| { | |
| "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": 2.385259024190774, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7548, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.045584045584045586, | |
| "grad_norm": 0.8123529833812405, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7009, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06837606837606838, | |
| "grad_norm": 0.9370244246162021, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6806, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.09116809116809117, | |
| "grad_norm": 0.8655853560135366, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6804, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.11396011396011396, | |
| "grad_norm": 0.8180572837688457, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6765, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.13675213675213677, | |
| "grad_norm": 0.7093860636634242, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6562, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.15954415954415954, | |
| "grad_norm": 0.4818088804643291, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6529, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.18233618233618235, | |
| "grad_norm": 0.3912278847825945, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6556, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.20512820512820512, | |
| "grad_norm": 0.3215150077404874, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6402, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.22792022792022792, | |
| "grad_norm": 0.300655966335076, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6414, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.25071225071225073, | |
| "grad_norm": 0.34016523750354943, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6326, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.27350427350427353, | |
| "grad_norm": 0.3082171859656368, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6409, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.2962962962962963, | |
| "grad_norm": 0.2871758335134722, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6418, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.3190883190883191, | |
| "grad_norm": 0.3016573193865793, | |
| "learning_rate": 5e-06, | |
| "loss": 0.644, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.3418803418803419, | |
| "grad_norm": 0.3245714553050615, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6365, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.3646723646723647, | |
| "grad_norm": 0.3095587744419788, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6416, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.38746438746438744, | |
| "grad_norm": 0.3459161982130226, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6334, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.41025641025641024, | |
| "grad_norm": 0.2994880078186018, | |
| "learning_rate": 5e-06, | |
| "loss": 0.639, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.43304843304843305, | |
| "grad_norm": 0.3040019029032286, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6315, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.45584045584045585, | |
| "grad_norm": 0.3643957444928807, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6396, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.47863247863247865, | |
| "grad_norm": 0.30480683216487126, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6359, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.5014245014245015, | |
| "grad_norm": 0.29947146923893814, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6396, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.5242165242165242, | |
| "grad_norm": 0.32582064184580617, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6352, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.5470085470085471, | |
| "grad_norm": 0.30252410341946956, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6311, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.5698005698005698, | |
| "grad_norm": 0.3358250403363141, | |
| "learning_rate": 5e-06, | |
| "loss": 0.636, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.5925925925925926, | |
| "grad_norm": 0.30807735109494233, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6342, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.6153846153846154, | |
| "grad_norm": 0.3131812728861157, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6313, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.6381766381766382, | |
| "grad_norm": 0.31985241120653257, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6421, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.6609686609686609, | |
| "grad_norm": 0.324476247054874, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6308, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.6837606837606838, | |
| "grad_norm": 0.28883012776471284, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6288, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.7065527065527065, | |
| "grad_norm": 0.2970547925823876, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6287, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.7293447293447294, | |
| "grad_norm": 0.341548316793182, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6292, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.7521367521367521, | |
| "grad_norm": 0.3033814568485461, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6259, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.7749287749287749, | |
| "grad_norm": 0.328449831938576, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6317, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.7977207977207977, | |
| "grad_norm": 0.3371917707440557, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6388, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.8205128205128205, | |
| "grad_norm": 0.31461587606014585, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6305, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.8433048433048433, | |
| "grad_norm": 0.33907135118113235, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6243, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.8660968660968661, | |
| "grad_norm": 0.31120719532837904, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6366, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "grad_norm": 0.3280827254175563, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6352, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.9116809116809117, | |
| "grad_norm": 0.2976231396161992, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6384, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.9344729344729344, | |
| "grad_norm": 0.28856802825621314, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6346, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.9572649572649573, | |
| "grad_norm": 0.30274834115512034, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6215, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.98005698005698, | |
| "grad_norm": 0.3405357700109309, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6345, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.9982905982905983, | |
| "eval_loss": 0.6251771450042725, | |
| "eval_runtime": 441.0835, | |
| "eval_samples_per_second": 26.804, | |
| "eval_steps_per_second": 0.419, | |
| "step": 438 | |
| }, | |
| { | |
| "epoch": 1.0034188034188034, | |
| "grad_norm": 0.3526043748031207, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6473, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.0262108262108263, | |
| "grad_norm": 0.3319043583132696, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6019, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.049002849002849, | |
| "grad_norm": 0.3007005214276095, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5956, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.0717948717948718, | |
| "grad_norm": 0.2919687932138887, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5965, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.0945868945868946, | |
| "grad_norm": 0.3068988143487303, | |
| "learning_rate": 5e-06, | |
| "loss": 0.604, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.1173789173789175, | |
| "grad_norm": 0.32280952438742344, | |
| "learning_rate": 5e-06, | |
| "loss": 0.609, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.1401709401709401, | |
| "grad_norm": 0.2954901833336679, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5988, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.162962962962963, | |
| "grad_norm": 0.31133600652457694, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5968, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.1857549857549858, | |
| "grad_norm": 0.29782206144100504, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6025, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.2085470085470085, | |
| "grad_norm": 0.32243670462431007, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5954, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.2313390313390313, | |
| "grad_norm": 0.28737683552377413, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6057, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.2541310541310542, | |
| "grad_norm": 0.3449585599543857, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6024, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.2769230769230768, | |
| "grad_norm": 0.28830841917644784, | |
| "learning_rate": 5e-06, | |
| "loss": 0.604, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.2997150997150997, | |
| "grad_norm": 0.30612494842503374, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5978, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.3225071225071225, | |
| "grad_norm": 0.2724077727638273, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5963, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.3452991452991454, | |
| "grad_norm": 0.29877934311409626, | |
| "learning_rate": 5e-06, | |
| "loss": 0.596, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.368091168091168, | |
| "grad_norm": 0.34680996564801814, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6016, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.390883190883191, | |
| "grad_norm": 0.31986987718999754, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6017, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.4136752136752135, | |
| "grad_norm": 0.2966866180175517, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6043, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.4364672364672364, | |
| "grad_norm": 0.3137779112309709, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6023, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.4592592592592593, | |
| "grad_norm": 0.3096331947645023, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5971, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.4820512820512821, | |
| "grad_norm": 0.2966178587528764, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5951, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.504843304843305, | |
| "grad_norm": 0.29594439286210916, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5948, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.5276353276353276, | |
| "grad_norm": 0.3126484811119376, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6024, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.5504273504273505, | |
| "grad_norm": 0.27860775073751143, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5909, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.573219373219373, | |
| "grad_norm": 0.3266295092665208, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5949, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.596011396011396, | |
| "grad_norm": 0.2842030090288304, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6104, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.6188034188034188, | |
| "grad_norm": 0.32121111384458395, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5975, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.6415954415954417, | |
| "grad_norm": 0.29063941900587575, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6021, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.6643874643874645, | |
| "grad_norm": 0.32700601541341673, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5951, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 1.6871794871794872, | |
| "grad_norm": 0.3203353680503934, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5963, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.7099715099715098, | |
| "grad_norm": 0.2979570919587926, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5936, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.7327635327635327, | |
| "grad_norm": 0.3075332516169518, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5976, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 1.7555555555555555, | |
| "grad_norm": 0.29585676758575824, | |
| "learning_rate": 5e-06, | |
| "loss": 0.594, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 1.7783475783475784, | |
| "grad_norm": 0.3089318908749895, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6011, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 1.8011396011396013, | |
| "grad_norm": 0.2973271362521097, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5986, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 1.823931623931624, | |
| "grad_norm": 0.3110764584316045, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5855, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.8467236467236468, | |
| "grad_norm": 0.3124880561801754, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5934, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 1.8695156695156694, | |
| "grad_norm": 0.30291702147004973, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5911, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 1.8923076923076922, | |
| "grad_norm": 0.32631521859125023, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5949, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 1.915099715099715, | |
| "grad_norm": 0.31134842892261755, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5993, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 1.937891737891738, | |
| "grad_norm": 0.2973092874298441, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5975, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.9606837606837608, | |
| "grad_norm": 0.3135983174480875, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5988, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 1.9834757834757835, | |
| "grad_norm": 0.3588843911614199, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5962, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 1.9994301994301993, | |
| "eval_loss": 0.6187435388565063, | |
| "eval_runtime": 442.4932, | |
| "eval_samples_per_second": 26.719, | |
| "eval_steps_per_second": 0.418, | |
| "step": 877 | |
| }, | |
| { | |
| "epoch": 2.006837606837607, | |
| "grad_norm": 0.33146665781755474, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6157, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 2.0296296296296297, | |
| "grad_norm": 0.3417879164889085, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5552, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 2.0524216524216525, | |
| "grad_norm": 0.31311130133402526, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5703, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.0752136752136754, | |
| "grad_norm": 0.36299710241549005, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5684, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 2.098005698005698, | |
| "grad_norm": 0.3234011191276784, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5715, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 2.1207977207977207, | |
| "grad_norm": 0.2872017880714933, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5695, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 2.1435897435897435, | |
| "grad_norm": 0.3040973085910502, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5642, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 2.1663817663817664, | |
| "grad_norm": 0.31464737696561895, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5651, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 2.1891737891737892, | |
| "grad_norm": 0.30721153233486376, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5702, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 2.211965811965812, | |
| "grad_norm": 0.29100570938815024, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5696, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 2.234757834757835, | |
| "grad_norm": 0.2865330940363621, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5592, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 2.2575498575498574, | |
| "grad_norm": 0.32262288007644346, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5683, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 2.2803418803418802, | |
| "grad_norm": 0.3105400955944539, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5686, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.303133903133903, | |
| "grad_norm": 0.3099166916965722, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5661, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 2.325925925925926, | |
| "grad_norm": 0.3155525112335734, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5691, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 2.348717948717949, | |
| "grad_norm": 0.35065823324178585, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5704, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 2.3715099715099717, | |
| "grad_norm": 0.3040779955508841, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5683, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 2.394301994301994, | |
| "grad_norm": 0.30725601996623925, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5677, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 2.417094017094017, | |
| "grad_norm": 0.3105228961513666, | |
| "learning_rate": 5e-06, | |
| "loss": 0.576, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 2.43988603988604, | |
| "grad_norm": 0.3055210157169179, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5788, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 2.4626780626780627, | |
| "grad_norm": 0.2994955220915457, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5741, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 2.4854700854700855, | |
| "grad_norm": 0.3020646523694022, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5718, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 2.5082621082621084, | |
| "grad_norm": 0.3106622215375145, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5782, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.5310541310541312, | |
| "grad_norm": 0.3098804695854211, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5717, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 2.5538461538461537, | |
| "grad_norm": 0.30535958301464405, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5698, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 2.5766381766381765, | |
| "grad_norm": 0.3128065336180961, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5693, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 2.5994301994301994, | |
| "grad_norm": 0.3130918719392634, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5689, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 2.6222222222222222, | |
| "grad_norm": 0.30237657391826733, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5692, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 2.645014245014245, | |
| "grad_norm": 0.3100505807857925, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5703, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 2.667806267806268, | |
| "grad_norm": 0.30792158331270064, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5731, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 2.690598290598291, | |
| "grad_norm": 0.29314623782482024, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5682, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 2.7133903133903132, | |
| "grad_norm": 0.28727948476065146, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5694, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 2.736182336182336, | |
| "grad_norm": 0.28933455870139535, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5725, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.758974358974359, | |
| "grad_norm": 0.28963278859483754, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5759, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 2.781766381766382, | |
| "grad_norm": 0.2875749861529812, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5658, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 2.8045584045584047, | |
| "grad_norm": 0.2973063720548093, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5643, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 2.827350427350427, | |
| "grad_norm": 0.3147480931046027, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5791, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 2.8501424501424504, | |
| "grad_norm": 0.2995369698557402, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5757, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 2.872934472934473, | |
| "grad_norm": 0.3004285006684937, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5729, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 2.8957264957264957, | |
| "grad_norm": 0.3037842000082908, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5739, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 2.9185185185185185, | |
| "grad_norm": 0.2868126060885826, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5641, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 2.9413105413105414, | |
| "grad_norm": 0.30141853606157404, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5643, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 2.9641025641025642, | |
| "grad_norm": 0.35584532467341695, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5654, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 2.9868945868945866, | |
| "grad_norm": 0.3043876172487461, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5752, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 2.996011396011396, | |
| "eval_loss": 0.6186951398849487, | |
| "eval_runtime": 441.5424, | |
| "eval_samples_per_second": 26.777, | |
| "eval_steps_per_second": 0.419, | |
| "step": 1314 | |
| }, | |
| { | |
| "epoch": 2.996011396011396, | |
| "step": 1314, | |
| "total_flos": 2755219238682624.0, | |
| "train_loss": 0.6042390294270973, | |
| "train_runtime": 70307.8473, | |
| "train_samples_per_second": 9.584, | |
| "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 | |
| } | |