| { | |
| "best_metric": 0.5487671335091459, | |
| "best_model_checkpoint": "/mnt/data/bert24/fineweb_edu/checkpoints/5e-5_one_label/checkpoint-13149", | |
| "epoch": 3.0, | |
| "eval_steps": 1000, | |
| "global_step": 13149, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.022815423226100844, | |
| "grad_norm": 3.930772542953491, | |
| "learning_rate": 1.1407711613050422e-06, | |
| "loss": 0.8134, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.04563084645220169, | |
| "grad_norm": 3.383699655532837, | |
| "learning_rate": 2.2815423226100845e-06, | |
| "loss": 0.4827, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.06844626967830253, | |
| "grad_norm": 13.854891777038574, | |
| "learning_rate": 3.4223134839151265e-06, | |
| "loss": 0.386, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.09126169290440338, | |
| "grad_norm": 4.105241775512695, | |
| "learning_rate": 4.563084645220169e-06, | |
| "loss": 0.3565, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.11407711613050422, | |
| "grad_norm": 3.2210636138916016, | |
| "learning_rate": 5.703855806525212e-06, | |
| "loss": 0.3272, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.13689253935660506, | |
| "grad_norm": 4.857998847961426, | |
| "learning_rate": 6.844626967830253e-06, | |
| "loss": 0.3297, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.15970796258270592, | |
| "grad_norm": 2.4987571239471436, | |
| "learning_rate": 7.985398129135297e-06, | |
| "loss": 0.3093, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.18252338580880675, | |
| "grad_norm": 6.888661861419678, | |
| "learning_rate": 9.126169290440338e-06, | |
| "loss": 0.3108, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.2053388090349076, | |
| "grad_norm": 4.0510358810424805, | |
| "learning_rate": 1.0266940451745379e-05, | |
| "loss": 0.318, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.22815423226100845, | |
| "grad_norm": 7.22244119644165, | |
| "learning_rate": 1.1407711613050424e-05, | |
| "loss": 0.293, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.2509696554871093, | |
| "grad_norm": 7.43681526184082, | |
| "learning_rate": 1.2548482774355466e-05, | |
| "loss": 0.2853, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.2737850787132101, | |
| "grad_norm": 3.81840443611145, | |
| "learning_rate": 1.3689253935660506e-05, | |
| "loss": 0.2784, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.296600501939311, | |
| "grad_norm": 8.012810707092285, | |
| "learning_rate": 1.4830025096965549e-05, | |
| "loss": 0.2698, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.31941592516541184, | |
| "grad_norm": 4.390589714050293, | |
| "learning_rate": 1.5970796258270593e-05, | |
| "loss": 0.2653, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.34223134839151265, | |
| "grad_norm": 9.778414726257324, | |
| "learning_rate": 1.7111567419575633e-05, | |
| "loss": 0.2666, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.3650467716176135, | |
| "grad_norm": 3.7897677421569824, | |
| "learning_rate": 1.8252338580880676e-05, | |
| "loss": 0.259, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.38786219484371437, | |
| "grad_norm": 3.3615636825561523, | |
| "learning_rate": 1.939310974218572e-05, | |
| "loss": 0.2522, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.4106776180698152, | |
| "grad_norm": 5.232314109802246, | |
| "learning_rate": 2.0533880903490758e-05, | |
| "loss": 0.2547, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.43349304129591604, | |
| "grad_norm": 3.6110997200012207, | |
| "learning_rate": 2.1674652064795804e-05, | |
| "loss": 0.2594, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.4563084645220169, | |
| "grad_norm": 2.4445459842681885, | |
| "learning_rate": 2.2815423226100847e-05, | |
| "loss": 0.2537, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.4791238877481177, | |
| "grad_norm": 3.6951136589050293, | |
| "learning_rate": 2.3956194387405887e-05, | |
| "loss": 0.2518, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.5019393109742186, | |
| "grad_norm": 3.9381537437438965, | |
| "learning_rate": 2.5096965548710933e-05, | |
| "loss": 0.2516, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.5247547342003194, | |
| "grad_norm": 1.5301635265350342, | |
| "learning_rate": 2.623773671001597e-05, | |
| "loss": 0.2435, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.5475701574264202, | |
| "grad_norm": 4.029539585113525, | |
| "learning_rate": 2.7378507871321012e-05, | |
| "loss": 0.2467, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.5703855806525211, | |
| "grad_norm": 5.817471027374268, | |
| "learning_rate": 2.8519279032626055e-05, | |
| "loss": 0.2452, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.593201003878622, | |
| "grad_norm": 3.2799909114837646, | |
| "learning_rate": 2.9660050193931098e-05, | |
| "loss": 0.2425, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.6160164271047228, | |
| "grad_norm": 1.8384263515472412, | |
| "learning_rate": 3.080082135523614e-05, | |
| "loss": 0.2371, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.6388318503308237, | |
| "grad_norm": 2.4290475845336914, | |
| "learning_rate": 3.194159251654119e-05, | |
| "loss": 0.2484, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.6616472735569244, | |
| "grad_norm": 1.5778276920318604, | |
| "learning_rate": 3.3082363677846226e-05, | |
| "loss": 0.2328, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.6844626967830253, | |
| "grad_norm": 2.872375249862671, | |
| "learning_rate": 3.4223134839151266e-05, | |
| "loss": 0.2546, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.7072781200091262, | |
| "grad_norm": 1.8962109088897705, | |
| "learning_rate": 3.536390600045631e-05, | |
| "loss": 0.236, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.730093543235227, | |
| "grad_norm": 2.156942129135132, | |
| "learning_rate": 3.650467716176135e-05, | |
| "loss": 0.2366, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.7529089664613279, | |
| "grad_norm": 2.4454355239868164, | |
| "learning_rate": 3.76454483230664e-05, | |
| "loss": 0.2304, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.7757243896874287, | |
| "grad_norm": 4.029500961303711, | |
| "learning_rate": 3.878621948437144e-05, | |
| "loss": 0.2353, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.7985398129135296, | |
| "grad_norm": 1.7412891387939453, | |
| "learning_rate": 3.9926990645676483e-05, | |
| "loss": 0.2314, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.8213552361396304, | |
| "grad_norm": 2.626089572906494, | |
| "learning_rate": 4.1067761806981516e-05, | |
| "loss": 0.2327, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.8441706593657312, | |
| "grad_norm": 1.2162595987319946, | |
| "learning_rate": 4.220853296828656e-05, | |
| "loss": 0.2367, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.8669860825918321, | |
| "grad_norm": 2.4519355297088623, | |
| "learning_rate": 4.334930412959161e-05, | |
| "loss": 0.2269, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.8898015058179329, | |
| "grad_norm": 1.2700366973876953, | |
| "learning_rate": 4.449007529089665e-05, | |
| "loss": 0.2334, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 0.9126169290440338, | |
| "grad_norm": 2.6412575244903564, | |
| "learning_rate": 4.5630846452201694e-05, | |
| "loss": 0.2315, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.9354323522701347, | |
| "grad_norm": 1.5039851665496826, | |
| "learning_rate": 4.6771617613506734e-05, | |
| "loss": 0.2335, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 0.9582477754962354, | |
| "grad_norm": 5.099658012390137, | |
| "learning_rate": 4.791238877481177e-05, | |
| "loss": 0.2341, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.9810631987223363, | |
| "grad_norm": 3.0738842487335205, | |
| "learning_rate": 4.905315993611681e-05, | |
| "loss": 0.2375, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.7342489784566673, | |
| "eval_f1_macro": 0.49721066997853086, | |
| "eval_loss": 0.2188662439584732, | |
| "eval_precision": 0.6009352545578245, | |
| "eval_recall": 0.4565070202147285, | |
| "eval_runtime": 19.3025, | |
| "eval_samples_per_second": 2421.601, | |
| "eval_steps_per_second": 3.16, | |
| "step": 4383 | |
| }, | |
| { | |
| "epoch": 1.0038786219484372, | |
| "grad_norm": 0.8934878706932068, | |
| "learning_rate": 4.997845210028646e-05, | |
| "loss": 0.2254, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 1.0266940451745379, | |
| "grad_norm": 2.297649621963501, | |
| "learning_rate": 4.985169974903035e-05, | |
| "loss": 0.2097, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.0495094684006387, | |
| "grad_norm": 1.5094428062438965, | |
| "learning_rate": 4.972494739777423e-05, | |
| "loss": 0.208, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 1.0723248916267396, | |
| "grad_norm": 1.9187654256820679, | |
| "learning_rate": 4.9598195046518116e-05, | |
| "loss": 0.2003, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 1.0951403148528405, | |
| "grad_norm": 0.9724093079566956, | |
| "learning_rate": 4.9471442695262e-05, | |
| "loss": 0.1976, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 1.1179557380789413, | |
| "grad_norm": 1.6662517786026, | |
| "learning_rate": 4.9344690344005885e-05, | |
| "loss": 0.1982, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 1.1407711613050422, | |
| "grad_norm": 0.7583943009376526, | |
| "learning_rate": 4.921793799274977e-05, | |
| "loss": 0.2014, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.163586584531143, | |
| "grad_norm": 3.5475401878356934, | |
| "learning_rate": 4.9091185641493654e-05, | |
| "loss": 0.1982, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 1.186402007757244, | |
| "grad_norm": 1.741073727607727, | |
| "learning_rate": 4.896443329023754e-05, | |
| "loss": 0.2044, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 1.2092174309833448, | |
| "grad_norm": 1.7129486799240112, | |
| "learning_rate": 4.883768093898142e-05, | |
| "loss": 0.2039, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 1.2320328542094456, | |
| "grad_norm": 1.3080261945724487, | |
| "learning_rate": 4.87109285877253e-05, | |
| "loss": 0.1997, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 1.2548482774355465, | |
| "grad_norm": 2.1321465969085693, | |
| "learning_rate": 4.8584176236469186e-05, | |
| "loss": 0.2013, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.2776637006616474, | |
| "grad_norm": 1.2857780456542969, | |
| "learning_rate": 4.845742388521307e-05, | |
| "loss": 0.2038, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 1.3004791238877482, | |
| "grad_norm": 2.0227644443511963, | |
| "learning_rate": 4.8330671533956955e-05, | |
| "loss": 0.1952, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 1.323294547113849, | |
| "grad_norm": 1.627146601676941, | |
| "learning_rate": 4.820391918270084e-05, | |
| "loss": 0.1971, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 1.3461099703399497, | |
| "grad_norm": 1.5856671333312988, | |
| "learning_rate": 4.8077166831444724e-05, | |
| "loss": 0.1966, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 1.3689253935660506, | |
| "grad_norm": 0.9896683692932129, | |
| "learning_rate": 4.795041448018861e-05, | |
| "loss": 0.1949, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.3917408167921514, | |
| "grad_norm": 1.0868607759475708, | |
| "learning_rate": 4.782366212893249e-05, | |
| "loss": 0.1936, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 1.4145562400182523, | |
| "grad_norm": 1.2213613986968994, | |
| "learning_rate": 4.769690977767638e-05, | |
| "loss": 0.1951, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 1.4373716632443532, | |
| "grad_norm": 2.0876383781433105, | |
| "learning_rate": 4.757015742642026e-05, | |
| "loss": 0.1956, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 1.460187086470454, | |
| "grad_norm": 3.948638916015625, | |
| "learning_rate": 4.7443405075164146e-05, | |
| "loss": 0.1999, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 1.483002509696555, | |
| "grad_norm": 2.2048580646514893, | |
| "learning_rate": 4.731665272390803e-05, | |
| "loss": 0.1984, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 1.5058179329226558, | |
| "grad_norm": 1.1835227012634277, | |
| "learning_rate": 4.7189900372651915e-05, | |
| "loss": 0.1936, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 1.5286333561487564, | |
| "grad_norm": 1.2532591819763184, | |
| "learning_rate": 4.70631480213958e-05, | |
| "loss": 0.2015, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 1.5514487793748573, | |
| "grad_norm": 1.1021713018417358, | |
| "learning_rate": 4.6936395670139684e-05, | |
| "loss": 0.1946, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 1.5742642026009581, | |
| "grad_norm": 0.7517445087432861, | |
| "learning_rate": 4.680964331888357e-05, | |
| "loss": 0.2024, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 1.597079625827059, | |
| "grad_norm": 1.0925252437591553, | |
| "learning_rate": 4.668289096762745e-05, | |
| "loss": 0.2004, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 1.6198950490531598, | |
| "grad_norm": 1.2946810722351074, | |
| "learning_rate": 4.655613861637134e-05, | |
| "loss": 0.1941, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 1.6427104722792607, | |
| "grad_norm": 1.1611590385437012, | |
| "learning_rate": 4.642938626511522e-05, | |
| "loss": 0.1987, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 1.6655258955053616, | |
| "grad_norm": 0.7706720232963562, | |
| "learning_rate": 4.6302633913859107e-05, | |
| "loss": 0.1977, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 1.6883413187314624, | |
| "grad_norm": 2.32635760307312, | |
| "learning_rate": 4.617588156260299e-05, | |
| "loss": 0.2002, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 1.7111567419575633, | |
| "grad_norm": 2.003863573074341, | |
| "learning_rate": 4.6049129211346876e-05, | |
| "loss": 0.1981, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 1.7339721651836641, | |
| "grad_norm": 0.9495589137077332, | |
| "learning_rate": 4.592237686009075e-05, | |
| "loss": 0.1969, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 1.756787588409765, | |
| "grad_norm": 1.1177550554275513, | |
| "learning_rate": 4.579562450883464e-05, | |
| "loss": 0.196, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 1.7796030116358659, | |
| "grad_norm": 2.062082290649414, | |
| "learning_rate": 4.566887215757852e-05, | |
| "loss": 0.1979, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 1.8024184348619667, | |
| "grad_norm": 1.265002965927124, | |
| "learning_rate": 4.554211980632241e-05, | |
| "loss": 0.1911, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 1.8252338580880676, | |
| "grad_norm": 1.4993034601211548, | |
| "learning_rate": 4.541536745506629e-05, | |
| "loss": 0.1917, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 1.8480492813141685, | |
| "grad_norm": 0.7223235964775085, | |
| "learning_rate": 4.5288615103810176e-05, | |
| "loss": 0.1887, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 1.8708647045402693, | |
| "grad_norm": 2.019066095352173, | |
| "learning_rate": 4.516186275255406e-05, | |
| "loss": 0.1963, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 1.8936801277663702, | |
| "grad_norm": 1.8746905326843262, | |
| "learning_rate": 4.5035110401297945e-05, | |
| "loss": 0.191, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 1.916495550992471, | |
| "grad_norm": 1.852623701095581, | |
| "learning_rate": 4.490835805004183e-05, | |
| "loss": 0.1923, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 1.939310974218572, | |
| "grad_norm": 1.784754753112793, | |
| "learning_rate": 4.4781605698785714e-05, | |
| "loss": 0.1931, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 1.9621263974446728, | |
| "grad_norm": 1.1549110412597656, | |
| "learning_rate": 4.46548533475296e-05, | |
| "loss": 0.196, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 1.9849418206707734, | |
| "grad_norm": 1.884442925453186, | |
| "learning_rate": 4.452810099627348e-05, | |
| "loss": 0.1864, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.7550221423528657, | |
| "eval_f1_macro": 0.46991506497740926, | |
| "eval_loss": 0.2009369283914566, | |
| "eval_precision": 0.6326650393349825, | |
| "eval_recall": 0.44929900989141963, | |
| "eval_runtime": 18.7453, | |
| "eval_samples_per_second": 2493.578, | |
| "eval_steps_per_second": 3.254, | |
| "step": 8766 | |
| }, | |
| { | |
| "epoch": 2.0077572438968745, | |
| "grad_norm": 0.6890222430229187, | |
| "learning_rate": 4.440134864501737e-05, | |
| "loss": 0.1749, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 2.0305726671229753, | |
| "grad_norm": 0.682909369468689, | |
| "learning_rate": 4.427459629376125e-05, | |
| "loss": 0.1359, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 2.0533880903490758, | |
| "grad_norm": 0.7629422545433044, | |
| "learning_rate": 4.4147843942505136e-05, | |
| "loss": 0.1367, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 2.0762035135751766, | |
| "grad_norm": 0.9653803110122681, | |
| "learning_rate": 4.402109159124902e-05, | |
| "loss": 0.1358, | |
| "step": 9100 | |
| }, | |
| { | |
| "epoch": 2.0990189368012775, | |
| "grad_norm": 1.0762972831726074, | |
| "learning_rate": 4.3894339239992905e-05, | |
| "loss": 0.136, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 2.1218343600273784, | |
| "grad_norm": 0.9004037976264954, | |
| "learning_rate": 4.376758688873679e-05, | |
| "loss": 0.1287, | |
| "step": 9300 | |
| }, | |
| { | |
| "epoch": 2.144649783253479, | |
| "grad_norm": 1.2514455318450928, | |
| "learning_rate": 4.3640834537480674e-05, | |
| "loss": 0.1296, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 2.16746520647958, | |
| "grad_norm": 0.9992089867591858, | |
| "learning_rate": 4.351408218622456e-05, | |
| "loss": 0.1343, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 2.190280629705681, | |
| "grad_norm": 1.090753197669983, | |
| "learning_rate": 4.338732983496844e-05, | |
| "loss": 0.1314, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 2.213096052931782, | |
| "grad_norm": 1.0993868112564087, | |
| "learning_rate": 4.326057748371232e-05, | |
| "loss": 0.1294, | |
| "step": 9700 | |
| }, | |
| { | |
| "epoch": 2.2359114761578827, | |
| "grad_norm": 7.720792770385742, | |
| "learning_rate": 4.3133825132456206e-05, | |
| "loss": 0.1311, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 2.2587268993839835, | |
| "grad_norm": 0.968745768070221, | |
| "learning_rate": 4.300707278120009e-05, | |
| "loss": 0.1339, | |
| "step": 9900 | |
| }, | |
| { | |
| "epoch": 2.2815423226100844, | |
| "grad_norm": 1.4330673217773438, | |
| "learning_rate": 4.2880320429943975e-05, | |
| "loss": 0.1354, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 2.3043577458361852, | |
| "grad_norm": 1.1297446489334106, | |
| "learning_rate": 4.275356807868786e-05, | |
| "loss": 0.1343, | |
| "step": 10100 | |
| }, | |
| { | |
| "epoch": 2.327173169062286, | |
| "grad_norm": 1.1260323524475098, | |
| "learning_rate": 4.2626815727431744e-05, | |
| "loss": 0.1324, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 2.349988592288387, | |
| "grad_norm": 1.0184403657913208, | |
| "learning_rate": 4.250006337617563e-05, | |
| "loss": 0.13, | |
| "step": 10300 | |
| }, | |
| { | |
| "epoch": 2.372804015514488, | |
| "grad_norm": 3.17570161819458, | |
| "learning_rate": 4.237331102491951e-05, | |
| "loss": 0.1316, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 2.3956194387405887, | |
| "grad_norm": 0.9891201257705688, | |
| "learning_rate": 4.22465586736634e-05, | |
| "loss": 0.133, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 2.4184348619666896, | |
| "grad_norm": 1.0855801105499268, | |
| "learning_rate": 4.211980632240728e-05, | |
| "loss": 0.1362, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 2.4412502851927904, | |
| "grad_norm": 1.94706392288208, | |
| "learning_rate": 4.199305397115117e-05, | |
| "loss": 0.1275, | |
| "step": 10700 | |
| }, | |
| { | |
| "epoch": 2.4640657084188913, | |
| "grad_norm": 1.3414404392242432, | |
| "learning_rate": 4.186630161989505e-05, | |
| "loss": 0.1332, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 2.486881131644992, | |
| "grad_norm": 1.5227530002593994, | |
| "learning_rate": 4.1739549268638935e-05, | |
| "loss": 0.1313, | |
| "step": 10900 | |
| }, | |
| { | |
| "epoch": 2.509696554871093, | |
| "grad_norm": 1.4501299858093262, | |
| "learning_rate": 4.161279691738282e-05, | |
| "loss": 0.1368, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 2.532511978097194, | |
| "grad_norm": 1.6044068336486816, | |
| "learning_rate": 4.1486044566126704e-05, | |
| "loss": 0.1341, | |
| "step": 11100 | |
| }, | |
| { | |
| "epoch": 2.5553274013232947, | |
| "grad_norm": 1.1524112224578857, | |
| "learning_rate": 4.135929221487059e-05, | |
| "loss": 0.134, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 2.5781428245493956, | |
| "grad_norm": 2.4395620822906494, | |
| "learning_rate": 4.123253986361447e-05, | |
| "loss": 0.135, | |
| "step": 11300 | |
| }, | |
| { | |
| "epoch": 2.6009582477754964, | |
| "grad_norm": 1.3260228633880615, | |
| "learning_rate": 4.110578751235836e-05, | |
| "loss": 0.1322, | |
| "step": 11400 | |
| }, | |
| { | |
| "epoch": 2.6237736710015973, | |
| "grad_norm": 1.1100713014602661, | |
| "learning_rate": 4.097903516110224e-05, | |
| "loss": 0.1328, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 2.646589094227698, | |
| "grad_norm": 0.9172728061676025, | |
| "learning_rate": 4.0852282809846127e-05, | |
| "loss": 0.1286, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 2.669404517453799, | |
| "grad_norm": 1.2171121835708618, | |
| "learning_rate": 4.072553045859001e-05, | |
| "loss": 0.1337, | |
| "step": 11700 | |
| }, | |
| { | |
| "epoch": 2.6922199406798994, | |
| "grad_norm": 1.0674031972885132, | |
| "learning_rate": 4.0598778107333896e-05, | |
| "loss": 0.1324, | |
| "step": 11800 | |
| }, | |
| { | |
| "epoch": 2.7150353639060003, | |
| "grad_norm": 1.2550758123397827, | |
| "learning_rate": 4.047202575607777e-05, | |
| "loss": 0.1342, | |
| "step": 11900 | |
| }, | |
| { | |
| "epoch": 2.737850787132101, | |
| "grad_norm": 0.9326576590538025, | |
| "learning_rate": 4.034527340482166e-05, | |
| "loss": 0.1313, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 2.760666210358202, | |
| "grad_norm": 0.8683038949966431, | |
| "learning_rate": 4.021852105356554e-05, | |
| "loss": 0.1352, | |
| "step": 12100 | |
| }, | |
| { | |
| "epoch": 2.783481633584303, | |
| "grad_norm": 1.100682020187378, | |
| "learning_rate": 4.009176870230943e-05, | |
| "loss": 0.1332, | |
| "step": 12200 | |
| }, | |
| { | |
| "epoch": 2.8062970568104038, | |
| "grad_norm": 1.1301831007003784, | |
| "learning_rate": 3.996501635105331e-05, | |
| "loss": 0.1308, | |
| "step": 12300 | |
| }, | |
| { | |
| "epoch": 2.8291124800365046, | |
| "grad_norm": 1.2631456851959229, | |
| "learning_rate": 3.9838263999797196e-05, | |
| "loss": 0.1324, | |
| "step": 12400 | |
| }, | |
| { | |
| "epoch": 2.8519279032626055, | |
| "grad_norm": 1.0373079776763916, | |
| "learning_rate": 3.971151164854108e-05, | |
| "loss": 0.1311, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 2.8747433264887063, | |
| "grad_norm": 1.5447543859481812, | |
| "learning_rate": 3.9584759297284965e-05, | |
| "loss": 0.133, | |
| "step": 12600 | |
| }, | |
| { | |
| "epoch": 2.897558749714807, | |
| "grad_norm": 1.0701638460159302, | |
| "learning_rate": 3.945800694602885e-05, | |
| "loss": 0.1313, | |
| "step": 12700 | |
| }, | |
| { | |
| "epoch": 2.920374172940908, | |
| "grad_norm": 1.3061041831970215, | |
| "learning_rate": 3.933125459477274e-05, | |
| "loss": 0.1355, | |
| "step": 12800 | |
| }, | |
| { | |
| "epoch": 2.943189596167009, | |
| "grad_norm": 1.4337469339370728, | |
| "learning_rate": 3.920450224351662e-05, | |
| "loss": 0.134, | |
| "step": 12900 | |
| }, | |
| { | |
| "epoch": 2.96600501939311, | |
| "grad_norm": 1.2338460683822632, | |
| "learning_rate": 3.90777498922605e-05, | |
| "loss": 0.1334, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 2.9888204426192106, | |
| "grad_norm": 1.1828727722167969, | |
| "learning_rate": 3.895099754100439e-05, | |
| "loss": 0.1374, | |
| "step": 13100 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.7612476734484308, | |
| "eval_f1_macro": 0.5487671335091459, | |
| "eval_loss": 0.19929102063179016, | |
| "eval_precision": 0.6182830803008168, | |
| "eval_recall": 0.5145348157777688, | |
| "eval_runtime": 18.7521, | |
| "eval_samples_per_second": 2492.68, | |
| "eval_steps_per_second": 3.253, | |
| "step": 13149 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 43830, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 1000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8.58047685121278e+17, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |