| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.996011396011396, |
| "eval_steps": 500, |
| "global_step": 1314, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.022792022792022793, |
| "grad_norm": 1.5942931133990415, |
| "learning_rate": 5e-06, |
| "loss": 0.7549, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.045584045584045586, |
| "grad_norm": 0.7991857713565693, |
| "learning_rate": 5e-06, |
| "loss": 0.6994, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.06837606837606838, |
| "grad_norm": 0.9140901710862966, |
| "learning_rate": 5e-06, |
| "loss": 0.6793, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.09116809116809117, |
| "grad_norm": 0.8624389510365172, |
| "learning_rate": 5e-06, |
| "loss": 0.6793, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.11396011396011396, |
| "grad_norm": 0.8028764412199226, |
| "learning_rate": 5e-06, |
| "loss": 0.6755, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.13675213675213677, |
| "grad_norm": 0.6930416014863396, |
| "learning_rate": 5e-06, |
| "loss": 0.6552, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.15954415954415954, |
| "grad_norm": 0.4455024735977556, |
| "learning_rate": 5e-06, |
| "loss": 0.6522, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.18233618233618235, |
| "grad_norm": 0.3756857882664714, |
| "learning_rate": 5e-06, |
| "loss": 0.6551, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.20512820512820512, |
| "grad_norm": 0.3156561509106738, |
| "learning_rate": 5e-06, |
| "loss": 0.6399, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.22792022792022792, |
| "grad_norm": 0.29899840534733946, |
| "learning_rate": 5e-06, |
| "loss": 0.6412, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.25071225071225073, |
| "grad_norm": 0.34252407396552015, |
| "learning_rate": 5e-06, |
| "loss": 0.6325, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.27350427350427353, |
| "grad_norm": 0.30998458350162983, |
| "learning_rate": 5e-06, |
| "loss": 0.6408, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.2962962962962963, |
| "grad_norm": 0.2926854368606822, |
| "learning_rate": 5e-06, |
| "loss": 0.6417, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.3190883190883191, |
| "grad_norm": 0.3080999788506512, |
| "learning_rate": 5e-06, |
| "loss": 0.6439, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.3418803418803419, |
| "grad_norm": 0.3127485634838126, |
| "learning_rate": 5e-06, |
| "loss": 0.6364, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.3646723646723647, |
| "grad_norm": 0.3087938694119076, |
| "learning_rate": 5e-06, |
| "loss": 0.6415, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.38746438746438744, |
| "grad_norm": 0.34551514282855184, |
| "learning_rate": 5e-06, |
| "loss": 0.6333, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.41025641025641024, |
| "grad_norm": 0.30597627367751323, |
| "learning_rate": 5e-06, |
| "loss": 0.6389, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.43304843304843305, |
| "grad_norm": 0.3049360684986122, |
| "learning_rate": 5e-06, |
| "loss": 0.6315, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.45584045584045585, |
| "grad_norm": 0.3074419647258456, |
| "learning_rate": 5e-06, |
| "loss": 0.6395, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.47863247863247865, |
| "grad_norm": 0.3063058787636533, |
| "learning_rate": 5e-06, |
| "loss": 0.6358, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.5014245014245015, |
| "grad_norm": 0.3041422736519924, |
| "learning_rate": 5e-06, |
| "loss": 0.6395, |
| "step": 220 |
| }, |
| { |
| "epoch": 0.5242165242165242, |
| "grad_norm": 0.32829490899150954, |
| "learning_rate": 5e-06, |
| "loss": 0.6351, |
| "step": 230 |
| }, |
| { |
| "epoch": 0.5470085470085471, |
| "grad_norm": 0.29928422865161575, |
| "learning_rate": 5e-06, |
| "loss": 0.631, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.5698005698005698, |
| "grad_norm": 0.33677512408683524, |
| "learning_rate": 5e-06, |
| "loss": 0.6359, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.5925925925925926, |
| "grad_norm": 0.2993988920643164, |
| "learning_rate": 5e-06, |
| "loss": 0.6341, |
| "step": 260 |
| }, |
| { |
| "epoch": 0.6153846153846154, |
| "grad_norm": 0.30876659846443666, |
| "learning_rate": 5e-06, |
| "loss": 0.6313, |
| "step": 270 |
| }, |
| { |
| "epoch": 0.6381766381766382, |
| "grad_norm": 0.32259158385550957, |
| "learning_rate": 5e-06, |
| "loss": 0.642, |
| "step": 280 |
| }, |
| { |
| "epoch": 0.6609686609686609, |
| "grad_norm": 0.3197871052607408, |
| "learning_rate": 5e-06, |
| "loss": 0.6307, |
| "step": 290 |
| }, |
| { |
| "epoch": 0.6837606837606838, |
| "grad_norm": 0.29048014792039156, |
| "learning_rate": 5e-06, |
| "loss": 0.6288, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.7065527065527065, |
| "grad_norm": 0.2966702478614644, |
| "learning_rate": 5e-06, |
| "loss": 0.6286, |
| "step": 310 |
| }, |
| { |
| "epoch": 0.7293447293447294, |
| "grad_norm": 0.3519767606180092, |
| "learning_rate": 5e-06, |
| "loss": 0.6292, |
| "step": 320 |
| }, |
| { |
| "epoch": 0.7521367521367521, |
| "grad_norm": 0.30112693706715865, |
| "learning_rate": 5e-06, |
| "loss": 0.6259, |
| "step": 330 |
| }, |
| { |
| "epoch": 0.7749287749287749, |
| "grad_norm": 0.32981109923647717, |
| "learning_rate": 5e-06, |
| "loss": 0.6317, |
| "step": 340 |
| }, |
| { |
| "epoch": 0.7977207977207977, |
| "grad_norm": 0.3379743113463029, |
| "learning_rate": 5e-06, |
| "loss": 0.6388, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.8205128205128205, |
| "grad_norm": 0.31778267166425295, |
| "learning_rate": 5e-06, |
| "loss": 0.6305, |
| "step": 360 |
| }, |
| { |
| "epoch": 0.8433048433048433, |
| "grad_norm": 0.32877700363036355, |
| "learning_rate": 5e-06, |
| "loss": 0.6242, |
| "step": 370 |
| }, |
| { |
| "epoch": 0.8660968660968661, |
| "grad_norm": 0.31412737317524975, |
| "learning_rate": 5e-06, |
| "loss": 0.6365, |
| "step": 380 |
| }, |
| { |
| "epoch": 0.8888888888888888, |
| "grad_norm": 0.32966589895492693, |
| "learning_rate": 5e-06, |
| "loss": 0.6351, |
| "step": 390 |
| }, |
| { |
| "epoch": 0.9116809116809117, |
| "grad_norm": 0.29745488244467155, |
| "learning_rate": 5e-06, |
| "loss": 0.6383, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.9344729344729344, |
| "grad_norm": 0.2919883778250579, |
| "learning_rate": 5e-06, |
| "loss": 0.6346, |
| "step": 410 |
| }, |
| { |
| "epoch": 0.9572649572649573, |
| "grad_norm": 0.30167260294917214, |
| "learning_rate": 5e-06, |
| "loss": 0.6215, |
| "step": 420 |
| }, |
| { |
| "epoch": 0.98005698005698, |
| "grad_norm": 0.3438748501573607, |
| "learning_rate": 5e-06, |
| "loss": 0.6345, |
| "step": 430 |
| }, |
| { |
| "epoch": 0.9982905982905983, |
| "eval_loss": 0.6251519918441772, |
| "eval_runtime": 443.0692, |
| "eval_samples_per_second": 26.684, |
| "eval_steps_per_second": 0.418, |
| "step": 438 |
| }, |
| { |
| "epoch": 1.0034188034188034, |
| "grad_norm": 0.3459020392679368, |
| "learning_rate": 5e-06, |
| "loss": 0.6472, |
| "step": 440 |
| }, |
| { |
| "epoch": 1.0262108262108263, |
| "grad_norm": 0.32697315311473785, |
| "learning_rate": 5e-06, |
| "loss": 0.6018, |
| "step": 450 |
| }, |
| { |
| "epoch": 1.049002849002849, |
| "grad_norm": 0.3171861516185578, |
| "learning_rate": 5e-06, |
| "loss": 0.5955, |
| "step": 460 |
| }, |
| { |
| "epoch": 1.0717948717948718, |
| "grad_norm": 0.29168258487993265, |
| "learning_rate": 5e-06, |
| "loss": 0.5964, |
| "step": 470 |
| }, |
| { |
| "epoch": 1.0945868945868946, |
| "grad_norm": 0.3034763127234757, |
| "learning_rate": 5e-06, |
| "loss": 0.6039, |
| "step": 480 |
| }, |
| { |
| "epoch": 1.1173789173789175, |
| "grad_norm": 0.32769639645593956, |
| "learning_rate": 5e-06, |
| "loss": 0.609, |
| "step": 490 |
| }, |
| { |
| "epoch": 1.1401709401709401, |
| "grad_norm": 0.2880222885136017, |
| "learning_rate": 5e-06, |
| "loss": 0.5989, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.162962962962963, |
| "grad_norm": 0.30914814663756, |
| "learning_rate": 5e-06, |
| "loss": 0.5967, |
| "step": 510 |
| }, |
| { |
| "epoch": 1.1857549857549858, |
| "grad_norm": 0.29385232942814227, |
| "learning_rate": 5e-06, |
| "loss": 0.6024, |
| "step": 520 |
| }, |
| { |
| "epoch": 1.2085470085470085, |
| "grad_norm": 0.3201681881923973, |
| "learning_rate": 5e-06, |
| "loss": 0.5954, |
| "step": 530 |
| }, |
| { |
| "epoch": 1.2313390313390313, |
| "grad_norm": 0.28750007966527424, |
| "learning_rate": 5e-06, |
| "loss": 0.6056, |
| "step": 540 |
| }, |
| { |
| "epoch": 1.2541310541310542, |
| "grad_norm": 0.3281465711913005, |
| "learning_rate": 5e-06, |
| "loss": 0.6023, |
| "step": 550 |
| }, |
| { |
| "epoch": 1.2769230769230768, |
| "grad_norm": 0.29382468903317155, |
| "learning_rate": 5e-06, |
| "loss": 0.6038, |
| "step": 560 |
| }, |
| { |
| "epoch": 1.2997150997150997, |
| "grad_norm": 0.3036959327802699, |
| "learning_rate": 5e-06, |
| "loss": 0.5978, |
| "step": 570 |
| }, |
| { |
| "epoch": 1.3225071225071225, |
| "grad_norm": 0.26943940882681405, |
| "learning_rate": 5e-06, |
| "loss": 0.5963, |
| "step": 580 |
| }, |
| { |
| "epoch": 1.3452991452991454, |
| "grad_norm": 0.298273916186228, |
| "learning_rate": 5e-06, |
| "loss": 0.596, |
| "step": 590 |
| }, |
| { |
| "epoch": 1.368091168091168, |
| "grad_norm": 0.34574684084574675, |
| "learning_rate": 5e-06, |
| "loss": 0.6016, |
| "step": 600 |
| }, |
| { |
| "epoch": 1.390883190883191, |
| "grad_norm": 0.3258123058692053, |
| "learning_rate": 5e-06, |
| "loss": 0.6017, |
| "step": 610 |
| }, |
| { |
| "epoch": 1.4136752136752135, |
| "grad_norm": 0.294536307772471, |
| "learning_rate": 5e-06, |
| "loss": 0.6042, |
| "step": 620 |
| }, |
| { |
| "epoch": 1.4364672364672364, |
| "grad_norm": 0.31504584520370943, |
| "learning_rate": 5e-06, |
| "loss": 0.6023, |
| "step": 630 |
| }, |
| { |
| "epoch": 1.4592592592592593, |
| "grad_norm": 0.30604961408134723, |
| "learning_rate": 5e-06, |
| "loss": 0.5972, |
| "step": 640 |
| }, |
| { |
| "epoch": 1.4820512820512821, |
| "grad_norm": 0.2950602116536018, |
| "learning_rate": 5e-06, |
| "loss": 0.595, |
| "step": 650 |
| }, |
| { |
| "epoch": 1.504843304843305, |
| "grad_norm": 0.2896756188515609, |
| "learning_rate": 5e-06, |
| "loss": 0.5947, |
| "step": 660 |
| }, |
| { |
| "epoch": 1.5276353276353276, |
| "grad_norm": 0.31387439824127616, |
| "learning_rate": 5e-06, |
| "loss": 0.6023, |
| "step": 670 |
| }, |
| { |
| "epoch": 1.5504273504273505, |
| "grad_norm": 0.2790769431581845, |
| "learning_rate": 5e-06, |
| "loss": 0.5909, |
| "step": 680 |
| }, |
| { |
| "epoch": 1.573219373219373, |
| "grad_norm": 0.32973139286846626, |
| "learning_rate": 5e-06, |
| "loss": 0.5948, |
| "step": 690 |
| }, |
| { |
| "epoch": 1.596011396011396, |
| "grad_norm": 0.2825398981392269, |
| "learning_rate": 5e-06, |
| "loss": 0.6103, |
| "step": 700 |
| }, |
| { |
| "epoch": 1.6188034188034188, |
| "grad_norm": 0.31992609589931237, |
| "learning_rate": 5e-06, |
| "loss": 0.5974, |
| "step": 710 |
| }, |
| { |
| "epoch": 1.6415954415954417, |
| "grad_norm": 0.29209597743589527, |
| "learning_rate": 5e-06, |
| "loss": 0.602, |
| "step": 720 |
| }, |
| { |
| "epoch": 1.6643874643874645, |
| "grad_norm": 0.33062720968069753, |
| "learning_rate": 5e-06, |
| "loss": 0.5951, |
| "step": 730 |
| }, |
| { |
| "epoch": 1.6871794871794872, |
| "grad_norm": 0.32026043128181125, |
| "learning_rate": 5e-06, |
| "loss": 0.5962, |
| "step": 740 |
| }, |
| { |
| "epoch": 1.7099715099715098, |
| "grad_norm": 0.2988581337724783, |
| "learning_rate": 5e-06, |
| "loss": 0.5936, |
| "step": 750 |
| }, |
| { |
| "epoch": 1.7327635327635327, |
| "grad_norm": 0.31646301036239316, |
| "learning_rate": 5e-06, |
| "loss": 0.5975, |
| "step": 760 |
| }, |
| { |
| "epoch": 1.7555555555555555, |
| "grad_norm": 0.29584933557518556, |
| "learning_rate": 5e-06, |
| "loss": 0.5939, |
| "step": 770 |
| }, |
| { |
| "epoch": 1.7783475783475784, |
| "grad_norm": 0.3061122974181554, |
| "learning_rate": 5e-06, |
| "loss": 0.6011, |
| "step": 780 |
| }, |
| { |
| "epoch": 1.8011396011396013, |
| "grad_norm": 0.29700773168004596, |
| "learning_rate": 5e-06, |
| "loss": 0.5986, |
| "step": 790 |
| }, |
| { |
| "epoch": 1.823931623931624, |
| "grad_norm": 0.3130877658149532, |
| "learning_rate": 5e-06, |
| "loss": 0.5854, |
| "step": 800 |
| }, |
| { |
| "epoch": 1.8467236467236468, |
| "grad_norm": 0.30652907764081355, |
| "learning_rate": 5e-06, |
| "loss": 0.5933, |
| "step": 810 |
| }, |
| { |
| "epoch": 1.8695156695156694, |
| "grad_norm": 0.30324181889932617, |
| "learning_rate": 5e-06, |
| "loss": 0.591, |
| "step": 820 |
| }, |
| { |
| "epoch": 1.8923076923076922, |
| "grad_norm": 0.3209281064222872, |
| "learning_rate": 5e-06, |
| "loss": 0.5948, |
| "step": 830 |
| }, |
| { |
| "epoch": 1.915099715099715, |
| "grad_norm": 0.30993083993967313, |
| "learning_rate": 5e-06, |
| "loss": 0.5993, |
| "step": 840 |
| }, |
| { |
| "epoch": 1.937891737891738, |
| "grad_norm": 0.29782452339093207, |
| "learning_rate": 5e-06, |
| "loss": 0.5974, |
| "step": 850 |
| }, |
| { |
| "epoch": 1.9606837606837608, |
| "grad_norm": 0.3120408307151448, |
| "learning_rate": 5e-06, |
| "loss": 0.5987, |
| "step": 860 |
| }, |
| { |
| "epoch": 1.9834757834757835, |
| "grad_norm": 0.3495642451386505, |
| "learning_rate": 5e-06, |
| "loss": 0.5962, |
| "step": 870 |
| }, |
| { |
| "epoch": 1.9994301994301993, |
| "eval_loss": 0.618661105632782, |
| "eval_runtime": 441.7624, |
| "eval_samples_per_second": 26.763, |
| "eval_steps_per_second": 0.419, |
| "step": 877 |
| }, |
| { |
| "epoch": 2.006837606837607, |
| "grad_norm": 0.3400684860080135, |
| "learning_rate": 5e-06, |
| "loss": 0.6155, |
| "step": 880 |
| }, |
| { |
| "epoch": 2.0296296296296297, |
| "grad_norm": 0.3462799786659649, |
| "learning_rate": 5e-06, |
| "loss": 0.5548, |
| "step": 890 |
| }, |
| { |
| "epoch": 2.0524216524216525, |
| "grad_norm": 0.29842918201231594, |
| "learning_rate": 5e-06, |
| "loss": 0.5699, |
| "step": 900 |
| }, |
| { |
| "epoch": 2.0752136752136754, |
| "grad_norm": 0.3624056715301109, |
| "learning_rate": 5e-06, |
| "loss": 0.5681, |
| "step": 910 |
| }, |
| { |
| "epoch": 2.098005698005698, |
| "grad_norm": 0.3295683404704144, |
| "learning_rate": 5e-06, |
| "loss": 0.5711, |
| "step": 920 |
| }, |
| { |
| "epoch": 2.1207977207977207, |
| "grad_norm": 0.28521749821432146, |
| "learning_rate": 5e-06, |
| "loss": 0.5692, |
| "step": 930 |
| }, |
| { |
| "epoch": 2.1435897435897435, |
| "grad_norm": 0.2987785127871981, |
| "learning_rate": 5e-06, |
| "loss": 0.5639, |
| "step": 940 |
| }, |
| { |
| "epoch": 2.1663817663817664, |
| "grad_norm": 0.31072610747726004, |
| "learning_rate": 5e-06, |
| "loss": 0.5648, |
| "step": 950 |
| }, |
| { |
| "epoch": 2.1891737891737892, |
| "grad_norm": 0.3083648386177692, |
| "learning_rate": 5e-06, |
| "loss": 0.5699, |
| "step": 960 |
| }, |
| { |
| "epoch": 2.211965811965812, |
| "grad_norm": 0.28810608254610576, |
| "learning_rate": 5e-06, |
| "loss": 0.5693, |
| "step": 970 |
| }, |
| { |
| "epoch": 2.234757834757835, |
| "grad_norm": 0.284468926920409, |
| "learning_rate": 5e-06, |
| "loss": 0.5589, |
| "step": 980 |
| }, |
| { |
| "epoch": 2.2575498575498574, |
| "grad_norm": 0.31920675568274887, |
| "learning_rate": 5e-06, |
| "loss": 0.568, |
| "step": 990 |
| }, |
| { |
| "epoch": 2.2803418803418802, |
| "grad_norm": 0.3031537221394061, |
| "learning_rate": 5e-06, |
| "loss": 0.5683, |
| "step": 1000 |
| }, |
| { |
| "epoch": 2.303133903133903, |
| "grad_norm": 0.33063531398708745, |
| "learning_rate": 5e-06, |
| "loss": 0.5658, |
| "step": 1010 |
| }, |
| { |
| "epoch": 2.325925925925926, |
| "grad_norm": 0.3118803957682583, |
| "learning_rate": 5e-06, |
| "loss": 0.5688, |
| "step": 1020 |
| }, |
| { |
| "epoch": 2.348717948717949, |
| "grad_norm": 0.34442965042332235, |
| "learning_rate": 5e-06, |
| "loss": 0.5701, |
| "step": 1030 |
| }, |
| { |
| "epoch": 2.3715099715099717, |
| "grad_norm": 0.2978535776786599, |
| "learning_rate": 5e-06, |
| "loss": 0.5681, |
| "step": 1040 |
| }, |
| { |
| "epoch": 2.394301994301994, |
| "grad_norm": 0.3030396515239551, |
| "learning_rate": 5e-06, |
| "loss": 0.5674, |
| "step": 1050 |
| }, |
| { |
| "epoch": 2.417094017094017, |
| "grad_norm": 0.2993669833981522, |
| "learning_rate": 5e-06, |
| "loss": 0.5758, |
| "step": 1060 |
| }, |
| { |
| "epoch": 2.43988603988604, |
| "grad_norm": 0.304258136262077, |
| "learning_rate": 5e-06, |
| "loss": 0.5787, |
| "step": 1070 |
| }, |
| { |
| "epoch": 2.4626780626780627, |
| "grad_norm": 0.30342406132461924, |
| "learning_rate": 5e-06, |
| "loss": 0.5739, |
| "step": 1080 |
| }, |
| { |
| "epoch": 2.4854700854700855, |
| "grad_norm": 0.30057774605326515, |
| "learning_rate": 5e-06, |
| "loss": 0.5715, |
| "step": 1090 |
| }, |
| { |
| "epoch": 2.5082621082621084, |
| "grad_norm": 0.30766798961642455, |
| "learning_rate": 5e-06, |
| "loss": 0.578, |
| "step": 1100 |
| }, |
| { |
| "epoch": 2.5310541310541312, |
| "grad_norm": 0.3162741067156514, |
| "learning_rate": 5e-06, |
| "loss": 0.5715, |
| "step": 1110 |
| }, |
| { |
| "epoch": 2.5538461538461537, |
| "grad_norm": 0.3020804595639734, |
| "learning_rate": 5e-06, |
| "loss": 0.5696, |
| "step": 1120 |
| }, |
| { |
| "epoch": 2.5766381766381765, |
| "grad_norm": 0.2976289222693161, |
| "learning_rate": 5e-06, |
| "loss": 0.569, |
| "step": 1130 |
| }, |
| { |
| "epoch": 2.5994301994301994, |
| "grad_norm": 0.31378852848615507, |
| "learning_rate": 5e-06, |
| "loss": 0.5686, |
| "step": 1140 |
| }, |
| { |
| "epoch": 2.6222222222222222, |
| "grad_norm": 0.30690612972894366, |
| "learning_rate": 5e-06, |
| "loss": 0.569, |
| "step": 1150 |
| }, |
| { |
| "epoch": 2.645014245014245, |
| "grad_norm": 0.3104076296392732, |
| "learning_rate": 5e-06, |
| "loss": 0.5701, |
| "step": 1160 |
| }, |
| { |
| "epoch": 2.667806267806268, |
| "grad_norm": 0.29271285420919807, |
| "learning_rate": 5e-06, |
| "loss": 0.5729, |
| "step": 1170 |
| }, |
| { |
| "epoch": 2.690598290598291, |
| "grad_norm": 0.2909504253156579, |
| "learning_rate": 5e-06, |
| "loss": 0.568, |
| "step": 1180 |
| }, |
| { |
| "epoch": 2.7133903133903132, |
| "grad_norm": 0.2874132176143875, |
| "learning_rate": 5e-06, |
| "loss": 0.5691, |
| "step": 1190 |
| }, |
| { |
| "epoch": 2.736182336182336, |
| "grad_norm": 0.28746329274930527, |
| "learning_rate": 5e-06, |
| "loss": 0.5723, |
| "step": 1200 |
| }, |
| { |
| "epoch": 2.758974358974359, |
| "grad_norm": 0.2919881849186529, |
| "learning_rate": 5e-06, |
| "loss": 0.5757, |
| "step": 1210 |
| }, |
| { |
| "epoch": 2.781766381766382, |
| "grad_norm": 0.2890199125554714, |
| "learning_rate": 5e-06, |
| "loss": 0.5656, |
| "step": 1220 |
| }, |
| { |
| "epoch": 2.8045584045584047, |
| "grad_norm": 0.29380259374252815, |
| "learning_rate": 5e-06, |
| "loss": 0.564, |
| "step": 1230 |
| }, |
| { |
| "epoch": 2.827350427350427, |
| "grad_norm": 0.31447441207827603, |
| "learning_rate": 5e-06, |
| "loss": 0.5789, |
| "step": 1240 |
| }, |
| { |
| "epoch": 2.8501424501424504, |
| "grad_norm": 0.30187509267816504, |
| "learning_rate": 5e-06, |
| "loss": 0.5755, |
| "step": 1250 |
| }, |
| { |
| "epoch": 2.872934472934473, |
| "grad_norm": 0.29842306226554516, |
| "learning_rate": 5e-06, |
| "loss": 0.5727, |
| "step": 1260 |
| }, |
| { |
| "epoch": 2.8957264957264957, |
| "grad_norm": 0.3060981730198397, |
| "learning_rate": 5e-06, |
| "loss": 0.5736, |
| "step": 1270 |
| }, |
| { |
| "epoch": 2.9185185185185185, |
| "grad_norm": 0.2856721618735277, |
| "learning_rate": 5e-06, |
| "loss": 0.5638, |
| "step": 1280 |
| }, |
| { |
| "epoch": 2.9413105413105414, |
| "grad_norm": 0.29923276315660907, |
| "learning_rate": 5e-06, |
| "loss": 0.5641, |
| "step": 1290 |
| }, |
| { |
| "epoch": 2.9641025641025642, |
| "grad_norm": 0.3445130813946357, |
| "learning_rate": 5e-06, |
| "loss": 0.5652, |
| "step": 1300 |
| }, |
| { |
| "epoch": 2.9868945868945866, |
| "grad_norm": 0.3058550170645596, |
| "learning_rate": 5e-06, |
| "loss": 0.575, |
| "step": 1310 |
| }, |
| { |
| "epoch": 2.996011396011396, |
| "eval_loss": 0.6185689568519592, |
| "eval_runtime": 445.432, |
| "eval_samples_per_second": 26.543, |
| "eval_steps_per_second": 0.415, |
| "step": 1314 |
| }, |
| { |
| "epoch": 2.996011396011396, |
| "step": 1314, |
| "total_flos": 2755219238682624.0, |
| "train_loss": 0.6040635954480919, |
| "train_runtime": 70694.8554, |
| "train_samples_per_second": 9.532, |
| "train_steps_per_second": 0.019 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 1314, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "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": 2755219238682624.0, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
