| { | |
| "best_metric": 1.159261703491211, | |
| "best_model_checkpoint": "data/tinyllama_moe_sft_ultrachat200k_v2/checkpoint-1100", | |
| "epoch": 0.9995619798510732, | |
| "eval_steps": 100, | |
| "global_step": 1141, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 1.7391304347826088e-07, | |
| "loss": 2.7477, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 8.695652173913044e-07, | |
| "loss": 2.6989, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.7391304347826088e-06, | |
| "loss": 2.7026, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 2.6086956521739132e-06, | |
| "loss": 2.5994, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 3.4782608695652175e-06, | |
| "loss": 2.4353, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.347826086956522e-06, | |
| "loss": 2.0773, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 5.2173913043478265e-06, | |
| "loss": 1.8706, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 6.086956521739132e-06, | |
| "loss": 1.7352, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 6.956521739130435e-06, | |
| "loss": 1.6574, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 7.82608695652174e-06, | |
| "loss": 1.5879, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 8.695652173913044e-06, | |
| "loss": 1.5429, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 9.565217391304349e-06, | |
| "loss": 1.4804, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 1.0434782608695653e-05, | |
| "loss": 1.4633, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 1.1304347826086957e-05, | |
| "loss": 1.4199, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 1.2173913043478263e-05, | |
| "loss": 1.4117, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1.3043478260869566e-05, | |
| "loss": 1.3667, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1.391304347826087e-05, | |
| "loss": 1.359, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1.4782608695652174e-05, | |
| "loss": 1.3563, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1.565217391304348e-05, | |
| "loss": 1.3425, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1.6521739130434785e-05, | |
| "loss": 1.3117, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.739130434782609e-05, | |
| "loss": 1.336, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 1.3140063285827637, | |
| "eval_runtime": 441.4184, | |
| "eval_samples_per_second": 36.623, | |
| "eval_steps_per_second": 1.146, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.8260869565217393e-05, | |
| "loss": 1.3087, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1.9130434782608697e-05, | |
| "loss": 1.2993, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 2e-05, | |
| "loss": 1.2998, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1.99988280568259e-05, | |
| "loss": 1.2738, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1.9995312501993765e-05, | |
| "loss": 1.277, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1.998945415950969e-05, | |
| "loss": 1.255, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1.9981254402502568e-05, | |
| "loss": 1.271, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1.9970715152902257e-05, | |
| "loss": 1.282, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 1.9957838880989076e-05, | |
| "loss": 1.2598, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 1.9942628604814827e-05, | |
| "loss": 1.2623, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 1.9925087889495374e-05, | |
| "loss": 1.2542, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 1.990522084637503e-05, | |
| "loss": 1.2481, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 1.9883032132062926e-05, | |
| "loss": 1.2445, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 1.98585269473415e-05, | |
| "loss": 1.2483, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 1.9831711035947552e-05, | |
| "loss": 1.2575, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1.9802590683225945e-05, | |
| "loss": 1.2308, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1.97711727146564e-05, | |
| "loss": 1.2328, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1.973746449425368e-05, | |
| "loss": 1.2423, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1.970147392284154e-05, | |
| "loss": 1.2272, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 1.9663209436200887e-05, | |
| "loss": 1.2426, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_loss": 1.2375621795654297, | |
| "eval_runtime": 439.5821, | |
| "eval_samples_per_second": 36.776, | |
| "eval_steps_per_second": 1.151, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 1.9622680003092503e-05, | |
| "loss": 1.2404, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 1.957989512315489e-05, | |
| "loss": 1.2137, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 1.953486482467764e-05, | |
| "loss": 1.2462, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 1.9487599662250945e-05, | |
| "loss": 1.2199, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1.9438110714291697e-05, | |
| "loss": 1.2038, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1.9386409580446846e-05, | |
| "loss": 1.2223, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 1.933250837887457e-05, | |
| "loss": 1.2325, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 1.9276419743403934e-05, | |
| "loss": 1.2049, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 1.9218156820573618e-05, | |
| "loss": 1.2341, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 1.9157733266550577e-05, | |
| "loss": 1.2086, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 1.9095163243929143e-05, | |
| "loss": 1.2172, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 1.9030461418411498e-05, | |
| "loss": 1.2212, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 1.8963642955370203e-05, | |
| "loss": 1.2019, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 1.889472351629358e-05, | |
| "loss": 1.2031, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 1.882371925511488e-05, | |
| "loss": 1.2174, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 1.875064681442594e-05, | |
| "loss": 1.1925, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 1.867552332157637e-05, | |
| "loss": 1.2244, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 1.8598366384659113e-05, | |
| "loss": 1.1928, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 1.851919408838327e-05, | |
| "loss": 1.2125, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 1.843802498983529e-05, | |
| "loss": 1.2083, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "eval_loss": 1.2099547386169434, | |
| "eval_runtime": 440.0729, | |
| "eval_samples_per_second": 36.735, | |
| "eval_steps_per_second": 1.15, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 1.8354878114129368e-05, | |
| "loss": 1.2108, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 1.8269772949948185e-05, | |
| "loss": 1.1779, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 1.8182729444974993e-05, | |
| "loss": 1.2009, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 1.8093768001218096e-05, | |
| "loss": 1.1952, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 1.800290947022884e-05, | |
| "loss": 1.1917, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 1.7910175148214274e-05, | |
| "loss": 1.1865, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 1.7815586771045535e-05, | |
| "loss": 1.238, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 1.771916650916321e-05, | |
| "loss": 1.1902, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 1.762093696238086e-05, | |
| "loss": 1.1978, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 1.752092115458784e-05, | |
| "loss": 1.1917, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 1.7419142528352815e-05, | |
| "loss": 1.1908, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 1.731562493942904e-05, | |
| "loss": 1.1964, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 1.721039265116285e-05, | |
| "loss": 1.1929, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 1.710347032880664e-05, | |
| "loss": 1.1871, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 1.6994883033737582e-05, | |
| "loss": 1.1787, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 1.688465621758352e-05, | |
| "loss": 1.1942, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 1.6772815716257414e-05, | |
| "loss": 1.1841, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 1.6659387743901688e-05, | |
| "loss": 1.1773, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 1.6544398886743934e-05, | |
| "loss": 1.1789, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 1.6427876096865394e-05, | |
| "loss": 1.1862, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "eval_loss": 1.1934226751327515, | |
| "eval_runtime": 441.3165, | |
| "eval_samples_per_second": 36.631, | |
| "eval_steps_per_second": 1.147, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 1.6309846685883726e-05, | |
| "loss": 1.2072, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 1.6190338318551426e-05, | |
| "loss": 1.1989, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 1.606937900627157e-05, | |
| "loss": 1.1853, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 1.594699710053223e-05, | |
| "loss": 1.1869, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 1.5823221286261217e-05, | |
| "loss": 1.1782, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 1.5698080575102662e-05, | |
| "loss": 1.1856, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 1.557160429861702e-05, | |
| "loss": 1.1724, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 1.5443822101406066e-05, | |
| "loss": 1.1868, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 1.531476393416456e-05, | |
| "loss": 1.1764, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 1.5184460046660139e-05, | |
| "loss": 1.2012, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 1.50529409806431e-05, | |
| "loss": 1.1718, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 1.4920237562687784e-05, | |
| "loss": 1.1708, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 1.478638089696716e-05, | |
| "loss": 1.1811, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 1.4651402357962368e-05, | |
| "loss": 1.1852, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1.4515333583108896e-05, | |
| "loss": 1.1792, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1.4378206465381122e-05, | |
| "loss": 1.1866, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1.4240053145816968e-05, | |
| "loss": 1.1529, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 1.4100906005984404e-05, | |
| "loss": 1.1858, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 1.396079766039157e-05, | |
| "loss": 1.1694, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 1.381976094884232e-05, | |
| "loss": 1.1567, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_loss": 1.181981086730957, | |
| "eval_runtime": 440.5529, | |
| "eval_samples_per_second": 36.695, | |
| "eval_steps_per_second": 1.149, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 1.3677828928738934e-05, | |
| "loss": 1.1706, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 1.3535034867333838e-05, | |
| "loss": 1.1738, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 1.3391412233932148e-05, | |
| "loss": 1.1816, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 1.3246994692046837e-05, | |
| "loss": 1.1519, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 1.3101816091508389e-05, | |
| "loss": 1.1715, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 1.2955910460530787e-05, | |
| "loss": 1.162, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 1.2809311997735697e-05, | |
| "loss": 1.1583, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 1.266205506413667e-05, | |
| "loss": 1.173, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 1.2514174175085346e-05, | |
| "loss": 1.1622, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 1.2365703992181425e-05, | |
| "loss": 1.1742, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 1.2216679315148388e-05, | |
| "loss": 1.1752, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 1.2067135073676841e-05, | |
| "loss": 1.1819, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 1.1917106319237386e-05, | |
| "loss": 1.179, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 1.1766628216864961e-05, | |
| "loss": 1.1706, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 1.161573603691655e-05, | |
| "loss": 1.1717, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 1.1464465146804218e-05, | |
| "loss": 1.1563, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 1.1312851002705383e-05, | |
| "loss": 1.1721, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 1.1160929141252303e-05, | |
| "loss": 1.1635, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 1.1008735171202685e-05, | |
| "loss": 1.1883, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 1.0856304765093391e-05, | |
| "loss": 1.1777, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_loss": 1.1737236976623535, | |
| "eval_runtime": 439.8017, | |
| "eval_samples_per_second": 36.757, | |
| "eval_steps_per_second": 1.151, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 1.0703673650879219e-05, | |
| "loss": 1.1483, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 1.0550877603558656e-05, | |
| "loss": 1.1606, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 1.0397952436788643e-05, | |
| "loss": 1.1813, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 1.024493399449025e-05, | |
| "loss": 1.1574, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 1.0091858142447266e-05, | |
| "loss": 1.1614, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 9.938760759899674e-06, | |
| "loss": 1.1617, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 9.785677731133972e-06, | |
| "loss": 1.1814, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 9.632644937072277e-06, | |
| "loss": 1.1725, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 9.479698246862277e-06, | |
| "loss": 1.1692, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 9.326873509469887e-06, | |
| "loss": 1.1591, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 9.174206545276678e-06, | |
| "loss": 1.1652, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 9.021733137683963e-06, | |
| "loss": 1.1701, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 8.869489024725595e-06, | |
| "loss": 1.1608, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 8.717509890691369e-06, | |
| "loss": 1.1485, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 8.565831357763039e-06, | |
| "loss": 1.1717, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 8.414488977664858e-06, | |
| "loss": 1.1788, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 8.263518223330698e-06, | |
| "loss": 1.1595, | |
| "step": 685 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 8.112954480589558e-06, | |
| "loss": 1.1612, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 7.962833039871562e-06, | |
| "loss": 1.1542, | |
| "step": 695 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 7.813189087936243e-06, | |
| "loss": 1.1666, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "eval_loss": 1.167747974395752, | |
| "eval_runtime": 441.5379, | |
| "eval_samples_per_second": 36.613, | |
| "eval_steps_per_second": 1.146, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 7.664057699625215e-06, | |
| "loss": 1.1644, | |
| "step": 705 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 7.515473829640987e-06, | |
| "loss": 1.1369, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 7.367472304354011e-06, | |
| "loss": 1.1445, | |
| "step": 715 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 7.2200878136397355e-06, | |
| "loss": 1.1747, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 7.073354902747742e-06, | |
| "loss": 1.1431, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 6.927307964204695e-06, | |
| "loss": 1.1846, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 6.781981229753145e-06, | |
| "loss": 1.1693, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 6.637408762327972e-06, | |
| "loss": 1.1575, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 6.4936244480724575e-06, | |
| "loss": 1.1708, | |
| "step": 745 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 6.350661988395723e-06, | |
| "loss": 1.156, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 6.208554892073528e-06, | |
| "loss": 1.1704, | |
| "step": 755 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 6.067336467394169e-06, | |
| "loss": 1.1596, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 5.927039814351426e-06, | |
| "loss": 1.1438, | |
| "step": 765 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 5.787697816886273e-06, | |
| "loss": 1.1443, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 5.649343135179271e-06, | |
| "loss": 1.1509, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 5.512008197995379e-06, | |
| "loss": 1.1432, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 5.375725195083046e-06, | |
| "loss": 1.1613, | |
| "step": 785 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 5.240526069629265e-06, | |
| "loss": 1.1385, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 5.106442510772489e-06, | |
| "loss": 1.1672, | |
| "step": 795 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 4.97350594617502e-06, | |
| "loss": 1.1531, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "eval_loss": 1.1635608673095703, | |
| "eval_runtime": 440.8581, | |
| "eval_samples_per_second": 36.669, | |
| "eval_steps_per_second": 1.148, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 4.8417475346567635e-06, | |
| "loss": 1.138, | |
| "step": 805 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 4.711198158891909e-06, | |
| "loss": 1.1437, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 4.581888418170429e-06, | |
| "loss": 1.141, | |
| "step": 815 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 4.453848621225913e-06, | |
| "loss": 1.1341, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 4.327108779131573e-06, | |
| "loss": 1.1565, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 4.201698598265973e-06, | |
| "loss": 1.1516, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 4.077647473350201e-06, | |
| "loss": 1.1764, | |
| "step": 835 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 3.954984480558071e-06, | |
| "loss": 1.1538, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 3.83373837070101e-06, | |
| "loss": 1.1691, | |
| "step": 845 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 3.7139375624891795e-06, | |
| "loss": 1.1479, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 3.595610135870472e-06, | |
| "loss": 1.1609, | |
| "step": 855 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 3.478783825448869e-06, | |
| "loss": 1.1556, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 3.3634860139837877e-06, | |
| "loss": 1.1711, | |
| "step": 865 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 3.249743725971849e-06, | |
| "loss": 1.1623, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 3.1375836213126653e-06, | |
| "loss": 1.144, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 3.0270319890600465e-06, | |
| "loss": 1.1572, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 2.918114741260156e-06, | |
| "loss": 1.1427, | |
| "step": 885 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 2.8108574068780093e-06, | |
| "loss": 1.1427, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 2.7052851258137936e-06, | |
| "loss": 1.1488, | |
| "step": 895 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 2.601422643010335e-06, | |
| "loss": 1.1525, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "eval_loss": 1.1609553098678589, | |
| "eval_runtime": 441.3737, | |
| "eval_samples_per_second": 36.627, | |
| "eval_steps_per_second": 1.146, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 2.4992943026531935e-06, | |
| "loss": 1.1582, | |
| "step": 905 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 2.3989240424646355e-06, | |
| "loss": 1.1551, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 2.300335388092929e-06, | |
| "loss": 1.1683, | |
| "step": 915 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 2.2035514475981756e-06, | |
| "loss": 1.1447, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 2.1085949060360654e-06, | |
| "loss": 1.1543, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 2.015488020140737e-06, | |
| "loss": 1.1448, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 1.924252613108073e-06, | |
| "loss": 1.1677, | |
| "step": 935 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 1.8349100694805711e-06, | |
| "loss": 1.1586, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 1.7474813301350668e-06, | |
| "loss": 1.1592, | |
| "step": 945 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 1.661986887374415e-06, | |
| "loss": 1.1702, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 1.578446780124344e-06, | |
| "loss": 1.1667, | |
| "step": 955 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 1.49688058923654e-06, | |
| "loss": 1.1489, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 1.4173074328991376e-06, | |
| "loss": 1.1448, | |
| "step": 965 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 1.339745962155613e-06, | |
| "loss": 1.1531, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 1.2642143565332154e-06, | |
| "loss": 1.1668, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 1.1907303197818665e-06, | |
| "loss": 1.1618, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 1.1193110757246251e-06, | |
| "loss": 1.1456, | |
| "step": 985 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 1.0499733642206034e-06, | |
| "loss": 1.1493, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 9.827334372413444e-07, | |
| "loss": 1.1657, | |
| "step": 995 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 9.176070550615379e-07, | |
| "loss": 1.1396, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "eval_loss": 1.1596382856369019, | |
| "eval_runtime": 440.1747, | |
| "eval_samples_per_second": 36.726, | |
| "eval_steps_per_second": 1.15, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 8.546094825649909e-07, | |
| "loss": 1.1409, | |
| "step": 1005 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 7.937554856667196e-07, | |
| "loss": 1.1476, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 7.350593278519824e-07, | |
| "loss": 1.1424, | |
| "step": 1015 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 6.785347668330777e-07, | |
| "loss": 1.1394, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 6.241950513246931e-07, | |
| "loss": 1.159, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 5.720529179385659e-07, | |
| "loss": 1.139, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 5.221205881981594e-07, | |
| "loss": 1.15, | |
| "step": 1035 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 4.7440976567407096e-07, | |
| "loss": 1.1592, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 4.2893163324085886e-07, | |
| "loss": 1.1574, | |
| "step": 1045 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 3.856968504558989e-07, | |
| "loss": 1.1491, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 3.4471555106090573e-07, | |
| "loss": 1.1452, | |
| "step": 1055 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 3.059973406066963e-07, | |
| "loss": 1.1886, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 2.6955129420176193e-07, | |
| "loss": 1.1573, | |
| "step": 1065 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 2.3538595438516442e-07, | |
| "loss": 1.1489, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 2.035093291242607e-07, | |
| "loss": 1.1433, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 1.7392888993773005e-07, | |
| "loss": 1.1521, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 1.466515701443294e-07, | |
| "loss": 1.1386, | |
| "step": 1085 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 1.2168376323780652e-07, | |
| "loss": 1.1377, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 9.90313213883376e-08, | |
| "loss": 1.1554, | |
| "step": 1095 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 7.86995540708424e-08, | |
| "loss": 1.1681, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_loss": 1.159261703491211, | |
| "eval_runtime": 441.2771, | |
| "eval_samples_per_second": 36.635, | |
| "eval_steps_per_second": 1.147, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 6.069322682050516e-08, | |
| "loss": 1.1621, | |
| "step": 1105 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 4.501656011579037e-08, | |
| "loss": 1.135, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 3.167322838920406e-08, | |
| "loss": 1.1301, | |
| "step": 1115 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 2.066635916605386e-08, | |
| "loss": 1.1462, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 1.1998532331389812e-08, | |
| "loss": 1.1398, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 5.671779525311394e-09, | |
| "loss": 1.1599, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 1.6875836667729073e-09, | |
| "loss": 1.1463, | |
| "step": 1135 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 4.687860599927874e-11, | |
| "loss": 1.1576, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 1141, | |
| "total_flos": 1.1420601686146679e+19, | |
| "train_loss": 1.2278979039839963, | |
| "train_runtime": 17901.7657, | |
| "train_samples_per_second": 8.159, | |
| "train_steps_per_second": 0.064 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 1141, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "total_flos": 1.1420601686146679e+19, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |