| { | |
| "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": 0.9612148767433503, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7547, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.045584045584045586, | |
| "grad_norm": 0.7997141003635311, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6991, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06837606837606838, | |
| "grad_norm": 0.9121267413614776, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6793, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.09116809116809117, | |
| "grad_norm": 0.86204794791273, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6793, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.11396011396011396, | |
| "grad_norm": 0.8030605128866188, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6755, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.13675213675213677, | |
| "grad_norm": 0.6822414102294643, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6553, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.15954415954415954, | |
| "grad_norm": 0.44808748326570386, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6522, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.18233618233618235, | |
| "grad_norm": 0.3791223515568693, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6551, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.20512820512820512, | |
| "grad_norm": 0.31763684615487103, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6399, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.22792022792022792, | |
| "grad_norm": 0.2981701938215843, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6412, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.25071225071225073, | |
| "grad_norm": 0.3428250211338594, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6325, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.27350427350427353, | |
| "grad_norm": 0.3070161637797585, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6408, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.2962962962962963, | |
| "grad_norm": 0.2888639098751282, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6417, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.3190883190883191, | |
| "grad_norm": 0.3157215590364913, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6439, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.3418803418803419, | |
| "grad_norm": 0.315183712810667, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6364, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.3646723646723647, | |
| "grad_norm": 0.3093972068246558, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6415, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.38746438746438744, | |
| "grad_norm": 0.3495506721530869, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6333, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.41025641025641024, | |
| "grad_norm": 0.29765720327358774, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6389, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.43304843304843305, | |
| "grad_norm": 0.30411341618159515, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6315, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.45584045584045585, | |
| "grad_norm": 0.30635769670111296, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6395, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.47863247863247865, | |
| "grad_norm": 0.30569029005516996, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6358, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.5014245014245015, | |
| "grad_norm": 0.29997414596023386, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6395, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.5242165242165242, | |
| "grad_norm": 0.32466919910130243, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6351, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.5470085470085471, | |
| "grad_norm": 0.30203510436959724, | |
| "learning_rate": 5e-06, | |
| "loss": 0.631, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.5698005698005698, | |
| "grad_norm": 0.3360511348551209, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6359, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.5925925925925926, | |
| "grad_norm": 0.30384498279768646, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6341, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.6153846153846154, | |
| "grad_norm": 0.3116425785281825, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6313, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.6381766381766382, | |
| "grad_norm": 0.3153038886272474, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6421, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.6609686609686609, | |
| "grad_norm": 0.31808293544343713, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6308, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.6837606837606838, | |
| "grad_norm": 0.28939681832659503, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6288, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.7065527065527065, | |
| "grad_norm": 0.2983944157681865, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6287, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.7293447293447294, | |
| "grad_norm": 0.3420169689414905, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6292, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.7521367521367521, | |
| "grad_norm": 0.30105747400759053, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6259, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.7749287749287749, | |
| "grad_norm": 0.3280939111221987, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6317, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.7977207977207977, | |
| "grad_norm": 0.32951471421867023, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6388, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.8205128205128205, | |
| "grad_norm": 0.315499333433496, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6305, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.8433048433048433, | |
| "grad_norm": 0.32711983465794453, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6242, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.8660968660968661, | |
| "grad_norm": 0.314997898279295, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6365, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "grad_norm": 0.329418947505792, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6351, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.9116809116809117, | |
| "grad_norm": 0.29798177397239883, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6383, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.9344729344729344, | |
| "grad_norm": 0.2856728671584142, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6346, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.9572649572649573, | |
| "grad_norm": 0.29857740515231224, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6215, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.98005698005698, | |
| "grad_norm": 0.3412082338616238, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6345, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.9982905982905983, | |
| "eval_loss": 0.6251770257949829, | |
| "eval_runtime": 441.0434, | |
| "eval_samples_per_second": 26.807, | |
| "eval_steps_per_second": 0.419, | |
| "step": 438 | |
| }, | |
| { | |
| "epoch": 1.0034188034188034, | |
| "grad_norm": 0.34750580465330755, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6472, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.0262108262108263, | |
| "grad_norm": 0.32940696566952404, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6018, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.049002849002849, | |
| "grad_norm": 0.3073828015647151, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5955, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.0717948717948718, | |
| "grad_norm": 0.29054718111436684, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5964, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.0945868945868946, | |
| "grad_norm": 0.3066027724866585, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6039, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.1173789173789175, | |
| "grad_norm": 0.3306339455338018, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6089, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.1401709401709401, | |
| "grad_norm": 0.2875501501843064, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5988, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.162962962962963, | |
| "grad_norm": 0.3112163337309756, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5967, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.1857549857549858, | |
| "grad_norm": 0.29388597419002327, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6024, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.2085470085470085, | |
| "grad_norm": 0.31777759323005383, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5953, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.2313390313390313, | |
| "grad_norm": 0.2883969947566689, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6056, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.2541310541310542, | |
| "grad_norm": 0.33200446355362834, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6022, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.2769230769230768, | |
| "grad_norm": 0.29410943053771615, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6037, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.2997150997150997, | |
| "grad_norm": 0.3047896002395558, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5977, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.3225071225071225, | |
| "grad_norm": 0.2733432853678115, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5963, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.3452991452991454, | |
| "grad_norm": 0.29745608895936143, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5959, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.368091168091168, | |
| "grad_norm": 0.34443296432697823, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6016, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.390883190883191, | |
| "grad_norm": 0.32216177400222945, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6016, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.4136752136752135, | |
| "grad_norm": 0.29553893460559305, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6042, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.4364672364672364, | |
| "grad_norm": 0.3186307948607715, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6022, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.4592592592592593, | |
| "grad_norm": 0.30787292724931864, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5971, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.4820512820512821, | |
| "grad_norm": 0.29433199176663055, | |
| "learning_rate": 5e-06, | |
| "loss": 0.595, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.504843304843305, | |
| "grad_norm": 0.2920474652799635, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5946, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.5276353276353276, | |
| "grad_norm": 0.3128521309660125, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6023, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.5504273504273505, | |
| "grad_norm": 0.27310246096174334, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5908, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.573219373219373, | |
| "grad_norm": 0.3289094150246118, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5948, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.596011396011396, | |
| "grad_norm": 0.28819624079339967, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6104, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.6188034188034188, | |
| "grad_norm": 0.31105998668661555, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5974, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.6415954415954417, | |
| "grad_norm": 0.29155905299357293, | |
| "learning_rate": 5e-06, | |
| "loss": 0.602, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.6643874643874645, | |
| "grad_norm": 0.3328932592393567, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5951, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 1.6871794871794872, | |
| "grad_norm": 0.317715798341111, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5962, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.7099715099715098, | |
| "grad_norm": 0.30104161557501546, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5936, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.7327635327635327, | |
| "grad_norm": 0.3112482434088396, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5975, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 1.7555555555555555, | |
| "grad_norm": 0.2974948608112604, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5939, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 1.7783475783475784, | |
| "grad_norm": 0.30935865459333384, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6011, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 1.8011396011396013, | |
| "grad_norm": 0.29331943595400467, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5986, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 1.823931623931624, | |
| "grad_norm": 0.30966536055153665, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5854, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.8467236467236468, | |
| "grad_norm": 0.3063659957255996, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5933, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 1.8695156695156694, | |
| "grad_norm": 0.304443857589856, | |
| "learning_rate": 5e-06, | |
| "loss": 0.591, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 1.8923076923076922, | |
| "grad_norm": 0.32984166821289046, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5948, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 1.915099715099715, | |
| "grad_norm": 0.30553149714241074, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5993, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 1.937891737891738, | |
| "grad_norm": 0.30326624509606676, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5974, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.9606837606837608, | |
| "grad_norm": 0.3120685241482079, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5987, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 1.9834757834757835, | |
| "grad_norm": 0.34328030601005816, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5962, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 1.9994301994301993, | |
| "eval_loss": 0.6187289953231812, | |
| "eval_runtime": 444.8953, | |
| "eval_samples_per_second": 26.575, | |
| "eval_steps_per_second": 0.416, | |
| "step": 877 | |
| }, | |
| { | |
| "epoch": 2.006837606837607, | |
| "grad_norm": 0.3454160859457254, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6155, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 2.0296296296296297, | |
| "grad_norm": 0.3552005634856205, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5547, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 2.0524216524216525, | |
| "grad_norm": 0.3093045958949004, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5698, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.0752136752136754, | |
| "grad_norm": 0.36118578457072004, | |
| "learning_rate": 5e-06, | |
| "loss": 0.568, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 2.098005698005698, | |
| "grad_norm": 0.3341205193056571, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5711, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 2.1207977207977207, | |
| "grad_norm": 0.28498038809642434, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5691, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 2.1435897435897435, | |
| "grad_norm": 0.2961620424528584, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5638, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 2.1663817663817664, | |
| "grad_norm": 0.3058824651199554, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5647, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 2.1891737891737892, | |
| "grad_norm": 0.3112761553094641, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5698, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 2.211965811965812, | |
| "grad_norm": 0.29116238623419916, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5692, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 2.234757834757835, | |
| "grad_norm": 0.2872550645325756, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5588, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 2.2575498575498574, | |
| "grad_norm": 0.3161679027238176, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5679, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 2.2803418803418802, | |
| "grad_norm": 0.30130441531950675, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5682, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.303133903133903, | |
| "grad_norm": 0.3262470875137944, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5657, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 2.325925925925926, | |
| "grad_norm": 0.3131869592712844, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5688, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 2.348717948717949, | |
| "grad_norm": 0.3446939006044128, | |
| "learning_rate": 5e-06, | |
| "loss": 0.57, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 2.3715099715099717, | |
| "grad_norm": 0.2975329889141797, | |
| "learning_rate": 5e-06, | |
| "loss": 0.568, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 2.394301994301994, | |
| "grad_norm": 0.30352208364705696, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5674, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 2.417094017094017, | |
| "grad_norm": 0.2996629983248489, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5756, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 2.43988603988604, | |
| "grad_norm": 0.3061792748857846, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5785, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 2.4626780626780627, | |
| "grad_norm": 0.30277334361474345, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5738, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 2.4854700854700855, | |
| "grad_norm": 0.30079831640965243, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5714, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 2.5082621082621084, | |
| "grad_norm": 0.3065001118477464, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5779, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.5310541310541312, | |
| "grad_norm": 0.3182762867488757, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5714, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 2.5538461538461537, | |
| "grad_norm": 0.3094471604825108, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5695, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 2.5766381766381765, | |
| "grad_norm": 0.30223082344106555, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5689, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 2.5994301994301994, | |
| "grad_norm": 0.3131152439981633, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5686, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 2.6222222222222222, | |
| "grad_norm": 0.30148860802102845, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5689, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 2.645014245014245, | |
| "grad_norm": 0.31078780436205244, | |
| "learning_rate": 5e-06, | |
| "loss": 0.57, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 2.667806267806268, | |
| "grad_norm": 0.2922233784416252, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5728, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 2.690598290598291, | |
| "grad_norm": 0.29534794980699774, | |
| "learning_rate": 5e-06, | |
| "loss": 0.568, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 2.7133903133903132, | |
| "grad_norm": 0.28935604553126804, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5691, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 2.736182336182336, | |
| "grad_norm": 0.28546532066063657, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5722, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.758974358974359, | |
| "grad_norm": 0.28928994720672957, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5756, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 2.781766381766382, | |
| "grad_norm": 0.28622119127178924, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5655, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 2.8045584045584047, | |
| "grad_norm": 0.29572922347942976, | |
| "learning_rate": 5e-06, | |
| "loss": 0.564, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 2.827350427350427, | |
| "grad_norm": 0.31181265070196107, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5788, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 2.8501424501424504, | |
| "grad_norm": 0.29823473240720333, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5754, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 2.872934472934473, | |
| "grad_norm": 0.2959643746098219, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5726, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 2.8957264957264957, | |
| "grad_norm": 0.2986760217005674, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5735, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 2.9185185185185185, | |
| "grad_norm": 0.28706540203736464, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5637, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 2.9413105413105414, | |
| "grad_norm": 0.3031414521350752, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5639, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 2.9641025641025642, | |
| "grad_norm": 0.34532907399831536, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5651, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 2.9868945868945866, | |
| "grad_norm": 0.309464903284651, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5749, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 2.996011396011396, | |
| "eval_loss": 0.618689239025116, | |
| "eval_runtime": 445.6352, | |
| "eval_samples_per_second": 26.531, | |
| "eval_steps_per_second": 0.415, | |
| "step": 1314 | |
| }, | |
| { | |
| "epoch": 2.996011396011396, | |
| "step": 1314, | |
| "total_flos": 2755219238682624.0, | |
| "train_loss": 0.6040235166317434, | |
| "train_runtime": 70686.1657, | |
| "train_samples_per_second": 9.533, | |
| "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 | |
| } | |