| { | |
| "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": 0.9913745871891702, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7541, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.045584045584045586, | |
| "grad_norm": 0.8058329212680375, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6991, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06837606837606838, | |
| "grad_norm": 0.9069211145981375, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6793, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.09116809116809117, | |
| "grad_norm": 0.8570335892214022, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6794, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.11396011396011396, | |
| "grad_norm": 0.802843687947037, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6756, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.13675213675213677, | |
| "grad_norm": 0.6873049350374213, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6554, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.15954415954415954, | |
| "grad_norm": 0.45466439096013433, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6523, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.18233618233618235, | |
| "grad_norm": 0.38146601944331043, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6552, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.20512820512820512, | |
| "grad_norm": 0.3162527990101672, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6399, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.22792022792022792, | |
| "grad_norm": 0.30011589794037985, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6412, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.25071225071225073, | |
| "grad_norm": 0.34195750339372744, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6325, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.27350427350427353, | |
| "grad_norm": 0.3059511350844825, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6408, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.2962962962962963, | |
| "grad_norm": 0.2940710239242246, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6417, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.3190883190883191, | |
| "grad_norm": 0.3057782824758884, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6439, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.3418803418803419, | |
| "grad_norm": 0.30760783816406423, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6363, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.3646723646723647, | |
| "grad_norm": 0.31217901075866494, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6415, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.38746438746438744, | |
| "grad_norm": 0.35091381824914636, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6333, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.41025641025641024, | |
| "grad_norm": 0.3049235643850345, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6389, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.43304843304843305, | |
| "grad_norm": 0.3016434822974565, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6315, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.45584045584045585, | |
| "grad_norm": 0.3039253378744192, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6395, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.47863247863247865, | |
| "grad_norm": 0.3070300337406078, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6358, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.5014245014245015, | |
| "grad_norm": 0.30097108255485006, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6395, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.5242165242165242, | |
| "grad_norm": 0.329134454431384, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6351, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.5470085470085471, | |
| "grad_norm": 0.29593738514275947, | |
| "learning_rate": 5e-06, | |
| "loss": 0.631, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.5698005698005698, | |
| "grad_norm": 0.34016946025375455, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6359, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.5925925925925926, | |
| "grad_norm": 0.3009965016963588, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6341, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.6153846153846154, | |
| "grad_norm": 0.30901913627951677, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6313, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.6381766381766382, | |
| "grad_norm": 0.3192044357041116, | |
| "learning_rate": 5e-06, | |
| "loss": 0.642, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.6609686609686609, | |
| "grad_norm": 0.31849090452354817, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6307, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.6837606837606838, | |
| "grad_norm": 0.2858936470531545, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6288, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.7065527065527065, | |
| "grad_norm": 0.29488117187305224, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6286, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.7293447293447294, | |
| "grad_norm": 0.34145959399461273, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6292, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.7521367521367521, | |
| "grad_norm": 0.30384225514426305, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6258, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.7749287749287749, | |
| "grad_norm": 0.32059900970096983, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6317, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.7977207977207977, | |
| "grad_norm": 0.3312783214270119, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6388, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.8205128205128205, | |
| "grad_norm": 0.31621539083663247, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6305, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.8433048433048433, | |
| "grad_norm": 0.3350244102238827, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6243, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.8660968660968661, | |
| "grad_norm": 0.3191170035723703, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6366, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "grad_norm": 0.33723812739187703, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6351, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.9116809116809117, | |
| "grad_norm": 0.2987527325131014, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6383, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.9344729344729344, | |
| "grad_norm": 0.28687146003488806, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6346, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.9572649572649573, | |
| "grad_norm": 0.3037008334110837, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6215, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.98005698005698, | |
| "grad_norm": 0.3474156352959759, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6345, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.9982905982905983, | |
| "eval_loss": 0.6251600980758667, | |
| "eval_runtime": 443.2135, | |
| "eval_samples_per_second": 26.676, | |
| "eval_steps_per_second": 0.417, | |
| "step": 438 | |
| }, | |
| { | |
| "epoch": 1.0034188034188034, | |
| "grad_norm": 0.3533678798683419, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6472, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.0262108262108263, | |
| "grad_norm": 0.32202778229047824, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6018, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.049002849002849, | |
| "grad_norm": 0.3099738953428901, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5955, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.0717948717948718, | |
| "grad_norm": 0.2917005940911086, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5964, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.0945868945868946, | |
| "grad_norm": 0.30954587571192854, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6038, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.1173789173789175, | |
| "grad_norm": 0.33040562688826836, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6089, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.1401709401709401, | |
| "grad_norm": 0.2902775524301021, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5988, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.162962962962963, | |
| "grad_norm": 0.31529234056987576, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5967, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.1857549857549858, | |
| "grad_norm": 0.29241487696095003, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6023, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.2085470085470085, | |
| "grad_norm": 0.32162741616325297, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5953, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.2313390313390313, | |
| "grad_norm": 0.2878063689469862, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6056, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.2541310541310542, | |
| "grad_norm": 0.33297683489558294, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6022, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.2769230769230768, | |
| "grad_norm": 0.29314536415428305, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6038, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.2997150997150997, | |
| "grad_norm": 0.2998764843700674, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5977, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.3225071225071225, | |
| "grad_norm": 0.270867646623825, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5963, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.3452991452991454, | |
| "grad_norm": 0.2948227631183101, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5959, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.368091168091168, | |
| "grad_norm": 0.35801019319924016, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6016, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.390883190883191, | |
| "grad_norm": 0.320183948419336, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6016, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.4136752136752135, | |
| "grad_norm": 0.2918318011697476, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6042, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.4364672364672364, | |
| "grad_norm": 0.31953623090161754, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6022, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.4592592592592593, | |
| "grad_norm": 0.30535411178887806, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5971, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.4820512820512821, | |
| "grad_norm": 0.295960971760162, | |
| "learning_rate": 5e-06, | |
| "loss": 0.595, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.504843304843305, | |
| "grad_norm": 0.29076482419470795, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5946, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.5276353276353276, | |
| "grad_norm": 0.3167985158090234, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6023, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.5504273504273505, | |
| "grad_norm": 0.27426253896083747, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5909, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.573219373219373, | |
| "grad_norm": 0.3275859560806823, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5948, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.596011396011396, | |
| "grad_norm": 0.28728466772531613, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6104, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.6188034188034188, | |
| "grad_norm": 0.30856027035930683, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5974, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.6415954415954417, | |
| "grad_norm": 0.2914661491086178, | |
| "learning_rate": 5e-06, | |
| "loss": 0.602, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.6643874643874645, | |
| "grad_norm": 0.3321365462012038, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5951, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 1.6871794871794872, | |
| "grad_norm": 0.3266418712549308, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5962, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.7099715099715098, | |
| "grad_norm": 0.29865420590571234, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5936, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.7327635327635327, | |
| "grad_norm": 0.30909993073968745, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5974, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 1.7555555555555555, | |
| "grad_norm": 0.296288918799106, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5939, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 1.7783475783475784, | |
| "grad_norm": 0.3078006114107322, | |
| "learning_rate": 5e-06, | |
| "loss": 0.601, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 1.8011396011396013, | |
| "grad_norm": 0.29745486204451266, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5986, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 1.823931623931624, | |
| "grad_norm": 0.3090839139318477, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5854, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.8467236467236468, | |
| "grad_norm": 0.31222782536612537, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5932, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 1.8695156695156694, | |
| "grad_norm": 0.30374349519238386, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5909, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 1.8923076923076922, | |
| "grad_norm": 0.32980961664440184, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5948, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 1.915099715099715, | |
| "grad_norm": 0.30826930305804884, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5993, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 1.937891737891738, | |
| "grad_norm": 0.3002232515157311, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5974, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.9606837606837608, | |
| "grad_norm": 0.3086823988093375, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5987, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 1.9834757834757835, | |
| "grad_norm": 0.35370185998380055, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5962, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 1.9994301994301993, | |
| "eval_loss": 0.6187165379524231, | |
| "eval_runtime": 440.7632, | |
| "eval_samples_per_second": 26.824, | |
| "eval_steps_per_second": 0.42, | |
| "step": 877 | |
| }, | |
| { | |
| "epoch": 2.006837606837607, | |
| "grad_norm": 0.33992957291872394, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6156, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 2.0296296296296297, | |
| "grad_norm": 0.3476097020988058, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5549, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 2.0524216524216525, | |
| "grad_norm": 0.3114366402689008, | |
| "learning_rate": 5e-06, | |
| "loss": 0.57, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.0752136752136754, | |
| "grad_norm": 0.3495949626005044, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5682, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 2.098005698005698, | |
| "grad_norm": 0.3296798083770889, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5712, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 2.1207977207977207, | |
| "grad_norm": 0.2883162659897996, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5692, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 2.1435897435897435, | |
| "grad_norm": 0.3034432481059968, | |
| "learning_rate": 5e-06, | |
| "loss": 0.564, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 2.1663817663817664, | |
| "grad_norm": 0.30773382289616413, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5649, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 2.1891737891737892, | |
| "grad_norm": 0.30915073035475893, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5699, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 2.211965811965812, | |
| "grad_norm": 0.2912445385558842, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5694, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 2.234757834757835, | |
| "grad_norm": 0.2877045347015826, | |
| "learning_rate": 5e-06, | |
| "loss": 0.559, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 2.2575498575498574, | |
| "grad_norm": 0.32319066858316836, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5681, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 2.2803418803418802, | |
| "grad_norm": 0.3015677882163033, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5684, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.303133903133903, | |
| "grad_norm": 0.32127984336455057, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5658, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 2.325925925925926, | |
| "grad_norm": 0.3134730626862636, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5689, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 2.348717948717949, | |
| "grad_norm": 0.3502864498915539, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5702, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 2.3715099715099717, | |
| "grad_norm": 0.3016875271736186, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5682, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 2.394301994301994, | |
| "grad_norm": 0.30479557615064035, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5675, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 2.417094017094017, | |
| "grad_norm": 0.2950094635886404, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5758, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 2.43988603988604, | |
| "grad_norm": 0.3010416504497748, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5786, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 2.4626780626780627, | |
| "grad_norm": 0.3028713187472215, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5739, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 2.4854700854700855, | |
| "grad_norm": 0.2990558641345095, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5716, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 2.5082621082621084, | |
| "grad_norm": 0.3067918103380767, | |
| "learning_rate": 5e-06, | |
| "loss": 0.578, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.5310541310541312, | |
| "grad_norm": 0.3121825313770296, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5715, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 2.5538461538461537, | |
| "grad_norm": 0.3084726512296357, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5696, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 2.5766381766381765, | |
| "grad_norm": 0.30678468475123843, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5691, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 2.5994301994301994, | |
| "grad_norm": 0.317462950476869, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5687, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 2.6222222222222222, | |
| "grad_norm": 0.3031144808585946, | |
| "learning_rate": 5e-06, | |
| "loss": 0.569, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 2.645014245014245, | |
| "grad_norm": 0.3084015952636802, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5701, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 2.667806267806268, | |
| "grad_norm": 0.2942323715360351, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5729, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 2.690598290598291, | |
| "grad_norm": 0.29381894792448754, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5681, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 2.7133903133903132, | |
| "grad_norm": 0.29252947046397587, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5691, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 2.736182336182336, | |
| "grad_norm": 0.2898735014405475, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5724, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.758974358974359, | |
| "grad_norm": 0.28602751496070977, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5757, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 2.781766381766382, | |
| "grad_norm": 0.2868165392206672, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5656, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 2.8045584045584047, | |
| "grad_norm": 0.2953535674855941, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5641, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 2.827350427350427, | |
| "grad_norm": 0.30647914203545074, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5789, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 2.8501424501424504, | |
| "grad_norm": 0.30458940735390855, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5755, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 2.872934472934473, | |
| "grad_norm": 0.2959720170100575, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5727, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 2.8957264957264957, | |
| "grad_norm": 0.3049006876264681, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5736, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 2.9185185185185185, | |
| "grad_norm": 0.28843579399797875, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5638, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 2.9413105413105414, | |
| "grad_norm": 0.2973335894890414, | |
| "learning_rate": 5e-06, | |
| "loss": 0.564, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 2.9641025641025642, | |
| "grad_norm": 0.3503572385426782, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5652, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 2.9868945868945866, | |
| "grad_norm": 0.30675912607811706, | |
| "learning_rate": 5e-06, | |
| "loss": 0.575, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 2.996011396011396, | |
| "eval_loss": 0.6186762452125549, | |
| "eval_runtime": 442.5165, | |
| "eval_samples_per_second": 26.718, | |
| "eval_steps_per_second": 0.418, | |
| "step": 1314 | |
| }, | |
| { | |
| "epoch": 2.996011396011396, | |
| "step": 1314, | |
| "total_flos": 2755219238682624.0, | |
| "train_loss": 0.6040605018127999, | |
| "train_runtime": 70543.6764, | |
| "train_samples_per_second": 9.552, | |
| "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 | |
| } | |