| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.8328365053886724, |
| "eval_steps": 30, |
| "global_step": 1000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.018344416418252695, |
| "grad_norm": 7.795040130615234, |
| "learning_rate": 1.6363636363636366e-05, |
| "loss": 2.6173, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.03668883283650539, |
| "grad_norm": 0.6880274415016174, |
| "learning_rate": 3.454545454545455e-05, |
| "loss": 0.9115, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.05503324925475808, |
| "grad_norm": 0.5830976963043213, |
| "learning_rate": 5.272727272727272e-05, |
| "loss": 0.5658, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.05503324925475808, |
| "eval_loss": 0.5072382092475891, |
| "eval_runtime": 49.4282, |
| "eval_samples_per_second": 4.653, |
| "eval_steps_per_second": 4.653, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.07337766567301078, |
| "grad_norm": 0.6845789551734924, |
| "learning_rate": 7.090909090909092e-05, |
| "loss": 0.4196, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.09172208209126347, |
| "grad_norm": 0.7662066221237183, |
| "learning_rate": 8.90909090909091e-05, |
| "loss": 0.3444, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.11006649850951616, |
| "grad_norm": 0.7642600536346436, |
| "learning_rate": 0.00010727272727272728, |
| "loss": 0.2597, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.11006649850951616, |
| "eval_loss": 0.25273433327674866, |
| "eval_runtime": 48.8989, |
| "eval_samples_per_second": 4.704, |
| "eval_steps_per_second": 4.704, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.12841091492776885, |
| "grad_norm": 0.48377156257629395, |
| "learning_rate": 0.00012545454545454546, |
| "loss": 0.2275, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.14675533134602156, |
| "grad_norm": 0.343270480632782, |
| "learning_rate": 0.00014363636363636363, |
| "loss": 0.227, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.16509974776427425, |
| "grad_norm": 0.4066845774650574, |
| "learning_rate": 0.00016181818181818184, |
| "loss": 0.1879, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.16509974776427425, |
| "eval_loss": 0.19945120811462402, |
| "eval_runtime": 48.8856, |
| "eval_samples_per_second": 4.705, |
| "eval_steps_per_second": 4.705, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.18344416418252693, |
| "grad_norm": 0.31925588846206665, |
| "learning_rate": 0.00018, |
| "loss": 0.1751, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.20178858060077964, |
| "grad_norm": 0.3936826288700104, |
| "learning_rate": 0.00019818181818181821, |
| "loss": 0.1742, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.22013299701903233, |
| "grad_norm": 0.3444064259529114, |
| "learning_rate": 0.00019995855217078221, |
| "loss": 0.1745, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.22013299701903233, |
| "eval_loss": 0.16547603905200958, |
| "eval_runtime": 49.0551, |
| "eval_samples_per_second": 4.689, |
| "eval_steps_per_second": 4.689, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.238477413437285, |
| "grad_norm": 0.38167741894721985, |
| "learning_rate": 0.0001998153198346097, |
| "loss": 0.1758, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.2568218298555377, |
| "grad_norm": 0.38544419407844543, |
| "learning_rate": 0.00019956993783702592, |
| "loss": 0.1559, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.27516624627379044, |
| "grad_norm": 0.19193893671035767, |
| "learning_rate": 0.00019922265729868066, |
| "loss": 0.1596, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.27516624627379044, |
| "eval_loss": 0.14603756368160248, |
| "eval_runtime": 48.8719, |
| "eval_samples_per_second": 4.706, |
| "eval_steps_per_second": 4.706, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.2935106626920431, |
| "grad_norm": 0.2377977967262268, |
| "learning_rate": 0.0001987738336218254, |
| "loss": 0.1529, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.3118550791102958, |
| "grad_norm": 0.24111273884773254, |
| "learning_rate": 0.00019822392612659965, |
| "loss": 0.1422, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.3301994955285485, |
| "grad_norm": 0.2043677717447281, |
| "learning_rate": 0.00019757349758096855, |
| "loss": 0.1466, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.3301994955285485, |
| "eval_loss": 0.14219357073307037, |
| "eval_runtime": 48.9834, |
| "eval_samples_per_second": 4.695, |
| "eval_steps_per_second": 4.695, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.3485439119468012, |
| "grad_norm": 0.14538665115833282, |
| "learning_rate": 0.00019682321362479407, |
| "loss": 0.1431, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.36688832836505386, |
| "grad_norm": 0.16464489698410034, |
| "learning_rate": 0.00019597384208862778, |
| "loss": 0.1462, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.3852327447833066, |
| "grad_norm": 0.1624147742986679, |
| "learning_rate": 0.00019502625220792346, |
| "loss": 0.1405, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.3852327447833066, |
| "eval_loss": 0.1425054669380188, |
| "eval_runtime": 48.8411, |
| "eval_samples_per_second": 4.709, |
| "eval_steps_per_second": 4.709, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.4035771612015593, |
| "grad_norm": 0.32471776008605957, |
| "learning_rate": 0.00019398141373347318, |
| "loss": 0.1367, |
| "step": 220 |
| }, |
| { |
| "epoch": 0.42192157761981197, |
| "grad_norm": 0.1439230591058731, |
| "learning_rate": 0.00019284039593897733, |
| "loss": 0.1378, |
| "step": 230 |
| }, |
| { |
| "epoch": 0.44026599403806466, |
| "grad_norm": 0.2199280858039856, |
| "learning_rate": 0.00019160436652676427, |
| "loss": 0.1471, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.44026599403806466, |
| "eval_loss": 0.1684170663356781, |
| "eval_runtime": 48.9029, |
| "eval_samples_per_second": 4.703, |
| "eval_steps_per_second": 4.703, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.45861041045631734, |
| "grad_norm": 0.46398675441741943, |
| "learning_rate": 0.0001902745904327792, |
| "loss": 0.1367, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.47695482687457, |
| "grad_norm": 0.45815974473953247, |
| "learning_rate": 0.00018885242853206605, |
| "loss": 0.1346, |
| "step": 260 |
| }, |
| { |
| "epoch": 0.49529924329282277, |
| "grad_norm": 0.29094287753105164, |
| "learning_rate": 0.00018733933624606576, |
| "loss": 0.1443, |
| "step": 270 |
| }, |
| { |
| "epoch": 0.49529924329282277, |
| "eval_loss": 0.1330244541168213, |
| "eval_runtime": 48.9904, |
| "eval_samples_per_second": 4.695, |
| "eval_steps_per_second": 4.695, |
| "step": 270 |
| }, |
| { |
| "epoch": 0.5136436597110754, |
| "grad_norm": 0.22784261405467987, |
| "learning_rate": 0.0001857368620531578, |
| "loss": 0.1403, |
| "step": 280 |
| }, |
| { |
| "epoch": 0.5319880761293282, |
| "grad_norm": 0.16252748668193817, |
| "learning_rate": 0.00018404664590396794, |
| "loss": 0.1375, |
| "step": 290 |
| }, |
| { |
| "epoch": 0.5503324925475809, |
| "grad_norm": 0.296027809381485, |
| "learning_rate": 0.00018227041754306485, |
| "loss": 0.1429, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.5503324925475809, |
| "eval_loss": 0.1296931356191635, |
| "eval_runtime": 49.3388, |
| "eval_samples_per_second": 4.662, |
| "eval_steps_per_second": 4.662, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.5686769089658336, |
| "grad_norm": 0.16931048035621643, |
| "learning_rate": 0.00018040999473876258, |
| "loss": 0.132, |
| "step": 310 |
| }, |
| { |
| "epoch": 0.5870213253840862, |
| "grad_norm": 0.15758486092090607, |
| "learning_rate": 0.0001784672814228409, |
| "loss": 0.1439, |
| "step": 320 |
| }, |
| { |
| "epoch": 0.6053657418023389, |
| "grad_norm": 0.2505033016204834, |
| "learning_rate": 0.00017644426574208697, |
| "loss": 0.1313, |
| "step": 330 |
| }, |
| { |
| "epoch": 0.6053657418023389, |
| "eval_loss": 0.1264232099056244, |
| "eval_runtime": 49.2647, |
| "eval_samples_per_second": 4.669, |
| "eval_steps_per_second": 4.669, |
| "step": 330 |
| }, |
| { |
| "epoch": 0.6237101582205916, |
| "grad_norm": 0.15784454345703125, |
| "learning_rate": 0.00017434301802365265, |
| "loss": 0.1359, |
| "step": 340 |
| }, |
| { |
| "epoch": 0.6420545746388443, |
| "grad_norm": 0.1714029461145401, |
| "learning_rate": 0.00017216568865630923, |
| "loss": 0.1394, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.660398991057097, |
| "grad_norm": 0.1297195553779602, |
| "learning_rate": 0.0001699145058897685, |
| "loss": 0.1297, |
| "step": 360 |
| }, |
| { |
| "epoch": 0.660398991057097, |
| "eval_loss": 0.122822105884552, |
| "eval_runtime": 49.3023, |
| "eval_samples_per_second": 4.665, |
| "eval_steps_per_second": 4.665, |
| "step": 360 |
| }, |
| { |
| "epoch": 0.6787434074753497, |
| "grad_norm": 0.10573259741067886, |
| "learning_rate": 0.00016759177355432186, |
| "loss": 0.1253, |
| "step": 370 |
| }, |
| { |
| "epoch": 0.6970878238936024, |
| "grad_norm": 0.11619006097316742, |
| "learning_rate": 0.00016519986870313117, |
| "loss": 0.1361, |
| "step": 380 |
| }, |
| { |
| "epoch": 0.715432240311855, |
| "grad_norm": 0.11721345037221909, |
| "learning_rate": 0.00016274123917958436, |
| "loss": 0.123, |
| "step": 390 |
| }, |
| { |
| "epoch": 0.715432240311855, |
| "eval_loss": 0.12079351395368576, |
| "eval_runtime": 49.4755, |
| "eval_samples_per_second": 4.649, |
| "eval_steps_per_second": 4.649, |
| "step": 390 |
| }, |
| { |
| "epoch": 0.7337766567301077, |
| "grad_norm": 0.10461968928575516, |
| "learning_rate": 0.00016021840111220547, |
| "loss": 0.1186, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.7521210731483605, |
| "grad_norm": 0.11793247610330582, |
| "learning_rate": 0.0001576339363396822, |
| "loss": 0.1326, |
| "step": 410 |
| }, |
| { |
| "epoch": 0.7704654895666132, |
| "grad_norm": 0.09142949432134628, |
| "learning_rate": 0.00015499048976864698, |
| "loss": 0.1338, |
| "step": 420 |
| }, |
| { |
| "epoch": 0.7704654895666132, |
| "eval_loss": 0.11926981061697006, |
| "eval_runtime": 49.3242, |
| "eval_samples_per_second": 4.663, |
| "eval_steps_per_second": 4.663, |
| "step": 420 |
| }, |
| { |
| "epoch": 0.7888099059848659, |
| "grad_norm": 0.12111407518386841, |
| "learning_rate": 0.0001522907666669147, |
| "loss": 0.1296, |
| "step": 430 |
| }, |
| { |
| "epoch": 0.8071543224031186, |
| "grad_norm": 0.1540282666683197, |
| "learning_rate": 0.00014953752989494814, |
| "loss": 0.1371, |
| "step": 440 |
| }, |
| { |
| "epoch": 0.8254987388213713, |
| "grad_norm": 0.10127419233322144, |
| "learning_rate": 0.00014673359707838336, |
| "loss": 0.1263, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.8254987388213713, |
| "eval_loss": 0.11757560074329376, |
| "eval_runtime": 49.3842, |
| "eval_samples_per_second": 4.657, |
| "eval_steps_per_second": 4.657, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.8438431552396239, |
| "grad_norm": 0.10976914316415787, |
| "learning_rate": 0.00014388183772450955, |
| "loss": 0.1268, |
| "step": 460 |
| }, |
| { |
| "epoch": 0.8621875716578766, |
| "grad_norm": 0.08922591060400009, |
| "learning_rate": 0.0001409851702856535, |
| "loss": 0.1252, |
| "step": 470 |
| }, |
| { |
| "epoch": 0.8805319880761293, |
| "grad_norm": 0.09157353639602661, |
| "learning_rate": 0.00013804655917247472, |
| "loss": 0.1341, |
| "step": 480 |
| }, |
| { |
| "epoch": 0.8805319880761293, |
| "eval_loss": 0.11754835397005081, |
| "eval_runtime": 49.3415, |
| "eval_samples_per_second": 4.661, |
| "eval_steps_per_second": 4.661, |
| "step": 480 |
| }, |
| { |
| "epoch": 0.898876404494382, |
| "grad_norm": 0.2666095793247223, |
| "learning_rate": 0.00013506901172022722, |
| "loss": 0.1235, |
| "step": 490 |
| }, |
| { |
| "epoch": 0.9172208209126347, |
| "grad_norm": 0.10213123261928558, |
| "learning_rate": 0.00013205557511109295, |
| "loss": 0.1221, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.9355652373308874, |
| "grad_norm": 0.11488551646471024, |
| "learning_rate": 0.00012900933325573637, |
| "loss": 0.129, |
| "step": 510 |
| }, |
| { |
| "epoch": 0.9355652373308874, |
| "eval_loss": 0.11715804040431976, |
| "eval_runtime": 49.2999, |
| "eval_samples_per_second": 4.665, |
| "eval_steps_per_second": 4.665, |
| "step": 510 |
| }, |
| { |
| "epoch": 0.95390965374914, |
| "grad_norm": 0.12331929802894592, |
| "learning_rate": 0.00012593340363727131, |
| "loss": 0.1224, |
| "step": 520 |
| }, |
| { |
| "epoch": 0.9722540701673928, |
| "grad_norm": 0.11989827454090118, |
| "learning_rate": 0.000122830934120871, |
| "loss": 0.1269, |
| "step": 530 |
| }, |
| { |
| "epoch": 0.9905984865856455, |
| "grad_norm": 0.08979545533657074, |
| "learning_rate": 0.00011970509973228458, |
| "loss": 0.1223, |
| "step": 540 |
| }, |
| { |
| "epoch": 0.9905984865856455, |
| "eval_loss": 0.11745806038379669, |
| "eval_runtime": 49.2732, |
| "eval_samples_per_second": 4.668, |
| "eval_steps_per_second": 4.668, |
| "step": 540 |
| }, |
| { |
| "epoch": 1.0073377665673011, |
| "grad_norm": 0.10322548449039459, |
| "learning_rate": 0.00011655909940855851, |
| "loss": 0.111, |
| "step": 550 |
| }, |
| { |
| "epoch": 1.0256821829855538, |
| "grad_norm": 0.09024786949157715, |
| "learning_rate": 0.0001133961527242872, |
| "loss": 0.1142, |
| "step": 560 |
| }, |
| { |
| "epoch": 1.0440265994038065, |
| "grad_norm": 0.09547445923089981, |
| "learning_rate": 0.00011021949659674338, |
| "loss": 0.1322, |
| "step": 570 |
| }, |
| { |
| "epoch": 1.0440265994038065, |
| "eval_loss": 0.11743354052305222, |
| "eval_runtime": 49.2711, |
| "eval_samples_per_second": 4.668, |
| "eval_steps_per_second": 4.668, |
| "step": 570 |
| }, |
| { |
| "epoch": 1.0623710158220592, |
| "grad_norm": 0.08737261593341827, |
| "learning_rate": 0.00010703238197326042, |
| "loss": 0.1224, |
| "step": 580 |
| }, |
| { |
| "epoch": 1.0807154322403119, |
| "grad_norm": 0.08432964235544205, |
| "learning_rate": 0.00010383807050425646, |
| "loss": 0.12, |
| "step": 590 |
| }, |
| { |
| "epoch": 1.0990598486585645, |
| "grad_norm": 0.09570309519767761, |
| "learning_rate": 0.0001006398312053048, |
| "loss": 0.1142, |
| "step": 600 |
| }, |
| { |
| "epoch": 1.0990598486585645, |
| "eval_loss": 0.11705348640680313, |
| "eval_runtime": 49.3215, |
| "eval_samples_per_second": 4.663, |
| "eval_steps_per_second": 4.663, |
| "step": 600 |
| }, |
| { |
| "epoch": 1.1174042650768172, |
| "grad_norm": 0.10215649008750916, |
| "learning_rate": 9.744093711166744e-05, |
| "loss": 0.1256, |
| "step": 610 |
| }, |
| { |
| "epoch": 1.13574868149507, |
| "grad_norm": 0.09788327664136887, |
| "learning_rate": 9.42446619287144e-05, |
| "loss": 0.1285, |
| "step": 620 |
| }, |
| { |
| "epoch": 1.1540930979133226, |
| "grad_norm": 0.07625731825828552, |
| "learning_rate": 9.105427668165755e-05, |
| "loss": 0.1188, |
| "step": 630 |
| }, |
| { |
| "epoch": 1.1540930979133226, |
| "eval_loss": 0.11599662899971008, |
| "eval_runtime": 49.3627, |
| "eval_samples_per_second": 4.659, |
| "eval_steps_per_second": 4.659, |
| "step": 630 |
| }, |
| { |
| "epoch": 1.1724375143315753, |
| "grad_norm": 0.07791601866483688, |
| "learning_rate": 8.787304636802742e-05, |
| "loss": 0.1192, |
| "step": 640 |
| }, |
| { |
| "epoch": 1.190781930749828, |
| "grad_norm": 0.08331194519996643, |
| "learning_rate": 8.47042266163181e-05, |
| "loss": 0.1224, |
| "step": 650 |
| }, |
| { |
| "epoch": 1.2091263471680807, |
| "grad_norm": 0.1000560000538826, |
| "learning_rate": 8.155106035422095e-05, |
| "loss": 0.1187, |
| "step": 660 |
| }, |
| { |
| "epoch": 1.2091263471680807, |
| "eval_loss": 0.11565903574228287, |
| "eval_runtime": 49.4108, |
| "eval_samples_per_second": 4.655, |
| "eval_steps_per_second": 4.655, |
| "step": 660 |
| }, |
| { |
| "epoch": 1.2274707635863333, |
| "grad_norm": 0.09680289030075073, |
| "learning_rate": 7.841677448985571e-05, |
| "loss": 0.1203, |
| "step": 670 |
| }, |
| { |
| "epoch": 1.245815180004586, |
| "grad_norm": 0.0752745121717453, |
| "learning_rate": 7.530457660939587e-05, |
| "loss": 0.1208, |
| "step": 680 |
| }, |
| { |
| "epoch": 1.264159596422839, |
| "grad_norm": 0.5036187171936035, |
| "learning_rate": 7.22176516944682e-05, |
| "loss": 0.1179, |
| "step": 690 |
| }, |
| { |
| "epoch": 1.264159596422839, |
| "eval_loss": 0.11543552577495575, |
| "eval_runtime": 49.3311, |
| "eval_samples_per_second": 4.662, |
| "eval_steps_per_second": 4.662, |
| "step": 690 |
| }, |
| { |
| "epoch": 1.2825040128410916, |
| "grad_norm": 0.09510516375303268, |
| "learning_rate": 6.915915886268485e-05, |
| "loss": 0.1215, |
| "step": 700 |
| }, |
| { |
| "epoch": 1.3008484292593443, |
| "grad_norm": 0.08249227702617645, |
| "learning_rate": 6.613222813464508e-05, |
| "loss": 0.1192, |
| "step": 710 |
| }, |
| { |
| "epoch": 1.319192845677597, |
| "grad_norm": 0.0947667732834816, |
| "learning_rate": 6.313995723071377e-05, |
| "loss": 0.1248, |
| "step": 720 |
| }, |
| { |
| "epoch": 1.319192845677597, |
| "eval_loss": 0.11455719918012619, |
| "eval_runtime": 49.2423, |
| "eval_samples_per_second": 4.671, |
| "eval_steps_per_second": 4.671, |
| "step": 720 |
| }, |
| { |
| "epoch": 1.3375372620958497, |
| "grad_norm": 0.09012740105390549, |
| "learning_rate": 6.0185408400856116e-05, |
| "loss": 0.1152, |
| "step": 730 |
| }, |
| { |
| "epoch": 1.3558816785141024, |
| "grad_norm": 0.11220687627792358, |
| "learning_rate": 5.727160529077189e-05, |
| "loss": 0.1232, |
| "step": 740 |
| }, |
| { |
| "epoch": 1.374226094932355, |
| "grad_norm": 0.09022535383701324, |
| "learning_rate": 5.440152984753709e-05, |
| "loss": 0.1179, |
| "step": 750 |
| }, |
| { |
| "epoch": 1.374226094932355, |
| "eval_loss": 0.1143663227558136, |
| "eval_runtime": 49.3543, |
| "eval_samples_per_second": 4.66, |
| "eval_steps_per_second": 4.66, |
| "step": 750 |
| }, |
| { |
| "epoch": 1.3925705113506077, |
| "grad_norm": 0.08042389154434204, |
| "learning_rate": 5.157811926791905e-05, |
| "loss": 0.1219, |
| "step": 760 |
| }, |
| { |
| "epoch": 1.4109149277688604, |
| "grad_norm": 0.09887140244245529, |
| "learning_rate": 4.880426299248867e-05, |
| "loss": 0.1172, |
| "step": 770 |
| }, |
| { |
| "epoch": 1.429259344187113, |
| "grad_norm": 0.08288570493459702, |
| "learning_rate": 4.608279974860581e-05, |
| "loss": 0.1222, |
| "step": 780 |
| }, |
| { |
| "epoch": 1.429259344187113, |
| "eval_loss": 0.11446955054998398, |
| "eval_runtime": 49.3093, |
| "eval_samples_per_second": 4.664, |
| "eval_steps_per_second": 4.664, |
| "step": 780 |
| }, |
| { |
| "epoch": 1.4476037606053658, |
| "grad_norm": 0.08059478551149368, |
| "learning_rate": 4.341651464530341e-05, |
| "loss": 0.1236, |
| "step": 790 |
| }, |
| { |
| "epoch": 1.4659481770236185, |
| "grad_norm": 0.08869417011737823, |
| "learning_rate": 4.0808136323044554e-05, |
| "loss": 0.1209, |
| "step": 800 |
| }, |
| { |
| "epoch": 1.4842925934418711, |
| "grad_norm": 0.09369216859340668, |
| "learning_rate": 3.8260334161268077e-05, |
| "loss": 0.1228, |
| "step": 810 |
| }, |
| { |
| "epoch": 1.4842925934418711, |
| "eval_loss": 0.11371872574090958, |
| "eval_runtime": 49.2681, |
| "eval_samples_per_second": 4.668, |
| "eval_steps_per_second": 4.668, |
| "step": 810 |
| }, |
| { |
| "epoch": 1.5026370098601238, |
| "grad_norm": 0.07937419414520264, |
| "learning_rate": 3.577571554658154e-05, |
| "loss": 0.1144, |
| "step": 820 |
| }, |
| { |
| "epoch": 1.5209814262783765, |
| "grad_norm": 0.09610588103532791, |
| "learning_rate": 3.33568232043967e-05, |
| "loss": 0.1158, |
| "step": 830 |
| }, |
| { |
| "epoch": 1.5393258426966292, |
| "grad_norm": 0.1910742223262787, |
| "learning_rate": 3.100613259673843e-05, |
| "loss": 0.1261, |
| "step": 840 |
| }, |
| { |
| "epoch": 1.5393258426966292, |
| "eval_loss": 0.11366112530231476, |
| "eval_runtime": 49.3771, |
| "eval_samples_per_second": 4.658, |
| "eval_steps_per_second": 4.658, |
| "step": 840 |
| }, |
| { |
| "epoch": 1.5576702591148819, |
| "grad_norm": 0.07669960707426071, |
| "learning_rate": 2.8726049388889807e-05, |
| "loss": 0.1165, |
| "step": 850 |
| }, |
| { |
| "epoch": 1.5760146755331346, |
| "grad_norm": 0.08569029718637466, |
| "learning_rate": 2.651890698746682e-05, |
| "loss": 0.1192, |
| "step": 860 |
| }, |
| { |
| "epoch": 1.5943590919513873, |
| "grad_norm": 0.09321046620607376, |
| "learning_rate": 2.4386964152441018e-05, |
| "loss": 0.1237, |
| "step": 870 |
| }, |
| { |
| "epoch": 1.5943590919513873, |
| "eval_loss": 0.11372239142656326, |
| "eval_runtime": 49.3141, |
| "eval_samples_per_second": 4.664, |
| "eval_steps_per_second": 4.664, |
| "step": 870 |
| }, |
| { |
| "epoch": 1.61270350836964, |
| "grad_norm": 0.08224959671497345, |
| "learning_rate": 2.2332402685554876e-05, |
| "loss": 0.1149, |
| "step": 880 |
| }, |
| { |
| "epoch": 1.6310479247878926, |
| "grad_norm": 0.07479019463062286, |
| "learning_rate": 2.035732519749528e-05, |
| "loss": 0.1237, |
| "step": 890 |
| }, |
| { |
| "epoch": 1.6493923412061453, |
| "grad_norm": 0.0903916209936142, |
| "learning_rate": 1.8463752956109615e-05, |
| "loss": 0.1167, |
| "step": 900 |
| }, |
| { |
| "epoch": 1.6493923412061453, |
| "eval_loss": 0.1136728897690773, |
| "eval_runtime": 49.4665, |
| "eval_samples_per_second": 4.65, |
| "eval_steps_per_second": 4.65, |
| "step": 900 |
| }, |
| { |
| "epoch": 1.667736757624398, |
| "grad_norm": 0.08336473256349564, |
| "learning_rate": 1.6653623817867637e-05, |
| "loss": 0.1171, |
| "step": 910 |
| }, |
| { |
| "epoch": 1.6860811740426507, |
| "grad_norm": 0.08168327063322067, |
| "learning_rate": 1.4928790244684865e-05, |
| "loss": 0.1189, |
| "step": 920 |
| }, |
| { |
| "epoch": 1.7044255904609034, |
| "grad_norm": 0.08606237918138504, |
| "learning_rate": 1.3291017408138006e-05, |
| "loss": 0.1184, |
| "step": 930 |
| }, |
| { |
| "epoch": 1.7044255904609034, |
| "eval_loss": 0.11324052512645721, |
| "eval_runtime": 49.4226, |
| "eval_samples_per_second": 4.654, |
| "eval_steps_per_second": 4.654, |
| "step": 930 |
| }, |
| { |
| "epoch": 1.722770006879156, |
| "grad_norm": 0.09091446548700333, |
| "learning_rate": 1.1741981383011924e-05, |
| "loss": 0.1184, |
| "step": 940 |
| }, |
| { |
| "epoch": 1.7411144232974087, |
| "grad_norm": 0.0911412388086319, |
| "learning_rate": 1.02832674320273e-05, |
| "loss": 0.1156, |
| "step": 950 |
| }, |
| { |
| "epoch": 1.7594588397156614, |
| "grad_norm": 0.11093633621931076, |
| "learning_rate": 8.916368383503781e-06, |
| "loss": 0.1231, |
| "step": 960 |
| }, |
| { |
| "epoch": 1.7594588397156614, |
| "eval_loss": 0.11301500350236893, |
| "eval_runtime": 49.4575, |
| "eval_samples_per_second": 4.65, |
| "eval_steps_per_second": 4.65, |
| "step": 960 |
| }, |
| { |
| "epoch": 1.777803256133914, |
| "grad_norm": 0.08233562856912613, |
| "learning_rate": 7.642683103619686e-06, |
| "loss": 0.1193, |
| "step": 970 |
| }, |
| { |
| "epoch": 1.7961476725521668, |
| "grad_norm": 0.08492106199264526, |
| "learning_rate": 6.463515064830916e-06, |
| "loss": 0.1113, |
| "step": 980 |
| }, |
| { |
| "epoch": 1.8144920889704195, |
| "grad_norm": 0.07636568695306778, |
| "learning_rate": 5.380071011914822e-06, |
| "loss": 0.1229, |
| "step": 990 |
| }, |
| { |
| "epoch": 1.8144920889704195, |
| "eval_loss": 0.11294619739055634, |
| "eval_runtime": 49.6347, |
| "eval_samples_per_second": 4.634, |
| "eval_steps_per_second": 4.634, |
| "step": 990 |
| }, |
| { |
| "epoch": 1.8328365053886724, |
| "grad_norm": 0.08528682589530945, |
| "learning_rate": 4.393459727003701e-06, |
| "loss": 0.1297, |
| "step": 1000 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 1092, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "save_steps": 100, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.4621136161220403e+17, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
