, |
| "grad_norm": 0.009825549088418484, |
| "learning_rate": 0.0002, |
| "loss": 0.640619158744812, |
| "mean_token_accuracy": 0.7399841696023941, |
| "num_tokens": 13805320.0, |
| "step": 369 |
| }, |
| { |
| "entropy": 0.6430623680353165, |
| "epoch": 2.3584, |
| "grad_norm": 0.008325744420289993, |
| "learning_rate": 0.0002, |
| "loss": 0.6433535814285278, |
| "mean_token_accuracy": 0.7388209700584412, |
| "num_tokens": 13843211.0, |
| "step": 370 |
| }, |
| { |
| "entropy": 0.6459617763757706, |
| "epoch": 2.3648, |
| "grad_norm": 0.009273998439311981, |
| "learning_rate": 0.0002, |
| "loss": 0.6418501138687134, |
| "mean_token_accuracy": 0.7380605787038803, |
| "num_tokens": 13880860.0, |
| "step": 371 |
| }, |
| { |
| "entropy": 0.6389967799186707, |
| "epoch": 2.3712, |
| "grad_norm": 0.009662107564508915, |
| "learning_rate": 0.0002, |
| "loss": 0.6336321830749512, |
| "mean_token_accuracy": 0.7438643798232079, |
| "num_tokens": 13918761.0, |
| "step": 372 |
| }, |
| { |
| "entropy": 0.638178676366806, |
| "epoch": 2.3776, |
| "grad_norm": 0.009039600379765034, |
| "learning_rate": 0.0002, |
| "loss": 0.642177164554596, |
| "mean_token_accuracy": 0.7402292564511299, |
| "num_tokens": 13956629.0, |
| "step": 373 |
| }, |
| { |
| "entropy": 0.6183496937155724, |
| "epoch": 2.384, |
| "grad_norm": 0.00997725035995245, |
| "learning_rate": 0.0002, |
| "loss": 0.6257633566856384, |
| "mean_token_accuracy": 0.7432282716035843, |
| "num_tokens": 13993705.0, |
| "step": 374 |
| }, |
| { |
| "entropy": 0.6249210014939308, |
| "epoch": 2.3904, |
| "grad_norm": 0.007910847663879395, |
| "learning_rate": 0.0002, |
| "loss": 0.625819981098175, |
| "mean_token_accuracy": 0.7441049888730049, |
| "num_tokens": 14031321.0, |
| "step": 375 |
| }, |
| { |
| "entropy": 0.6479079499840736, |
| "epoch": 2.3968, |
| "grad_norm": 0.00891756173223257, |
| "learning_rate": 0.0002, |
| "loss": 0.6501407623291016, |
| "mean_token_accuracy": 0.7355809286236763, |
| "num_tokens": 14069143.0, |
| "step": 376 |
| }, |
| { |
| "entropy": 0.6394218653440475, |
| "epoch": 2.4032, |
| "grad_norm": 0.00850125402212143, |
| "learning_rate": 0.0002, |
| "loss": 0.6394637823104858, |
| "mean_token_accuracy": 0.7385919019579887, |
| "num_tokens": 14106711.0, |
| "step": 377 |
| }, |
| { |
| "entropy": 0.6354732289910316, |
| "epoch": 2.4096, |
| "grad_norm": 0.008283271454274654, |
| "learning_rate": 0.0002, |
| "loss": 0.6353892087936401, |
| "mean_token_accuracy": 0.7419078797101974, |
| "num_tokens": 14144364.0, |
| "step": 378 |
| }, |
| { |
| "entropy": 0.6316136568784714, |
| "epoch": 2.416, |
| "grad_norm": 0.009771537035703659, |
| "learning_rate": 0.0002, |
| "loss": 0.6347823143005371, |
| "mean_token_accuracy": 0.7427188232541084, |
| "num_tokens": 14181995.0, |
| "step": 379 |
| }, |
| { |
| "entropy": 0.6375484988093376, |
| "epoch": 2.4224, |
| "grad_norm": 0.008568905293941498, |
| "learning_rate": 0.0002, |
| "loss": 0.6410992741584778, |
| "mean_token_accuracy": 0.7378129065036774, |
| "num_tokens": 14219687.0, |
| "step": 380 |
| }, |
| { |
| "entropy": 0.6333465948700905, |
| "epoch": 2.4288, |
| "grad_norm": 0.007412395905703306, |
| "learning_rate": 0.0002, |
| "loss": 0.6309605836868286, |
| "mean_token_accuracy": 0.7434795945882797, |
| "num_tokens": 14257055.0, |
| "step": 381 |
| }, |
| { |
| "entropy": 0.6269642487168312, |
| "epoch": 2.4352, |
| "grad_norm": 0.008765887469053268, |
| "learning_rate": 0.0002, |
| "loss": 0.6296891570091248, |
| "mean_token_accuracy": 0.7441322207450867, |
| "num_tokens": 14294332.0, |
| "step": 382 |
| }, |
| { |
| "entropy": 0.6352812573313713, |
| "epoch": 2.4416, |
| "grad_norm": 0.009595113806426525, |
| "learning_rate": 0.0002, |
| "loss": 0.6348291039466858, |
| "mean_token_accuracy": 0.7420725524425507, |
| "num_tokens": 14331865.0, |
| "step": 383 |
| }, |
| { |
| "entropy": 0.6441971585154533, |
| "epoch": 2.448, |
| "grad_norm": 0.008584806695580482, |
| "learning_rate": 0.0002, |
| "loss": 0.6498426198959351, |
| "mean_token_accuracy": 0.7357524335384369, |
| "num_tokens": 14369788.0, |
| "step": 384 |
| }, |
| { |
| "entropy": 0.6287561655044556, |
| "epoch": 2.4544, |
| "grad_norm": 0.008044449612498283, |
| "learning_rate": 0.0002, |
| "loss": 0.6315615177154541, |
| "mean_token_accuracy": 0.7426558956503868, |
| "num_tokens": 14407482.0, |
| "step": 385 |
| }, |
| { |
| "entropy": 0.6339204907417297, |
| "epoch": 2.4608, |
| "grad_norm": 0.007299972232431173, |
| "learning_rate": 0.0002, |
| "loss": 0.6352561116218567, |
| "mean_token_accuracy": 0.74134461581707, |
| "num_tokens": 14445123.0, |
| "step": 386 |
| }, |
| { |
| "entropy": 0.6295419782400131, |
| "epoch": 2.4672, |
| "grad_norm": 0.008794458582997322, |
| "learning_rate": 0.0002, |
| "loss": 0.6306071281433105, |
| "mean_token_accuracy": 0.7435100376605988, |
| "num_tokens": 14482719.0, |
| "step": 387 |
| }, |
| { |
| "entropy": 0.622240737080574, |
| "epoch": 2.4736000000000002, |
| "grad_norm": 0.008617876097559929, |
| "learning_rate": 0.0002, |
| "loss": 0.6234915256500244, |
| "mean_token_accuracy": 0.7468436509370804, |
| "num_tokens": 14520261.0, |
| "step": 388 |
| }, |
| { |
| "entropy": 0.6362800300121307, |
| "epoch": 2.48, |
| "grad_norm": 0.008423526771366596, |
| "learning_rate": 0.0002, |
| "loss": 0.641099214553833, |
| "mean_token_accuracy": 0.7397967800498009, |
| "num_tokens": 14557676.0, |
| "step": 389 |
| }, |
| { |
| "entropy": 0.6532713696360588, |
| "epoch": 2.4864, |
| "grad_norm": 0.008641418069601059, |
| "learning_rate": 0.0002, |
| "loss": 0.6506437063217163, |
| "mean_token_accuracy": 0.7350734695792198, |
| "num_tokens": 14595548.0, |
| "step": 390 |
| }, |
| { |
| "entropy": 0.6302274093031883, |
| "epoch": 2.4928, |
| "grad_norm": 0.00921640731394291, |
| "learning_rate": 0.0002, |
| "loss": 0.6322726607322693, |
| "mean_token_accuracy": 0.7424062266945839, |
| "num_tokens": 14632684.0, |
| "step": 391 |
| }, |
| { |
| "entropy": 0.6293173208832741, |
| "epoch": 2.4992, |
| "grad_norm": 0.008461368270218372, |
| "learning_rate": 0.0002, |
| "loss": 0.6278185844421387, |
| "mean_token_accuracy": 0.744764506816864, |
| "num_tokens": 14670523.0, |
| "step": 392 |
| }, |
| { |
| "entropy": 0.6276180446147919, |
| "epoch": 2.5056000000000003, |
| "grad_norm": 0.008572320453822613, |
| "learning_rate": 0.0002, |
| "loss": 0.631564736366272, |
| "mean_token_accuracy": 0.7426915839314461, |
| "num_tokens": 14708031.0, |
| "step": 393 |
| }, |
| { |
| "entropy": 0.6308008059859276, |
| "epoch": 2.512, |
| "grad_norm": 0.008926871232688427, |
| "learning_rate": 0.0002, |
| "loss": 0.633114755153656, |
| "mean_token_accuracy": 0.7416298165917397, |
| "num_tokens": 14745679.0, |
| "step": 394 |
| }, |
| { |
| "entropy": 0.6268336623907089, |
| "epoch": 2.5183999999999997, |
| "grad_norm": 0.008902951143682003, |
| "learning_rate": 0.0002, |
| "loss": 0.627051830291748, |
| "mean_token_accuracy": 0.7439748197793961, |
| "num_tokens": 14783397.0, |
| "step": 395 |
| }, |
| { |
| "entropy": 0.634651429951191, |
| "epoch": 2.5248, |
| "grad_norm": 0.00856532622128725, |
| "learning_rate": 0.0002, |
| "loss": 0.6363992691040039, |
| "mean_token_accuracy": 0.7408565506339073, |
| "num_tokens": 14820870.0, |
| "step": 396 |
| }, |
| { |
| "entropy": 0.6315286681056023, |
| "epoch": 2.5312, |
| "grad_norm": 0.009570743888616562, |
| "learning_rate": 0.0002, |
| "loss": 0.6403943300247192, |
| "mean_token_accuracy": 0.7384237721562386, |
| "num_tokens": 14858066.0, |
| "step": 397 |
| }, |
| { |
| "entropy": 0.6313930228352547, |
| "epoch": 2.5376, |
| "grad_norm": 0.007634198758751154, |
| "learning_rate": 0.0002, |
| "loss": 0.63489830493927, |
| "mean_token_accuracy": 0.740663692355156, |
| "num_tokens": 14895686.0, |
| "step": 398 |
| }, |
| { |
| "entropy": 0.6275153756141663, |
| "epoch": 2.544, |
| "grad_norm": 0.00890920590609312, |
| "learning_rate": 0.0002, |
| "loss": 0.6264928579330444, |
| "mean_token_accuracy": 0.7460935115814209, |
| "num_tokens": 14933293.0, |
| "step": 399 |
| }, |
| { |
| "entropy": 0.6245445236563683, |
| "epoch": 2.5504, |
| "grad_norm": 0.009081481955945492, |
| "learning_rate": 0.0002, |
| "loss": 0.6231961250305176, |
| "mean_token_accuracy": 0.7458623945713043, |
| "num_tokens": 14970626.0, |
| "step": 400 |
| }, |
| { |
| "entropy": 0.6321042701601982, |
| "epoch": 2.5568, |
| "grad_norm": 0.01011180505156517, |
| "learning_rate": 0.0002, |
| "loss": 0.6376926898956299, |
| "mean_token_accuracy": 0.7382810115814209, |
| "num_tokens": 15008147.0, |
| "step": 401 |
| }, |
| { |
| "entropy": 0.6281652376055717, |
| "epoch": 2.5632, |
| "grad_norm": 0.008269083686172962, |
| "learning_rate": 0.0002, |
| "loss": 0.6288952231407166, |
| "mean_token_accuracy": 0.7468898370862007, |
| "num_tokens": 15045200.0, |
| "step": 402 |
| }, |
| { |
| "entropy": 0.6325756087899208, |
| "epoch": 2.5696, |
| "grad_norm": 0.009284023195505142, |
| "learning_rate": 0.0002, |
| "loss": 0.6372162103652954, |
| "mean_token_accuracy": 0.7393135726451874, |
| "num_tokens": 15082728.0, |
| "step": 403 |
| }, |
| { |
| "entropy": 0.6326915472745895, |
| "epoch": 2.576, |
| "grad_norm": 0.008368260227143764, |
| "learning_rate": 0.0002, |
| "loss": 0.6289712190628052, |
| "mean_token_accuracy": 0.7438352182507515, |
| "num_tokens": 15120176.0, |
| "step": 404 |
| }, |
| { |
| "entropy": 0.6458227932453156, |
| "epoch": 2.5824, |
| "grad_norm": 0.008600444532930851, |
| "learning_rate": 0.0002, |
| "loss": 0.6437180042266846, |
| "mean_token_accuracy": 0.7360183447599411, |
| "num_tokens": 15157874.0, |
| "step": 405 |
| }, |
| { |
| "entropy": 0.6378503367304802, |
| "epoch": 2.5888, |
| "grad_norm": 0.008291950449347496, |
| "learning_rate": 0.0002, |
| "loss": 0.6357482075691223, |
| "mean_token_accuracy": 0.7405651807785034, |
| "num_tokens": 15195757.0, |
| "step": 406 |
| }, |
| { |
| "entropy": 0.6248553469777107, |
| "epoch": 2.5952, |
| "grad_norm": 0.009239988401532173, |
| "learning_rate": 0.0002, |
| "loss": 0.6330691576004028, |
| "mean_token_accuracy": 0.7403087541460991, |
| "num_tokens": 15232888.0, |
| "step": 407 |
| }, |
| { |
| "entropy": 0.6266547441482544, |
| "epoch": 2.6016, |
| "grad_norm": 0.008323184214532375, |
| "learning_rate": 0.0002, |
| "loss": 0.6295891404151917, |
| "mean_token_accuracy": 0.7445848137140274, |
| "num_tokens": 15270471.0, |
| "step": 408 |
| }, |
| { |
| "entropy": 0.6273859366774559, |
| "epoch": 2.608, |
| "grad_norm": 0.008808370679616928, |
| "learning_rate": 0.0002, |
| "loss": 0.6343215107917786, |
| "mean_token_accuracy": 0.7426254749298096, |
| "num_tokens": 15307996.0, |
| "step": 409 |
| }, |
| { |
| "entropy": 0.649120107293129, |
| "epoch": 2.6144, |
| "grad_norm": 0.008977086283266544, |
| "learning_rate": 0.0002, |
| "loss": 0.6475695371627808, |
| "mean_token_accuracy": 0.7367869392037392, |
| "num_tokens": 15345526.0, |
| "step": 410 |
| }, |
| { |
| "entropy": 0.6383312568068504, |
| "epoch": 2.6208, |
| "grad_norm": 0.009833469986915588, |
| "learning_rate": 0.0002, |
| "loss": 0.6327086091041565, |
| "mean_token_accuracy": 0.7418203428387642, |
| "num_tokens": 15382760.0, |
| "step": 411 |
| }, |
| { |
| "entropy": 0.6142470389604568, |
| "epoch": 2.6272, |
| "grad_norm": 0.007820895873010159, |
| "learning_rate": 0.0002, |
| "loss": 0.614084780216217, |
| "mean_token_accuracy": 0.7492156624794006, |
| "num_tokens": 15420133.0, |
| "step": 412 |
| }, |
| { |
| "entropy": 0.6232952103018761, |
| "epoch": 2.6336, |
| "grad_norm": 0.010564403608441353, |
| "learning_rate": 0.0002, |
| "loss": 0.6333082318305969, |
| "mean_token_accuracy": 0.7423960939049721, |
| "num_tokens": 15457883.0, |
| "step": 413 |
| }, |
| { |
| "entropy": 0.6330999732017517, |
| "epoch": 2.64, |
| "grad_norm": 0.009710205718874931, |
| "learning_rate": 0.0002, |
| "loss": 0.6388413906097412, |
| "mean_token_accuracy": 0.7408091574907303, |
| "num_tokens": 15495425.0, |
| "step": 414 |
| }, |
| { |
| "entropy": 0.6545180752873421, |
| "epoch": 2.6464, |
| "grad_norm": 0.00887272972613573, |
| "learning_rate": 0.0002, |
| "loss": 0.6515014171600342, |
| "mean_token_accuracy": 0.7343106046319008, |
| "num_tokens": 15532965.0, |
| "step": 415 |
| }, |
| { |
| "entropy": 0.6397780776023865, |
| "epoch": 2.6528, |
| "grad_norm": 0.008293447084724903, |
| "learning_rate": 0.0002, |
| "loss": 0.6368398666381836, |
| "mean_token_accuracy": 0.7398713007569313, |
| "num_tokens": 15570436.0, |
| "step": 416 |
| }, |
| { |
| "entropy": 0.6291993260383606, |
| "epoch": 2.6592000000000002, |
| "grad_norm": 0.008709436282515526, |
| "learning_rate": 0.0002, |
| "loss": 0.6272790431976318, |
| "mean_token_accuracy": 0.745321199297905, |
| "num_tokens": 15607874.0, |
| "step": 417 |
| }, |
| { |
| "entropy": 0.648408018052578, |
| "epoch": 2.6656, |
| "grad_norm": 0.009814375080168247, |
| "learning_rate": 0.0002, |
| "loss": 0.6569237112998962, |
| "mean_token_accuracy": 0.7306895926594734, |
| "num_tokens": 15645823.0, |
| "step": 418 |
| }, |
| { |
| "entropy": 0.6370497196912766, |
| "epoch": 2.672, |
| "grad_norm": 0.00858649704605341, |
| "learning_rate": 0.0002, |
| "loss": 0.6417921781539917, |
| "mean_token_accuracy": 0.738996684551239, |
| "num_tokens": 15683110.0, |
| "step": 419 |
| }, |
| { |
| "entropy": 0.6393727734684944, |
| "epoch": 2.6784, |
| "grad_norm": 0.009777788072824478, |
| "learning_rate": 0.0002, |
| "loss": 0.6401950120925903, |
| "mean_token_accuracy": 0.7391480058431625, |
| "num_tokens": 15720611.0, |
| "step": 420 |
| }, |
| { |
| "entropy": 0.63716159760952, |
| "epoch": 2.6848, |
| "grad_norm": 0.008626547642052174, |
| "learning_rate": 0.0002, |
| "loss": 0.6399793028831482, |
| "mean_token_accuracy": 0.739508643746376, |
| "num_tokens": 15758221.0, |
| "step": 421 |
| }, |
| { |
| "entropy": 0.6414335444569588, |
| "epoch": 2.6912000000000003, |
| "grad_norm": 0.009168457239866257, |
| "learning_rate": 0.0002, |
| "loss": 0.6497803926467896, |
| "mean_token_accuracy": 0.7342201620340347, |
| "num_tokens": 15795862.0, |
| "step": 422 |
| }, |
| { |
| "entropy": 0.6342490315437317, |
| "epoch": 2.6976, |
| "grad_norm": 0.009793863631784916, |
| "learning_rate": 0.0002, |
| "loss": 0.6359165906906128, |
| "mean_token_accuracy": 0.7401581779122353, |
| "num_tokens": 15833350.0, |
| "step": 423 |
| }, |
| { |
| "entropy": 0.6518041715025902, |
| "epoch": 2.7039999999999997, |
| "grad_norm": 0.0076965210027992725, |
| "learning_rate": 0.0002, |
| "loss": 0.649188756942749, |
| "mean_token_accuracy": 0.735841915011406, |
| "num_tokens": 15871335.0, |
| "step": 424 |
| }, |
| { |
| "entropy": 0.6324848383665085, |
| "epoch": 2.7104, |
| "grad_norm": 0.007825566455721855, |
| "learning_rate": 0.0002, |
| "loss": 0.6314542293548584, |
| "mean_token_accuracy": 0.7424084842205048, |
| "num_tokens": 15909163.0, |
| "step": 425 |
| }, |
| { |
| "entropy": 0.6271793767809868, |
| "epoch": 2.7168, |
| "grad_norm": 0.007992296479642391, |
| "learning_rate": 0.0002, |
| "loss": 0.6311610341072083, |
| "mean_token_accuracy": 0.7418703660368919, |
| "num_tokens": 15946937.0, |
| "step": 426 |
| }, |
| { |
| "entropy": 0.6191146075725555, |
| "epoch": 2.7232, |
| "grad_norm": 0.007840313948690891, |
| "learning_rate": 0.0002, |
| "loss": 0.6227446794509888, |
| "mean_token_accuracy": 0.7470360621809959, |
| "num_tokens": 15984420.0, |
| "step": 427 |
| }, |
| { |
| "entropy": 0.6226735487580299, |
| "epoch": 2.7296, |
| "grad_norm": 0.007951436564326286, |
| "learning_rate": 0.0002, |
| "loss": 0.6275327205657959, |
| "mean_token_accuracy": 0.7467052638530731, |
| "num_tokens": 16021985.0, |
| "step": 428 |
| }, |
| { |
| "entropy": 0.6366565078496933, |
| "epoch": 2.7359999999999998, |
| "grad_norm": 0.007951410487294197, |
| "learning_rate": 0.0002, |
| "loss": 0.6385185122489929, |
| "mean_token_accuracy": 0.7392742782831192, |
| "num_tokens": 16059718.0, |
| "step": 429 |
| }, |
| { |
| "entropy": 0.6241059601306915, |
| "epoch": 2.7424, |
| "grad_norm": 0.008495664224028587, |
| "learning_rate": 0.0002, |
| "loss": 0.6223422288894653, |
| "mean_token_accuracy": 0.7480814754962921, |
| "num_tokens": 16096969.0, |
| "step": 430 |
| }, |
| { |
| "entropy": 0.6395189017057419, |
| "epoch": 2.7488, |
| "grad_norm": 0.008117246441543102, |
| "learning_rate": 0.0002, |
| "loss": 0.6383851766586304, |
| "mean_token_accuracy": 0.7399205639958382, |
| "num_tokens": 16135311.0, |
| "step": 431 |
| }, |
| { |
| "entropy": 0.6342849209904671, |
| "epoch": 2.7552, |
| "grad_norm": 0.007573962211608887, |
| "learning_rate": 0.0002, |
| "loss": 0.6357378959655762, |
| "mean_token_accuracy": 0.7413295134902, |
| "num_tokens": 16173264.0, |
| "step": 432 |
| }, |
| { |
| "entropy": 0.6290313079953194, |
| "epoch": 2.7616, |
| "grad_norm": 0.00819240789860487, |
| "learning_rate": 0.0002, |
| "loss": 0.6312831044197083, |
| "mean_token_accuracy": 0.7436259835958481, |
| "num_tokens": 16210940.0, |
| "step": 433 |
| }, |
| { |
| "entropy": 0.6433441936969757, |
| "epoch": 2.768, |
| "grad_norm": 0.00860763993114233, |
| "learning_rate": 0.0002, |
| "loss": 0.6448662877082825, |
| "mean_token_accuracy": 0.7353287860751152, |
| "num_tokens": 16248287.0, |
| "step": 434 |
| }, |
| { |
| "entropy": 0.6330644562840462, |
| "epoch": 2.7744, |
| "grad_norm": 0.0077530574053525925, |
| "learning_rate": 0.0002, |
| "loss": 0.6352605819702148, |
| "mean_token_accuracy": 0.7418182790279388, |
| "num_tokens": 16285750.0, |
| "step": 435 |
| }, |
| { |
| "entropy": 0.6248625069856644, |
| "epoch": 2.7808, |
| "grad_norm": 0.007953410036861897, |
| "learning_rate": 0.0002, |
| "loss": 0.6288837790489197, |
| "mean_token_accuracy": 0.7424777820706367, |
| "num_tokens": 16322871.0, |
| "step": 436 |
| }, |
| { |
| "entropy": 0.6338153034448624, |
| "epoch": 2.7872, |
| "grad_norm": 0.008173540234565735, |
| "learning_rate": 0.0002, |
| "loss": 0.6316856145858765, |
| "mean_token_accuracy": 0.743153415620327, |
| "num_tokens": 16360741.0, |
| "step": 437 |
| }, |
| { |
| "entropy": 0.6180099546909332, |
| "epoch": 2.7936, |
| "grad_norm": 0.008011853322386742, |
| "learning_rate": 0.0002, |
| "loss": 0.6195465922355652, |
| "mean_token_accuracy": 0.7491164207458496, |
| "num_tokens": 16398052.0, |
| "step": 438 |
| }, |
| { |
| "entropy": 0.6288798898458481, |
| "epoch": 2.8, |
| "grad_norm": 0.008486307226121426, |
| "learning_rate": 0.0002, |
| "loss": 0.6308120489120483, |
| "mean_token_accuracy": 0.7431682348251343, |
| "num_tokens": 16435504.0, |
| "step": 439 |
| }, |
| { |
| "entropy": 0.6349303498864174, |
| "epoch": 2.8064, |
| "grad_norm": 0.009010681882500648, |
| "learning_rate": 0.0002, |
| "loss": 0.632607102394104, |
| "mean_token_accuracy": 0.7425792217254639, |
| "num_tokens": 16473212.0, |
| "step": 440 |
| }, |
| { |
| "entropy": 0.630001574754715, |
| "epoch": 2.8128, |
| "grad_norm": 0.008531573228538036, |
| "learning_rate": 0.0002, |
| "loss": 0.6290241479873657, |
| "mean_token_accuracy": 0.7448351979255676, |
| "num_tokens": 16510183.0, |
| "step": 441 |
| }, |
| { |
| "entropy": 0.6317692324519157, |
| "epoch": 2.8192, |
| "grad_norm": 0.008379535749554634, |
| "learning_rate": 0.0002, |
| "loss": 0.6360982656478882, |
| "mean_token_accuracy": 0.7403805702924728, |
| "num_tokens": 16547649.0, |
| "step": 442 |
| }, |
| { |
| "entropy": 0.6221532076597214, |
| "epoch": 2.8256, |
| "grad_norm": 0.00981364119797945, |
| "learning_rate": 0.0002, |
| "loss": 0.6305652856826782, |
| "mean_token_accuracy": 0.7410502806305885, |
| "num_tokens": 16584772.0, |
| "step": 443 |
| }, |
| { |
| "entropy": 0.6281775683164597, |
| "epoch": 2.832, |
| "grad_norm": 0.009363848716020584, |
| "learning_rate": 0.0002, |
| "loss": 0.6325273513793945, |
| "mean_token_accuracy": 0.7412790656089783, |
| "num_tokens": 16622377.0, |
| "step": 444 |
| }, |
| { |
| "entropy": 0.6282860860228539, |
| "epoch": 2.8384, |
| "grad_norm": 0.008815777488052845, |
| "learning_rate": 0.0002, |
| "loss": 0.6224972009658813, |
| "mean_token_accuracy": 0.7473303973674774, |
| "num_tokens": 16659850.0, |
| "step": 445 |
| }, |
| { |
| "entropy": 0.6256547048687935, |
| "epoch": 2.8448, |
| "grad_norm": 0.008997517637908459, |
| "learning_rate": 0.0002, |
| "loss": 0.6249480247497559, |
| "mean_token_accuracy": 0.744784526526928, |
| "num_tokens": 16697507.0, |
| "step": 446 |
| }, |
| { |
| "entropy": 0.6432123258709908, |
| "epoch": 2.8512, |
| "grad_norm": 0.007546784356236458, |
| "learning_rate": 0.0002, |
| "loss": 0.6468585133552551, |
| "mean_token_accuracy": 0.7387454062700272, |
| "num_tokens": 16735166.0, |
| "step": 447 |
| }, |
| { |
| "entropy": 0.6291612312197685, |
| "epoch": 2.8576, |
| "grad_norm": 0.008677622303366661, |
| "learning_rate": 0.0002, |
| "loss": 0.6363067030906677, |
| "mean_token_accuracy": 0.7402229011058807, |
| "num_tokens": 16772700.0, |
| "step": 448 |
| }, |
| { |
| "entropy": 0.6394010931253433, |
| "epoch": 2.864, |
| "grad_norm": 0.008233144879341125, |
| "learning_rate": 0.0002, |
| "loss": 0.6435496807098389, |
| "mean_token_accuracy": 0.7371494546532631, |
| "num_tokens": 16810206.0, |
| "step": 449 |
| }, |
| { |
| "entropy": 0.6323223188519478, |
| "epoch": 2.8704, |
| "grad_norm": 0.009190903976559639, |
| "learning_rate": 0.0002, |
| "loss": 0.6313977837562561, |
| "mean_token_accuracy": 0.74195995926857, |
| "num_tokens": 16847440.0, |
| "step": 450 |
| }, |
| { |
| "entropy": 0.6317964419722557, |
| "epoch": 2.8768000000000002, |
| "grad_norm": 0.008045881986618042, |
| "learning_rate": 0.0002, |
| "loss": 0.6350542306900024, |
| "mean_token_accuracy": 0.7399737685918808, |
| "num_tokens": 16884842.0, |
| "step": 451 |
| }, |
| { |
| "entropy": 0.6307216063141823, |
| "epoch": 2.8832, |
| "grad_norm": 0.008613558486104012, |
| "learning_rate": 0.0002, |
| "loss": 0.6330459117889404, |
| "mean_token_accuracy": 0.7425104603171349, |
| "num_tokens": 16922153.0, |
| "step": 452 |
| }, |
| { |
| "entropy": 0.6381876915693283, |
| "epoch": 2.8895999999999997, |
| "grad_norm": 0.008792484179139137, |
| "learning_rate": 0.0002, |
| "loss": 0.6396152973175049, |
| "mean_token_accuracy": 0.7395381852984428, |
| "num_tokens": 16959837.0, |
| "step": 453 |
| }, |
| { |
| "entropy": 0.6402597278356552, |
| "epoch": 2.896, |
| "grad_norm": 0.008886914700269699, |
| "learning_rate": 0.0002, |
| "loss": 0.6391183137893677, |
| "mean_token_accuracy": 0.7400619834661484, |
| "num_tokens": 16997252.0, |
| "step": 454 |
| }, |
| { |
| "entropy": 0.6395518109202385, |
| "epoch": 2.9024, |
| "grad_norm": 0.008145366795361042, |
| "learning_rate": 0.0002, |
| "loss": 0.6410524845123291, |
| "mean_token_accuracy": 0.7384562343358994, |
| "num_tokens": 17034792.0, |
| "step": 455 |
| }, |
| { |
| "entropy": 0.6335340291261673, |
| "epoch": 2.9088000000000003, |
| "grad_norm": 0.008513481356203556, |
| "learning_rate": 0.0002, |
| "loss": 0.6360284686088562, |
| "mean_token_accuracy": 0.7419657409191132, |
| "num_tokens": 17072806.0, |
| "step": 456 |
| }, |
| { |
| "entropy": 0.6339850574731827, |
| "epoch": 2.9152, |
| "grad_norm": 0.00826951116323471, |
| "learning_rate": 0.0002, |
| "loss": 0.6338396668434143, |
| "mean_token_accuracy": 0.7435676008462906, |
| "num_tokens": 17110256.0, |
| "step": 457 |
| }, |
| { |
| "entropy": 0.6330336853861809, |
| "epoch": 2.9215999999999998, |
| "grad_norm": 0.008118857629597187, |
| "learning_rate": 0.0002, |
| "loss": 0.6347401738166809, |
| "mean_token_accuracy": 0.7419733926653862, |
| "num_tokens": 17147669.0, |
| "step": 458 |
| }, |
| { |
| "entropy": 0.6518657803535461, |
| "epoch": 2.928, |
| "grad_norm": 0.008373484946787357, |
| "learning_rate": 0.0002, |
| "loss": 0.6521078944206238, |
| "mean_token_accuracy": 0.7351536229252815, |
| "num_tokens": 17185406.0, |
| "step": 459 |
| }, |
| { |
| "entropy": 0.6362840831279755, |
| "epoch": 2.9344, |
| "grad_norm": 0.00781342200934887, |
| "learning_rate": 0.0002, |
| "loss": 0.6393336057662964, |
| "mean_token_accuracy": 0.7391062676906586, |
| "num_tokens": 17223104.0, |
| "step": 460 |
| }, |
| { |
| "entropy": 0.6365083158016205, |
| "epoch": 2.9408, |
| "grad_norm": 0.010520093142986298, |
| "learning_rate": 0.0002, |
| "loss": 0.643227219581604, |
| "mean_token_accuracy": 0.7367514818906784, |
| "num_tokens": 17260499.0, |
| "step": 461 |
| }, |
| { |
| "entropy": 0.6365673765540123, |
| "epoch": 2.9472, |
| "grad_norm": 0.008144881576299667, |
| "learning_rate": 0.0002, |
| "loss": 0.6345622539520264, |
| "mean_token_accuracy": 0.7417429983615875, |
| "num_tokens": 17298154.0, |
| "step": 462 |
| }, |
| { |
| "entropy": 0.6422977894544601, |
| "epoch": 2.9536, |
| "grad_norm": 0.007375301793217659, |
| "learning_rate": 0.0002, |
| "loss": 0.6420764923095703, |
| "mean_token_accuracy": 0.737017072737217, |
| "num_tokens": 17336075.0, |
| "step": 463 |
| }, |
| { |
| "entropy": 0.6339726597070694, |
| "epoch": 2.96, |
| "grad_norm": 0.008432124741375446, |
| "learning_rate": 0.0002, |
| "loss": 0.6357682347297668, |
| "mean_token_accuracy": 0.742248572409153, |
| "num_tokens": 17373430.0, |
| "step": 464 |
| }, |
| { |
| "entropy": 0.6369189694523811, |
| "epoch": 2.9664, |
| "grad_norm": 0.008471203036606312, |
| "learning_rate": 0.0002, |
| "loss": 0.6386595964431763, |
| "mean_token_accuracy": 0.7397382780909538, |
| "num_tokens": 17411298.0, |
| "step": 465 |
| }, |
| { |
| "entropy": 0.6291254833340645, |
| "epoch": 2.9728, |
| "grad_norm": 0.007794877514243126, |
| "learning_rate": 0.0002, |
| "loss": 0.6330430507659912, |
| "mean_token_accuracy": 0.743395060300827, |
| "num_tokens": 17448723.0, |
| "step": 466 |
| }, |
| { |
| "entropy": 0.6243666335940361, |
| "epoch": 2.9792, |
| "grad_norm": 0.008405648171901703, |
| "learning_rate": 0.0002, |
| "loss": 0.6291847229003906, |
| "mean_token_accuracy": 0.7437793165445328, |
| "num_tokens": 17486207.0, |
| "step": 467 |
| }, |
| { |
| "entropy": 0.6350819692015648, |
| "epoch": 2.9856, |
| "grad_norm": 0.008273884654045105, |
| "learning_rate": 0.0002, |
| "loss": 0.6370283365249634, |
| "mean_token_accuracy": 0.7423520013689995, |
| "num_tokens": 17524019.0, |
| "step": 468 |
| }, |
| { |
| "entropy": 0.6391937509179115, |
| "epoch": 2.992, |
| "grad_norm": 0.008686189539730549, |
| "learning_rate": 0.0002, |
| "loss": 0.6426953077316284, |
| "mean_token_accuracy": 0.7379648461937904, |
| "num_tokens": 17561604.0, |
| "step": 469 |
| }, |
| { |
| "entropy": 0.6394234076142311, |
| "epoch": 2.9984, |
| "grad_norm": 0.008572033606469631, |
| "learning_rate": 0.0002, |
| "loss": 0.6405370235443115, |
| "mean_token_accuracy": 0.7394323572516441, |
| "num_tokens": 17599047.0, |
| "step": 470 |
| }, |
| { |
| "entropy": 0.646001398563385, |
| "epoch": 3.0, |
| "grad_norm": 0.016055934131145477, |
| "learning_rate": 0.0002, |
| "loss": 0.654330313205719, |
| "mean_token_accuracy": 0.7357074916362762, |
| "num_tokens": 17608447.0, |
| "step": 471 |
| }, |
| { |
| "entropy": 0.6399871557950974, |
| "epoch": 3.0064, |
| "grad_norm": 0.010128894820809364, |
| "learning_rate": 0.0002, |
| "loss": 0.630492091178894, |
| "mean_token_accuracy": 0.7438428327441216, |
| "num_tokens": 17646580.0, |
| "step": 472 |
| }, |
| { |
| "entropy": 0.6400877311825752, |
| "epoch": 3.0128, |
| "grad_norm": 0.0109670115634799, |
| "learning_rate": 0.0002, |
| "loss": 0.6348856687545776, |
| "mean_token_accuracy": 0.7409028187394142, |
| "num_tokens": 17684203.0, |
| "step": 473 |
| }, |
| { |
| "entropy": 0.6349283009767532, |
| "epoch": 3.0192, |
| "grad_norm": 0.010457641445100307, |
| "learning_rate": 0.0002, |
| "loss": 0.6400600671768188, |
| "mean_token_accuracy": 0.7396369203925133, |
| "num_tokens": 17721781.0, |
| "step": 474 |
| }, |
| { |
| "entropy": 0.6234990581870079, |
| "epoch": 3.0256, |
| "grad_norm": 0.01080863457173109, |
| "learning_rate": 0.0002, |
| "loss": 0.6308765411376953, |
| "mean_token_accuracy": 0.7440793961286545, |
| "num_tokens": 17759054.0, |
| "step": 475 |
| }, |
| { |
| "entropy": 0.6226209849119186, |
| "epoch": 3.032, |
| "grad_norm": 0.010244046337902546, |
| "learning_rate": 0.0002, |
| "loss": 0.6284743547439575, |
| "mean_token_accuracy": 0.7413820326328278, |
| "num_tokens": 17796583.0, |
| "step": 476 |
| }, |
| { |
| "entropy": 0.626485787332058, |
| "epoch": 3.0384, |
| "grad_norm": 0.00895832572132349, |
| "learning_rate": 0.0002, |
| "loss": 0.6250468492507935, |
| "mean_token_accuracy": 0.7454337328672409, |
| "num_tokens": 17833917.0, |
| "step": 477 |
| }, |
| { |
| "entropy": 0.6430812701582909, |
| "epoch": 3.0448, |
| "grad_norm": 0.011450681835412979, |
| "learning_rate": 0.0002, |
| "loss": 0.636460542678833, |
| "mean_token_accuracy": 0.737629309296608, |
| "num_tokens": 17871185.0, |
| "step": 478 |
| }, |
| { |
| "entropy": 0.6313450038433075, |
| "epoch": 3.0512, |
| "grad_norm": 0.010822657495737076, |
| "learning_rate": 0.0002, |
| "loss": 0.6283341646194458, |
| "mean_token_accuracy": 0.7447119951248169, |
| "num_tokens": 17909021.0, |
| "step": 479 |
| }, |
| { |
| "entropy": 0.616793729364872, |
| "epoch": 3.0576, |
| "grad_norm": 0.012827937491238117, |
| "learning_rate": 0.0002, |
| "loss": 0.6257752180099487, |
| "mean_token_accuracy": 0.7451038733124733, |
| "num_tokens": 17946561.0, |
| "step": 480 |
| }, |
| { |
| "entropy": 0.6195474341511726, |
| "epoch": 3.064, |
| "grad_norm": 0.011573764495551586, |
| "learning_rate": 0.0002, |
| "loss": 0.630095899105072, |
| "mean_token_accuracy": 0.7431527376174927, |
| "num_tokens": 17983774.0, |
| "step": 481 |
| }, |
| { |
| "entropy": 0.6207288056612015, |
| "epoch": 3.0704, |
| "grad_norm": 0.008784581907093525, |
| "learning_rate": 0.0002, |
| "loss": 0.6228084564208984, |
| "mean_token_accuracy": 0.7441780641674995, |
| "num_tokens": 18021797.0, |
| "step": 482 |
| }, |
| { |
| "entropy": 0.6219965890049934, |
| "epoch": 3.0768, |
| "grad_norm": 0.009525037370622158, |
| "learning_rate": 0.0002, |
| "loss": 0.6203585863113403, |
| "mean_token_accuracy": 0.7454776242375374, |
| "num_tokens": 18059600.0, |
| "step": 483 |
| }, |
| { |
| "entropy": 0.6240369379520416, |
| "epoch": 3.0832, |
| "grad_norm": 0.010099082253873348, |
| "learning_rate": 0.0002, |
| "loss": 0.6236456632614136, |
| "mean_token_accuracy": 0.7461361885070801, |
| "num_tokens": 18097249.0, |
| "step": 484 |
| }, |
| { |
| "entropy": 0.6231376677751541, |
| "epoch": 3.0896, |
| "grad_norm": 0.009384946897625923, |
| "learning_rate": 0.0002, |
| "loss": 0.6250054240226746, |
| "mean_token_accuracy": 0.7437941208481789, |
| "num_tokens": 18134395.0, |
| "step": 485 |
| }, |
| { |
| "entropy": 0.6311322897672653, |
| "epoch": 3.096, |
| "grad_norm": 0.010897154919803143, |
| "learning_rate": 0.0002, |
| "loss": 0.6397508978843689, |
| "mean_token_accuracy": 0.7386776655912399, |
| "num_tokens": 18171963.0, |
| "step": 486 |
| }, |
| { |
| "entropy": 0.62527284771204, |
| "epoch": 3.1024, |
| "grad_norm": 0.009014398790895939, |
| "learning_rate": 0.0002, |
| "loss": 0.629889726638794, |
| "mean_token_accuracy": 0.7426332533359528, |
| "num_tokens": 18209290.0, |
| "step": 487 |
| }, |
| { |
| "entropy": 0.6315117180347443, |
| "epoch": 3.1088, |
| "grad_norm": 0.010383408516645432, |
| "learning_rate": 0.0002, |
| "loss": 0.6257723569869995, |
| "mean_token_accuracy": 0.7457722872495651, |
| "num_tokens": 18247004.0, |
| "step": 488 |
| }, |
| { |
| "entropy": 0.6517661288380623, |
| "epoch": 3.1152, |
| "grad_norm": 0.009840711019933224, |
| "learning_rate": 0.0002, |
| "loss": 0.6448700428009033, |
| "mean_token_accuracy": 0.7368841990828514, |
| "num_tokens": 18284521.0, |
| "step": 489 |
| }, |
| { |
| "entropy": 0.6304850652813911, |
| "epoch": 3.1216, |
| "grad_norm": 0.009999154135584831, |
| "learning_rate": 0.0002, |
| "loss": 0.6314412951469421, |
| "mean_token_accuracy": 0.7430186495184898, |
| "num_tokens": 18321986.0, |
| "step": 490 |
| }, |
| { |
| "entropy": 0.6318495348095894, |
| "epoch": 3.128, |
| "grad_norm": 0.011276421137154102, |
| "learning_rate": 0.0002, |
| "loss": 0.6365323066711426, |
| "mean_token_accuracy": 0.7421404719352722, |
| "num_tokens": 18359940.0, |
| "step": 491 |
| }, |
| { |
| "entropy": 0.6343097537755966, |
| "epoch": 3.1344, |
| "grad_norm": 0.009451535530388355, |
| "learning_rate": 0.0002, |
| "loss": 0.6381996273994446, |
| "mean_token_accuracy": 0.7415077835321426, |
| "num_tokens": 18397600.0, |
| "step": 492 |
| }, |
| { |
| "entropy": 0.6369383260607719, |
| "epoch": 3.1408, |
| "grad_norm": 0.009595794603228569, |
| "learning_rate": 0.0002, |
| "loss": 0.6356371641159058, |
| "mean_token_accuracy": 0.7401534095406532, |
| "num_tokens": 18435100.0, |
| "step": 493 |
| }, |
| { |
| "entropy": 0.6311136037111282, |
| "epoch": 3.1471999999999998, |
| "grad_norm": 0.011402090080082417, |
| "learning_rate": 0.0002, |
| "loss": 0.630678117275238, |
| "mean_token_accuracy": 0.7420787587761879, |
| "num_tokens": 18472437.0, |
| "step": 494 |
| }, |
| { |
| "entropy": 0.6152165159583092, |
| "epoch": 3.1536, |
| "grad_norm": 0.009202217683196068, |
| "learning_rate": 0.0002, |
| "loss": 0.6150789260864258, |
| "mean_token_accuracy": 0.749266542494297, |
| "num_tokens": 18509694.0, |
| "step": 495 |
| }, |
| { |
| "entropy": 0.6187552213668823, |
| "epoch": 3.16, |
| "grad_norm": 0.012286514043807983, |
| "learning_rate": 0.0002, |
| "loss": 0.6278830170631409, |
| "mean_token_accuracy": 0.7449735552072525, |
| "num_tokens": 18547270.0, |
| "step": 496 |
| }, |
| { |
| "entropy": 0.624017171561718, |
| "epoch": 3.1664, |
| "grad_norm": 0.009709254838526249, |
| "learning_rate": 0.0002, |
| "loss": 0.6308646202087402, |
| "mean_token_accuracy": 0.7407297566533089, |
| "num_tokens": 18584781.0, |
| "step": 497 |
| }, |
| { |
| "entropy": 0.6381459310650826, |
| "epoch": 3.1728, |
| "grad_norm": 0.010118975304067135, |
| "learning_rate": 0.0002, |
| "loss": 0.6422901153564453, |
| "mean_token_accuracy": 0.7380207404494286, |
| "num_tokens": 18622605.0, |
| "step": 498 |
| }, |
| { |
| "entropy": 0.6330775320529938, |
| "epoch": 3.1792, |
| "grad_norm": 0.010614707134664059, |
| "learning_rate": 0.0002, |
| "loss": 0.626909613609314, |
| "mean_token_accuracy": 0.7434390485286713, |
| "num_tokens": 18660181.0, |
| "step": 499 |
| }, |
| { |
| "entropy": 0.6467690318822861, |
| "epoch": 3.1856, |
| "grad_norm": 0.011636339128017426, |
| "learning_rate": 0.0002, |
| "loss": 0.6417078971862793, |
| "mean_token_accuracy": 0.7391890659928322, |
| "num_tokens": 18697960.0, |
| "step": 500 |
| }, |
| { |
| "entropy": 0.642953485250473, |
| "epoch": 3.192, |
| "grad_norm": 0.009976604022085667, |
| "learning_rate": 0.0002, |
| "loss": 0.6437498331069946, |
| "mean_token_accuracy": 0.7397104203701019, |
| "num_tokens": 18735678.0, |
| "step": 501 |
| }, |
| { |
| "entropy": 0.6099938452243805, |
| "epoch": 3.1984, |
| "grad_norm": 0.012410764582455158, |
| "learning_rate": 0.0002, |
| "loss": 0.6217681169509888, |
| "mean_token_accuracy": 0.7468984425067902, |
| "num_tokens": 18773294.0, |
| "step": 502 |
| }, |
| { |
| "entropy": 0.6207045987248421, |
| "epoch": 3.2048, |
| "grad_norm": 0.01231430098414421, |
| "learning_rate": 0.0002, |
| "loss": 0.6315573453903198, |
| "mean_token_accuracy": 0.7444091141223907, |
| "num_tokens": 18810845.0, |
| "step": 503 |
| }, |
| { |
| "entropy": 0.6327609792351723, |
| "epoch": 3.2112, |
| "grad_norm": 0.009783076122403145, |
| "learning_rate": 0.0002, |
| "loss": 0.6313201189041138, |
| "mean_token_accuracy": 0.7418917194008827, |
| "num_tokens": 18848236.0, |
| "step": 504 |
| }, |
| { |
| "entropy": 0.6450697854161263, |
| "epoch": 3.2176, |
| "grad_norm": 0.011842023581266403, |
| "learning_rate": 0.0002, |
| "loss": 0.6390271186828613, |
| "mean_token_accuracy": 0.7399028763175011, |
| "num_tokens": 18885816.0, |
| "step": 505 |
| }, |
| { |
| "entropy": 0.6308076307177544, |
| "epoch": 3.224, |
| "grad_norm": 0.009748830460011959, |
| "learning_rate": 0.0002, |
| "loss": 0.6288598775863647, |
| "mean_token_accuracy": 0.7437896579504013, |
| "num_tokens": 18923477.0, |
| "step": 506 |
| }, |
| { |
| "entropy": 0.6379056051373482, |
| "epoch": 3.2304, |
| "grad_norm": 0.009498417377471924, |
| "learning_rate": 0.0002, |
| "loss": 0.6368851661682129, |
| "mean_token_accuracy": 0.740045078098774, |
| "num_tokens": 18960975.0, |
| "step": 507 |
| }, |
| { |
| "entropy": 0.6196693256497383, |
| "epoch": 3.2368, |
| "grad_norm": 0.010206184349954128, |
| "learning_rate": 0.0002, |
| "loss": 0.6276986598968506, |
| "mean_token_accuracy": 0.7443438991904259, |
| "num_tokens": 18998695.0, |
| "step": 508 |
| }, |
| { |
| "entropy": 0.6081546768546104, |
| "epoch": 3.2432, |
| "grad_norm": 0.011067412793636322, |
| "learning_rate": 0.0002, |
| "loss": 0.617774248123169, |
| "mean_token_accuracy": 0.7473630830645561, |
| "num_tokens": 19036024.0, |
| "step": 509 |
| }, |
| { |
| "entropy": 0.621229961514473, |
| "epoch": 3.2496, |
| "grad_norm": 0.009409903548657894, |
| "learning_rate": 0.0002, |
| "loss": 0.6242153644561768, |
| "mean_token_accuracy": 0.7461365386843681, |
| "num_tokens": 19073279.0, |
| "step": 510 |
| }, |
| { |
| "entropy": 0.6359136626124382, |
| "epoch": 3.2560000000000002, |
| "grad_norm": 0.01134317647665739, |
| "learning_rate": 0.0002, |
| "loss": 0.6272875070571899, |
| "mean_token_accuracy": 0.7440386563539505, |
| "num_tokens": 19110879.0, |
| "step": 511 |
| }, |
| { |
| "entropy": 0.6344882696866989, |
| "epoch": 3.2624, |
| "grad_norm": 0.009477692656219006, |
| "learning_rate": 0.0002, |
| "loss": 0.6296730041503906, |
| "mean_token_accuracy": 0.7432499378919601, |
| "num_tokens": 19148500.0, |
| "step": 512 |
| }, |
| { |
| "entropy": 0.6398265957832336, |
| "epoch": 3.2688, |
| "grad_norm": 0.009287470020353794, |
| "learning_rate": 0.0002, |
| "loss": 0.6409690976142883, |
| "mean_token_accuracy": 0.7397137433290482, |
| "num_tokens": 19186265.0, |
| "step": 513 |
| }, |
| { |
| "entropy": 0.6291618198156357, |
| "epoch": 3.2752, |
| "grad_norm": 0.010224799625575542, |
| "learning_rate": 0.0002, |
| "loss": 0.6341534852981567, |
| "mean_token_accuracy": 0.7401559799909592, |
| "num_tokens": 19224100.0, |
| "step": 514 |
| }, |
| { |
| "entropy": 0.6363715305924416, |
| "epoch": 3.2816, |
| "grad_norm": 0.009469510987401009, |
| "learning_rate": 0.0002, |
| "loss": 0.6414492130279541, |
| "mean_token_accuracy": 0.7395576015114784, |
| "num_tokens": 19261530.0, |
| "step": 515 |
| }, |
| { |
| "entropy": 0.623082734644413, |
| "epoch": 3.288, |
| "grad_norm": 0.009947684593498707, |
| "learning_rate": 0.0002, |
| "loss": 0.6218703985214233, |
| "mean_token_accuracy": 0.7470062673091888, |
| "num_tokens": 19299016.0, |
| "step": 516 |
| }, |
| { |
| "entropy": 0.6309391483664513, |
| "epoch": 3.2944, |
| "grad_norm": 0.008808617480099201, |
| "learning_rate": 0.0002, |
| "loss": 0.6311261653900146, |
| "mean_token_accuracy": 0.7421472296118736, |
| "num_tokens": 19336795.0, |
| "step": 517 |
| }, |
| { |
| "entropy": 0.6172879338264465, |
| "epoch": 3.3008, |
| "grad_norm": 0.009716369211673737, |
| "learning_rate": 0.0002, |
| "loss": 0.6209211945533752, |
| "mean_token_accuracy": 0.7458591684699059, |
| "num_tokens": 19374516.0, |
| "step": 518 |
| }, |
| { |
| "entropy": 0.624429427087307, |
| "epoch": 3.3072, |
| "grad_norm": 0.00985341053456068, |
| "learning_rate": 0.0002, |
| "loss": 0.6280737519264221, |
| "mean_token_accuracy": 0.7443241253495216, |
| "num_tokens": 19412000.0, |
| "step": 519 |
| }, |
| { |
| "entropy": 0.6387547329068184, |
| "epoch": 3.3136, |
| "grad_norm": 0.010449756868183613, |
| "learning_rate": 0.0002, |
| "loss": 0.6452560424804688, |
| "mean_token_accuracy": 0.7374782711267471, |
| "num_tokens": 19449428.0, |
| "step": 520 |
| }, |
| { |
| "entropy": 0.6452173292636871, |
| "epoch": 3.32, |
| "grad_norm": 0.010232311673462391, |
| "learning_rate": 0.0002, |
| "loss": 0.6446540355682373, |
| "mean_token_accuracy": 0.7369571030139923, |
| "num_tokens": 19486584.0, |
| "step": 521 |
| }, |
| { |
| "entropy": 0.6503598615527153, |
| "epoch": 3.3264, |
| "grad_norm": 0.009941341355443, |
| "learning_rate": 0.0002, |
| "loss": 0.6453627347946167, |
| "mean_token_accuracy": 0.736748069524765, |
| "num_tokens": 19524352.0, |
| "step": 522 |
| }, |
| { |
| "entropy": 0.6315410137176514, |
| "epoch": 3.3327999999999998, |
| "grad_norm": 0.011314695701003075, |
| "learning_rate": 0.0002, |
| "loss": 0.6289575099945068, |
| "mean_token_accuracy": 0.7419339716434479, |
| "num_tokens": 19561915.0, |
| "step": 523 |
| }, |
| { |
| "entropy": 0.6262854412198067, |
| "epoch": 3.3392, |
| "grad_norm": 0.010391976684331894, |
| "learning_rate": 0.0002, |
| "loss": 0.6323624849319458, |
| "mean_token_accuracy": 0.7404907718300819, |
| "num_tokens": 19599545.0, |
| "step": 524 |
| }, |
| { |
| "entropy": 0.6337175592780113, |
| "epoch": 3.3456, |
| "grad_norm": 0.011693738400936127, |
| "learning_rate": 0.0002, |
| "loss": 0.6432880163192749, |
| "mean_token_accuracy": 0.7387639954686165, |
| "num_tokens": 19637116.0, |
| "step": 525 |
| }, |
| { |
| "entropy": 0.633139468729496, |
| "epoch": 3.352, |
| "grad_norm": 0.009820731356739998, |
| "learning_rate": 0.0002, |
| "loss": 0.6332041621208191, |
| "mean_token_accuracy": 0.7423391342163086, |
| "num_tokens": 19674921.0, |
| "step": 526 |
| }, |
| { |
| "entropy": 0.6280725598335266, |
| "epoch": 3.3584, |
| "grad_norm": 0.009054291062057018, |
| "learning_rate": 0.0002, |
| "loss": 0.628294825553894, |
| "mean_token_accuracy": 0.7419228628277779, |
| "num_tokens": 19712717.0, |
| "step": 527 |
| }, |
| { |
| "entropy": 0.6336539536714554, |
| "epoch": 3.3648, |
| "grad_norm": 0.010253396816551685, |
| "learning_rate": 0.0002, |
| "loss": 0.6339755654335022, |
| "mean_token_accuracy": 0.7397957965731621, |
| "num_tokens": 19749941.0, |
| "step": 528 |
| }, |
| { |
| "entropy": 0.6203584149479866, |
| "epoch": 3.3712, |
| "grad_norm": 0.009867236949503422, |
| "learning_rate": 0.0002, |
| "loss": 0.6247453689575195, |
| "mean_token_accuracy": 0.7431770488619804, |
| "num_tokens": 19787178.0, |
| "step": 529 |
| }, |
| { |
| "entropy": 0.6316971704363823, |
| "epoch": 3.3776, |
| "grad_norm": 0.009513068944215775, |
| "learning_rate": 0.0002, |
| "loss": 0.6362742781639099, |
| "mean_token_accuracy": 0.737493634223938, |
| "num_tokens": 19824578.0, |
| "step": 530 |
| }, |
| { |
| "entropy": 0.6340960711240768, |
| "epoch": 3.384, |
| "grad_norm": 0.009593709371984005, |
| "learning_rate": 0.0002, |
| "loss": 0.6331235766410828, |
| "mean_token_accuracy": 0.7399430274963379, |
| "num_tokens": 19862390.0, |
| "step": 531 |
| }, |
| { |
| "entropy": 0.6132048889994621, |
| "epoch": 3.3904, |
| "grad_norm": 0.010046555660665035, |
| "learning_rate": 0.0002, |
| "loss": 0.6161696910858154, |
| "mean_token_accuracy": 0.7499357238411903, |
| "num_tokens": 19899845.0, |
| "step": 532 |
| }, |
| { |
| "entropy": 0.6227102503180504, |
| "epoch": 3.3968, |
| "grad_norm": 0.010463609360158443, |
| "learning_rate": 0.0002, |
| "loss": 0.6273203492164612, |
| "mean_token_accuracy": 0.7455707415938377, |
| "num_tokens": 19937650.0, |
| "step": 533 |
| }, |
| { |
| "entropy": 0.6323057189583778, |
| "epoch": 3.4032, |
| "grad_norm": 0.011215063743293285, |
| "learning_rate": 0.0002, |
| "loss": 0.6333843469619751, |
| "mean_token_accuracy": 0.7426166757941246, |
| "num_tokens": 19975460.0, |
| "step": 534 |
| }, |
| { |
| "entropy": 0.6401225328445435, |
| "epoch": 3.4096, |
| "grad_norm": 0.009196775034070015, |
| "learning_rate": 0.0002, |
| "loss": 0.6394823789596558, |
| "mean_token_accuracy": 0.738113172352314, |
| "num_tokens": 20013373.0, |
| "step": 535 |
| }, |
| { |
| "entropy": 0.6456998661160469, |
| "epoch": 3.416, |
| "grad_norm": 0.010047613643109798, |
| "learning_rate": 0.0002, |
| "loss": 0.6439746618270874, |
| "mean_token_accuracy": 0.7357992008328438, |
| "num_tokens": 20051018.0, |
| "step": 536 |
| }, |
| { |
| "entropy": 0.6272638514637947, |
| "epoch": 3.4224, |
| "grad_norm": 0.011030818335711956, |
| "learning_rate": 0.0002, |
| "loss": 0.6313672065734863, |
| "mean_token_accuracy": 0.7423597574234009, |
| "num_tokens": 20088324.0, |
| "step": 537 |
| }, |
| { |
| "entropy": 0.6197195202112198, |
| "epoch": 3.4288, |
| "grad_norm": 0.010905069299042225, |
| "learning_rate": 0.0002, |
| "loss": 0.6300115585327148, |
| "mean_token_accuracy": 0.7445831671357155, |
| "num_tokens": 20125821.0, |
| "step": 538 |
| }, |
| { |
| "entropy": 0.616571269929409, |
| "epoch": 3.4352, |
| "grad_norm": 0.00983978621661663, |
| "learning_rate": 0.0002, |
| "loss": 0.6236230134963989, |
| "mean_token_accuracy": 0.7451280057430267, |
| "num_tokens": 20163266.0, |
| "step": 539 |
| }, |
| { |
| "entropy": 0.6327468827366829, |
| "epoch": 3.4416, |
| "grad_norm": 0.00972190871834755, |
| "learning_rate": 0.0002, |
| "loss": 0.6347957849502563, |
| "mean_token_accuracy": 0.7411710619926453, |
| "num_tokens": 20201024.0, |
| "step": 540 |
| }, |
| { |
| "entropy": 0.6288504004478455, |
| "epoch": 3.448, |
| "grad_norm": 0.011150616221129894, |
| "learning_rate": 0.0002, |
| "loss": 0.6228883266448975, |
| "mean_token_accuracy": 0.7468400076031685, |
| "num_tokens": 20238093.0, |
| "step": 541 |
| }, |
| { |
| "entropy": 0.6300643384456635, |
| "epoch": 3.4544, |
| "grad_norm": 0.01008420716971159, |
| "learning_rate": 0.0002, |
| "loss": 0.6263501048088074, |
| "mean_token_accuracy": 0.7454875409603119, |
| "num_tokens": 20275846.0, |
| "step": 542 |
| }, |
| { |
| "entropy": 0.621397003531456, |
| "epoch": 3.4608, |
| "grad_norm": 0.009655226953327656, |
| "learning_rate": 0.0002, |
| "loss": 0.626434862613678, |
| "mean_token_accuracy": 0.7454000115394592, |
| "num_tokens": 20313165.0, |
| "step": 543 |
| }, |
| { |
| "entropy": 0.625905841588974, |
| "epoch": 3.4672, |
| "grad_norm": 0.012401984073221684, |
| "learning_rate": 0.0002, |
| "loss": 0.6340878009796143, |
| "mean_token_accuracy": 0.74062430113554, |
| "num_tokens": 20351212.0, |
| "step": 544 |
| }, |
| { |
| "entropy": 0.6408397778868675, |
| "epoch": 3.4736000000000002, |
| "grad_norm": 0.010497737675905228, |
| "learning_rate": 0.0002, |
| "loss": 0.6416893601417542, |
| "mean_token_accuracy": 0.7387349084019661, |
| "num_tokens": 20388632.0, |
| "step": 545 |
| }, |
| { |
| "entropy": 0.6322543397545815, |
| "epoch": 3.48, |
| "grad_norm": 0.010267537087202072, |
| "learning_rate": 0.0002, |
| "loss": 0.6245300769805908, |
| "mean_token_accuracy": 0.7472849115729332, |
| "num_tokens": 20426503.0, |
| "step": 546 |
| }, |
| { |
| "entropy": 0.6428259909152985, |
| "epoch": 3.4864, |
| "grad_norm": 0.010037362575531006, |
| "learning_rate": 0.0002, |
| "loss": 0.6373123526573181, |
| "mean_token_accuracy": 0.7395420894026756, |
| "num_tokens": 20464010.0, |
| "step": 547 |
| }, |
| { |
| "entropy": 0.6270901411771774, |
| "epoch": 3.4928, |
| "grad_norm": 0.008532303385436535, |
| "learning_rate": 0.0002, |
| "loss": 0.6293808221817017, |
| "mean_token_accuracy": 0.7432048991322517, |
| "num_tokens": 20501515.0, |
| "step": 548 |
| }, |
| { |
| "entropy": 0.6149459034204483, |
| "epoch": 3.4992, |
| "grad_norm": 0.009804856963455677, |
| "learning_rate": 0.0002, |
| "loss": 0.6234340667724609, |
| "mean_token_accuracy": 0.7474272325634956, |
| "num_tokens": 20539328.0, |
| "step": 549 |
| }, |
| { |
| "entropy": 0.6115493848919868, |
| "epoch": 3.5056000000000003, |
| "grad_norm": 0.01168244518339634, |
| "learning_rate": 0.0002, |
| "loss": 0.6256985068321228, |
| "mean_token_accuracy": 0.7442245110869408, |
| "num_tokens": 20576414.0, |
| "step": 550 |
| }, |
| { |
| "entropy": 0.6242030709981918, |
| "epoch": 3.512, |
| "grad_norm": 0.00905383937060833, |
| "learning_rate": 0.0002, |
| "loss": 0.6286660432815552, |
| "mean_token_accuracy": 0.7437908053398132, |
| "num_tokens": 20614078.0, |
| "step": 551 |
| }, |
| { |
| "entropy": 0.6304361894726753, |
| "epoch": 3.5183999999999997, |
| "grad_norm": 0.008661957457661629, |
| "learning_rate": 0.0002, |
| "loss": 0.6304973363876343, |
| "mean_token_accuracy": 0.7443248927593231, |
| "num_tokens": 20651484.0, |
| "step": 552 |
| }, |
| { |
| "entropy": 0.6485093608498573, |
| "epoch": 3.5248, |
| "grad_norm": 0.008023140951991081, |
| "learning_rate": 0.0002, |
| "loss": 0.64768385887146, |
| "mean_token_accuracy": 0.7372199594974518, |
| "num_tokens": 20688874.0, |
| "step": 553 |
| }, |
| { |
| "entropy": 0.6480056494474411, |
| "epoch": 3.5312, |
| "grad_norm": 0.009417054243385792, |
| "learning_rate": 0.0002, |
| "loss": 0.6428097486495972, |
| "mean_token_accuracy": 0.7367473617196083, |
| "num_tokens": 20726632.0, |
| "step": 554 |
| }, |
| { |
| "entropy": 0.6245403215289116, |
| "epoch": 3.5376, |
| "grad_norm": 0.008958806283771992, |
| "learning_rate": 0.0002, |
| "loss": 0.6215206980705261, |
| "mean_token_accuracy": 0.745918445289135, |
| "num_tokens": 20764598.0, |
| "step": 555 |
| }, |
| { |
| "entropy": 0.6468629390001297, |
| "epoch": 3.544, |
| "grad_norm": 0.009944718331098557, |
| "learning_rate": 0.0002, |
| "loss": 0.6501193046569824, |
| "mean_token_accuracy": 0.7350190952420235, |
| "num_tokens": 20802384.0, |
| "step": 556 |
| }, |
| { |
| "entropy": 0.6288837715983391, |
| "epoch": 3.5504, |
| "grad_norm": 0.009102506563067436, |
| "learning_rate": 0.0002, |
| "loss": 0.6321202516555786, |
| "mean_token_accuracy": 0.7416860312223434, |
| "num_tokens": 20839585.0, |
| "step": 557 |
| }, |
| { |
| "entropy": 0.6316198781132698, |
| "epoch": 3.5568, |
| "grad_norm": 0.009831351228058338, |
| "learning_rate": 0.0002, |
| "loss": 0.6349937319755554, |
| "mean_token_accuracy": 0.7422218322753906, |
| "num_tokens": 20877319.0, |
| "step": 558 |
| }, |
| { |
| "entropy": 0.640017494559288, |
| "epoch": 3.5632, |
| "grad_norm": 0.00992864090949297, |
| "learning_rate": 0.0002, |
| "loss": 0.6386250853538513, |
| "mean_token_accuracy": 0.7408555001020432, |
| "num_tokens": 20915060.0, |
| "step": 559 |
| }, |
| { |
| "entropy": 0.650281272828579, |
| "epoch": 3.5696, |
| "grad_norm": 0.008609931915998459, |
| "learning_rate": 0.0002, |
| "loss": 0.6503854393959045, |
| "mean_token_accuracy": 0.7330696955323219, |
| "num_tokens": 20953081.0, |
| "step": 560 |
| }, |
| { |
| "entropy": 0.6279073059558868, |
| "epoch": 3.576, |
| "grad_norm": 0.01186640840023756, |
| "learning_rate": 0.0002, |
| "loss": 0.627372145652771, |
| "mean_token_accuracy": 0.7447227090597153, |
| "num_tokens": 20990338.0, |
| "step": 561 |
| }, |
| { |
| "entropy": 0.634159728884697, |
| "epoch": 3.5824, |
| "grad_norm": 0.008970306254923344, |
| "learning_rate": 0.0002, |
| "loss": 0.6346087455749512, |
| "mean_token_accuracy": 0.7415203601121902, |
| "num_tokens": 21028096.0, |
| "step": 562 |
| }, |
| { |
| "entropy": 0.633803091943264, |
| "epoch": 3.5888, |
| "grad_norm": 0.011358493939042091, |
| "learning_rate": 0.0002, |
| "loss": 0.6442689895629883, |
| "mean_token_accuracy": 0.7374193891882896, |
| "num_tokens": 21065835.0, |
| "step": 563 |
| }, |
| { |
| "entropy": 0.623796708881855, |
| "epoch": 3.5952, |
| "grad_norm": 0.011994842439889908, |
| "learning_rate": 0.0002, |
| "loss": 0.6334537267684937, |
| "mean_token_accuracy": 0.7415754497051239, |
| "num_tokens": 21103469.0, |
| "step": 564 |
| }, |
| { |
| "entropy": 0.635470986366272, |
| "epoch": 3.6016, |
| "grad_norm": 0.009826122783124447, |
| "learning_rate": 0.0002, |
| "loss": 0.6419943571090698, |
| "mean_token_accuracy": 0.7378642708063126, |
| "num_tokens": 21141513.0, |
| "step": 565 |
| }, |
| { |
| "entropy": 0.6463486775755882, |
| "epoch": 3.608, |
| "grad_norm": 0.010555503889918327, |
| "learning_rate": 0.0002, |
| "loss": 0.640326738357544, |
| "mean_token_accuracy": 0.7372942119836807, |
| "num_tokens": 21178927.0, |
| "step": 566 |
| }, |
| { |
| "entropy": 0.6457525193691254, |
| "epoch": 3.6144, |
| "grad_norm": 0.010458976030349731, |
| "learning_rate": 0.0002, |
| "loss": 0.6402060985565186, |
| "mean_token_accuracy": 0.7400226071476936, |
| "num_tokens": 21216291.0, |
| "step": 567 |
| }, |
| { |
| "entropy": 0.633650466799736, |
| "epoch": 3.6208, |
| "grad_norm": 0.009390798397362232, |
| "learning_rate": 0.0002, |
| "loss": 0.6331945657730103, |
| "mean_token_accuracy": 0.7403992488980293, |
| "num_tokens": 21253727.0, |
| "step": 568 |
| }, |
| { |
| "entropy": 0.632075347006321, |
| "epoch": 3.6272, |
| "grad_norm": 0.01025348249822855, |
| "learning_rate": 0.0002, |
| "loss": 0.6355302333831787, |
| "mean_token_accuracy": 0.7413225471973419, |
| "num_tokens": 21291493.0, |
| "step": 569 |
| }, |
| { |
| "entropy": 0.6219524443149567, |
| "epoch": 3.6336, |
| "grad_norm": 0.011700067669153214, |
| "learning_rate": 0.0002, |
| "loss": 0.6319601535797119, |
| "mean_token_accuracy": 0.7412790209054947, |
| "num_tokens": 21329474.0, |
| "step": 570 |
| }, |
| { |
| "entropy": 0.6328660994768143, |
| "epoch": 3.64, |
| "grad_norm": 0.009544705040752888, |
| "learning_rate": 0.0002, |
| "loss": 0.6347973346710205, |
| "mean_token_accuracy": 0.742459200322628, |
| "num_tokens": 21367274.0, |
| "step": 571 |
| }, |
| { |
| "entropy": 0.6382363438606262, |
| "epoch": 3.6464, |
| "grad_norm": 0.009506464004516602, |
| "learning_rate": 0.0002, |
| "loss": 0.632327675819397, |
| "mean_token_accuracy": 0.741349458694458, |
| "num_tokens": 21405027.0, |
| "step": 572 |
| }, |
| { |
| "entropy": 0.6429821029305458, |
| "epoch": 3.6528, |
| "grad_norm": 0.008949574083089828, |
| "learning_rate": 0.0002, |
| "loss": 0.6385926008224487, |
| "mean_token_accuracy": 0.7412813901901245, |
| "num_tokens": 21442485.0, |
| "step": 573 |
| }, |
| { |
| "entropy": 0.6392761990427971, |
| "epoch": 3.6592000000000002, |
| "grad_norm": 0.008819608017802238, |
| "learning_rate": 0.0002, |
| "loss": 0.6387146711349487, |
| "mean_token_accuracy": 0.7381789684295654, |
| "num_tokens": 21480245.0, |
| "step": 574 |
| }, |
| { |
| "entropy": 0.6092662885785103, |
| "epoch": 3.6656, |
| "grad_norm": 0.009008620865643024, |
| "learning_rate": 0.0002, |
| "loss": 0.6131871342658997, |
| "mean_token_accuracy": 0.7484863623976707, |
| "num_tokens": 21517658.0, |
| "step": 575 |
| }, |
| { |
| "entropy": 0.6172466725111008, |
| "epoch": 3.672, |
| "grad_norm": 0.008723135106265545, |
| "learning_rate": 0.0002, |
| "loss": 0.6228119730949402, |
| "mean_token_accuracy": 0.747119203209877, |
| "num_tokens": 21555161.0, |
| "step": 576 |
| }, |
| { |
| "entropy": 0.6264480575919151, |
| "epoch": 3.6784, |
| "grad_norm": 0.008482584729790688, |
| "learning_rate": 0.0002, |
| "loss": 0.6291134357452393, |
| "mean_token_accuracy": 0.7445547953248024, |
| "num_tokens": 21592408.0, |
| "step": 577 |
| }, |
| { |
| "entropy": 0.635237880051136, |
| "epoch": 3.6848, |
| "grad_norm": 0.00850406102836132, |
| "learning_rate": 0.0002, |
| "loss": 0.6362268328666687, |
| "mean_token_accuracy": 0.7393738552927971, |
| "num_tokens": 21630282.0, |
| "step": 578 |
| }, |
| { |
| "entropy": 0.6200535595417023, |
| "epoch": 3.6912000000000003, |
| "grad_norm": 0.009778933599591255, |
| "learning_rate": 0.0002, |
| "loss": 0.6221815347671509, |
| "mean_token_accuracy": 0.7469090595841408, |
| "num_tokens": 21667708.0, |
| "step": 579 |
| }, |
| { |
| "entropy": 0.63077662140131, |
| "epoch": 3.6976, |
| "grad_norm": 0.009218033403158188, |
| "learning_rate": 0.0002, |
| "loss": 0.6323422193527222, |
| "mean_token_accuracy": 0.7421467453241348, |
| "num_tokens": 21705244.0, |
| "step": 580 |
| }, |
| { |
| "entropy": 0.6420226320624352, |
| "epoch": 3.7039999999999997, |
| "grad_norm": 0.009507461450994015, |
| "learning_rate": 0.0002, |
| "loss": 0.6403417587280273, |
| "mean_token_accuracy": 0.739894188940525, |
| "num_tokens": 21743055.0, |
| "step": 581 |
| }, |
| { |
| "entropy": 0.6300998106598854, |
| "epoch": 3.7104, |
| "grad_norm": 0.009341172873973846, |
| "learning_rate": 0.0002, |
| "loss": 0.6311365962028503, |
| "mean_token_accuracy": 0.7414052486419678, |
| "num_tokens": 21780375.0, |
| "step": 582 |
| }, |
| { |
| "entropy": 0.6306213289499283, |
| "epoch": 3.7168, |
| "grad_norm": 0.010440697893500328, |
| "learning_rate": 0.0002, |
| "loss": 0.6373945474624634, |
| "mean_token_accuracy": 0.7419358193874359, |
| "num_tokens": 21817708.0, |
| "step": 583 |
| }, |
| { |
| "entropy": 0.6163543164730072, |
| "epoch": 3.7232, |
| "grad_norm": 0.009331561625003815, |
| "learning_rate": 0.0002, |
| "loss": 0.6209964156150818, |
| "mean_token_accuracy": 0.7463705316185951, |
| "num_tokens": 21854937.0, |
| "step": 584 |
| }, |
| { |
| "entropy": 0.6321230009198189, |
| "epoch": 3.7296, |
| "grad_norm": 0.00952980387955904, |
| "learning_rate": 0.0002, |
| "loss": 0.6340712308883667, |
| "mean_token_accuracy": 0.7384133115410805, |
| "num_tokens": 21892727.0, |
| "step": 585 |
| }, |
| { |
| "entropy": 0.6275918409228325, |
| "epoch": 3.7359999999999998, |
| "grad_norm": 0.009358996525406837, |
| "learning_rate": 0.0002, |
| "loss": 0.6279775500297546, |
| "mean_token_accuracy": 0.7420656681060791, |
| "num_tokens": 21930361.0, |
| "step": 586 |
| }, |
| { |
| "entropy": 0.6374326348304749, |
| "epoch": 3.7424, |
| "grad_norm": 0.00851542316377163, |
| "learning_rate": 0.0002, |
| "loss": 0.6387336254119873, |
| "mean_token_accuracy": 0.7408188581466675, |
| "num_tokens": 21967769.0, |
| "step": 587 |
| }, |
| { |
| "entropy": 0.6265183612704277, |
| "epoch": 3.7488, |
| "grad_norm": 0.010128417983651161, |
| "learning_rate": 0.0002, |
| "loss": 0.6304729580879211, |
| "mean_token_accuracy": 0.74308130890131, |
| "num_tokens": 22005268.0, |
| "step": 588 |
| }, |
| { |
| "entropy": 0.6259055137634277, |
| "epoch": 3.7552, |
| "grad_norm": 0.00949757732450962, |
| "learning_rate": 0.0002, |
| "loss": 0.6271415948867798, |
| "mean_token_accuracy": 0.7445643469691277, |
| "num_tokens": 22042740.0, |
| "step": 589 |
| }, |
| { |
| "entropy": 0.621527373790741, |
| "epoch": 3.7616, |
| "grad_norm": 0.011297403834760189, |
| "learning_rate": 0.0002, |
| "loss": 0.6193302869796753, |
| "mean_token_accuracy": 0.7481779083609581, |
| "num_tokens": 22080705.0, |
| "step": 590 |
| }, |
| { |
| "entropy": 0.6351140215992928, |
| "epoch": 3.768, |
| "grad_norm": 0.01007875707000494, |
| "learning_rate": 0.0002, |
| "loss": 0.636103093624115, |
| "mean_token_accuracy": 0.7403137609362602, |
| "num_tokens": 22118187.0, |
| "step": 591 |
| }, |
| { |
| "entropy": 0.6164060086011887, |
| "epoch": 3.7744, |
| "grad_norm": 0.00851944275200367, |
| "learning_rate": 0.0002, |
| "loss": 0.620150089263916, |
| "mean_token_accuracy": 0.7468870654702187, |
| "num_tokens": 22155780.0, |
| "step": 592 |
| }, |
| { |
| "entropy": 0.6220516487956047, |
| "epoch": 3.7808, |
| "grad_norm": 0.011541093699634075, |
| "learning_rate": 0.0002, |
| "loss": 0.6253345012664795, |
| "mean_token_accuracy": 0.7459988221526146, |
| "num_tokens": 22193401.0, |
| "step": 593 |
| }, |
| { |
| "entropy": 0.6525481268763542, |
| "epoch": 3.7872, |
| "grad_norm": 0.009819903410971165, |
| "learning_rate": 0.0002, |
| "loss": 0.6519078016281128, |
| "mean_token_accuracy": 0.7341204807162285, |
| "num_tokens": 22230608.0, |
| "step": 594 |
| }, |
| { |
| "entropy": 0.6331318765878677, |
| "epoch": 3.7936, |
| "grad_norm": 0.010822438634932041, |
| "learning_rate": 0.0002, |
| "loss": 0.627253532409668, |
| "mean_token_accuracy": 0.7452663481235504, |
| "num_tokens": 22268376.0, |
| "step": 595 |
| }, |
| { |
| "entropy": 0.6378331705927849, |
| "epoch": 3.8, |
| "grad_norm": 0.010335801169276237, |
| "learning_rate": 0.0002, |
| "loss": 0.6402156949043274, |
| "mean_token_accuracy": 0.7388675063848495, |
| "num_tokens": 22305874.0, |
| "step": 596 |
| }, |
| { |
| "entropy": 0.6241042613983154, |
| "epoch": 3.8064, |
| "grad_norm": 0.011212136596441269, |
| "learning_rate": 0.0002, |
| "loss": 0.6346319913864136, |
| "mean_token_accuracy": 0.7422374039888382, |
| "num_tokens": 22343270.0, |
| "step": 597 |
| }, |
| { |
| "entropy": 0.6304724365472794, |
| "epoch": 3.8128, |
| "grad_norm": 0.010530945844948292, |
| "learning_rate": 0.0002, |
| "loss": 0.6360510587692261, |
| "mean_token_accuracy": 0.7418438643217087, |
| "num_tokens": 22380767.0, |
| "step": 598 |
| }, |
| { |
| "entropy": 0.630512535572052, |
| "epoch": 3.8192, |
| "grad_norm": 0.01047790888696909, |
| "learning_rate": 0.0002, |
| "loss": 0.6310948133468628, |
| "mean_token_accuracy": 0.7418612614274025, |
| "num_tokens": 22417973.0, |
| "step": 599 |
| }, |
| { |
| "entropy": 0.6289901584386826, |
| "epoch": 3.8256, |
| "grad_norm": 0.009985234588384628, |
| "learning_rate": 0.0002, |
| "loss": 0.6236091256141663, |
| "mean_token_accuracy": 0.745183065533638, |
| "num_tokens": 22455401.0, |
| "step": 600 |
| }, |
| { |
| "entropy": 0.6390504911541939, |
| "epoch": 3.832, |
| "grad_norm": 0.009776836261153221, |
| "learning_rate": 0.0002, |
| "loss": 0.6361709237098694, |
| "mean_token_accuracy": 0.7415382042527199, |
| "num_tokens": 22493019.0, |
| "step": 601 |
| }, |
| { |
| "entropy": 0.6260226741433144, |
| "epoch": 3.8384, |
| "grad_norm": 0.009412144310772419, |
| "learning_rate": 0.0002, |
| "loss": 0.62882399559021, |
| "mean_token_accuracy": 0.7436661571264267, |
| "num_tokens": 22530628.0, |
| "step": 602 |
| }, |
| { |
| "entropy": 0.6180827915668488, |
| "epoch": 3.8448, |
| "grad_norm": 0.009917755611240864, |
| "learning_rate": 0.0002, |
| "loss": 0.6258498430252075, |
| "mean_token_accuracy": 0.7454487532377243, |
| "num_tokens": 22568202.0, |
| "step": 603 |
| }, |
| { |
| "entropy": 0.6200235038995743, |
| "epoch": 3.8512, |
| "grad_norm": 0.010199918411672115, |
| "learning_rate": 0.0002, |
| "loss": 0.6277583837509155, |
| "mean_token_accuracy": 0.7435891628265381, |
| "num_tokens": 22605838.0, |
| "step": 604 |
| }, |
| { |
| "entropy": 0.6254613697528839, |
| "epoch": 3.8576, |
| "grad_norm": 0.009225446730852127, |
| "learning_rate": 0.0002, |
| "loss": 0.6330975294113159, |
| "mean_token_accuracy": 0.7417056709527969, |
| "num_tokens": 22643315.0, |
| "step": 605 |
| }, |
| { |
| "entropy": 0.6374992206692696, |
| "epoch": 3.864, |
| "grad_norm": 0.009426961652934551, |
| "learning_rate": 0.0002, |
| "loss": 0.6333073377609253, |
| "mean_token_accuracy": 0.743529699742794, |
| "num_tokens": 22681260.0, |
| "step": 606 |
| }, |
| { |
| "entropy": 0.6427751928567886, |
| "epoch": 3.8704, |
| "grad_norm": 0.01109833549708128, |
| "learning_rate": 0.0002, |
| "loss": 0.6365841627120972, |
| "mean_token_accuracy": 0.740449033677578, |
| "num_tokens": 22718725.0, |
| "step": 607 |
| }, |
| { |
| "entropy": 0.6293874457478523, |
| "epoch": 3.8768000000000002, |
| "grad_norm": 0.009044543839991093, |
| "learning_rate": 0.0002, |
| "loss": 0.6291689872741699, |
| "mean_token_accuracy": 0.7439134269952774, |
| "num_tokens": 22756018.0, |
| "step": 608 |
| }, |
| { |
| "entropy": 0.6215147376060486, |
| "epoch": 3.8832, |
| "grad_norm": 0.010903657414019108, |
| "learning_rate": 0.0002, |
| "loss": 0.6296993494033813, |
| "mean_token_accuracy": 0.7446267232298851, |
| "num_tokens": 22793251.0, |
| "step": 609 |
| }, |
| { |
| "entropy": 0.6157297044992447, |
| "epoch": 3.8895999999999997, |
| "grad_norm": 0.010149014182388783, |
| "learning_rate": 0.0002, |
| "loss": 0.6224344968795776, |
| "mean_token_accuracy": 0.7450227364897728, |
| "num_tokens": 22830782.0, |
| "step": 610 |
| }, |
| { |
| "entropy": 0.6204625591635704, |
| "epoch": 3.896, |
| "grad_norm": 0.008899394422769547, |
| "learning_rate": 0.0002, |
| "loss": 0.6236724257469177, |
| "mean_token_accuracy": 0.7457845434546471, |
| "num_tokens": 22868292.0, |
| "step": 611 |
| }, |
| { |
| "entropy": 0.6289186328649521, |
| "epoch": 3.9024, |
| "grad_norm": 0.009715489111840725, |
| "learning_rate": 0.0002, |
| "loss": 0.6255042552947998, |
| "mean_token_accuracy": 0.743945874273777, |
| "num_tokens": 22905960.0, |
| "step": 612 |
| }, |
| { |
| "entropy": 0.6272325441241264, |
| "epoch": 3.9088000000000003, |
| "grad_norm": 0.010841017588973045, |
| "learning_rate": 0.0002, |
| "loss": 0.6241690516471863, |
| "mean_token_accuracy": 0.7436103969812393, |
| "num_tokens": 22943043.0, |
| "step": 613 |
| }, |
| { |
| "entropy": 0.6414704546332359, |
| "epoch": 3.9152, |
| "grad_norm": 0.009553831070661545, |
| "learning_rate": 0.0002, |
| "loss": 0.6447999477386475, |
| "mean_token_accuracy": 0.7391496151685715, |
| "num_tokens": 22980557.0, |
| "step": 614 |
| }, |
| { |
| "entropy": 0.6307174563407898, |
| "epoch": 3.9215999999999998, |
| "grad_norm": 0.009158959612250328, |
| "learning_rate": 0.0002, |
| "loss": 0.6336820721626282, |
| "mean_token_accuracy": 0.7413525283336639, |
| "num_tokens": 23018134.0, |
| "step": 615 |
| }, |
| { |
| "entropy": 0.6336700096726418, |
| "epoch": 3.928, |
| "grad_norm": 0.010397304780781269, |
| "learning_rate": 0.0002, |
| "loss": 0.6412237882614136, |
| "mean_token_accuracy": 0.7389427125453949, |
| "num_tokens": 23055656.0, |
| "step": 616 |
| }, |
| { |
| "entropy": 0.6292953938245773, |
| "epoch": 3.9344, |
| "grad_norm": 0.009029161185026169, |
| "learning_rate": 0.0002, |
| "loss": 0.6302052736282349, |
| "mean_token_accuracy": 0.7432261779904366, |
| "num_tokens": 23093414.0, |
| "step": 617 |
| }, |
| { |
| "entropy": 0.6511750519275665, |
| "epoch": 3.9408, |
| "grad_norm": 0.011078661307692528, |
| "learning_rate": 0.0002, |
| "loss": 0.6470860242843628, |
| "mean_token_accuracy": 0.7365722432732582, |
| "num_tokens": 23131307.0, |
| "step": 618 |
| }, |
| { |
| "entropy": 0.640938051044941, |
| "epoch": 3.9472, |
| "grad_norm": 0.009597877971827984, |
| "learning_rate": 0.0002, |
| "loss": 0.6369379758834839, |
| "mean_token_accuracy": 0.7396447286009789, |
| "num_tokens": 23168894.0, |
| "step": 619 |
| }, |
| { |
| "entropy": 0.6210119426250458, |
| "epoch": 3.9536, |
| "grad_norm": 0.010679766535758972, |
| "learning_rate": 0.0002, |
| "loss": 0.6260274052619934, |
| "mean_token_accuracy": 0.7466530501842499, |
| "num_tokens": 23206378.0, |
| "step": 620 |
| }, |
| { |
| "entropy": 0.615054301917553, |
| "epoch": 3.96, |
| "grad_norm": 0.010784207843244076, |
| "learning_rate": 0.0002, |
| "loss": 0.6229560375213623, |
| "mean_token_accuracy": 0.7456069514155388, |
| "num_tokens": 23243675.0, |
| "step": 621 |
| }, |
| { |
| "entropy": 0.6250587999820709, |
| "epoch": 3.9664, |
| "grad_norm": 0.009625584818422794, |
| "learning_rate": 0.0002, |
| "loss": 0.6281651258468628, |
| "mean_token_accuracy": 0.7444300353527069, |
| "num_tokens": 23281000.0, |
| "step": 622 |
| }, |
| { |
| "entropy": 0.6295294389128685, |
| "epoch": 3.9728, |
| "grad_norm": 0.009764077141880989, |
| "learning_rate": 0.0002, |
| "loss": 0.6305609941482544, |
| "mean_token_accuracy": 0.7441380247473717, |
| "num_tokens": 23318554.0, |
| "step": 623 |
| }, |
| { |
| "entropy": 0.619350254535675, |
| "epoch": 3.9792, |
| "grad_norm": 0.009161337278783321, |
| "learning_rate": 0.0002, |
| "loss": 0.6201272010803223, |
| "mean_token_accuracy": 0.7485333606600761, |
| "num_tokens": 23355649.0, |
| "step": 624 |
| }, |
| { |
| "entropy": 0.6401965990662575, |
| "epoch": 3.9856, |
| "grad_norm": 0.010438468307256699, |
| "learning_rate": 0.0002, |
| "loss": 0.6402089595794678, |
| "mean_token_accuracy": 0.7383991852402687, |
| "num_tokens": 23393568.0, |
| "step": 625 |
| }, |
| { |
| "entropy": 0.6330313384532928, |
| "epoch": 3.992, |
| "grad_norm": 0.009565716609358788, |
| "learning_rate": 0.0002, |
| "loss": 0.6326834559440613, |
| "mean_token_accuracy": 0.7425080984830856, |
| "num_tokens": 23431086.0, |
| "step": 626 |
| }, |
| { |
| "entropy": 0.6277460902929306, |
| "epoch": 3.9984, |
| "grad_norm": 0.009916098788380623, |
| "learning_rate": 0.0002, |
| "loss": 0.6327950954437256, |
| "mean_token_accuracy": 0.7417906895279884, |
| "num_tokens": 23468619.0, |
| "step": 627 |
| }, |
| { |
| "entropy": 0.6479776203632355, |
| "epoch": 4.0, |
| "grad_norm": 0.016998078674077988, |
| "learning_rate": 0.0002, |
| "loss": 0.6533247828483582, |
| "mean_token_accuracy": 0.7333799302577972, |
| "num_tokens": 23477894.0, |
| "step": 628 |
| }, |
| { |
| "entropy": 0.6334798634052277, |
| "epoch": 4.0064, |
| "grad_norm": 0.011177260428667068, |
| "learning_rate": 0.0002, |
| "loss": 0.6274731159210205, |
| "mean_token_accuracy": 0.7418768331408501, |
| "num_tokens": 23515512.0, |
| "step": 629 |
| }, |
| { |
| "entropy": 0.6426746100187302, |
| "epoch": 4.0128, |
| "grad_norm": 0.010523858480155468, |
| "learning_rate": 0.0002, |
| "loss": 0.639644980430603, |
| "mean_token_accuracy": 0.738319605588913, |
| "num_tokens": 23553199.0, |
| "step": 630 |
| }, |
| { |
| "entropy": 0.6350331977009773, |
| "epoch": 4.0192, |
| "grad_norm": 0.013215194456279278, |
| "learning_rate": 0.0002, |
| "loss": 0.6405128836631775, |
| "mean_token_accuracy": 0.739054262638092, |
| "num_tokens": 23590684.0, |
| "step": 631 |
| }, |
| { |
| "entropy": 0.6201648041605949, |
| "epoch": 4.0256, |
| "grad_norm": 0.00981956534087658, |
| "learning_rate": 0.0002, |
| "loss": 0.6236424446105957, |
| "mean_token_accuracy": 0.7453638687729836, |
| "num_tokens": 23628151.0, |
| "step": 632 |
| }, |
| { |
| "entropy": 0.6195686236023903, |
| "epoch": 4.032, |
| "grad_norm": 0.011942672543227673, |
| "learning_rate": 0.0002, |
| "loss": 0.6226350665092468, |
| "mean_token_accuracy": 0.7457711473107338, |
| "num_tokens": 23665791.0, |
| "step": 633 |
| }, |
| { |
| "entropy": 0.621765486896038, |
| "epoch": 4.0384, |
| "grad_norm": 0.011674079112708569, |
| "learning_rate": 0.0002, |
| "loss": 0.6212641000747681, |
| "mean_token_accuracy": 0.7444254085421562, |
| "num_tokens": 23703897.0, |
| "step": 634 |
| }, |
| { |
| "entropy": 0.6218401342630386, |
| "epoch": 4.0448, |
| "grad_norm": 0.011382197961211205, |
| "learning_rate": 0.0002, |
| "loss": 0.6188787221908569, |
| "mean_token_accuracy": 0.7439982444047928, |
| "num_tokens": 23741726.0, |
| "step": 635 |
| }, |
| { |
| "entropy": 0.6302961930632591, |
| "epoch": 4.0512, |
| "grad_norm": 0.0122229540720582, |
| "learning_rate": 0.0002, |
| "loss": 0.6310756802558899, |
| "mean_token_accuracy": 0.7416332587599754, |
| "num_tokens": 23779347.0, |
| "step": 636 |
| }, |
| { |
| "entropy": 0.6179258972406387, |
| "epoch": 4.0576, |
| "grad_norm": 0.013323783874511719, |
| "learning_rate": 0.0002, |
| "loss": 0.6242649555206299, |
| "mean_token_accuracy": 0.7424203455448151, |
| "num_tokens": 23816946.0, |
| "step": 637 |
| }, |
| { |
| "entropy": 0.6160242184996605, |
| "epoch": 4.064, |
| "grad_norm": 0.011928076855838299, |
| "learning_rate": 0.0002, |
| "loss": 0.6227492094039917, |
| "mean_token_accuracy": 0.7461478784680367, |
| "num_tokens": 23854267.0, |
| "step": 638 |
| }, |
| { |
| "entropy": 0.6243119761347771, |
| "epoch": 4.0704, |
| "grad_norm": 0.01218615286052227, |
| "learning_rate": 0.0002, |
| "loss": 0.6247442960739136, |
| "mean_token_accuracy": 0.7416555359959602, |
| "num_tokens": 23891647.0, |
| "step": 639 |
| }, |
| { |
| "entropy": 0.6283975690603256, |
| "epoch": 4.0768, |
| "grad_norm": 0.011089140549302101, |
| "learning_rate": 0.0002, |
| "loss": 0.6262081861495972, |
| "mean_token_accuracy": 0.7418273463845253, |
| "num_tokens": 23928978.0, |
| "step": 640 |
| }, |
| { |
| "entropy": 0.6230043172836304, |
| "epoch": 4.0832, |
| "grad_norm": 0.010514283552765846, |
| "learning_rate": 0.0002, |
| "loss": 0.6210086345672607, |
| "mean_token_accuracy": 0.7470921650528908, |
| "num_tokens": 23966589.0, |
| "step": 641 |
| }, |
| { |
| "entropy": 0.6316242590546608, |
| "epoch": 4.0896, |
| "grad_norm": 0.010836183093488216, |
| "learning_rate": 0.0002, |
| "loss": 0.6322799324989319, |
| "mean_token_accuracy": 0.7397365495562553, |
| "num_tokens": 24004549.0, |
| "step": 642 |
| }, |
| { |
| "entropy": 0.6093735992908478, |
| "epoch": 4.096, |
| "grad_norm": 0.010521575808525085, |
| "learning_rate": 0.0002, |
| "loss": 0.6142085790634155, |
| "mean_token_accuracy": 0.7481302842497826, |
| "num_tokens": 24041703.0, |
| "step": 643 |
| }, |
| { |
| "entropy": 0.6217071115970612, |
| "epoch": 4.1024, |
| "grad_norm": 0.01190858706831932, |
| "learning_rate": 0.0002, |
| "loss": 0.6301581859588623, |
| "mean_token_accuracy": 0.7421037778258324, |
| "num_tokens": 24079260.0, |
| "step": 644 |
| }, |
| { |
| "entropy": 0.6213275268673897, |
| "epoch": 4.1088, |
| "grad_norm": 0.010940197855234146, |
| "learning_rate": 0.0002, |
| "loss": 0.6227558851242065, |
| "mean_token_accuracy": 0.7450557425618172, |
| "num_tokens": 24116868.0, |
| "step": 645 |
| }, |
| { |
| "entropy": 0.6183237135410309, |
| "epoch": 4.1152, |
| "grad_norm": 0.01106048934161663, |
| "learning_rate": 0.0002, |
| "loss": 0.62211012840271, |
| "mean_token_accuracy": 0.7469884529709816, |
| "num_tokens": 24154196.0, |
| "step": 646 |
| }, |
| { |
| "entropy": 0.6235630884766579, |
| "epoch": 4.1216, |
| "grad_norm": 0.01147097535431385, |
| "learning_rate": 0.0002, |
| "loss": 0.6238754987716675, |
| "mean_token_accuracy": 0.7457621321082115, |
| "num_tokens": 24191940.0, |
| "step": 647 |
| }, |
| { |
| "entropy": 0.628976970911026, |
| "epoch": 4.128, |
| "grad_norm": 0.0103966249153018, |
| "learning_rate": 0.0002, |
| "loss": 0.6279858946800232, |
| "mean_token_accuracy": 0.7433076053857803, |
| "num_tokens": 24229689.0, |
| "step": 648 |
| }, |
| { |
| "entropy": 0.6148188188672066, |
| "epoch": 4.1344, |
| "grad_norm": 0.012693977914750576, |
| "learning_rate": 0.0002, |
| "loss": 0.6150864362716675, |
| "mean_token_accuracy": 0.7493811547756195, |
| "num_tokens": 24267208.0, |
| "step": 649 |
| }, |
| { |
| "entropy": 0.6325013488531113, |
| "epoch": 4.1408, |
| "grad_norm": 0.010917159728705883, |
| "learning_rate": 0.0002, |
| "loss": 0.629578709602356, |
| "mean_token_accuracy": 0.742595799267292, |
| "num_tokens": 24305147.0, |
| "step": 650 |
| }, |
| { |
| "entropy": 0.6269365176558495, |
| "epoch": 4.1472, |
| "grad_norm": 0.011673609726130962, |
| "learning_rate": 0.0002, |
| "loss": 0.6288695931434631, |
| "mean_token_accuracy": 0.7425840869545937, |
| "num_tokens": 24342617.0, |
| "step": 651 |
| }, |
| { |
| "entropy": 0.6115541234612465, |
| "epoch": 4.1536, |
| "grad_norm": 0.012632826343178749, |
| "learning_rate": 0.0002, |
| "loss": 0.6173226833343506, |
| "mean_token_accuracy": 0.7491206377744675, |
| "num_tokens": 24379680.0, |
| "step": 652 |
| }, |
| { |
| "entropy": 0.605757087469101, |
| "epoch": 4.16, |
| "grad_norm": 0.012048393487930298, |
| "learning_rate": 0.0002, |
| "loss": 0.6072964668273926, |
| "mean_token_accuracy": 0.7492575421929359, |
| "num_tokens": 24416439.0, |
| "step": 653 |
| }, |
| { |
| "entropy": 0.6210080906748772, |
| "epoch": 4.1664, |
| "grad_norm": 0.010533303022384644, |
| "learning_rate": 0.0002, |
| "loss": 0.6225767731666565, |
| "mean_token_accuracy": 0.7443814054131508, |
| "num_tokens": 24454195.0, |
| "step": 654 |
| }, |
| { |
| "entropy": 0.6205269917845726, |
| "epoch": 4.1728, |
| "grad_norm": 0.012937111780047417, |
| "learning_rate": 0.0002, |
| "loss": 0.621825635433197, |
| "mean_token_accuracy": 0.7476101964712143, |
| "num_tokens": 24491632.0, |
| "step": 655 |
| }, |
| { |
| "entropy": 0.6158983781933784, |
| "epoch": 4.1792, |
| "grad_norm": 0.011887785978615284, |
| "learning_rate": 0.0002, |
| "loss": 0.6177083253860474, |
| "mean_token_accuracy": 0.7477908208966255, |
| "num_tokens": 24529207.0, |
| "step": 656 |
| }, |
| { |
| "entropy": 0.6310747787356377, |
| "epoch": 4.1856, |
| "grad_norm": 0.01170266792178154, |
| "learning_rate": 0.0002, |
| "loss": 0.6338661313056946, |
| "mean_token_accuracy": 0.7413427755236626, |
| "num_tokens": 24566764.0, |
| "step": 657 |
| }, |
| { |
| "entropy": 0.632545068860054, |
| "epoch": 4.192, |
| "grad_norm": 0.012931435368955135, |
| "learning_rate": 0.0002, |
| "loss": 0.6379810571670532, |
| "mean_token_accuracy": 0.7372681424021721, |
| "num_tokens": 24604691.0, |
| "step": 658 |
| }, |
| { |
| "entropy": 0.6272072345018387, |
| "epoch": 4.1984, |
| "grad_norm": 0.012254653498530388, |
| "learning_rate": 0.0002, |
| "loss": 0.6317451000213623, |
| "mean_token_accuracy": 0.7407561391592026, |
| "num_tokens": 24642250.0, |
| "step": 659 |
| }, |
| { |
| "entropy": 0.6200175136327744, |
| "epoch": 4.2048, |
| "grad_norm": 0.012181897647678852, |
| "learning_rate": 0.0002, |
| "loss": 0.6207621097564697, |
| "mean_token_accuracy": 0.7452465370297432, |
| "num_tokens": 24679770.0, |
| "step": 660 |
| }, |
| { |
| "entropy": 0.6108414232730865, |
| "epoch": 4.2112, |
| "grad_norm": 0.010735893622040749, |
| "learning_rate": 0.0002, |
| "loss": 0.6087774038314819, |
| "mean_token_accuracy": 0.7506056129932404, |
| "num_tokens": 24717292.0, |
| "step": 661 |
| }, |
| { |
| "entropy": 0.6238648667931557, |
| "epoch": 4.2176, |
| "grad_norm": 0.010975925251841545, |
| "learning_rate": 0.0002, |
| "loss": 0.6241613626480103, |
| "mean_token_accuracy": 0.7450825273990631, |
| "num_tokens": 24754935.0, |
| "step": 662 |
| }, |
| { |
| "entropy": 0.6437125504016876, |
| "epoch": 4.224, |
| "grad_norm": 0.01447360310703516, |
| "learning_rate": 0.0002, |
| "loss": 0.6416766047477722, |
| "mean_token_accuracy": 0.7382775098085403, |
| "num_tokens": 24792852.0, |
| "step": 663 |
| }, |
| { |
| "entropy": 0.6239062771201134, |
| "epoch": 4.2304, |
| "grad_norm": 0.014347578398883343, |
| "learning_rate": 0.0002, |
| "loss": 0.6313333511352539, |
| "mean_token_accuracy": 0.7430859357118607, |
| "num_tokens": 24830405.0, |
| "step": 664 |
| }, |
| { |
| "entropy": 0.622043676674366, |
| "epoch": 4.2368, |
| "grad_norm": 0.01144686434417963, |
| "learning_rate": 0.0002, |
| "loss": 0.6238901615142822, |
| "mean_token_accuracy": 0.7450033724308014, |
| "num_tokens": 24867891.0, |
| "step": 665 |
| }, |
| { |
| "entropy": 0.6423631235957146, |
| "epoch": 4.2432, |
| "grad_norm": 0.012929810211062431, |
| "learning_rate": 0.0002, |
| "loss": 0.6390476226806641, |
| "mean_token_accuracy": 0.7388838231563568, |
| "num_tokens": 24905463.0, |
| "step": 666 |
| }, |
| { |
| "entropy": 0.6159037128090858, |
| "epoch": 4.2496, |
| "grad_norm": 0.012308385223150253, |
| "learning_rate": 0.0002, |
| "loss": 0.6162548065185547, |
| "mean_token_accuracy": 0.7489078938961029, |
| "num_tokens": 24942905.0, |
| "step": 667 |
| }, |
| { |
| "entropy": 0.6265198811888695, |
| "epoch": 4.256, |
| "grad_norm": 0.01269616186618805, |
| "learning_rate": 0.0002, |
| "loss": 0.6306416988372803, |
| "mean_token_accuracy": 0.7422251328825951, |
| "num_tokens": 24980486.0, |
| "step": 668 |
| }, |
| { |
| "entropy": 0.6116967797279358, |
| "epoch": 4.2624, |
| "grad_norm": 0.012161326594650745, |
| "learning_rate": 0.0002, |
| "loss": 0.6166009902954102, |
| "mean_token_accuracy": 0.747859038412571, |
| "num_tokens": 25018467.0, |
| "step": 669 |
| }, |
| { |
| "entropy": 0.6185164824128151, |
| "epoch": 4.2688, |
| "grad_norm": 0.012251926586031914, |
| "learning_rate": 0.0002, |
| "loss": 0.6215794682502747, |
| "mean_token_accuracy": 0.7451242059469223, |
| "num_tokens": 25056006.0, |
| "step": 670 |
| }, |
| { |
| "entropy": 0.6283984705805779, |
| "epoch": 4.2752, |
| "grad_norm": 0.011603674851357937, |
| "learning_rate": 0.0002, |
| "loss": 0.627375066280365, |
| "mean_token_accuracy": 0.7432128861546516, |
| "num_tokens": 25093408.0, |
| "step": 671 |
| }, |
| { |
| "entropy": 0.609025202691555, |
| "epoch": 4.2816, |
| "grad_norm": 0.011993130668997765, |
| "learning_rate": 0.0002, |
| "loss": 0.6099145412445068, |
| "mean_token_accuracy": 0.7511600032448769, |
| "num_tokens": 25130524.0, |
| "step": 672 |
| }, |
| { |
| "entropy": 0.6234938055276871, |
| "epoch": 4.288, |
| "grad_norm": 0.010231442749500275, |
| "learning_rate": 0.0002, |
| "loss": 0.6248447299003601, |
| "mean_token_accuracy": 0.7447694912552834, |
| "num_tokens": 25168063.0, |
| "step": 673 |
| }, |
| { |
| "entropy": 0.6148969978094101, |
| "epoch": 4.2943999999999996, |
| "grad_norm": 0.012821062467992306, |
| "learning_rate": 0.0002, |
| "loss": 0.6163221001625061, |
| "mean_token_accuracy": 0.7478527128696442, |
| "num_tokens": 25205806.0, |
| "step": 674 |
| }, |
| { |
| "entropy": 0.6235463097691536, |
| "epoch": 4.3008, |
| "grad_norm": 0.012431120499968529, |
| "learning_rate": 0.0002, |
| "loss": 0.6214525699615479, |
| "mean_token_accuracy": 0.744065910577774, |
| "num_tokens": 25243417.0, |
| "step": 675 |
| }, |
| { |
| "entropy": 0.6208379119634628, |
| "epoch": 4.3072, |
| "grad_norm": 0.011580659076571465, |
| "learning_rate": 0.0002, |
| "loss": 0.626810610294342, |
| "mean_token_accuracy": 0.7434930577874184, |
| "num_tokens": 25281000.0, |
| "step": 676 |
| }, |
| { |
| "entropy": 0.6189445853233337, |
| "epoch": 4.3136, |
| "grad_norm": 0.013887791894376278, |
| "learning_rate": 0.0002, |
| "loss": 0.6251901388168335, |
| "mean_token_accuracy": 0.7435762509703636, |
| "num_tokens": 25318324.0, |
| "step": 677 |
| }, |
| { |
| "entropy": 0.623921662569046, |
| "epoch": 4.32, |
| "grad_norm": 0.011908493936061859, |
| "learning_rate": 0.0002, |
| "loss": 0.6203892230987549, |
| "mean_token_accuracy": 0.7473464608192444, |
| "num_tokens": 25356360.0, |
| "step": 678 |
| }, |
| { |
| "entropy": 0.631057970225811, |
| "epoch": 4.3264, |
| "grad_norm": 0.013283537700772285, |
| "learning_rate": 0.0002, |
| "loss": 0.6287419199943542, |
| "mean_token_accuracy": 0.7408920601010323, |
| "num_tokens": 25393819.0, |
| "step": 679 |
| }, |
| { |
| "entropy": 0.6219344884157181, |
| "epoch": 4.3328, |
| "grad_norm": 0.011869650334119797, |
| "learning_rate": 0.0002, |
| "loss": 0.6282262802124023, |
| "mean_token_accuracy": 0.7440148293972015, |
| "num_tokens": 25431318.0, |
| "step": 680 |
| }, |
| { |
| "entropy": 0.6188084334135056, |
| "epoch": 4.3392, |
| "grad_norm": 0.010526369325816631, |
| "learning_rate": 0.0002, |
| "loss": 0.6230930685997009, |
| "mean_token_accuracy": 0.7453781887888908, |
| "num_tokens": 25468847.0, |
| "step": 681 |
| }, |
| { |
| "entropy": 0.6212713718414307, |
| "epoch": 4.3456, |
| "grad_norm": 0.011861243285238743, |
| "learning_rate": 0.0002, |
| "loss": 0.6226496696472168, |
| "mean_token_accuracy": 0.745365597307682, |
| "num_tokens": 25506347.0, |
| "step": 682 |
| }, |
| { |
| "entropy": 0.6259190738201141, |
| "epoch": 4.352, |
| "grad_norm": 0.010720842517912388, |
| "learning_rate": 0.0002, |
| "loss": 0.6282031536102295, |
| "mean_token_accuracy": 0.7432122975587845, |
| "num_tokens": 25543772.0, |
| "step": 683 |
| }, |
| { |
| "entropy": 0.6237253770232201, |
| "epoch": 4.3584, |
| "grad_norm": 0.01095424685627222, |
| "learning_rate": 0.0002, |
| "loss": 0.6262202262878418, |
| "mean_token_accuracy": 0.7435847371816635, |
| "num_tokens": 25581352.0, |
| "step": 684 |
| }, |
| { |
| "entropy": 0.6245952621102333, |
| "epoch": 4.3648, |
| "grad_norm": 0.010688689537346363, |
| "learning_rate": 0.0002, |
| "loss": 0.6216722726821899, |
| "mean_token_accuracy": 0.7473671957850456, |
| "num_tokens": 25619317.0, |
| "step": 685 |
| }, |
| { |
| "entropy": 0.6425120159983635, |
| "epoch": 4.3712, |
| "grad_norm": 0.011959290131926537, |
| "learning_rate": 0.0002, |
| "loss": 0.6369903087615967, |
| "mean_token_accuracy": 0.7412149682641029, |
| "num_tokens": 25657031.0, |
| "step": 686 |
| }, |
| { |
| "entropy": 0.6215310096740723, |
| "epoch": 4.3776, |
| "grad_norm": 0.01260219793766737, |
| "learning_rate": 0.0002, |
| "loss": 0.6221766471862793, |
| "mean_token_accuracy": 0.7461507469415665, |
| "num_tokens": 25694491.0, |
| "step": 687 |
| }, |
| { |
| "entropy": 0.6162081435322762, |
| "epoch": 4.384, |
| "grad_norm": 0.011745546013116837, |
| "learning_rate": 0.0002, |
| "loss": 0.6214650869369507, |
| "mean_token_accuracy": 0.7467240393161774, |
| "num_tokens": 25731722.0, |
| "step": 688 |
| }, |
| { |
| "entropy": 0.6213862374424934, |
| "epoch": 4.3904, |
| "grad_norm": 0.012498460710048676, |
| "learning_rate": 0.0002, |
| "loss": 0.6276631355285645, |
| "mean_token_accuracy": 0.7429244071245193, |
| "num_tokens": 25769429.0, |
| "step": 689 |
| }, |
| { |
| "entropy": 0.6275434419512749, |
| "epoch": 4.3968, |
| "grad_norm": 0.012363743036985397, |
| "learning_rate": 0.0002, |
| "loss": 0.6299156546592712, |
| "mean_token_accuracy": 0.742164358496666, |
| "num_tokens": 25807155.0, |
| "step": 690 |
| }, |
| { |
| "entropy": 0.6255523934960365, |
| "epoch": 4.4032, |
| "grad_norm": 0.012337331660091877, |
| "learning_rate": 0.0002, |
| "loss": 0.6276605725288391, |
| "mean_token_accuracy": 0.7422888278961182, |
| "num_tokens": 25844832.0, |
| "step": 691 |
| }, |
| { |
| "entropy": 0.618801973760128, |
| "epoch": 4.4096, |
| "grad_norm": 0.011720724403858185, |
| "learning_rate": 0.0002, |
| "loss": 0.6215369701385498, |
| "mean_token_accuracy": 0.7449894100427628, |
| "num_tokens": 25882641.0, |
| "step": 692 |
| }, |
| { |
| "entropy": 0.6298277974128723, |
| "epoch": 4.416, |
| "grad_norm": 0.011312286369502544, |
| "learning_rate": 0.0002, |
| "loss": 0.6291104555130005, |
| "mean_token_accuracy": 0.7415849938988686, |
| "num_tokens": 25920171.0, |
| "step": 693 |
| }, |
| { |
| "entropy": 0.6253160834312439, |
| "epoch": 4.4224, |
| "grad_norm": 0.011473000049591064, |
| "learning_rate": 0.0002, |
| "loss": 0.6265097856521606, |
| "mean_token_accuracy": 0.745900847017765, |
| "num_tokens": 25957661.0, |
| "step": 694 |
| }, |
| { |
| "entropy": 0.6151653453707695, |
| "epoch": 4.4288, |
| "grad_norm": 0.011200590059161186, |
| "learning_rate": 0.0002, |
| "loss": 0.6186162829399109, |
| "mean_token_accuracy": 0.7460164353251457, |
| "num_tokens": 25995288.0, |
| "step": 695 |
| }, |
| { |
| "entropy": 0.6358339488506317, |
| "epoch": 4.4352, |
| "grad_norm": 0.012506633065640926, |
| "learning_rate": 0.0002, |
| "loss": 0.6417111158370972, |
| "mean_token_accuracy": 0.7386213764548302, |
| "num_tokens": 26033219.0, |
| "step": 696 |
| }, |
| { |
| "entropy": 0.6197969987988472, |
| "epoch": 4.4416, |
| "grad_norm": 0.009830954484641552, |
| "learning_rate": 0.0002, |
| "loss": 0.6201560497283936, |
| "mean_token_accuracy": 0.7456861957907677, |
| "num_tokens": 26071131.0, |
| "step": 697 |
| }, |
| { |
| "entropy": 0.6429072171449661, |
| "epoch": 4.448, |
| "grad_norm": 0.011239229701459408, |
| "learning_rate": 0.0002, |
| "loss": 0.6405913829803467, |
| "mean_token_accuracy": 0.7353242784738541, |
| "num_tokens": 26108632.0, |
| "step": 698 |
| }, |
| { |
| "entropy": 0.6173607632517815, |
| "epoch": 4.4544, |
| "grad_norm": 0.012541512958705425, |
| "learning_rate": 0.0002, |
| "loss": 0.6168667078018188, |
| "mean_token_accuracy": 0.7472453713417053, |
| "num_tokens": 26145646.0, |
| "step": 699 |
| }, |
| { |
| "entropy": 0.6328746154904366, |
| "epoch": 4.4608, |
| "grad_norm": 0.011488271877169609, |
| "learning_rate": 0.0002, |
| "loss": 0.6352975368499756, |
| "mean_token_accuracy": 0.7387456595897675, |
| "num_tokens": 26183067.0, |
| "step": 700 |
| }, |
| { |
| "entropy": 0.6217170506715775, |
| "epoch": 4.4672, |
| "grad_norm": 0.010990316979587078, |
| "learning_rate": 0.0002, |
| "loss": 0.6259629726409912, |
| "mean_token_accuracy": 0.7441816553473473, |
| "num_tokens": 26220393.0, |
| "step": 701 |
| }, |
| { |
| "entropy": 0.609848141670227, |
| "epoch": 4.4736, |
| "grad_norm": 0.013483099639415741, |
| "learning_rate": 0.0002, |
| "loss": 0.6171920299530029, |
| "mean_token_accuracy": 0.7466985434293747, |
| "num_tokens": 26257715.0, |
| "step": 702 |
| }, |
| { |
| "entropy": 0.6218430995941162, |
| "epoch": 4.48, |
| "grad_norm": 0.011730284430086613, |
| "learning_rate": 0.0002, |
| "loss": 0.623494565486908, |
| "mean_token_accuracy": 0.7454787790775299, |
| "num_tokens": 26295447.0, |
| "step": 703 |
| }, |
| { |
| "entropy": 0.620815634727478, |
| "epoch": 4.4864, |
| "grad_norm": 0.010400974191725254, |
| "learning_rate": 0.0002, |
| "loss": 0.6193233132362366, |
| "mean_token_accuracy": 0.7462346330285072, |
| "num_tokens": 26332908.0, |
| "step": 704 |
| }, |
| { |
| "entropy": 0.6146924197673798, |
| "epoch": 4.4928, |
| "grad_norm": 0.01097558531910181, |
| "learning_rate": 0.0002, |
| "loss": 0.6141451001167297, |
| "mean_token_accuracy": 0.7498283833265305, |
| "num_tokens": 26370265.0, |
| "step": 705 |
| }, |
| { |
| "entropy": 0.6297887563705444, |
| "epoch": 4.4992, |
| "grad_norm": 0.011810330674052238, |
| "learning_rate": 0.0002, |
| "loss": 0.6298263669013977, |
| "mean_token_accuracy": 0.7408022508025169, |
| "num_tokens": 26407870.0, |
| "step": 706 |
| }, |
| { |
| "entropy": 0.6215150058269501, |
| "epoch": 4.5056, |
| "grad_norm": 0.009892682544887066, |
| "learning_rate": 0.0002, |
| "loss": 0.6210182905197144, |
| "mean_token_accuracy": 0.7464409321546555, |
| "num_tokens": 26445509.0, |
| "step": 707 |
| }, |
| { |
| "entropy": 0.6281390488147736, |
| "epoch": 4.5120000000000005, |
| "grad_norm": 0.011692460626363754, |
| "learning_rate": 0.0002, |
| "loss": 0.6285613179206848, |
| "mean_token_accuracy": 0.7438349798321724, |
| "num_tokens": 26483669.0, |
| "step": 708 |
| }, |
| { |
| "entropy": 0.6214175447821617, |
| "epoch": 4.5184, |
| "grad_norm": 0.011380224488675594, |
| "learning_rate": 0.0002, |
| "loss": 0.6210340261459351, |
| "mean_token_accuracy": 0.7459113150835037, |
| "num_tokens": 26521265.0, |
| "step": 709 |
| }, |
| { |
| "entropy": 0.6104562729597092, |
| "epoch": 4.5248, |
| "grad_norm": 0.01076613087207079, |
| "learning_rate": 0.0002, |
| "loss": 0.6165965795516968, |
| "mean_token_accuracy": 0.7475461736321449, |
| "num_tokens": 26558711.0, |
| "step": 710 |
| }, |
| { |
| "entropy": 0.6271610110998154, |
| "epoch": 4.5312, |
| "grad_norm": 0.010785672813653946, |
| "learning_rate": 0.0002, |
| "loss": 0.6283934116363525, |
| "mean_token_accuracy": 0.7444132044911385, |
| "num_tokens": 26596482.0, |
| "step": 711 |
| }, |
| { |
| "entropy": 0.6205542087554932, |
| "epoch": 4.5376, |
| "grad_norm": 0.010699622333049774, |
| "learning_rate": 0.0002, |
| "loss": 0.61879563331604, |
| "mean_token_accuracy": 0.7464459612965584, |
| "num_tokens": 26634130.0, |
| "step": 712 |
| }, |
| { |
| "entropy": 0.6333268582820892, |
| "epoch": 4.5440000000000005, |
| "grad_norm": 0.01175402756780386, |
| "learning_rate": 0.0002, |
| "loss": 0.6315722465515137, |
| "mean_token_accuracy": 0.7412132248282433, |
| "num_tokens": 26671733.0, |
| "step": 713 |
| }, |
| { |
| "entropy": 0.6141394674777985, |
| "epoch": 4.5504, |
| "grad_norm": 0.01065735798329115, |
| "learning_rate": 0.0002, |
| "loss": 0.6193619966506958, |
| "mean_token_accuracy": 0.7467841058969498, |
| "num_tokens": 26708976.0, |
| "step": 714 |
| }, |
| { |
| "entropy": 0.6316620260477066, |
| "epoch": 4.5568, |
| "grad_norm": 0.01289924792945385, |
| "learning_rate": 0.0002, |
| "loss": 0.6370086669921875, |
| "mean_token_accuracy": 0.7389457300305367, |
| "num_tokens": 26746597.0, |
| "step": 715 |
| }, |
| { |
| "entropy": 0.6334016472101212, |
| "epoch": 4.5632, |
| "grad_norm": 0.01159643568098545, |
| "learning_rate": 0.0002, |
| "loss": 0.6357477307319641, |
| "mean_token_accuracy": 0.7415767312049866, |
| "num_tokens": 26784347.0, |
| "step": 716 |
| }, |
| { |
| "entropy": 0.6209512129426003, |
| "epoch": 4.5696, |
| "grad_norm": 0.012357997708022594, |
| "learning_rate": 0.0002, |
| "loss": 0.620951235294342, |
| "mean_token_accuracy": 0.7445131912827492, |
| "num_tokens": 26821369.0, |
| "step": 717 |
| }, |
| { |
| "entropy": 0.6184145584702492, |
| "epoch": 4.576, |
| "grad_norm": 0.011790684424340725, |
| "learning_rate": 0.0002, |
| "loss": 0.6185816526412964, |
| "mean_token_accuracy": 0.7467178478837013, |
| "num_tokens": 26858658.0, |
| "step": 718 |
| }, |
| { |
| "entropy": 0.6372607722878456, |
| "epoch": 4.5824, |
| "grad_norm": 0.011222328059375286, |
| "learning_rate": 0.0002, |
| "loss": 0.6393177509307861, |
| "mean_token_accuracy": 0.7393923178315163, |
| "num_tokens": 26896679.0, |
| "step": 719 |
| }, |
| { |
| "entropy": 0.6263199970126152, |
| "epoch": 4.5888, |
| "grad_norm": 0.01184337493032217, |
| "learning_rate": 0.0002, |
| "loss": 0.6317442059516907, |
| "mean_token_accuracy": 0.7412994503974915, |
| "num_tokens": 26934191.0, |
| "step": 720 |
| }, |
| { |
| "entropy": 0.6313236430287361, |
| "epoch": 4.5952, |
| "grad_norm": 0.012818049639463425, |
| "learning_rate": 0.0002, |
| "loss": 0.6400792002677917, |
| "mean_token_accuracy": 0.7399108409881592, |
| "num_tokens": 26971795.0, |
| "step": 721 |
| }, |
| { |
| "entropy": 0.6408603191375732, |
| "epoch": 4.6016, |
| "grad_norm": 0.011262350715696812, |
| "learning_rate": 0.0002, |
| "loss": 0.6372708678245544, |
| "mean_token_accuracy": 0.7409083321690559, |
| "num_tokens": 27009541.0, |
| "step": 722 |
| }, |
| { |
| "entropy": 0.6237692162394524, |
| "epoch": 4.608, |
| "grad_norm": 0.01265136618167162, |
| "learning_rate": 0.0002, |
| "loss": 0.6219276189804077, |
| "mean_token_accuracy": 0.74643175303936, |
| "num_tokens": 27047207.0, |
| "step": 723 |
| }, |
| { |
| "entropy": 0.6229505017399788, |
| "epoch": 4.6144, |
| "grad_norm": 0.01034928485751152, |
| "learning_rate": 0.0002, |
| "loss": 0.6240932941436768, |
| "mean_token_accuracy": 0.7452475875616074, |
| "num_tokens": 27084670.0, |
| "step": 724 |
| }, |
| { |
| "entropy": 0.6106055229902267, |
| "epoch": 4.6208, |
| "grad_norm": 0.012862354516983032, |
| "learning_rate": 0.0002, |
| "loss": 0.6164753437042236, |
| "mean_token_accuracy": 0.7482388094067574, |
| "num_tokens": 27122124.0, |
| "step": 725 |
| }, |
| { |
| "entropy": 0.6230287775397301, |
| "epoch": 4.6272, |
| "grad_norm": 0.012530112639069557, |
| "learning_rate": 0.0002, |
| "loss": 0.6248811483383179, |
| "mean_token_accuracy": 0.745893694460392, |
| "num_tokens": 27159984.0, |
| "step": 726 |
| }, |
| { |
| "entropy": 0.6258671432733536, |
| "epoch": 4.6336, |
| "grad_norm": 0.011710980907082558, |
| "learning_rate": 0.0002, |
| "loss": 0.6271563768386841, |
| "mean_token_accuracy": 0.7450519576668739, |
| "num_tokens": 27197583.0, |
| "step": 727 |
| }, |
| { |
| "entropy": 0.6244168281555176, |
| "epoch": 4.64, |
| "grad_norm": 0.012283277697861195, |
| "learning_rate": 0.0002, |
| "loss": 0.6260854005813599, |
| "mean_token_accuracy": 0.7433378919959068, |
| "num_tokens": 27235084.0, |
| "step": 728 |
| }, |
| { |
| "entropy": 0.6399951577186584, |
| "epoch": 4.6464, |
| "grad_norm": 0.010510124266147614, |
| "learning_rate": 0.0002, |
| "loss": 0.6376748085021973, |
| "mean_token_accuracy": 0.7380894720554352, |
| "num_tokens": 27272833.0, |
| "step": 729 |
| }, |
| { |
| "entropy": 0.6234357804059982, |
| "epoch": 4.6528, |
| "grad_norm": 0.014871729537844658, |
| "learning_rate": 0.0002, |
| "loss": 0.6165429353713989, |
| "mean_token_accuracy": 0.7468608766794205, |
| "num_tokens": 27310301.0, |
| "step": 730 |
| }, |
| { |
| "entropy": 0.6247937902808189, |
| "epoch": 4.6592, |
| "grad_norm": 0.010685059241950512, |
| "learning_rate": 0.0002, |
| "loss": 0.6294916868209839, |
| "mean_token_accuracy": 0.7414043098688126, |
| "num_tokens": 27347720.0, |
| "step": 731 |
| }, |
| { |
| "entropy": 0.6104548647999763, |
| "epoch": 4.6655999999999995, |
| "grad_norm": 0.018121415749192238, |
| "learning_rate": 0.0002, |
| "loss": 0.6216402053833008, |
| "mean_token_accuracy": 0.7466417998075485, |
| "num_tokens": 27385336.0, |
| "step": 732 |
| }, |
| { |
| "entropy": 0.6151935011148453, |
| "epoch": 4.672, |
| "grad_norm": 0.010607750155031681, |
| "learning_rate": 0.0002, |
| "loss": 0.6190038323402405, |
| "mean_token_accuracy": 0.7471088394522667, |
| "num_tokens": 27422696.0, |
| "step": 733 |
| }, |
| { |
| "entropy": 0.625689759850502, |
| "epoch": 4.6784, |
| "grad_norm": 0.014054366387426853, |
| "learning_rate": 0.0002, |
| "loss": 0.6243985295295715, |
| "mean_token_accuracy": 0.7436644211411476, |
| "num_tokens": 27460268.0, |
| "step": 734 |
| }, |
| { |
| "entropy": 0.6268169730901718, |
| "epoch": 4.6848, |
| "grad_norm": 0.012450247071683407, |
| "learning_rate": 0.0002, |
| "loss": 0.6240094900131226, |
| "mean_token_accuracy": 0.743643693625927, |
| "num_tokens": 27498085.0, |
| "step": 735 |
| }, |
| { |
| "entropy": 0.6271230131387711, |
| "epoch": 4.6912, |
| "grad_norm": 0.011883650906383991, |
| "learning_rate": 0.0002, |
| "loss": 0.6317532062530518, |
| "mean_token_accuracy": 0.7423899173736572, |
| "num_tokens": 27535478.0, |
| "step": 736 |
| }, |
| { |
| "entropy": 0.6135580986738205, |
| "epoch": 4.6975999999999996, |
| "grad_norm": 0.014882571063935757, |
| "learning_rate": 0.0002, |
| "loss": 0.6232122182846069, |
| "mean_token_accuracy": 0.7451476007699966, |
| "num_tokens": 27572692.0, |
| "step": 737 |
| }, |
| { |
| "entropy": 0.6177224218845367, |
| "epoch": 4.704, |
| "grad_norm": 0.011081320233643055, |
| "learning_rate": 0.0002, |
| "loss": 0.6193344593048096, |
| "mean_token_accuracy": 0.7470099404454231, |
| "num_tokens": 27610526.0, |
| "step": 738 |
| }, |
| { |
| "entropy": 0.618368849158287, |
| "epoch": 4.7104, |
| "grad_norm": 0.01142704114317894, |
| "learning_rate": 0.0002, |
| "loss": 0.618331789970398, |
| "mean_token_accuracy": 0.7472382485866547, |
| "num_tokens": 27648029.0, |
| "step": 739 |
| }, |
| { |
| "entropy": 0.6240565925836563, |
| "epoch": 4.7168, |
| "grad_norm": 0.011985547840595245, |
| "learning_rate": 0.0002, |
| "loss": 0.624761700630188, |
| "mean_token_accuracy": 0.7442751675844193, |
| "num_tokens": 27685924.0, |
| "step": 740 |
| }, |
| { |
| "entropy": 0.6319902166724205, |
| "epoch": 4.7232, |
| "grad_norm": 0.012069285847246647, |
| "learning_rate": 0.0002, |
| "loss": 0.6318994164466858, |
| "mean_token_accuracy": 0.739115908741951, |
| "num_tokens": 27723816.0, |
| "step": 741 |
| }, |
| { |
| "entropy": 0.6412005797028542, |
| "epoch": 4.7296, |
| "grad_norm": 0.01274879090487957, |
| "learning_rate": 0.0002, |
| "loss": 0.6381031274795532, |
| "mean_token_accuracy": 0.7396308556199074, |
| "num_tokens": 27761867.0, |
| "step": 742 |
| }, |
| { |
| "entropy": 0.6192675158381462, |
| "epoch": 4.736, |
| "grad_norm": 0.00995372049510479, |
| "learning_rate": 0.0002, |
| "loss": 0.62370765209198, |
| "mean_token_accuracy": 0.7466439455747604, |
| "num_tokens": 27799496.0, |
| "step": 743 |
| }, |
| { |
| "entropy": 0.6180000007152557, |
| "epoch": 4.7424, |
| "grad_norm": 0.012485142797231674, |
| "learning_rate": 0.0002, |
| "loss": 0.618539035320282, |
| "mean_token_accuracy": 0.7472988590598106, |
| "num_tokens": 27836904.0, |
| "step": 744 |
| }, |
| { |
| "entropy": 0.6233759000897408, |
| "epoch": 4.7488, |
| "grad_norm": 0.01297292672097683, |
| "learning_rate": 0.0002, |
| "loss": 0.6253551244735718, |
| "mean_token_accuracy": 0.743793860077858, |
| "num_tokens": 27874562.0, |
| "step": 745 |
| }, |
| { |
| "entropy": 0.6195263043045998, |
| "epoch": 4.7552, |
| "grad_norm": 0.013405952602624893, |
| "learning_rate": 0.0002, |
| "loss": 0.6302239298820496, |
| "mean_token_accuracy": 0.7412486523389816, |
| "num_tokens": 27911903.0, |
| "step": 746 |
| }, |
| { |
| "entropy": 0.6423712894320488, |
| "epoch": 4.7616, |
| "grad_norm": 0.011862635612487793, |
| "learning_rate": 0.0002, |
| "loss": 0.6428091526031494, |
| "mean_token_accuracy": 0.735967144370079, |
| "num_tokens": 27949551.0, |
| "step": 747 |
| }, |
| { |
| "entropy": 0.6365993991494179, |
| "epoch": 4.768, |
| "grad_norm": 0.011519255116581917, |
| "learning_rate": 0.0002, |
| "loss": 0.6331340074539185, |
| "mean_token_accuracy": 0.7445235848426819, |
| "num_tokens": 27987167.0, |
| "step": 748 |
| }, |
| { |
| "entropy": 0.6285323649644852, |
| "epoch": 4.7744, |
| "grad_norm": 0.011068753898143768, |
| "learning_rate": 0.0002, |
| "loss": 0.6295030117034912, |
| "mean_token_accuracy": 0.7423546016216278, |
| "num_tokens": 28024667.0, |
| "step": 749 |
| }, |
| { |
| "entropy": 0.6225018426775932, |
| "epoch": 4.7808, |
| "grad_norm": 0.012251611799001694, |
| "learning_rate": 0.0002, |
| "loss": 0.6240028142929077, |
| "mean_token_accuracy": 0.7458074688911438, |
| "num_tokens": 28062045.0, |
| "step": 750 |
| }, |
| { |
| "entropy": 0.6218413189053535, |
| "epoch": 4.7872, |
| "grad_norm": 0.011230433359742165, |
| "learning_rate": 0.0002, |
| "loss": 0.625887393951416, |
| "mean_token_accuracy": 0.7432527989149094, |
| "num_tokens": 28099618.0, |
| "step": 751 |
| }, |
| { |
| "entropy": 0.605789877474308, |
| "epoch": 4.7936, |
| "grad_norm": 0.01227335911244154, |
| "learning_rate": 0.0002, |
| "loss": 0.6102015376091003, |
| "mean_token_accuracy": 0.7511238679289818, |
| "num_tokens": 28137039.0, |
| "step": 752 |
| }, |
| { |
| "entropy": 0.6157144531607628, |
| "epoch": 4.8, |
| "grad_norm": 0.01124510820955038, |
| "learning_rate": 0.0002, |
| "loss": 0.6144552230834961, |
| "mean_token_accuracy": 0.7501148656010628, |
| "num_tokens": 28174015.0, |
| "step": 753 |
| }, |
| { |
| "entropy": 0.6372276619076729, |
| "epoch": 4.8064, |
| "grad_norm": 0.012294857762753963, |
| "learning_rate": 0.0002, |
| "loss": 0.6344669461250305, |
| "mean_token_accuracy": 0.7430569604039192, |
| "num_tokens": 28211765.0, |
| "step": 754 |
| }, |
| { |
| "entropy": 0.618014894425869, |
| "epoch": 4.8128, |
| "grad_norm": 0.01041495706886053, |
| "learning_rate": 0.0002, |
| "loss": 0.6209543943405151, |
| "mean_token_accuracy": 0.7452011853456497, |
| "num_tokens": 28249441.0, |
| "step": 755 |
| }, |
| { |
| "entropy": 0.6153213605284691, |
| "epoch": 4.8192, |
| "grad_norm": 0.012670926749706268, |
| "learning_rate": 0.0002, |
| "loss": 0.6228734254837036, |
| "mean_token_accuracy": 0.7460622638463974, |
| "num_tokens": 28286854.0, |
| "step": 756 |
| }, |
| { |
| "entropy": 0.6158452033996582, |
| "epoch": 4.8256, |
| "grad_norm": 0.012129560112953186, |
| "learning_rate": 0.0002, |
| "loss": 0.6199190020561218, |
| "mean_token_accuracy": 0.747655563056469, |
| "num_tokens": 28323945.0, |
| "step": 757 |
| }, |
| { |
| "entropy": 0.6290484443306923, |
| "epoch": 4.832, |
| "grad_norm": 0.01301377359777689, |
| "learning_rate": 0.0002, |
| "loss": 0.6258755922317505, |
| "mean_token_accuracy": 0.7452258318662643, |
| "num_tokens": 28361641.0, |
| "step": 758 |
| }, |
| { |
| "entropy": 0.634510226547718, |
| "epoch": 4.8384, |
| "grad_norm": 0.011934357695281506, |
| "learning_rate": 0.0002, |
| "loss": 0.6296937465667725, |
| "mean_token_accuracy": 0.742583654820919, |
| "num_tokens": 28399119.0, |
| "step": 759 |
| }, |
| { |
| "entropy": 0.6339060291647911, |
| "epoch": 4.8448, |
| "grad_norm": 0.010478752665221691, |
| "learning_rate": 0.0002, |
| "loss": 0.6356696486473083, |
| "mean_token_accuracy": 0.7409758344292641, |
| "num_tokens": 28436921.0, |
| "step": 760 |
| }, |
| { |
| "entropy": 0.6190384924411774, |
| "epoch": 4.8512, |
| "grad_norm": 0.013402252458035946, |
| "learning_rate": 0.0002, |
| "loss": 0.6263437271118164, |
| "mean_token_accuracy": 0.7457704097032547, |
| "num_tokens": 28474709.0, |
| "step": 761 |
| }, |
| { |
| "entropy": 0.6296346411108971, |
| "epoch": 4.8576, |
| "grad_norm": 0.01403774507343769, |
| "learning_rate": 0.0002, |
| "loss": 0.6382781267166138, |
| "mean_token_accuracy": 0.740397572517395, |
| "num_tokens": 28512263.0, |
| "step": 762 |
| }, |
| { |
| "entropy": 0.6387407630681992, |
| "epoch": 4.864, |
| "grad_norm": 0.010807156562805176, |
| "learning_rate": 0.0002, |
| "loss": 0.6353914141654968, |
| "mean_token_accuracy": 0.7394013479351997, |
| "num_tokens": 28549975.0, |
| "step": 763 |
| }, |
| { |
| "entropy": 0.6354725807905197, |
| "epoch": 4.8704, |
| "grad_norm": 0.013257911428809166, |
| "learning_rate": 0.0002, |
| "loss": 0.6323150396347046, |
| "mean_token_accuracy": 0.7414470240473747, |
| "num_tokens": 28587095.0, |
| "step": 764 |
| }, |
| { |
| "entropy": 0.6424222439527512, |
| "epoch": 4.8768, |
| "grad_norm": 0.012375367805361748, |
| "learning_rate": 0.0002, |
| "loss": 0.64325350522995, |
| "mean_token_accuracy": 0.7369028478860855, |
| "num_tokens": 28624868.0, |
| "step": 765 |
| }, |
| { |
| "entropy": 0.6223215311765671, |
| "epoch": 4.8832, |
| "grad_norm": 0.013609180226922035, |
| "learning_rate": 0.0002, |
| "loss": 0.6308131217956543, |
| "mean_token_accuracy": 0.7428993359208107, |
| "num_tokens": 28662266.0, |
| "step": 766 |
| }, |
| { |
| "entropy": 0.6198636963963509, |
| "epoch": 4.8896, |
| "grad_norm": 0.011831787414848804, |
| "learning_rate": 0.0002, |
| "loss": 0.6238384246826172, |
| "mean_token_accuracy": 0.7449830919504166, |
| "num_tokens": 28700199.0, |
| "step": 767 |
| }, |
| { |
| "entropy": 0.6371955797076225, |
| "epoch": 4.896, |
| "grad_norm": 0.011555573903024197, |
| "learning_rate": 0.0002, |
| "loss": 0.6325588822364807, |
| "mean_token_accuracy": 0.7409590929746628, |
| "num_tokens": 28737979.0, |
| "step": 768 |
| }, |
| { |
| "entropy": 0.6182679012417793, |
| "epoch": 4.9024, |
| "grad_norm": 0.01133381575345993, |
| "learning_rate": 0.0002, |
| "loss": 0.6179029941558838, |
| "mean_token_accuracy": 0.7483383342623711, |
| "num_tokens": 28775432.0, |
| "step": 769 |
| }, |
| { |
| "entropy": 0.6291498392820358, |
| "epoch": 4.9088, |
| "grad_norm": 0.010519672185182571, |
| "learning_rate": 0.0002, |
| "loss": 0.6308712363243103, |
| "mean_token_accuracy": 0.7437527477741241, |
| "num_tokens": 28812536.0, |
| "step": 770 |
| }, |
| { |
| "entropy": 0.6246335506439209, |
| "epoch": 4.9152000000000005, |
| "grad_norm": 0.013134768232703209, |
| "learning_rate": 0.0002, |
| "loss": 0.6342728734016418, |
| "mean_token_accuracy": 0.7407044470310211, |
| "num_tokens": 28850060.0, |
| "step": 771 |
| }, |
| { |
| "entropy": 0.6130682453513145, |
| "epoch": 4.9216, |
| "grad_norm": 0.010492725297808647, |
| "learning_rate": 0.0002, |
| "loss": 0.6162416934967041, |
| "mean_token_accuracy": 0.7491699755191803, |
| "num_tokens": 28887643.0, |
| "step": 772 |
| }, |
| { |
| "entropy": 0.6313211023807526, |
| "epoch": 4.928, |
| "grad_norm": 0.011192471720278263, |
| "learning_rate": 0.0002, |
| "loss": 0.631119966506958, |
| "mean_token_accuracy": 0.741656944155693, |
| "num_tokens": 28925297.0, |
| "step": 773 |
| }, |
| { |
| "entropy": 0.6132954135537148, |
| "epoch": 4.9344, |
| "grad_norm": 0.00988168828189373, |
| "learning_rate": 0.0002, |
| "loss": 0.6083347201347351, |
| "mean_token_accuracy": 0.7506287023425102, |
| "num_tokens": 28962437.0, |
| "step": 774 |
| }, |
| { |
| "entropy": 0.6186309084296227, |
| "epoch": 4.9408, |
| "grad_norm": 0.011386038735508919, |
| "learning_rate": 0.0002, |
| "loss": 0.6201795339584351, |
| "mean_token_accuracy": 0.7484031617641449, |
| "num_tokens": 28999874.0, |
| "step": 775 |
| }, |
| { |
| "entropy": 0.6235462054610252, |
| "epoch": 4.9472000000000005, |
| "grad_norm": 0.011064821854233742, |
| "learning_rate": 0.0002, |
| "loss": 0.6267992258071899, |
| "mean_token_accuracy": 0.7443990632891655, |
| "num_tokens": 29037497.0, |
| "step": 776 |
| }, |
| { |
| "entropy": 0.6196893155574799, |
| "epoch": 4.9536, |
| "grad_norm": 0.012706468813121319, |
| "learning_rate": 0.0002, |
| "loss": 0.6288238763809204, |
| "mean_token_accuracy": 0.7432743161916733, |
| "num_tokens": 29074815.0, |
| "step": 777 |
| }, |
| { |
| "entropy": 0.6359954103827477, |
| "epoch": 4.96, |
| "grad_norm": 0.01185152493417263, |
| "learning_rate": 0.0002, |
| "loss": 0.6353201866149902, |
| "mean_token_accuracy": 0.7408851012587547, |
| "num_tokens": 29112518.0, |
| "step": 778 |
| }, |
| { |
| "entropy": 0.6222160458564758, |
| "epoch": 4.9664, |
| "grad_norm": 0.011700387112796307, |
| "learning_rate": 0.0002, |
| "loss": 0.6173217296600342, |
| "mean_token_accuracy": 0.7465430647134781, |
| "num_tokens": 29150199.0, |
| "step": 779 |
| }, |
| { |
| "entropy": 0.6329935416579247, |
| "epoch": 4.9728, |
| "grad_norm": 0.011351538822054863, |
| "learning_rate": 0.0002, |
| "loss": 0.6344210505485535, |
| "mean_token_accuracy": 0.7397899106144905, |
| "num_tokens": 29187985.0, |
| "step": 780 |
| }, |
| { |
| "entropy": 0.6197427585721016, |
| "epoch": 4.9792, |
| "grad_norm": 0.013295335695147514, |
| "learning_rate": 0.0002, |
| "loss": 0.6274314522743225, |
| "mean_token_accuracy": 0.742200955748558, |
| "num_tokens": 29225578.0, |
| "step": 781 |
| }, |
| { |
| "entropy": 0.6366394832730293, |
| "epoch": 4.9856, |
| "grad_norm": 0.011197940446436405, |
| "learning_rate": 0.0002, |
| "loss": 0.6420581340789795, |
| "mean_token_accuracy": 0.7372548654675484, |
| "num_tokens": 29263081.0, |
| "step": 782 |
| }, |
| { |
| "entropy": 0.623991571366787, |
| "epoch": 4.992, |
| "grad_norm": 0.012578215450048447, |
| "learning_rate": 0.0002, |
| "loss": 0.6253401041030884, |
| "mean_token_accuracy": 0.7438567355275154, |
| "num_tokens": 29300476.0, |
| "step": 783 |
| }, |
| { |
| "entropy": 0.6156981587409973, |
| "epoch": 4.9984, |
| "grad_norm": 0.010751175694167614, |
| "learning_rate": 0.0002, |
| "loss": 0.616902232170105, |
| "mean_token_accuracy": 0.7490730434656143, |
| "num_tokens": 29337892.0, |
| "step": 784 |
| }, |
| { |
| "entropy": 0.6212073564529419, |
| "epoch": 5.0, |
| "grad_norm": 0.0221311803907156, |
| "learning_rate": 0.0002, |
| "loss": 0.6252682209014893, |
| "mean_token_accuracy": 0.7461582720279694, |
| "num_tokens": 29347371.0, |
| "step": 785 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 785, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 5, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 2.7322491635624837e+18, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
