{ "best_metric": null, "best_model_checkpoint": null, "epoch": 3.0, "eval_steps": 500, "global_step": 351, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.008547008547008548, "grad_norm": 0.25262296199798584, "learning_rate": 2e-05, "loss": 1.288, "step": 1 }, { "epoch": 0.017094017094017096, "grad_norm": 0.2176843136548996, "learning_rate": 4e-05, "loss": 0.9905, "step": 2 }, { "epoch": 0.02564102564102564, "grad_norm": 0.2575605809688568, "learning_rate": 6e-05, "loss": 1.3014, "step": 3 }, { "epoch": 0.03418803418803419, "grad_norm": 0.1782544106245041, "learning_rate": 8e-05, "loss": 1.5081, "step": 4 }, { "epoch": 0.042735042735042736, "grad_norm": 0.33221080899238586, "learning_rate": 0.0001, "loss": 1.1328, "step": 5 }, { "epoch": 0.05128205128205128, "grad_norm": 0.28970077633857727, "learning_rate": 0.00012, "loss": 1.4862, "step": 6 }, { "epoch": 0.05982905982905983, "grad_norm": 0.32833603024482727, "learning_rate": 0.00014, "loss": 1.0591, "step": 7 }, { "epoch": 0.06837606837606838, "grad_norm": 0.35267820954322815, "learning_rate": 0.00016, "loss": 1.0766, "step": 8 }, { "epoch": 0.07692307692307693, "grad_norm": 0.402508020401001, "learning_rate": 0.00018, "loss": 0.9063, "step": 9 }, { "epoch": 0.08547008547008547, "grad_norm": 0.316371351480484, "learning_rate": 0.0002, "loss": 1.1015, "step": 10 }, { "epoch": 0.09401709401709402, "grad_norm": 0.32572099566459656, "learning_rate": 0.0001999976474595967, "loss": 1.08, "step": 11 }, { "epoch": 0.10256410256410256, "grad_norm": 0.18087100982666016, "learning_rate": 0.00019999058994907564, "loss": 0.8118, "step": 12 }, { "epoch": 0.1111111111111111, "grad_norm": 0.30534857511520386, "learning_rate": 0.00019997882780049847, "loss": 0.9287, "step": 13 }, { "epoch": 0.11965811965811966, "grad_norm": 0.332878053188324, "learning_rate": 0.0001999623615672837, "loss": 1.0165, "step": 14 }, { "epoch": 0.1282051282051282, "grad_norm": 0.17985212802886963, "learning_rate": 0.00019994119202418098, "loss": 1.1294, "step": 15 }, { "epoch": 0.13675213675213677, "grad_norm": 0.17866399884223938, "learning_rate": 0.00019991532016723439, "loss": 0.8047, "step": 16 }, { "epoch": 0.1452991452991453, "grad_norm": 0.10377021133899689, "learning_rate": 0.00019988474721373568, "loss": 1.193, "step": 17 }, { "epoch": 0.15384615384615385, "grad_norm": 0.11353971809148788, "learning_rate": 0.00019984947460216707, "loss": 0.6695, "step": 18 }, { "epoch": 0.1623931623931624, "grad_norm": 0.12540249526500702, "learning_rate": 0.00019980950399213344, "loss": 0.7988, "step": 19 }, { "epoch": 0.17094017094017094, "grad_norm": 0.11810794472694397, "learning_rate": 0.00019976483726428422, "loss": 0.6776, "step": 20 }, { "epoch": 0.1794871794871795, "grad_norm": 0.15847349166870117, "learning_rate": 0.0001997154765202251, "loss": 0.6852, "step": 21 }, { "epoch": 0.18803418803418803, "grad_norm": 0.13485313951969147, "learning_rate": 0.00019966142408241901, "loss": 0.7981, "step": 22 }, { "epoch": 0.19658119658119658, "grad_norm": 0.1381629854440689, "learning_rate": 0.00019960268249407675, "loss": 0.8672, "step": 23 }, { "epoch": 0.20512820512820512, "grad_norm": 0.18560636043548584, "learning_rate": 0.00019953925451903756, "loss": 0.8382, "step": 24 }, { "epoch": 0.21367521367521367, "grad_norm": 0.11415428668260574, "learning_rate": 0.0001994711431416389, "loss": 1.4257, "step": 25 }, { "epoch": 0.2222222222222222, "grad_norm": 0.1419740468263626, "learning_rate": 0.00019939835156657616, "loss": 1.2219, "step": 26 }, { "epoch": 0.23076923076923078, "grad_norm": 0.1541571021080017, "learning_rate": 0.00019932088321875172, "loss": 0.7459, "step": 27 }, { "epoch": 0.23931623931623933, "grad_norm": 0.16184499859809875, "learning_rate": 0.00019923874174311394, "loss": 0.66, "step": 28 }, { "epoch": 0.24786324786324787, "grad_norm": 0.13992361724376678, "learning_rate": 0.0001991519310044857, "loss": 1.0709, "step": 29 }, { "epoch": 0.2564102564102564, "grad_norm": 0.1397615224123001, "learning_rate": 0.00019906045508738228, "loss": 0.9601, "step": 30 }, { "epoch": 0.26495726495726496, "grad_norm": 0.15078146755695343, "learning_rate": 0.0001989643182958196, "loss": 0.678, "step": 31 }, { "epoch": 0.27350427350427353, "grad_norm": 0.18909209966659546, "learning_rate": 0.00019886352515311134, "loss": 0.7399, "step": 32 }, { "epoch": 0.28205128205128205, "grad_norm": 0.149637833237648, "learning_rate": 0.0001987580804016563, "loss": 0.9793, "step": 33 }, { "epoch": 0.2905982905982906, "grad_norm": 0.14903782308101654, "learning_rate": 0.00019864798900271532, "loss": 0.8615, "step": 34 }, { "epoch": 0.29914529914529914, "grad_norm": 0.13387615978717804, "learning_rate": 0.0001985332561361776, "loss": 0.6926, "step": 35 }, { "epoch": 0.3076923076923077, "grad_norm": 0.11794736236333847, "learning_rate": 0.00019841388720031727, "loss": 0.6114, "step": 36 }, { "epoch": 0.3162393162393162, "grad_norm": 0.14885829389095306, "learning_rate": 0.00019828988781153917, "loss": 0.7201, "step": 37 }, { "epoch": 0.3247863247863248, "grad_norm": 0.15518176555633545, "learning_rate": 0.00019816126380411476, "loss": 0.7263, "step": 38 }, { "epoch": 0.3333333333333333, "grad_norm": 0.13227546215057373, "learning_rate": 0.00019802802122990758, "loss": 0.7479, "step": 39 }, { "epoch": 0.3418803418803419, "grad_norm": 0.15872053802013397, "learning_rate": 0.00019789016635808837, "loss": 0.7847, "step": 40 }, { "epoch": 0.3504273504273504, "grad_norm": 0.13838137686252594, "learning_rate": 0.00019774770567484022, "loss": 0.9159, "step": 41 }, { "epoch": 0.358974358974359, "grad_norm": 0.11419806629419327, "learning_rate": 0.00019760064588305345, "loss": 0.6802, "step": 42 }, { "epoch": 0.36752136752136755, "grad_norm": 0.12754102051258087, "learning_rate": 0.00019744899390201006, "loss": 0.7116, "step": 43 }, { "epoch": 0.37606837606837606, "grad_norm": 0.12221560627222061, "learning_rate": 0.0001972927568670583, "loss": 1.0765, "step": 44 }, { "epoch": 0.38461538461538464, "grad_norm": 0.1402164101600647, "learning_rate": 0.00019713194212927696, "loss": 0.83, "step": 45 }, { "epoch": 0.39316239316239315, "grad_norm": 0.14776213467121124, "learning_rate": 0.00019696655725512933, "loss": 0.7333, "step": 46 }, { "epoch": 0.4017094017094017, "grad_norm": 0.14819088578224182, "learning_rate": 0.00019679661002610743, "loss": 0.8153, "step": 47 }, { "epoch": 0.41025641025641024, "grad_norm": 0.12451574206352234, "learning_rate": 0.00019662210843836574, "loss": 0.7028, "step": 48 }, { "epoch": 0.4188034188034188, "grad_norm": 0.14047390222549438, "learning_rate": 0.0001964430607023449, "loss": 0.6932, "step": 49 }, { "epoch": 0.42735042735042733, "grad_norm": 0.1826234757900238, "learning_rate": 0.00019625947524238563, "loss": 0.9923, "step": 50 }, { "epoch": 0.4358974358974359, "grad_norm": 0.14018255472183228, "learning_rate": 0.00019607136069633212, "loss": 0.6738, "step": 51 }, { "epoch": 0.4444444444444444, "grad_norm": 0.13014380633831024, "learning_rate": 0.0001958787259151258, "loss": 0.6896, "step": 52 }, { "epoch": 0.452991452991453, "grad_norm": 0.1482684463262558, "learning_rate": 0.00019568157996238884, "loss": 0.6597, "step": 53 }, { "epoch": 0.46153846153846156, "grad_norm": 0.12220227718353271, "learning_rate": 0.0001954799321139975, "loss": 0.9904, "step": 54 }, { "epoch": 0.4700854700854701, "grad_norm": 0.1338455229997635, "learning_rate": 0.00019527379185764612, "loss": 0.6457, "step": 55 }, { "epoch": 0.47863247863247865, "grad_norm": 0.17472369968891144, "learning_rate": 0.00019506316889240027, "loss": 1.134, "step": 56 }, { "epoch": 0.48717948717948717, "grad_norm": 0.14439380168914795, "learning_rate": 0.00019484807312824067, "loss": 0.6166, "step": 57 }, { "epoch": 0.49572649572649574, "grad_norm": 0.18377861380577087, "learning_rate": 0.0001946285146855968, "loss": 0.7602, "step": 58 }, { "epoch": 0.5042735042735043, "grad_norm": 0.159800723195076, "learning_rate": 0.0001944045038948709, "loss": 0.7342, "step": 59 }, { "epoch": 0.5128205128205128, "grad_norm": 0.17464005947113037, "learning_rate": 0.00019417605129595157, "loss": 0.6698, "step": 60 }, { "epoch": 0.5213675213675214, "grad_norm": 0.16266022622585297, "learning_rate": 0.0001939431676377183, "loss": 0.6718, "step": 61 }, { "epoch": 0.5299145299145299, "grad_norm": 0.14515793323516846, "learning_rate": 0.0001937058638775353, "loss": 0.6268, "step": 62 }, { "epoch": 0.5384615384615384, "grad_norm": 0.12234693765640259, "learning_rate": 0.00019346415118073632, "loss": 1.2523, "step": 63 }, { "epoch": 0.5470085470085471, "grad_norm": 0.17767716944217682, "learning_rate": 0.00019321804092009906, "loss": 0.7257, "step": 64 }, { "epoch": 0.5555555555555556, "grad_norm": 0.16069312393665314, "learning_rate": 0.00019296754467531014, "loss": 0.6947, "step": 65 }, { "epoch": 0.5641025641025641, "grad_norm": 0.18852359056472778, "learning_rate": 0.00019271267423242024, "loss": 0.6933, "step": 66 }, { "epoch": 0.5726495726495726, "grad_norm": 0.1703113317489624, "learning_rate": 0.00019245344158328972, "loss": 0.7734, "step": 67 }, { "epoch": 0.5811965811965812, "grad_norm": 0.1587096005678177, "learning_rate": 0.0001921898589250242, "loss": 0.6607, "step": 68 }, { "epoch": 0.5897435897435898, "grad_norm": 0.15161314606666565, "learning_rate": 0.0001919219386594007, "loss": 0.7139, "step": 69 }, { "epoch": 0.5982905982905983, "grad_norm": 0.15223422646522522, "learning_rate": 0.00019164969339228422, "loss": 0.7178, "step": 70 }, { "epoch": 0.6068376068376068, "grad_norm": 0.18094822764396667, "learning_rate": 0.00019137313593303463, "loss": 0.7735, "step": 71 }, { "epoch": 0.6153846153846154, "grad_norm": 0.13845407962799072, "learning_rate": 0.00019109227929390378, "loss": 1.3756, "step": 72 }, { "epoch": 0.6239316239316239, "grad_norm": 0.15550608932971954, "learning_rate": 0.00019080713668942356, "loss": 0.6475, "step": 73 }, { "epoch": 0.6324786324786325, "grad_norm": 0.16042666137218475, "learning_rate": 0.00019051772153578389, "loss": 0.6748, "step": 74 }, { "epoch": 0.6410256410256411, "grad_norm": 0.17203615605831146, "learning_rate": 0.00019022404745020163, "loss": 0.6711, "step": 75 }, { "epoch": 0.6495726495726496, "grad_norm": 0.14476130902767181, "learning_rate": 0.00018992612825027976, "loss": 0.7195, "step": 76 }, { "epoch": 0.6581196581196581, "grad_norm": 0.18853308260440826, "learning_rate": 0.0001896239779533575, "loss": 0.8027, "step": 77 }, { "epoch": 0.6666666666666666, "grad_norm": 0.1497141271829605, "learning_rate": 0.00018931761077585035, "loss": 0.6621, "step": 78 }, { "epoch": 0.6752136752136753, "grad_norm": 0.16902165114879608, "learning_rate": 0.00018900704113258165, "loss": 0.6437, "step": 79 }, { "epoch": 0.6837606837606838, "grad_norm": 0.1600257009267807, "learning_rate": 0.00018869228363610404, "loss": 0.6308, "step": 80 }, { "epoch": 0.6923076923076923, "grad_norm": 0.18659566342830658, "learning_rate": 0.00018837335309601213, "loss": 0.7028, "step": 81 }, { "epoch": 0.7008547008547008, "grad_norm": 0.14221739768981934, "learning_rate": 0.00018805026451824546, "loss": 1.2147, "step": 82 }, { "epoch": 0.7094017094017094, "grad_norm": 0.13898412883281708, "learning_rate": 0.00018772303310438275, "loss": 1.1227, "step": 83 }, { "epoch": 0.717948717948718, "grad_norm": 0.16075965762138367, "learning_rate": 0.00018739167425092644, "loss": 1.1104, "step": 84 }, { "epoch": 0.7264957264957265, "grad_norm": 0.1688220500946045, "learning_rate": 0.00018705620354857833, "loss": 0.6213, "step": 85 }, { "epoch": 0.7350427350427351, "grad_norm": 0.15251010656356812, "learning_rate": 0.00018671663678150607, "loss": 0.6059, "step": 86 }, { "epoch": 0.7435897435897436, "grad_norm": 0.14779676496982574, "learning_rate": 0.0001863729899266004, "loss": 0.6402, "step": 87 }, { "epoch": 0.7521367521367521, "grad_norm": 0.16805744171142578, "learning_rate": 0.0001860252791527236, "loss": 1.0025, "step": 88 }, { "epoch": 0.7606837606837606, "grad_norm": 0.13870711624622345, "learning_rate": 0.00018567352081994852, "loss": 1.1969, "step": 89 }, { "epoch": 0.7692307692307693, "grad_norm": 0.1410149782896042, "learning_rate": 0.00018531773147878895, "loss": 1.0952, "step": 90 }, { "epoch": 0.7777777777777778, "grad_norm": 0.16514992713928223, "learning_rate": 0.0001849579278694209, "loss": 0.6968, "step": 91 }, { "epoch": 0.7863247863247863, "grad_norm": 0.16152970492839813, "learning_rate": 0.00018459412692089494, "loss": 0.6271, "step": 92 }, { "epoch": 0.7948717948717948, "grad_norm": 0.1401905119419098, "learning_rate": 0.0001842263457503397, "loss": 0.5867, "step": 93 }, { "epoch": 0.8034188034188035, "grad_norm": 0.2006424516439438, "learning_rate": 0.00018385460166215638, "loss": 0.7979, "step": 94 }, { "epoch": 0.811965811965812, "grad_norm": 0.17356745898723602, "learning_rate": 0.00018347891214720477, "loss": 0.6557, "step": 95 }, { "epoch": 0.8205128205128205, "grad_norm": 0.13943414390087128, "learning_rate": 0.00018309929488198012, "loss": 1.1329, "step": 96 }, { "epoch": 0.8290598290598291, "grad_norm": 0.16562946140766144, "learning_rate": 0.00018271576772778154, "loss": 0.6571, "step": 97 }, { "epoch": 0.8376068376068376, "grad_norm": 0.1551978886127472, "learning_rate": 0.00018232834872987147, "loss": 1.1503, "step": 98 }, { "epoch": 0.8461538461538461, "grad_norm": 0.1753336638212204, "learning_rate": 0.00018193705611662696, "loss": 0.7613, "step": 99 }, { "epoch": 0.8547008547008547, "grad_norm": 0.21526718139648438, "learning_rate": 0.0001815419082986815, "loss": 0.7481, "step": 100 }, { "epoch": 0.8632478632478633, "grad_norm": 0.15033215284347534, "learning_rate": 0.00018114292386805936, "loss": 1.0287, "step": 101 }, { "epoch": 0.8717948717948718, "grad_norm": 0.15260834991931915, "learning_rate": 0.00018074012159730032, "loss": 1.1275, "step": 102 }, { "epoch": 0.8803418803418803, "grad_norm": 0.14884799718856812, "learning_rate": 0.00018033352043857675, "loss": 0.9348, "step": 103 }, { "epoch": 0.8888888888888888, "grad_norm": 0.1598692387342453, "learning_rate": 0.00017992313952280172, "loss": 1.0837, "step": 104 }, { "epoch": 0.8974358974358975, "grad_norm": 0.17874813079833984, "learning_rate": 0.00017950899815872892, "loss": 1.1863, "step": 105 }, { "epoch": 0.905982905982906, "grad_norm": 0.2233838587999344, "learning_rate": 0.00017909111583204422, "loss": 1.0691, "step": 106 }, { "epoch": 0.9145299145299145, "grad_norm": 0.2679513990879059, "learning_rate": 0.0001786695122044487, "loss": 0.8508, "step": 107 }, { "epoch": 0.9230769230769231, "grad_norm": 0.16150496900081635, "learning_rate": 0.0001782442071127338, "loss": 1.0845, "step": 108 }, { "epoch": 0.9316239316239316, "grad_norm": 0.23054973781108856, "learning_rate": 0.0001778152205678477, "loss": 1.0911, "step": 109 }, { "epoch": 0.9401709401709402, "grad_norm": 0.2072819173336029, "learning_rate": 0.00017738257275395404, "loss": 0.7793, "step": 110 }, { "epoch": 0.9487179487179487, "grad_norm": 0.18355989456176758, "learning_rate": 0.00017694628402748202, "loss": 0.6947, "step": 111 }, { "epoch": 0.9572649572649573, "grad_norm": 0.17697495222091675, "learning_rate": 0.0001765063749161688, "loss": 0.7191, "step": 112 }, { "epoch": 0.9658119658119658, "grad_norm": 0.1893756091594696, "learning_rate": 0.00017606286611809353, "loss": 0.7089, "step": 113 }, { "epoch": 0.9743589743589743, "grad_norm": 0.175858274102211, "learning_rate": 0.00017561577850070355, "loss": 0.8156, "step": 114 }, { "epoch": 0.9829059829059829, "grad_norm": 0.1497766226530075, "learning_rate": 0.00017516513309983253, "loss": 0.6113, "step": 115 }, { "epoch": 0.9914529914529915, "grad_norm": 0.2035011351108551, "learning_rate": 0.00017471095111871074, "loss": 0.7514, "step": 116 }, { "epoch": 1.0, "grad_norm": 0.19679343700408936, "learning_rate": 0.0001742532539269674, "loss": 0.6778, "step": 117 }, { "epoch": 1.0085470085470085, "grad_norm": 0.19897602498531342, "learning_rate": 0.00017379206305962526, "loss": 0.518, "step": 118 }, { "epoch": 1.017094017094017, "grad_norm": 0.17100335657596588, "learning_rate": 0.00017332740021608722, "loss": 0.5464, "step": 119 }, { "epoch": 1.0256410256410255, "grad_norm": 0.1799200475215912, "learning_rate": 0.00017285928725911562, "loss": 0.5751, "step": 120 }, { "epoch": 1.0341880341880343, "grad_norm": 0.2159220576286316, "learning_rate": 0.00017238774621380337, "loss": 0.5944, "step": 121 }, { "epoch": 1.0427350427350428, "grad_norm": 0.20010395348072052, "learning_rate": 0.00017191279926653761, "loss": 1.2068, "step": 122 }, { "epoch": 1.0512820512820513, "grad_norm": 0.20249801874160767, "learning_rate": 0.00017143446876395602, "loss": 1.0354, "step": 123 }, { "epoch": 1.0598290598290598, "grad_norm": 0.16663746535778046, "learning_rate": 0.00017095277721189528, "loss": 0.9905, "step": 124 }, { "epoch": 1.0683760683760684, "grad_norm": 0.22365769743919373, "learning_rate": 0.00017046774727433222, "loss": 0.6772, "step": 125 }, { "epoch": 1.0769230769230769, "grad_norm": 0.19689880311489105, "learning_rate": 0.00016997940177231722, "loss": 0.544, "step": 126 }, { "epoch": 1.0854700854700854, "grad_norm": 0.1540079563856125, "learning_rate": 0.00016948776368290084, "loss": 1.1138, "step": 127 }, { "epoch": 1.0940170940170941, "grad_norm": 0.21169312298297882, "learning_rate": 0.00016899285613805246, "loss": 0.4954, "step": 128 }, { "epoch": 1.1025641025641026, "grad_norm": 0.227870911359787, "learning_rate": 0.00016849470242357196, "loss": 0.5515, "step": 129 }, { "epoch": 1.1111111111111112, "grad_norm": 0.2119448482990265, "learning_rate": 0.00016799332597799413, "loss": 0.5498, "step": 130 }, { "epoch": 1.1196581196581197, "grad_norm": 0.1958005130290985, "learning_rate": 0.00016748875039148593, "loss": 0.9122, "step": 131 }, { "epoch": 1.1282051282051282, "grad_norm": 0.18614064157009125, "learning_rate": 0.0001669809994047364, "loss": 0.9878, "step": 132 }, { "epoch": 1.1367521367521367, "grad_norm": 0.22994214296340942, "learning_rate": 0.0001664700969078398, "loss": 0.6173, "step": 133 }, { "epoch": 1.1452991452991452, "grad_norm": 0.17942824959754944, "learning_rate": 0.00016595606693917142, "loss": 0.9871, "step": 134 }, { "epoch": 1.1538461538461537, "grad_norm": 0.19774889945983887, "learning_rate": 0.00016543893368425666, "loss": 0.531, "step": 135 }, { "epoch": 1.1623931623931625, "grad_norm": 0.2616710662841797, "learning_rate": 0.00016491872147463306, "loss": 0.5396, "step": 136 }, { "epoch": 1.170940170940171, "grad_norm": 0.19081617891788483, "learning_rate": 0.00016439545478670543, "loss": 1.4579, "step": 137 }, { "epoch": 1.1794871794871795, "grad_norm": 0.22909559309482574, "learning_rate": 0.00016386915824059427, "loss": 0.5076, "step": 138 }, { "epoch": 1.188034188034188, "grad_norm": 0.19601647555828094, "learning_rate": 0.00016333985659897735, "loss": 0.477, "step": 139 }, { "epoch": 1.1965811965811965, "grad_norm": 0.2791956067085266, "learning_rate": 0.00016280757476592466, "loss": 0.5587, "step": 140 }, { "epoch": 1.205128205128205, "grad_norm": 0.23856423795223236, "learning_rate": 0.0001622723377857265, "loss": 0.5495, "step": 141 }, { "epoch": 1.2136752136752136, "grad_norm": 0.2004079818725586, "learning_rate": 0.00016173417084171536, "loss": 1.0806, "step": 142 }, { "epoch": 1.2222222222222223, "grad_norm": 0.24053840339183807, "learning_rate": 0.00016119309925508078, "loss": 0.4846, "step": 143 }, { "epoch": 1.2307692307692308, "grad_norm": 0.2852567732334137, "learning_rate": 0.0001606491484836782, "loss": 0.5292, "step": 144 }, { "epoch": 1.2393162393162394, "grad_norm": 0.2828088402748108, "learning_rate": 0.00016010234412083086, "loss": 0.6061, "step": 145 }, { "epoch": 1.2478632478632479, "grad_norm": 0.2880561351776123, "learning_rate": 0.00015955271189412598, "loss": 0.6294, "step": 146 }, { "epoch": 1.2564102564102564, "grad_norm": 0.2703532576560974, "learning_rate": 0.00015900027766420393, "loss": 0.4802, "step": 147 }, { "epoch": 1.264957264957265, "grad_norm": 0.26987820863723755, "learning_rate": 0.00015844506742354164, "loss": 0.58, "step": 148 }, { "epoch": 1.2735042735042734, "grad_norm": 0.20799943804740906, "learning_rate": 0.00015788710729522953, "loss": 0.8506, "step": 149 }, { "epoch": 1.282051282051282, "grad_norm": 0.284532368183136, "learning_rate": 0.00015732642353174259, "loss": 0.9502, "step": 150 }, { "epoch": 1.2905982905982907, "grad_norm": 0.2279794067144394, "learning_rate": 0.0001567630425137049, "loss": 0.4345, "step": 151 }, { "epoch": 1.2991452991452992, "grad_norm": 0.27440500259399414, "learning_rate": 0.00015619699074864864, "loss": 0.5389, "step": 152 }, { "epoch": 1.3076923076923077, "grad_norm": 0.3192152976989746, "learning_rate": 0.00015562829486976673, "loss": 0.601, "step": 153 }, { "epoch": 1.3162393162393162, "grad_norm": 0.2619931995868683, "learning_rate": 0.00015505698163465986, "loss": 0.6321, "step": 154 }, { "epoch": 1.3247863247863247, "grad_norm": 0.3034244477748871, "learning_rate": 0.00015448307792407734, "loss": 0.5392, "step": 155 }, { "epoch": 1.3333333333333333, "grad_norm": 0.24447086453437805, "learning_rate": 0.00015390661074065256, "loss": 0.5294, "step": 156 }, { "epoch": 1.341880341880342, "grad_norm": 0.2406824827194214, "learning_rate": 0.00015332760720763232, "loss": 1.0088, "step": 157 }, { "epoch": 1.3504273504273505, "grad_norm": 0.33081722259521484, "learning_rate": 0.00015274609456760073, "loss": 0.6686, "step": 158 }, { "epoch": 1.358974358974359, "grad_norm": 0.2927612066268921, "learning_rate": 0.00015216210018119733, "loss": 0.6711, "step": 159 }, { "epoch": 1.3675213675213675, "grad_norm": 0.27662229537963867, "learning_rate": 0.00015157565152583002, "loss": 0.4599, "step": 160 }, { "epoch": 1.376068376068376, "grad_norm": 0.27406662702560425, "learning_rate": 0.0001509867761943818, "loss": 0.7595, "step": 161 }, { "epoch": 1.3846153846153846, "grad_norm": 0.2830904424190521, "learning_rate": 0.00015039550189391298, "loss": 0.5543, "step": 162 }, { "epoch": 1.393162393162393, "grad_norm": 0.2570502460002899, "learning_rate": 0.0001498018564443571, "loss": 0.796, "step": 163 }, { "epoch": 1.4017094017094016, "grad_norm": 0.3457013964653015, "learning_rate": 0.0001492058677772123, "loss": 0.6932, "step": 164 }, { "epoch": 1.4102564102564101, "grad_norm": 0.28781554102897644, "learning_rate": 0.000148607563934227, "loss": 0.5926, "step": 165 }, { "epoch": 1.4188034188034189, "grad_norm": 0.22006003558635712, "learning_rate": 0.00014800697306608044, "loss": 0.4337, "step": 166 }, { "epoch": 1.4273504273504274, "grad_norm": 0.26621371507644653, "learning_rate": 0.00014740412343105828, "loss": 0.7999, "step": 167 }, { "epoch": 1.435897435897436, "grad_norm": 0.25635233521461487, "learning_rate": 0.00014679904339372302, "loss": 0.4834, "step": 168 }, { "epoch": 1.4444444444444444, "grad_norm": 0.28802382946014404, "learning_rate": 0.00014619176142357935, "loss": 0.4865, "step": 169 }, { "epoch": 1.452991452991453, "grad_norm": 0.28858450055122375, "learning_rate": 0.0001455823060937347, "loss": 0.5757, "step": 170 }, { "epoch": 1.4615384615384617, "grad_norm": 0.3039717674255371, "learning_rate": 0.00014497070607955476, "loss": 0.5206, "step": 171 }, { "epoch": 1.4700854700854702, "grad_norm": 0.29578229784965515, "learning_rate": 0.00014435699015731448, "loss": 0.5103, "step": 172 }, { "epoch": 1.4786324786324787, "grad_norm": 0.2743285596370697, "learning_rate": 0.00014374118720284388, "loss": 0.5932, "step": 173 }, { "epoch": 1.4871794871794872, "grad_norm": 0.23295287787914276, "learning_rate": 0.00014312332619016965, "loss": 0.734, "step": 174 }, { "epoch": 1.4957264957264957, "grad_norm": 0.3224605917930603, "learning_rate": 0.0001425034361901516, "loss": 0.5668, "step": 175 }, { "epoch": 1.5042735042735043, "grad_norm": 0.28584739565849304, "learning_rate": 0.00014188154636911524, "loss": 1.1414, "step": 176 }, { "epoch": 1.5128205128205128, "grad_norm": 0.3341439664363861, "learning_rate": 0.0001412576859874791, "loss": 0.527, "step": 177 }, { "epoch": 1.5213675213675213, "grad_norm": 0.2781898081302643, "learning_rate": 0.00014063188439837832, "loss": 0.4599, "step": 178 }, { "epoch": 1.5299145299145298, "grad_norm": 0.2845589518547058, "learning_rate": 0.0001400041710462833, "loss": 0.4662, "step": 179 }, { "epoch": 1.5384615384615383, "grad_norm": 0.2917931079864502, "learning_rate": 0.0001393745754656146, "loss": 0.5176, "step": 180 }, { "epoch": 1.547008547008547, "grad_norm": 0.27486878633499146, "learning_rate": 0.00013874312727935292, "loss": 0.4756, "step": 181 }, { "epoch": 1.5555555555555556, "grad_norm": 0.29670944809913635, "learning_rate": 0.00013810985619764572, "loss": 0.9803, "step": 182 }, { "epoch": 1.564102564102564, "grad_norm": 0.282777339220047, "learning_rate": 0.00013747479201640914, "loss": 0.494, "step": 183 }, { "epoch": 1.5726495726495726, "grad_norm": 0.32058680057525635, "learning_rate": 0.00013683796461592604, "loss": 0.6009, "step": 184 }, { "epoch": 1.5811965811965814, "grad_norm": 0.2858709394931793, "learning_rate": 0.00013619940395944027, "loss": 0.5382, "step": 185 }, { "epoch": 1.5897435897435899, "grad_norm": 0.2902598977088928, "learning_rate": 0.00013555914009174663, "loss": 0.5271, "step": 186 }, { "epoch": 1.5982905982905984, "grad_norm": 0.30693796277046204, "learning_rate": 0.00013491720313777756, "loss": 0.8996, "step": 187 }, { "epoch": 1.606837606837607, "grad_norm": 0.30923569202423096, "learning_rate": 0.00013427362330118543, "loss": 0.5298, "step": 188 }, { "epoch": 1.6153846153846154, "grad_norm": 0.30768024921417236, "learning_rate": 0.0001336284308629216, "loss": 0.6628, "step": 189 }, { "epoch": 1.623931623931624, "grad_norm": 0.2818881571292877, "learning_rate": 0.00013298165617981172, "loss": 0.721, "step": 190 }, { "epoch": 1.6324786324786325, "grad_norm": 0.32291677594184875, "learning_rate": 0.00013233332968312715, "loss": 0.7519, "step": 191 }, { "epoch": 1.641025641025641, "grad_norm": 0.3007102310657501, "learning_rate": 0.0001316834818771535, "loss": 0.5748, "step": 192 }, { "epoch": 1.6495726495726495, "grad_norm": 0.3087317645549774, "learning_rate": 0.00013103214333775521, "loss": 0.5906, "step": 193 }, { "epoch": 1.658119658119658, "grad_norm": 0.3102208375930786, "learning_rate": 0.00013037934471093682, "loss": 0.5124, "step": 194 }, { "epoch": 1.6666666666666665, "grad_norm": 0.3031424283981323, "learning_rate": 0.00012972511671140125, "loss": 0.4928, "step": 195 }, { "epoch": 1.6752136752136753, "grad_norm": 0.28559157252311707, "learning_rate": 0.00012906949012110456, "loss": 0.7699, "step": 196 }, { "epoch": 1.6837606837606838, "grad_norm": 0.3253765106201172, "learning_rate": 0.00012841249578780757, "loss": 0.6912, "step": 197 }, { "epoch": 1.6923076923076923, "grad_norm": 0.25747209787368774, "learning_rate": 0.00012775416462362457, "loss": 0.5606, "step": 198 }, { "epoch": 1.7008547008547008, "grad_norm": 0.26116716861724854, "learning_rate": 0.00012709452760356884, "loss": 1.1407, "step": 199 }, { "epoch": 1.7094017094017095, "grad_norm": 0.2786200940608978, "learning_rate": 0.00012643361576409516, "loss": 0.5478, "step": 200 }, { "epoch": 1.717948717948718, "grad_norm": 0.3031173646450043, "learning_rate": 0.00012577146020163968, "loss": 0.6042, "step": 201 }, { "epoch": 1.7264957264957266, "grad_norm": 0.3398924469947815, "learning_rate": 0.00012510809207115666, "loss": 0.5367, "step": 202 }, { "epoch": 1.735042735042735, "grad_norm": 0.2823917865753174, "learning_rate": 0.00012444354258465268, "loss": 0.4997, "step": 203 }, { "epoch": 1.7435897435897436, "grad_norm": 0.3168320953845978, "learning_rate": 0.00012377784300971807, "loss": 0.8277, "step": 204 }, { "epoch": 1.7521367521367521, "grad_norm": 0.29730290174484253, "learning_rate": 0.0001231110246680558, "loss": 1.0703, "step": 205 }, { "epoch": 1.7606837606837606, "grad_norm": 0.3612962067127228, "learning_rate": 0.00012244311893400763, "loss": 0.622, "step": 206 }, { "epoch": 1.7692307692307692, "grad_norm": 0.35250765085220337, "learning_rate": 0.00012177415723307808, "loss": 0.5804, "step": 207 }, { "epoch": 1.7777777777777777, "grad_norm": 0.281643807888031, "learning_rate": 0.00012110417104045575, "loss": 0.4677, "step": 208 }, { "epoch": 1.7863247863247862, "grad_norm": 0.2842894196510315, "learning_rate": 0.00012043319187953241, "loss": 0.5971, "step": 209 }, { "epoch": 1.7948717948717947, "grad_norm": 0.30655983090400696, "learning_rate": 0.00011976125132041974, "loss": 0.5816, "step": 210 }, { "epoch": 1.8034188034188035, "grad_norm": 0.343220055103302, "learning_rate": 0.00011908838097846404, "loss": 0.6953, "step": 211 }, { "epoch": 1.811965811965812, "grad_norm": 0.3058364987373352, "learning_rate": 0.00011841461251275867, "loss": 0.7328, "step": 212 }, { "epoch": 1.8205128205128205, "grad_norm": 0.3523794710636139, "learning_rate": 0.00011773997762465429, "loss": 0.5407, "step": 213 }, { "epoch": 1.8290598290598292, "grad_norm": 0.28265875577926636, "learning_rate": 0.0001170645080562676, "loss": 0.6113, "step": 214 }, { "epoch": 1.8376068376068377, "grad_norm": 0.2768702805042267, "learning_rate": 0.00011638823558898762, "loss": 0.4853, "step": 215 }, { "epoch": 1.8461538461538463, "grad_norm": 0.30153489112854004, "learning_rate": 0.00011571119204198037, "loss": 0.5403, "step": 216 }, { "epoch": 1.8547008547008548, "grad_norm": 0.27942952513694763, "learning_rate": 0.00011503340927069189, "loss": 0.6213, "step": 217 }, { "epoch": 1.8632478632478633, "grad_norm": 0.2634161114692688, "learning_rate": 0.00011435491916534919, "loss": 0.5089, "step": 218 }, { "epoch": 1.8717948717948718, "grad_norm": 0.2846587598323822, "learning_rate": 0.00011367575364946006, "loss": 0.5329, "step": 219 }, { "epoch": 1.8803418803418803, "grad_norm": 0.3283989727497101, "learning_rate": 0.00011299594467831078, "loss": 0.516, "step": 220 }, { "epoch": 1.8888888888888888, "grad_norm": 0.3399990200996399, "learning_rate": 0.00011231552423746283, "loss": 0.5947, "step": 221 }, { "epoch": 1.8974358974358974, "grad_norm": 0.2741105258464813, "learning_rate": 0.00011163452434124773, "loss": 0.4982, "step": 222 }, { "epoch": 1.9059829059829059, "grad_norm": 0.3004041314125061, "learning_rate": 0.00011095297703126093, "loss": 0.4908, "step": 223 }, { "epoch": 1.9145299145299144, "grad_norm": 0.3036716878414154, "learning_rate": 0.00011027091437485404, "loss": 0.5979, "step": 224 }, { "epoch": 1.9230769230769231, "grad_norm": 0.30735576152801514, "learning_rate": 0.00010958836846362621, "loss": 0.6864, "step": 225 }, { "epoch": 1.9316239316239316, "grad_norm": 0.2979448437690735, "learning_rate": 0.00010890537141191417, "loss": 0.4901, "step": 226 }, { "epoch": 1.9401709401709402, "grad_norm": 0.557965874671936, "learning_rate": 0.00010822195535528106, "loss": 0.8011, "step": 227 }, { "epoch": 1.9487179487179487, "grad_norm": 0.28031420707702637, "learning_rate": 0.00010753815244900458, "loss": 0.4857, "step": 228 }, { "epoch": 1.9572649572649574, "grad_norm": 0.33071720600128174, "learning_rate": 0.00010685399486656406, "loss": 0.5614, "step": 229 }, { "epoch": 1.965811965811966, "grad_norm": 0.3054099678993225, "learning_rate": 0.00010616951479812658, "loss": 0.5198, "step": 230 }, { "epoch": 1.9743589743589745, "grad_norm": 0.33297890424728394, "learning_rate": 0.00010548474444903247, "loss": 0.4813, "step": 231 }, { "epoch": 1.982905982905983, "grad_norm": 0.29195529222488403, "learning_rate": 0.00010479971603828, "loss": 0.5025, "step": 232 }, { "epoch": 1.9914529914529915, "grad_norm": 0.27123546600341797, "learning_rate": 0.00010411446179700943, "loss": 0.5084, "step": 233 }, { "epoch": 2.0, "grad_norm": 0.44304001331329346, "learning_rate": 0.00010342901396698659, "loss": 0.4979, "step": 234 }, { "epoch": 2.0085470085470085, "grad_norm": 0.2400938868522644, "learning_rate": 0.00010274340479908568, "loss": 0.3224, "step": 235 }, { "epoch": 2.017094017094017, "grad_norm": 0.27192720770835876, "learning_rate": 0.00010205766655177215, "loss": 0.3318, "step": 236 }, { "epoch": 2.0256410256410255, "grad_norm": 0.26895493268966675, "learning_rate": 0.00010137183148958463, "loss": 0.4635, "step": 237 }, { "epoch": 2.034188034188034, "grad_norm": 0.3057348132133484, "learning_rate": 0.00010068593188161697, "loss": 0.3232, "step": 238 }, { "epoch": 2.0427350427350426, "grad_norm": 0.3629106283187866, "learning_rate": 0.0001, "loss": 0.4218, "step": 239 }, { "epoch": 2.051282051282051, "grad_norm": 0.32993799448013306, "learning_rate": 9.931406811838308e-05, "loss": 0.3268, "step": 240 }, { "epoch": 2.0598290598290596, "grad_norm": 0.3513668477535248, "learning_rate": 9.862816851041541e-05, "loss": 0.2956, "step": 241 }, { "epoch": 2.0683760683760686, "grad_norm": 0.2837519943714142, "learning_rate": 9.79423334482279e-05, "loss": 0.4016, "step": 242 }, { "epoch": 2.076923076923077, "grad_norm": 0.3597986400127411, "learning_rate": 9.725659520091433e-05, "loss": 0.3562, "step": 243 }, { "epoch": 2.0854700854700856, "grad_norm": 0.35644450783729553, "learning_rate": 9.657098603301346e-05, "loss": 0.389, "step": 244 }, { "epoch": 2.094017094017094, "grad_norm": 0.34318238496780396, "learning_rate": 9.588553820299056e-05, "loss": 0.3454, "step": 245 }, { "epoch": 2.1025641025641026, "grad_norm": 0.4194351136684418, "learning_rate": 9.520028396172003e-05, "loss": 0.5648, "step": 246 }, { "epoch": 2.111111111111111, "grad_norm": 0.3981444835662842, "learning_rate": 9.451525555096753e-05, "loss": 0.36, "step": 247 }, { "epoch": 2.1196581196581197, "grad_norm": 0.3543313145637512, "learning_rate": 9.383048520187344e-05, "loss": 0.3119, "step": 248 }, { "epoch": 2.128205128205128, "grad_norm": 0.3832297623157501, "learning_rate": 9.314600513343595e-05, "loss": 0.3295, "step": 249 }, { "epoch": 2.1367521367521367, "grad_norm": 0.36837905645370483, "learning_rate": 9.246184755099545e-05, "loss": 0.7314, "step": 250 }, { "epoch": 2.1452991452991452, "grad_norm": 0.3872221112251282, "learning_rate": 9.177804464471898e-05, "loss": 0.7813, "step": 251 }, { "epoch": 2.1538461538461537, "grad_norm": 0.3736673891544342, "learning_rate": 9.109462858808586e-05, "loss": 0.8241, "step": 252 }, { "epoch": 2.1623931623931623, "grad_norm": 0.34361720085144043, "learning_rate": 9.041163153637381e-05, "loss": 0.3305, "step": 253 }, { "epoch": 2.1709401709401708, "grad_norm": 0.41760456562042236, "learning_rate": 8.972908562514598e-05, "loss": 0.4005, "step": 254 }, { "epoch": 2.1794871794871793, "grad_norm": 0.43377965688705444, "learning_rate": 8.904702296873912e-05, "loss": 0.4007, "step": 255 }, { "epoch": 2.1880341880341883, "grad_norm": 0.37337392568588257, "learning_rate": 8.836547565875227e-05, "loss": 0.3498, "step": 256 }, { "epoch": 2.1965811965811968, "grad_norm": 0.315764456987381, "learning_rate": 8.76844757625372e-05, "loss": 0.9157, "step": 257 }, { "epoch": 2.2051282051282053, "grad_norm": 0.3888338506221771, "learning_rate": 8.70040553216892e-05, "loss": 0.3367, "step": 258 }, { "epoch": 2.213675213675214, "grad_norm": 0.40300390124320984, "learning_rate": 8.632424635053997e-05, "loss": 0.4922, "step": 259 }, { "epoch": 2.2222222222222223, "grad_norm": 0.33147263526916504, "learning_rate": 8.564508083465079e-05, "loss": 0.3226, "step": 260 }, { "epoch": 2.230769230769231, "grad_norm": 0.3483441174030304, "learning_rate": 8.496659072930813e-05, "loss": 0.3401, "step": 261 }, { "epoch": 2.2393162393162394, "grad_norm": 0.322630375623703, "learning_rate": 8.428880795801965e-05, "loss": 0.302, "step": 262 }, { "epoch": 2.247863247863248, "grad_norm": 0.43187469244003296, "learning_rate": 8.36117644110124e-05, "loss": 0.5119, "step": 263 }, { "epoch": 2.2564102564102564, "grad_norm": 0.39188244938850403, "learning_rate": 8.293549194373243e-05, "loss": 0.3031, "step": 264 }, { "epoch": 2.264957264957265, "grad_norm": 0.3352276086807251, "learning_rate": 8.226002237534572e-05, "loss": 0.3325, "step": 265 }, { "epoch": 2.2735042735042734, "grad_norm": 0.5547850728034973, "learning_rate": 8.158538748724139e-05, "loss": 0.6336, "step": 266 }, { "epoch": 2.282051282051282, "grad_norm": 0.46319064497947693, "learning_rate": 8.091161902153595e-05, "loss": 0.3795, "step": 267 }, { "epoch": 2.2905982905982905, "grad_norm": 0.3510757386684418, "learning_rate": 8.023874867958027e-05, "loss": 0.6465, "step": 268 }, { "epoch": 2.299145299145299, "grad_norm": 0.43491068482398987, "learning_rate": 7.95668081204676e-05, "loss": 0.4599, "step": 269 }, { "epoch": 2.3076923076923075, "grad_norm": 0.4005129039287567, "learning_rate": 7.889582895954427e-05, "loss": 0.3559, "step": 270 }, { "epoch": 2.316239316239316, "grad_norm": 0.4101939797401428, "learning_rate": 7.822584276692191e-05, "loss": 0.3069, "step": 271 }, { "epoch": 2.324786324786325, "grad_norm": 0.427969753742218, "learning_rate": 7.755688106599241e-05, "loss": 0.385, "step": 272 }, { "epoch": 2.3333333333333335, "grad_norm": 0.43213459849357605, "learning_rate": 7.688897533194424e-05, "loss": 0.4084, "step": 273 }, { "epoch": 2.341880341880342, "grad_norm": 0.4647037088871002, "learning_rate": 7.622215699028196e-05, "loss": 0.3018, "step": 274 }, { "epoch": 2.3504273504273505, "grad_norm": 0.3657461106777191, "learning_rate": 7.555645741534736e-05, "loss": 0.3205, "step": 275 }, { "epoch": 2.358974358974359, "grad_norm": 0.5432414412498474, "learning_rate": 7.489190792884338e-05, "loss": 0.769, "step": 276 }, { "epoch": 2.3675213675213675, "grad_norm": 0.4926995038986206, "learning_rate": 7.422853979836034e-05, "loss": 0.5702, "step": 277 }, { "epoch": 2.376068376068376, "grad_norm": 0.3982427418231964, "learning_rate": 7.356638423590485e-05, "loss": 0.3251, "step": 278 }, { "epoch": 2.3846153846153846, "grad_norm": 0.40389546751976013, "learning_rate": 7.290547239643117e-05, "loss": 0.3662, "step": 279 }, { "epoch": 2.393162393162393, "grad_norm": 0.35524460673332214, "learning_rate": 7.224583537637544e-05, "loss": 0.3679, "step": 280 }, { "epoch": 2.4017094017094016, "grad_norm": 0.5441136956214905, "learning_rate": 7.158750421219244e-05, "loss": 0.8657, "step": 281 }, { "epoch": 2.41025641025641, "grad_norm": 0.41349369287490845, "learning_rate": 7.093050987889547e-05, "loss": 0.3278, "step": 282 }, { "epoch": 2.4188034188034186, "grad_norm": 0.3926091492176056, "learning_rate": 7.027488328859876e-05, "loss": 0.3231, "step": 283 }, { "epoch": 2.427350427350427, "grad_norm": 0.34863772988319397, "learning_rate": 6.96206552890632e-05, "loss": 0.3693, "step": 284 }, { "epoch": 2.435897435897436, "grad_norm": 0.40613868832588196, "learning_rate": 6.896785666224481e-05, "loss": 0.3407, "step": 285 }, { "epoch": 2.4444444444444446, "grad_norm": 0.473646879196167, "learning_rate": 6.831651812284652e-05, "loss": 0.329, "step": 286 }, { "epoch": 2.452991452991453, "grad_norm": 0.39881348609924316, "learning_rate": 6.766667031687286e-05, "loss": 0.3874, "step": 287 }, { "epoch": 2.4615384615384617, "grad_norm": 0.42089781165122986, "learning_rate": 6.701834382018832e-05, "loss": 0.3636, "step": 288 }, { "epoch": 2.47008547008547, "grad_norm": 0.38163042068481445, "learning_rate": 6.637156913707839e-05, "loss": 0.3085, "step": 289 }, { "epoch": 2.4786324786324787, "grad_norm": 0.40398237109184265, "learning_rate": 6.572637669881458e-05, "loss": 0.3503, "step": 290 }, { "epoch": 2.4871794871794872, "grad_norm": 0.4506056010723114, "learning_rate": 6.508279686222243e-05, "loss": 0.7149, "step": 291 }, { "epoch": 2.4957264957264957, "grad_norm": 0.38534703850746155, "learning_rate": 6.444085990825338e-05, "loss": 0.3171, "step": 292 }, { "epoch": 2.5042735042735043, "grad_norm": 0.38602226972579956, "learning_rate": 6.380059604055974e-05, "loss": 0.3231, "step": 293 }, { "epoch": 2.5128205128205128, "grad_norm": 0.5425469279289246, "learning_rate": 6.316203538407397e-05, "loss": 0.51, "step": 294 }, { "epoch": 2.5213675213675213, "grad_norm": 0.4079858660697937, "learning_rate": 6.252520798359092e-05, "loss": 0.344, "step": 295 }, { "epoch": 2.52991452991453, "grad_norm": 0.40478408336639404, "learning_rate": 6.18901438023543e-05, "loss": 0.3031, "step": 296 }, { "epoch": 2.5384615384615383, "grad_norm": 0.39690130949020386, "learning_rate": 6.125687272064713e-05, "loss": 0.3678, "step": 297 }, { "epoch": 2.547008547008547, "grad_norm": 0.36282968521118164, "learning_rate": 6.0625424534385425e-05, "loss": 0.3354, "step": 298 }, { "epoch": 2.5555555555555554, "grad_norm": 0.5053970217704773, "learning_rate": 5.9995828953716695e-05, "loss": 0.4639, "step": 299 }, { "epoch": 2.564102564102564, "grad_norm": 0.42503127455711365, "learning_rate": 5.936811560162169e-05, "loss": 0.3738, "step": 300 }, { "epoch": 2.5726495726495724, "grad_norm": 0.38721203804016113, "learning_rate": 5.87423140125209e-05, "loss": 0.3075, "step": 301 }, { "epoch": 2.5811965811965814, "grad_norm": 0.3901880085468292, "learning_rate": 5.811845363088477e-05, "loss": 0.2714, "step": 302 }, { "epoch": 2.58974358974359, "grad_norm": 0.4684121012687683, "learning_rate": 5.749656380984844e-05, "loss": 0.3653, "step": 303 }, { "epoch": 2.5982905982905984, "grad_norm": 0.4713698625564575, "learning_rate": 5.687667380983037e-05, "loss": 0.3543, "step": 304 }, { "epoch": 2.606837606837607, "grad_norm": 0.36758852005004883, "learning_rate": 5.625881279715615e-05, "loss": 0.2852, "step": 305 }, { "epoch": 2.6153846153846154, "grad_norm": 0.41538846492767334, "learning_rate": 5.5643009842685554e-05, "loss": 0.758, "step": 306 }, { "epoch": 2.623931623931624, "grad_norm": 0.4570621848106384, "learning_rate": 5.502929392044528e-05, "loss": 0.3473, "step": 307 }, { "epoch": 2.6324786324786325, "grad_norm": 0.40662381052970886, "learning_rate": 5.4417693906265365e-05, "loss": 0.2796, "step": 308 }, { "epoch": 2.641025641025641, "grad_norm": 0.43923693895339966, "learning_rate": 5.380823857642069e-05, "loss": 0.3725, "step": 309 }, { "epoch": 2.6495726495726495, "grad_norm": 0.5465748310089111, "learning_rate": 5.3200956606277006e-05, "loss": 0.5495, "step": 310 }, { "epoch": 2.658119658119658, "grad_norm": 0.40495002269744873, "learning_rate": 5.259587656894174e-05, "loss": 0.3263, "step": 311 }, { "epoch": 2.6666666666666665, "grad_norm": 0.48158714175224304, "learning_rate": 5.199302693391959e-05, "loss": 0.3745, "step": 312 }, { "epoch": 2.6752136752136755, "grad_norm": 0.7670568227767944, "learning_rate": 5.139243606577302e-05, "loss": 0.5476, "step": 313 }, { "epoch": 2.683760683760684, "grad_norm": 0.4823751747608185, "learning_rate": 5.0794132222787707e-05, "loss": 0.3368, "step": 314 }, { "epoch": 2.6923076923076925, "grad_norm": 0.411697655916214, "learning_rate": 5.019814355564292e-05, "loss": 0.355, "step": 315 }, { "epoch": 2.700854700854701, "grad_norm": 0.4196050763130188, "learning_rate": 4.960449810608705e-05, "loss": 0.4464, "step": 316 }, { "epoch": 2.7094017094017095, "grad_norm": 0.4139435887336731, "learning_rate": 4.90132238056182e-05, "loss": 0.3277, "step": 317 }, { "epoch": 2.717948717948718, "grad_norm": 0.4168216586112976, "learning_rate": 4.8424348474170014e-05, "loss": 0.9034, "step": 318 }, { "epoch": 2.7264957264957266, "grad_norm": 0.44960731267929077, "learning_rate": 4.783789981880267e-05, "loss": 0.3108, "step": 319 }, { "epoch": 2.735042735042735, "grad_norm": 0.3782220780849457, "learning_rate": 4.725390543239929e-05, "loss": 0.245, "step": 320 }, { "epoch": 2.7435897435897436, "grad_norm": 0.43696412444114685, "learning_rate": 4.667239279236768e-05, "loss": 0.4948, "step": 321 }, { "epoch": 2.752136752136752, "grad_norm": 0.45195072889328003, "learning_rate": 4.609338925934743e-05, "loss": 0.362, "step": 322 }, { "epoch": 2.7606837606837606, "grad_norm": 0.46763068437576294, "learning_rate": 4.551692207592265e-05, "loss": 0.6228, "step": 323 }, { "epoch": 2.769230769230769, "grad_norm": 0.41138404607772827, "learning_rate": 4.494301836534016e-05, "loss": 0.2995, "step": 324 }, { "epoch": 2.7777777777777777, "grad_norm": 0.4764159619808197, "learning_rate": 4.4371705130233275e-05, "loss": 0.3723, "step": 325 }, { "epoch": 2.786324786324786, "grad_norm": 0.4093851149082184, "learning_rate": 4.380300925135138e-05, "loss": 0.283, "step": 326 }, { "epoch": 2.7948717948717947, "grad_norm": 0.420600950717926, "learning_rate": 4.3236957486295115e-05, "loss": 0.8561, "step": 327 }, { "epoch": 2.8034188034188032, "grad_norm": 0.5407417416572571, "learning_rate": 4.267357646825746e-05, "loss": 0.7904, "step": 328 }, { "epoch": 2.8119658119658117, "grad_norm": 0.4417356550693512, "learning_rate": 4.211289270477047e-05, "loss": 0.305, "step": 329 }, { "epoch": 2.8205128205128203, "grad_norm": 0.4245963394641876, "learning_rate": 4.1554932576458415e-05, "loss": 0.3333, "step": 330 }, { "epoch": 2.8290598290598292, "grad_norm": 0.5362535119056702, "learning_rate": 4.0999722335796075e-05, "loss": 0.6806, "step": 331 }, { "epoch": 2.8376068376068377, "grad_norm": 0.451956182718277, "learning_rate": 4.044728810587406e-05, "loss": 0.3372, "step": 332 }, { "epoch": 2.8461538461538463, "grad_norm": 0.45400282740592957, "learning_rate": 3.989765587916914e-05, "loss": 0.2777, "step": 333 }, { "epoch": 2.8547008547008548, "grad_norm": 0.41128432750701904, "learning_rate": 3.935085151632185e-05, "loss": 0.3847, "step": 334 }, { "epoch": 2.8632478632478633, "grad_norm": 0.389646053314209, "learning_rate": 3.8806900744919205e-05, "loss": 0.2392, "step": 335 }, { "epoch": 2.871794871794872, "grad_norm": 0.46181708574295044, "learning_rate": 3.826582915828468e-05, "loss": 0.4558, "step": 336 }, { "epoch": 2.8803418803418803, "grad_norm": 0.4526846706867218, "learning_rate": 3.7727662214273495e-05, "loss": 0.3063, "step": 337 }, { "epoch": 2.888888888888889, "grad_norm": 0.37001314759254456, "learning_rate": 3.719242523407539e-05, "loss": 0.2502, "step": 338 }, { "epoch": 2.8974358974358974, "grad_norm": 0.5281813740730286, "learning_rate": 3.666014340102268e-05, "loss": 0.6893, "step": 339 }, { "epoch": 2.905982905982906, "grad_norm": 0.4325254261493683, "learning_rate": 3.613084175940578e-05, "loss": 0.6278, "step": 340 }, { "epoch": 2.9145299145299144, "grad_norm": 0.40325087308883667, "learning_rate": 3.5604545213294616e-05, "loss": 0.685, "step": 341 }, { "epoch": 2.9230769230769234, "grad_norm": 0.40959540009498596, "learning_rate": 3.508127852536698e-05, "loss": 0.5414, "step": 342 }, { "epoch": 2.931623931623932, "grad_norm": 0.5315414071083069, "learning_rate": 3.456106631574336e-05, "loss": 0.4326, "step": 343 }, { "epoch": 2.9401709401709404, "grad_norm": 0.3776796758174896, "learning_rate": 3.4043933060828605e-05, "loss": 0.3252, "step": 344 }, { "epoch": 2.948717948717949, "grad_norm": 0.40619394183158875, "learning_rate": 3.352990309216022e-05, "loss": 0.6768, "step": 345 }, { "epoch": 2.9572649572649574, "grad_norm": 0.5160278081893921, "learning_rate": 3.3019000595263574e-05, "loss": 0.3474, "step": 346 }, { "epoch": 2.965811965811966, "grad_norm": 0.4317242205142975, "learning_rate": 3.251124960851408e-05, "loss": 0.2946, "step": 347 }, { "epoch": 2.9743589743589745, "grad_norm": 0.4935630261898041, "learning_rate": 3.200667402200586e-05, "loss": 0.3676, "step": 348 }, { "epoch": 2.982905982905983, "grad_norm": 0.4772558808326721, "learning_rate": 3.1505297576428075e-05, "loss": 0.3227, "step": 349 }, { "epoch": 2.9914529914529915, "grad_norm": 0.40967056155204773, "learning_rate": 3.100714386194757e-05, "loss": 0.3407, "step": 350 }, { "epoch": 3.0, "grad_norm": 0.4318535029888153, "learning_rate": 3.0512236317099175e-05, "loss": 0.3166, "step": 351 } ], "logging_steps": 1, "max_steps": 468, "num_input_tokens_seen": 0, "num_train_epochs": 4, "save_steps": 117, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 4.6065569888835994e+17, "train_batch_size": 1, "trial_name": null, "trial_params": null }