| { | |
| "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": 13.82025069118623, | |
| "learning_rate": 3.787878787878788e-07, | |
| "loss": 0.8308, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.045584045584045586, | |
| "grad_norm": 5.1319737789095115, | |
| "learning_rate": 7.575757575757576e-07, | |
| "loss": 0.8105, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06837606837606838, | |
| "grad_norm": 1.5861641573263008, | |
| "learning_rate": 1.1363636363636364e-06, | |
| "loss": 0.755, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.09116809116809117, | |
| "grad_norm": 1.0106444704636741, | |
| "learning_rate": 1.5151515151515152e-06, | |
| "loss": 0.7305, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.11396011396011396, | |
| "grad_norm": 0.9175747364460073, | |
| "learning_rate": 1.8939393939393941e-06, | |
| "loss": 0.7157, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.13675213675213677, | |
| "grad_norm": 0.858266416727724, | |
| "learning_rate": 2.2727272727272728e-06, | |
| "loss": 0.6902, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.15954415954415954, | |
| "grad_norm": 0.731139318802147, | |
| "learning_rate": 2.6515151515151514e-06, | |
| "loss": 0.6845, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.18233618233618235, | |
| "grad_norm": 0.8705067202079199, | |
| "learning_rate": 3.0303030303030305e-06, | |
| "loss": 0.6844, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.20512820512820512, | |
| "grad_norm": 0.7992611765746963, | |
| "learning_rate": 3.409090909090909e-06, | |
| "loss": 0.6652, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.22792022792022792, | |
| "grad_norm": 0.8520679580860977, | |
| "learning_rate": 3.7878787878787882e-06, | |
| "loss": 0.6616, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.25071225071225073, | |
| "grad_norm": 0.6676395021182464, | |
| "learning_rate": 4.166666666666667e-06, | |
| "loss": 0.6479, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.27350427350427353, | |
| "grad_norm": 0.5238136155306522, | |
| "learning_rate": 4.5454545454545455e-06, | |
| "loss": 0.6519, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.2962962962962963, | |
| "grad_norm": 0.3749174945670082, | |
| "learning_rate": 4.924242424242425e-06, | |
| "loss": 0.6501, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.3190883190883191, | |
| "grad_norm": 0.34219492738596635, | |
| "learning_rate": 4.966159052453469e-06, | |
| "loss": 0.6506, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.3418803418803419, | |
| "grad_norm": 0.3221830208753367, | |
| "learning_rate": 4.923857868020305e-06, | |
| "loss": 0.6424, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.3646723646723647, | |
| "grad_norm": 0.3211404670331441, | |
| "learning_rate": 4.881556683587141e-06, | |
| "loss": 0.6469, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.38746438746438744, | |
| "grad_norm": 0.36044993850226115, | |
| "learning_rate": 4.839255499153977e-06, | |
| "loss": 0.6384, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.41025641025641024, | |
| "grad_norm": 0.30662481311131046, | |
| "learning_rate": 4.796954314720812e-06, | |
| "loss": 0.6436, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.43304843304843305, | |
| "grad_norm": 0.30073652663910616, | |
| "learning_rate": 4.754653130287649e-06, | |
| "loss": 0.6357, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.45584045584045585, | |
| "grad_norm": 0.3159734259222124, | |
| "learning_rate": 4.712351945854484e-06, | |
| "loss": 0.6436, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.47863247863247865, | |
| "grad_norm": 0.30021799995563564, | |
| "learning_rate": 4.67005076142132e-06, | |
| "loss": 0.6397, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.5014245014245015, | |
| "grad_norm": 0.31027086609771876, | |
| "learning_rate": 4.6277495769881554e-06, | |
| "loss": 0.6433, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.5242165242165242, | |
| "grad_norm": 0.325996231603359, | |
| "learning_rate": 4.585448392554992e-06, | |
| "loss": 0.6386, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.5470085470085471, | |
| "grad_norm": 0.30447517334932556, | |
| "learning_rate": 4.543147208121828e-06, | |
| "loss": 0.6344, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.5698005698005698, | |
| "grad_norm": 0.31759320117316103, | |
| "learning_rate": 4.500846023688664e-06, | |
| "loss": 0.6392, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.5925925925925926, | |
| "grad_norm": 0.300042168313145, | |
| "learning_rate": 4.4585448392555e-06, | |
| "loss": 0.6373, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.6153846153846154, | |
| "grad_norm": 0.3103670553421643, | |
| "learning_rate": 4.4162436548223355e-06, | |
| "loss": 0.6343, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.6381766381766382, | |
| "grad_norm": 0.31371459349820763, | |
| "learning_rate": 4.373942470389172e-06, | |
| "loss": 0.645, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.6609686609686609, | |
| "grad_norm": 0.3177909350422278, | |
| "learning_rate": 4.331641285956007e-06, | |
| "loss": 0.6336, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.6837606837606838, | |
| "grad_norm": 0.2863080125345834, | |
| "learning_rate": 4.289340101522843e-06, | |
| "loss": 0.6316, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.7065527065527065, | |
| "grad_norm": 0.2967357656574432, | |
| "learning_rate": 4.2470389170896785e-06, | |
| "loss": 0.6314, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.7293447293447294, | |
| "grad_norm": 0.30731521673513923, | |
| "learning_rate": 4.204737732656515e-06, | |
| "loss": 0.6319, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.7521367521367521, | |
| "grad_norm": 0.2853284520723167, | |
| "learning_rate": 4.162436548223351e-06, | |
| "loss": 0.6285, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.7749287749287749, | |
| "grad_norm": 0.29173766094469944, | |
| "learning_rate": 4.120135363790186e-06, | |
| "loss": 0.6342, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.7977207977207977, | |
| "grad_norm": 0.31186096126009083, | |
| "learning_rate": 4.0778341793570224e-06, | |
| "loss": 0.6413, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.8205128205128205, | |
| "grad_norm": 0.31433308913944874, | |
| "learning_rate": 4.035532994923858e-06, | |
| "loss": 0.633, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.8433048433048433, | |
| "grad_norm": 0.30255898197587633, | |
| "learning_rate": 3.993231810490694e-06, | |
| "loss": 0.6267, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.8660968660968661, | |
| "grad_norm": 0.31742329834518057, | |
| "learning_rate": 3.95093062605753e-06, | |
| "loss": 0.639, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "grad_norm": 0.29347055532062, | |
| "learning_rate": 3.9086294416243655e-06, | |
| "loss": 0.6375, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.9116809116809117, | |
| "grad_norm": 0.304756355630385, | |
| "learning_rate": 3.866328257191202e-06, | |
| "loss": 0.6407, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.9344729344729344, | |
| "grad_norm": 0.27202304716855863, | |
| "learning_rate": 3.824027072758038e-06, | |
| "loss": 0.6369, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.9572649572649573, | |
| "grad_norm": 0.29824485775957277, | |
| "learning_rate": 3.7817258883248736e-06, | |
| "loss": 0.6238, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.98005698005698, | |
| "grad_norm": 0.316389910270352, | |
| "learning_rate": 3.7394247038917094e-06, | |
| "loss": 0.6369, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.9982905982905983, | |
| "eval_loss": 0.6274411082267761, | |
| "eval_runtime": 441.3291, | |
| "eval_samples_per_second": 26.79, | |
| "eval_steps_per_second": 0.419, | |
| "step": 438 | |
| }, | |
| { | |
| "epoch": 1.0034188034188034, | |
| "grad_norm": 0.2974179402853732, | |
| "learning_rate": 3.697123519458545e-06, | |
| "loss": 0.6504, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.0262108262108263, | |
| "grad_norm": 0.3328108426705853, | |
| "learning_rate": 3.654822335025381e-06, | |
| "loss": 0.6094, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.049002849002849, | |
| "grad_norm": 0.3468657832861117, | |
| "learning_rate": 3.612521150592217e-06, | |
| "loss": 0.603, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.0717948717948718, | |
| "grad_norm": 0.28130223618914374, | |
| "learning_rate": 3.5702199661590524e-06, | |
| "loss": 0.604, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.0945868945868946, | |
| "grad_norm": 0.2865481944718312, | |
| "learning_rate": 3.5279187817258886e-06, | |
| "loss": 0.6114, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.1173789173789175, | |
| "grad_norm": 0.3093784116984744, | |
| "learning_rate": 3.4856175972927248e-06, | |
| "loss": 0.6165, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.1401709401709401, | |
| "grad_norm": 0.27699299838421976, | |
| "learning_rate": 3.4433164128595605e-06, | |
| "loss": 0.6062, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.162962962962963, | |
| "grad_norm": 0.3008059331559106, | |
| "learning_rate": 3.4010152284263963e-06, | |
| "loss": 0.6039, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.1857549857549858, | |
| "grad_norm": 0.2944027438621198, | |
| "learning_rate": 3.358714043993232e-06, | |
| "loss": 0.6095, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.2085470085470085, | |
| "grad_norm": 0.28077870584088543, | |
| "learning_rate": 3.3164128595600682e-06, | |
| "loss": 0.6025, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.2313390313390313, | |
| "grad_norm": 0.30300062147380974, | |
| "learning_rate": 3.2741116751269036e-06, | |
| "loss": 0.6127, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.2541310541310542, | |
| "grad_norm": 0.2884948651021871, | |
| "learning_rate": 3.2318104906937397e-06, | |
| "loss": 0.6091, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.2769230769230768, | |
| "grad_norm": 0.29423227376682365, | |
| "learning_rate": 3.1895093062605755e-06, | |
| "loss": 0.6107, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.2997150997150997, | |
| "grad_norm": 0.2883105301897019, | |
| "learning_rate": 3.1472081218274113e-06, | |
| "loss": 0.6046, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.3225071225071225, | |
| "grad_norm": 0.2669594766065209, | |
| "learning_rate": 3.1049069373942474e-06, | |
| "loss": 0.6029, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.3452991452991454, | |
| "grad_norm": 0.2705243942286286, | |
| "learning_rate": 3.062605752961083e-06, | |
| "loss": 0.6028, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.368091168091168, | |
| "grad_norm": 0.3071464216067808, | |
| "learning_rate": 3.0203045685279194e-06, | |
| "loss": 0.6083, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.390883190883191, | |
| "grad_norm": 0.28705868161520925, | |
| "learning_rate": 2.9780033840947547e-06, | |
| "loss": 0.6084, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.4136752136752135, | |
| "grad_norm": 0.28840712136018964, | |
| "learning_rate": 2.935702199661591e-06, | |
| "loss": 0.611, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.4364672364672364, | |
| "grad_norm": 0.27939993462491286, | |
| "learning_rate": 2.8934010152284262e-06, | |
| "loss": 0.6088, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.4592592592592593, | |
| "grad_norm": 0.29201487779439644, | |
| "learning_rate": 2.8510998307952624e-06, | |
| "loss": 0.6036, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.4820512820512821, | |
| "grad_norm": 0.2962841211526053, | |
| "learning_rate": 2.808798646362098e-06, | |
| "loss": 0.6013, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.504843304843305, | |
| "grad_norm": 0.275474422497229, | |
| "learning_rate": 2.7664974619289344e-06, | |
| "loss": 0.6012, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.5276353276353276, | |
| "grad_norm": 0.2951169219112843, | |
| "learning_rate": 2.72419627749577e-06, | |
| "loss": 0.6088, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.5504273504273505, | |
| "grad_norm": 0.2664647901919578, | |
| "learning_rate": 2.681895093062606e-06, | |
| "loss": 0.5973, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.573219373219373, | |
| "grad_norm": 0.3278845948919461, | |
| "learning_rate": 2.639593908629442e-06, | |
| "loss": 0.6012, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.596011396011396, | |
| "grad_norm": 0.2834806718036075, | |
| "learning_rate": 2.5972927241962774e-06, | |
| "loss": 0.617, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.6188034188034188, | |
| "grad_norm": 0.2834945453709173, | |
| "learning_rate": 2.5549915397631136e-06, | |
| "loss": 0.6039, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.6415954415954417, | |
| "grad_norm": 0.2873120009439402, | |
| "learning_rate": 2.5126903553299493e-06, | |
| "loss": 0.6083, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.6643874643874645, | |
| "grad_norm": 0.29239006173806986, | |
| "learning_rate": 2.470389170896785e-06, | |
| "loss": 0.6014, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 1.6871794871794872, | |
| "grad_norm": 0.28777240203969917, | |
| "learning_rate": 2.4280879864636213e-06, | |
| "loss": 0.6023, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.7099715099715098, | |
| "grad_norm": 0.287251015630762, | |
| "learning_rate": 2.385786802030457e-06, | |
| "loss": 0.5995, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.7327635327635327, | |
| "grad_norm": 0.2833754954830982, | |
| "learning_rate": 2.343485617597293e-06, | |
| "loss": 0.6038, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 1.7555555555555555, | |
| "grad_norm": 0.29523465034573726, | |
| "learning_rate": 2.3011844331641286e-06, | |
| "loss": 0.6003, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 1.7783475783475784, | |
| "grad_norm": 0.2835164587155957, | |
| "learning_rate": 2.2588832487309648e-06, | |
| "loss": 0.6074, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 1.8011396011396013, | |
| "grad_norm": 0.2756554371766609, | |
| "learning_rate": 2.2165820642978005e-06, | |
| "loss": 0.6048, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 1.823931623931624, | |
| "grad_norm": 0.28250442965630257, | |
| "learning_rate": 2.1742808798646363e-06, | |
| "loss": 0.5916, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.8467236467236468, | |
| "grad_norm": 0.2972957948191103, | |
| "learning_rate": 2.1319796954314725e-06, | |
| "loss": 0.5995, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 1.8695156695156694, | |
| "grad_norm": 0.28171695683839987, | |
| "learning_rate": 2.0896785109983082e-06, | |
| "loss": 0.5972, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 1.8923076923076922, | |
| "grad_norm": 0.27265878199095367, | |
| "learning_rate": 2.047377326565144e-06, | |
| "loss": 0.601, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 1.915099715099715, | |
| "grad_norm": 0.2843738370580399, | |
| "learning_rate": 2.0050761421319797e-06, | |
| "loss": 0.6057, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 1.937891737891738, | |
| "grad_norm": 0.2867696310340715, | |
| "learning_rate": 1.9627749576988155e-06, | |
| "loss": 0.6036, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.9606837606837608, | |
| "grad_norm": 0.2783755363399772, | |
| "learning_rate": 1.9204737732656517e-06, | |
| "loss": 0.6048, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 1.9834757834757835, | |
| "grad_norm": 0.30245355783375416, | |
| "learning_rate": 1.8781725888324874e-06, | |
| "loss": 0.6024, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 1.9994301994301993, | |
| "eval_loss": 0.6210305690765381, | |
| "eval_runtime": 444.0845, | |
| "eval_samples_per_second": 26.623, | |
| "eval_steps_per_second": 0.417, | |
| "step": 877 | |
| }, | |
| { | |
| "epoch": 2.006837606837607, | |
| "grad_norm": 0.2701897779005862, | |
| "learning_rate": 1.8358714043993234e-06, | |
| "loss": 0.6254, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 2.0296296296296297, | |
| "grad_norm": 0.2822641812974091, | |
| "learning_rate": 1.7935702199661592e-06, | |
| "loss": 0.5721, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 2.0524216524216525, | |
| "grad_norm": 0.28903196675368076, | |
| "learning_rate": 1.7512690355329951e-06, | |
| "loss": 0.5881, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.0752136752136754, | |
| "grad_norm": 0.3078673635479466, | |
| "learning_rate": 1.708967851099831e-06, | |
| "loss": 0.586, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 2.098005698005698, | |
| "grad_norm": 0.2785177807663215, | |
| "learning_rate": 1.6666666666666667e-06, | |
| "loss": 0.589, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 2.1207977207977207, | |
| "grad_norm": 0.2774331957705802, | |
| "learning_rate": 1.6243654822335026e-06, | |
| "loss": 0.5866, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 2.1435897435897435, | |
| "grad_norm": 0.2798671208355392, | |
| "learning_rate": 1.5820642978003386e-06, | |
| "loss": 0.5812, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 2.1663817663817664, | |
| "grad_norm": 0.27132799501645843, | |
| "learning_rate": 1.5397631133671746e-06, | |
| "loss": 0.5822, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 2.1891737891737892, | |
| "grad_norm": 0.277820696734235, | |
| "learning_rate": 1.4974619289340103e-06, | |
| "loss": 0.5871, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 2.211965811965812, | |
| "grad_norm": 0.27608147560234303, | |
| "learning_rate": 1.455160744500846e-06, | |
| "loss": 0.5859, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 2.234757834757835, | |
| "grad_norm": 0.285099746375909, | |
| "learning_rate": 1.412859560067682e-06, | |
| "loss": 0.5755, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 2.2575498575498574, | |
| "grad_norm": 0.2834009068864172, | |
| "learning_rate": 1.3705583756345178e-06, | |
| "loss": 0.5845, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 2.2803418803418802, | |
| "grad_norm": 0.2659315972803874, | |
| "learning_rate": 1.3282571912013536e-06, | |
| "loss": 0.5847, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.303133903133903, | |
| "grad_norm": 0.2842998910857186, | |
| "learning_rate": 1.2859560067681896e-06, | |
| "loss": 0.5822, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 2.325925925925926, | |
| "grad_norm": 0.2925272042167459, | |
| "learning_rate": 1.2436548223350255e-06, | |
| "loss": 0.5851, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 2.348717948717949, | |
| "grad_norm": 0.2730212322505555, | |
| "learning_rate": 1.2013536379018613e-06, | |
| "loss": 0.5866, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 2.3715099715099717, | |
| "grad_norm": 0.2659809610224369, | |
| "learning_rate": 1.1590524534686973e-06, | |
| "loss": 0.5841, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 2.394301994301994, | |
| "grad_norm": 0.2887950743404575, | |
| "learning_rate": 1.116751269035533e-06, | |
| "loss": 0.5834, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 2.417094017094017, | |
| "grad_norm": 0.2748521691064405, | |
| "learning_rate": 1.074450084602369e-06, | |
| "loss": 0.5917, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 2.43988603988604, | |
| "grad_norm": 0.2647499378345614, | |
| "learning_rate": 1.0321489001692048e-06, | |
| "loss": 0.5948, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 2.4626780626780627, | |
| "grad_norm": 0.27739116649461487, | |
| "learning_rate": 9.898477157360407e-07, | |
| "loss": 0.59, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 2.4854700854700855, | |
| "grad_norm": 0.264670636993555, | |
| "learning_rate": 9.475465313028766e-07, | |
| "loss": 0.5873, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 2.5082621082621084, | |
| "grad_norm": 0.3050069220099809, | |
| "learning_rate": 9.052453468697125e-07, | |
| "loss": 0.5941, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.5310541310541312, | |
| "grad_norm": 0.2673821103230609, | |
| "learning_rate": 8.629441624365482e-07, | |
| "loss": 0.587, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 2.5538461538461537, | |
| "grad_norm": 0.26862153961949736, | |
| "learning_rate": 8.206429780033842e-07, | |
| "loss": 0.5852, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 2.5766381766381765, | |
| "grad_norm": 0.27402673827658036, | |
| "learning_rate": 7.7834179357022e-07, | |
| "loss": 0.5845, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 2.5994301994301994, | |
| "grad_norm": 0.27126620560352377, | |
| "learning_rate": 7.360406091370559e-07, | |
| "loss": 0.5842, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 2.6222222222222222, | |
| "grad_norm": 0.2795326890639239, | |
| "learning_rate": 6.937394247038917e-07, | |
| "loss": 0.5843, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 2.645014245014245, | |
| "grad_norm": 0.2755605775212532, | |
| "learning_rate": 6.514382402707276e-07, | |
| "loss": 0.585, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 2.667806267806268, | |
| "grad_norm": 0.2693489818532254, | |
| "learning_rate": 6.091370558375635e-07, | |
| "loss": 0.5883, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 2.690598290598291, | |
| "grad_norm": 0.27046692244308457, | |
| "learning_rate": 5.668358714043994e-07, | |
| "loss": 0.5833, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 2.7133903133903132, | |
| "grad_norm": 0.26289588127700764, | |
| "learning_rate": 5.245346869712352e-07, | |
| "loss": 0.5842, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 2.736182336182336, | |
| "grad_norm": 0.26779284153011157, | |
| "learning_rate": 4.822335025380711e-07, | |
| "loss": 0.5874, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.758974358974359, | |
| "grad_norm": 0.2635717002104139, | |
| "learning_rate": 4.39932318104907e-07, | |
| "loss": 0.5906, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 2.781766381766382, | |
| "grad_norm": 0.2619116219484112, | |
| "learning_rate": 3.9763113367174284e-07, | |
| "loss": 0.5803, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 2.8045584045584047, | |
| "grad_norm": 0.255714340845448, | |
| "learning_rate": 3.553299492385787e-07, | |
| "loss": 0.5788, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 2.827350427350427, | |
| "grad_norm": 0.2678196093330931, | |
| "learning_rate": 3.1302876480541457e-07, | |
| "loss": 0.5938, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 2.8501424501424504, | |
| "grad_norm": 0.2603561895360124, | |
| "learning_rate": 2.7072758037225044e-07, | |
| "loss": 0.5907, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 2.872934472934473, | |
| "grad_norm": 0.2659043115994451, | |
| "learning_rate": 2.284263959390863e-07, | |
| "loss": 0.5877, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 2.8957264957264957, | |
| "grad_norm": 0.2668875408756563, | |
| "learning_rate": 1.8612521150592217e-07, | |
| "loss": 0.5886, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 2.9185185185185185, | |
| "grad_norm": 0.2634976772367436, | |
| "learning_rate": 1.4382402707275804e-07, | |
| "loss": 0.5787, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 2.9413105413105414, | |
| "grad_norm": 0.2654663436073362, | |
| "learning_rate": 1.0152284263959391e-07, | |
| "loss": 0.5786, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 2.9641025641025642, | |
| "grad_norm": 0.27081875228470587, | |
| "learning_rate": 5.922165820642979e-08, | |
| "loss": 0.58, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 2.9868945868945866, | |
| "grad_norm": 0.2708769490432497, | |
| "learning_rate": 1.6920473773265652e-08, | |
| "loss": 0.5901, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 2.996011396011396, | |
| "eval_loss": 0.6205938458442688, | |
| "eval_runtime": 445.6085, | |
| "eval_samples_per_second": 26.532, | |
| "eval_steps_per_second": 0.415, | |
| "step": 1314 | |
| }, | |
| { | |
| "epoch": 2.996011396011396, | |
| "step": 1314, | |
| "total_flos": 2755219238682624.0, | |
| "train_loss": 0.6164092647430559, | |
| "train_runtime": 70895.1751, | |
| "train_samples_per_second": 9.505, | |
| "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 | |
| } | |