| { | |
| "best_metric": 1.3436678647994995, | |
| "best_model_checkpoint": "saves/ChineseLLaMA2-7B-Chat/lora/2023-09-07-12-02-29/checkpoint-2400", | |
| "epoch": 2.60092115957735, | |
| "eval_steps": 100, | |
| "global_step": 2400, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.0009999919374161553, | |
| "loss": 2.0025, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.0009999677499246417, | |
| "loss": 1.7737, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0009999274383055143, | |
| "loss": 1.7391, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0009998710038588363, | |
| "loss": 1.7959, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0009997984484046375, | |
| "loss": 1.713, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0009997097742828556, | |
| "loss": 1.6441, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0009996049843532607, | |
| "loss": 1.704, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0009994840819953633, | |
| "loss": 1.6532, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0009993470711083048, | |
| "loss": 1.6791, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0009991939561107325, | |
| "loss": 1.6465, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.000999024741940656, | |
| "loss": 1.6511, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0009988394340552898, | |
| "loss": 1.6727, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0009986380384308746, | |
| "loss": 1.6653, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0009984205615624873, | |
| "loss": 1.6339, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0009981870104638294, | |
| "loss": 1.5562, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.0009979373926670028, | |
| "loss": 1.6291, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.0009976717162222645, | |
| "loss": 1.625, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0009973899896977695, | |
| "loss": 1.6008, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.000997092222179292, | |
| "loss": 1.6821, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0009967784232699352, | |
| "loss": 1.582, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_loss": 1.6186352968215942, | |
| "eval_runtime": 10.6735, | |
| "eval_samples_per_second": 14.054, | |
| "eval_steps_per_second": 1.78, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0009964486030898186, | |
| "loss": 1.5769, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0009961027722757538, | |
| "loss": 1.5868, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0009957409419809006, | |
| "loss": 1.5601, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.000995363123874407, | |
| "loss": 1.6061, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0009949693301410341, | |
| "loss": 1.6073, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0009945595734807615, | |
| "loss": 1.4998, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0009941338671083794, | |
| "loss": 1.5295, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0009936922247530606, | |
| "loss": 1.5418, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.0009932346606579192, | |
| "loss": 1.554, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.0009927611895795513, | |
| "loss": 1.5509, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.0009922718267875571, | |
| "loss": 1.6123, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.0009917665880640515, | |
| "loss": 1.6267, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.0009912454897031524, | |
| "loss": 1.6116, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.0009907085485104568, | |
| "loss": 1.5618, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.0009901557818024981, | |
| "loss": 1.6085, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.0009895872074061885, | |
| "loss": 1.5829, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.0009890028436582426, | |
| "loss": 1.5407, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.0009884027094045871, | |
| "loss": 1.5568, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.0009877868239997532, | |
| "loss": 1.5831, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.0009871552073062516, | |
| "loss": 1.5231, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_loss": 1.5717933177947998, | |
| "eval_runtime": 10.6708, | |
| "eval_samples_per_second": 14.057, | |
| "eval_steps_per_second": 1.781, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.0009865078796939327, | |
| "loss": 1.5467, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.000985844862039329, | |
| "loss": 1.6403, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.0009851661757249823, | |
| "loss": 1.5352, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.0009844718426387537, | |
| "loss": 1.5616, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.000983761885173118, | |
| "loss": 1.5274, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.000983036326224442, | |
| "loss": 1.6153, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.0009822951891922448, | |
| "loss": 1.5062, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.0009815384979784444, | |
| "loss": 1.6038, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.000980766276986586, | |
| "loss": 1.5097, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.0009799785511210557, | |
| "loss": 1.535, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.000979175345786277, | |
| "loss": 1.52, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.0009783566868858912, | |
| "loss": 1.5678, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.0009775226008219224, | |
| "loss": 1.5536, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.0009766731144939258, | |
| "loss": 1.4826, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.0009758082552981204, | |
| "loss": 1.5537, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.0009749280511265056, | |
| "loss": 1.5277, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.0009740325303659609, | |
| "loss": 1.5445, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.000973121721897331, | |
| "loss": 1.4944, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.0009721956550944948, | |
| "loss": 1.5088, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.0009712543598234172, | |
| "loss": 1.585, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_loss": 1.5345921516418457, | |
| "eval_runtime": 10.6704, | |
| "eval_samples_per_second": 14.058, | |
| "eval_steps_per_second": 1.781, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.0009702978664411863, | |
| "loss": 1.5427, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.0009693262057950345, | |
| "loss": 1.4475, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.0009683394092213436, | |
| "loss": 1.5321, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.0009673375085446339, | |
| "loss": 1.5171, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.0009663205360765382, | |
| "loss": 1.5198, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.00096528852461476, | |
| "loss": 1.492, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.0009642415074420146, | |
| "loss": 1.5036, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.0009631795183249573, | |
| "loss": 1.5134, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.0009621025915130932, | |
| "loss": 1.5568, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.0009610107617376733, | |
| "loss": 1.503, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.0009599040642105736, | |
| "loss": 1.4584, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.000958782534623161, | |
| "loss": 1.4832, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.0009576462091451406, | |
| "loss": 1.4598, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.0009564951244233901, | |
| "loss": 1.5492, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.000955329317580778, | |
| "loss": 1.5145, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.0009541488262149661, | |
| "loss": 1.589, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.0009529536883971963, | |
| "loss": 1.6003, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.0009517439426710646, | |
| "loss": 1.55, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.0009505196280512762, | |
| "loss": 1.5359, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.0009492807840223881, | |
| "loss": 1.4854, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_loss": 1.5193477869033813, | |
| "eval_runtime": 10.6722, | |
| "eval_samples_per_second": 14.055, | |
| "eval_steps_per_second": 1.78, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.0009480274505375358, | |
| "loss": 1.4891, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.0009467596680171446, | |
| "loss": 1.4719, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.0009454774773476257, | |
| "loss": 1.4939, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.0009441809198800587, | |
| "loss": 1.4382, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.0009428700374288564, | |
| "loss": 1.4427, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.0009415448722704175, | |
| "loss": 1.4767, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.0009402054671417628, | |
| "loss": 1.4799, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.0009388518652391571, | |
| "loss": 1.4608, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.0009374841102167157, | |
| "loss": 1.4937, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.0009361022461849965, | |
| "loss": 1.5468, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.0009347063177095783, | |
| "loss": 1.5481, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.0009332963698096223, | |
| "loss": 1.4478, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.0009318724479564215, | |
| "loss": 1.4977, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.0009304345980719329, | |
| "loss": 1.5091, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.0009289828665272977, | |
| "loss": 1.43, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.0009275173001413448, | |
| "loss": 1.4725, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.0009260379461790822, | |
| "loss": 1.3741, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.0009245448523501708, | |
| "loss": 1.4917, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.0009230380668073877, | |
| "loss": 1.4684, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.0009215176381450717, | |
| "loss": 1.5209, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "eval_loss": 1.5050214529037476, | |
| "eval_runtime": 10.6706, | |
| "eval_samples_per_second": 14.057, | |
| "eval_steps_per_second": 1.781, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.0009199836153975573, | |
| "loss": 1.4913, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.0009184360480375926, | |
| "loss": 1.5377, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.0009168749859747438, | |
| "loss": 1.4608, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.0009153004795537861, | |
| "loss": 1.4738, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.0009137125795530795, | |
| "loss": 1.4947, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.0009121113371829318, | |
| "loss": 1.5267, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.0009104968040839463, | |
| "loss": 1.5116, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.000908869032325357, | |
| "loss": 1.4423, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.000907228074403349, | |
| "loss": 1.4565, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.0009055739832393655, | |
| "loss": 1.4923, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.0009039068121784016, | |
| "loss": 1.4304, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.0009022266149872829, | |
| "loss": 1.4422, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.0009005334458529322, | |
| "loss": 1.522, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.0008988273593806222, | |
| "loss": 1.499, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.0008971084105922139, | |
| "loss": 1.4796, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.0008953766549243818, | |
| "loss": 1.4231, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.0008936321482268275, | |
| "loss": 1.462, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.0008918749467604766, | |
| "loss": 1.5191, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.0008901051071956661, | |
| "loss": 1.4845, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.0008883226866103152, | |
| "loss": 1.4652, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_loss": 1.486396074295044, | |
| "eval_runtime": 10.6718, | |
| "eval_samples_per_second": 14.056, | |
| "eval_steps_per_second": 1.78, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.0008865277424880859, | |
| "loss": 1.4773, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.0008847203327165278, | |
| "loss": 1.4555, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.0008829005155852125, | |
| "loss": 1.5235, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.0008810683497838525, | |
| "loss": 1.4329, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 0.0008792238944004096, | |
| "loss": 1.4515, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 0.0008773672089191885, | |
| "loss": 1.4616, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.0008754983532189185, | |
| "loss": 1.3931, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.0008736173875708229, | |
| "loss": 1.4714, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.0008717243726366746, | |
| "loss": 1.4831, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.00086981936946684, | |
| "loss": 1.4928, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.0008679024394983105, | |
| "loss": 1.3735, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.0008659736445527202, | |
| "loss": 1.4587, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.0008640330468343532, | |
| "loss": 1.5138, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.0008620807089281364, | |
| "loss": 1.4625, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.0008601166937976226, | |
| "loss": 1.4173, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 0.000858141064782958, | |
| "loss": 1.4901, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 0.0008561538855988409, | |
| "loss": 1.4056, | |
| "step": 685 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.0008541552203324667, | |
| "loss": 1.4486, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.0008521451334414605, | |
| "loss": 1.4147, | |
| "step": 695 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 0.0008501236897517987, | |
| "loss": 1.4547, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_loss": 1.4729957580566406, | |
| "eval_runtime": 10.6704, | |
| "eval_samples_per_second": 14.058, | |
| "eval_steps_per_second": 1.781, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 0.000848090954455718, | |
| "loss": 1.4464, | |
| "step": 705 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 0.0008460469931096138, | |
| "loss": 1.4163, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 0.0008439918716319246, | |
| "loss": 1.5283, | |
| "step": 715 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.0008419256563010076, | |
| "loss": 1.4313, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 0.000839848413753, | |
| "loss": 1.3995, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 0.0008377602109796709, | |
| "loss": 1.4265, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.0008356611153262598, | |
| "loss": 1.4426, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.0008335511944893057, | |
| "loss": 1.4251, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 0.0008314305165144633, | |
| "loss": 1.4686, | |
| "step": 745 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 0.0008292991497943081, | |
| "loss": 1.4658, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 0.0008271571630661321, | |
| "loss": 1.4347, | |
| "step": 755 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 0.0008250046254097255, | |
| "loss": 1.4235, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 0.0008228416062451494, | |
| "loss": 1.5047, | |
| "step": 765 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 0.0008206681753304976, | |
| "loss": 1.445, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 0.0008184844027596461, | |
| "loss": 1.4077, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.0008162903589599924, | |
| "loss": 1.5057, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.0008140861146901849, | |
| "loss": 1.4445, | |
| "step": 785 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 0.0008118717410378407, | |
| "loss": 1.5333, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 0.0008096473094172527, | |
| "loss": 1.3786, | |
| "step": 795 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 0.0008074128915670868, | |
| "loss": 1.3781, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "eval_loss": 1.4600605964660645, | |
| "eval_runtime": 10.6704, | |
| "eval_samples_per_second": 14.058, | |
| "eval_steps_per_second": 1.781, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 0.0008051685595480678, | |
| "loss": 1.5097, | |
| "step": 805 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 0.0008029143857406563, | |
| "loss": 1.5608, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 0.0008006504428427133, | |
| "loss": 1.4113, | |
| "step": 815 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 0.0007983768038671568, | |
| "loss": 1.3781, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 0.0007960935421396062, | |
| "loss": 1.4056, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 0.0007938007312960178, | |
| "loss": 1.4463, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 0.0007914984452803105, | |
| "loss": 1.3983, | |
| "step": 835 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 0.0007891867583419805, | |
| "loss": 1.3968, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 0.0007868657450337066, | |
| "loss": 1.4587, | |
| "step": 845 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 0.0007845354802089463, | |
| "loss": 1.4654, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.0007821960390195224, | |
| "loss": 1.4384, | |
| "step": 855 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.0007798474969131971, | |
| "loss": 1.44, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 0.0007774899296312414, | |
| "loss": 1.4221, | |
| "step": 865 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 0.0007751234132059906, | |
| "loss": 1.3795, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 0.0007727480239583933, | |
| "loss": 1.4748, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 0.0007703638384955494, | |
| "loss": 1.5171, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 0.0007679709337082394, | |
| "loss": 1.3996, | |
| "step": 885 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 0.0007655693867684454, | |
| "loss": 1.4386, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 0.0007631592751268618, | |
| "loss": 1.3789, | |
| "step": 895 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 0.0007607406765103972, | |
| "loss": 1.4553, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "eval_loss": 1.4479364156723022, | |
| "eval_runtime": 10.6698, | |
| "eval_samples_per_second": 14.058, | |
| "eval_steps_per_second": 1.781, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 0.000758313668919668, | |
| "loss": 1.3962, | |
| "step": 905 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 0.000755878330626483, | |
| "loss": 1.3899, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 0.0007534347401713191, | |
| "loss": 1.3965, | |
| "step": 915 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.0007509829763607879, | |
| "loss": 1.367, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.0007485231182650945, | |
| "loss": 1.4027, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 0.0007460552452154877, | |
| "loss": 1.3563, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 0.0007435794368017007, | |
| "loss": 1.3192, | |
| "step": 935 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 0.0007410957728693856, | |
| "loss": 1.2772, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 0.0007386043335175367, | |
| "loss": 1.3291, | |
| "step": 945 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 0.000736105199095909, | |
| "loss": 1.304, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 0.0007335984502024256, | |
| "loss": 1.3832, | |
| "step": 955 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 0.0007310841676805791, | |
| "loss": 1.3351, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 0.000728562432616824, | |
| "loss": 1.3375, | |
| "step": 965 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 0.0007260333263379619, | |
| "loss": 1.3323, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 0.0007234969304085186, | |
| "loss": 1.3293, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 0.0007209533266281133, | |
| "loss": 1.3859, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.0007184025970288211, | |
| "loss": 1.3553, | |
| "step": 985 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.000715844823872527, | |
| "loss": 1.3607, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 0.0007132800896482731, | |
| "loss": 1.3457, | |
| "step": 995 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 0.0007107084770695986, | |
| "loss": 1.3788, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "eval_loss": 1.4371482133865356, | |
| "eval_runtime": 10.6719, | |
| "eval_samples_per_second": 14.056, | |
| "eval_steps_per_second": 1.78, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 0.0007081300690718709, | |
| "loss": 1.3039, | |
| "step": 1005 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 0.0007055449488096132, | |
| "loss": 1.2719, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 0.0007029531996538212, | |
| "loss": 1.4107, | |
| "step": 1015 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 0.0007003549051892738, | |
| "loss": 1.38, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 0.0006977501492118391, | |
| "loss": 1.3408, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 0.0006951390157257712, | |
| "loss": 1.3704, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 0.0006925215889410004, | |
| "loss": 1.345, | |
| "step": 1035 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 0.0006898979532704186, | |
| "loss": 1.3414, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 0.0006872681933271559, | |
| "loss": 1.3131, | |
| "step": 1045 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 0.0006846323939218526, | |
| "loss": 1.3363, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 0.0006819906400599234, | |
| "loss": 1.3659, | |
| "step": 1055 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 0.0006793430169388163, | |
| "loss": 1.3145, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 0.0006766896099452652, | |
| "loss": 1.3727, | |
| "step": 1065 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 0.0006740305046525351, | |
| "loss": 1.3478, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 0.0006713657868176639, | |
| "loss": 1.3848, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 0.0006686955423786951, | |
| "loss": 1.3501, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 0.0006660198574519078, | |
| "loss": 1.3782, | |
| "step": 1085 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 0.000663338818329038, | |
| "loss": 1.3767, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 0.0006606525114744965, | |
| "loss": 1.3665, | |
| "step": 1095 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 0.0006579610235225805, | |
| "loss": 1.2234, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "eval_loss": 1.4341663122177124, | |
| "eval_runtime": 10.6713, | |
| "eval_samples_per_second": 14.056, | |
| "eval_steps_per_second": 1.78, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 0.0006552644412746791, | |
| "loss": 1.4083, | |
| "step": 1105 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 0.0006525628516964741, | |
| "loss": 1.4225, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 0.0006498563419151354, | |
| "loss": 1.3677, | |
| "step": 1115 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 0.0006471449992165113, | |
| "loss": 1.2836, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 0.0006444289110423129, | |
| "loss": 1.3428, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 0.0006417081649872952, | |
| "loss": 1.3192, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 0.0006389828487964305, | |
| "loss": 1.3084, | |
| "step": 1135 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 0.00063625305036208, | |
| "loss": 1.3702, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 0.000633518857721159, | |
| "loss": 1.3054, | |
| "step": 1145 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 0.0006307803590522972, | |
| "loss": 1.3211, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 0.0006280376426729947, | |
| "loss": 1.3319, | |
| "step": 1155 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 0.0006252907970367749, | |
| "loss": 1.4346, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 0.0006225399107303309, | |
| "loss": 1.3938, | |
| "step": 1165 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 0.0006197850724706682, | |
| "loss": 1.4371, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 0.0006170263711022451, | |
| "loss": 1.2925, | |
| "step": 1175 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 0.0006142638955941057, | |
| "loss": 1.3135, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 0.0006114977350370114, | |
| "loss": 1.3572, | |
| "step": 1185 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 0.0006087279786405684, | |
| "loss": 1.3918, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 0.0006059547157303491, | |
| "loss": 1.3732, | |
| "step": 1195 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 0.0006031780357450124, | |
| "loss": 1.3541, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "eval_loss": 1.4208500385284424, | |
| "eval_runtime": 10.67, | |
| "eval_samples_per_second": 14.058, | |
| "eval_steps_per_second": 1.781, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 0.0006003980282334191, | |
| "loss": 1.2997, | |
| "step": 1205 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 0.0005976147828517439, | |
| "loss": 1.2832, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 0.0005948283893605839, | |
| "loss": 1.3863, | |
| "step": 1215 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 0.0005920389376220633, | |
| "loss": 1.3599, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 0.0005892465175969366, | |
| "loss": 1.3085, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 0.000586451219341686, | |
| "loss": 1.3355, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 0.0005836531330056176, | |
| "loss": 1.291, | |
| "step": 1235 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 0.0005808523488279542, | |
| "loss": 1.3286, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 0.0005780489571349249, | |
| "loss": 1.3704, | |
| "step": 1245 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 0.000575243048336852, | |
| "loss": 1.3263, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 0.0005724347129252354, | |
| "loss": 1.3357, | |
| "step": 1255 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 0.0005696240414698337, | |
| "loss": 1.3665, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 0.0005668111246157441, | |
| "loss": 1.2568, | |
| "step": 1265 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 0.0005639960530804787, | |
| "loss": 1.3212, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 0.0005611789176510384, | |
| "loss": 1.3358, | |
| "step": 1275 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 0.0005583598091809859, | |
| "loss": 1.3618, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 0.0005555388185875146, | |
| "loss": 1.3273, | |
| "step": 1285 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 0.0005527160368485172, | |
| "loss": 1.284, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 0.0005498915549996516, | |
| "loss": 1.3665, | |
| "step": 1295 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 0.0005470654641314045, | |
| "loss": 1.2796, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "eval_loss": 1.4054052829742432, | |
| "eval_runtime": 10.6703, | |
| "eval_samples_per_second": 14.058, | |
| "eval_steps_per_second": 1.781, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 0.0005442378553861545, | |
| "loss": 1.3107, | |
| "step": 1305 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 0.0005414088199552319, | |
| "loss": 1.3665, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 0.000538578449075978, | |
| "loss": 1.3326, | |
| "step": 1315 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 0.0005357468340288031, | |
| "loss": 1.3383, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 0.000532914066134242, | |
| "loss": 1.336, | |
| "step": 1325 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 0.0005300802367500093, | |
| "loss": 1.3949, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 0.0005272454372680532, | |
| "loss": 1.3214, | |
| "step": 1335 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 0.0005244097591116077, | |
| "loss": 1.376, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 0.0005215732937322439, | |
| "loss": 1.2345, | |
| "step": 1345 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 0.0005187361326069224, | |
| "loss": 1.4495, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 0.0005158983672350405, | |
| "loss": 1.3978, | |
| "step": 1355 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 0.0005130600891354833, | |
| "loss": 1.2517, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 0.0005102213898436715, | |
| "loss": 1.3823, | |
| "step": 1365 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 0.0005073823609086091, | |
| "loss": 1.3219, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 0.0005045430938899315, | |
| "loss": 1.3354, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 0.0005017036803549523, | |
| "loss": 1.3054, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 0.0004988642118757102, | |
| "loss": 1.2346, | |
| "step": 1385 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 0.0004960247800260161, | |
| "loss": 1.274, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 0.0004931854763784994, | |
| "loss": 1.4231, | |
| "step": 1395 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 0.000490346392501655, | |
| "loss": 1.2872, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "eval_loss": 1.3990795612335205, | |
| "eval_runtime": 10.6706, | |
| "eval_samples_per_second": 14.057, | |
| "eval_steps_per_second": 1.781, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 0.00048750761995688984, | |
| "loss": 1.4041, | |
| "step": 1405 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 0.0004846692502955709, | |
| "loss": 1.3405, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 0.00048183137505607154, | |
| "loss": 1.3198, | |
| "step": 1415 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 0.00047899408576082016, | |
| "loss": 1.3528, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 0.0004761574739133478, | |
| "loss": 1.3095, | |
| "step": 1425 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 0.00047332163099533787, | |
| "loss": 1.3278, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 0.00047048664846367587, | |
| "loss": 1.3305, | |
| "step": 1435 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 0.0004676526177474991, | |
| "loss": 1.3997, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 0.00046481963024524846, | |
| "loss": 1.341, | |
| "step": 1445 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 0.00046198777732172133, | |
| "loss": 1.3008, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 0.00045915715030512405, | |
| "loss": 1.2643, | |
| "step": 1455 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 0.0004563278404841273, | |
| "loss": 1.3169, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 0.00045349993910492154, | |
| "loss": 1.3062, | |
| "step": 1465 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 0.00045067353736827495, | |
| "loss": 1.2876, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 0.0004478487264265913, | |
| "loss": 1.3534, | |
| "step": 1475 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 0.0004450255973809707, | |
| "loss": 1.318, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 0.000442204241278272, | |
| "loss": 1.3195, | |
| "step": 1485 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 0.0004393847491081756, | |
| "loss": 1.3208, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 0.0004365672118002494, | |
| "loss": 1.3879, | |
| "step": 1495 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 0.0004337517202210168, | |
| "loss": 1.3356, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "eval_loss": 1.3873966932296753, | |
| "eval_runtime": 10.6704, | |
| "eval_samples_per_second": 14.058, | |
| "eval_steps_per_second": 1.781, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 0.0004309383651710254, | |
| "loss": 1.3163, | |
| "step": 1505 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 0.00042812723738191896, | |
| "loss": 1.3119, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 0.0004253184275135116, | |
| "loss": 1.2777, | |
| "step": 1515 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 0.0004225120261508637, | |
| "loss": 1.3624, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 0.0004197081238013602, | |
| "loss": 1.3231, | |
| "step": 1525 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 0.0004169068108917924, | |
| "loss": 1.3807, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 0.0004141081777654412, | |
| "loss": 1.3301, | |
| "step": 1535 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 0.0004113123146791633, | |
| "loss": 1.3032, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 0.000408519311800481, | |
| "loss": 1.2957, | |
| "step": 1545 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 0.00040572925920467375, | |
| "loss": 1.3138, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 0.0004029422468718737, | |
| "loss": 1.2496, | |
| "step": 1555 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 0.0004001583646841632, | |
| "loss": 1.3796, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 0.00039737770242267637, | |
| "loss": 1.3492, | |
| "step": 1565 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 0.00039460034976470396, | |
| "loss": 1.3138, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 0.0003918263962808004, | |
| "loss": 1.3172, | |
| "step": 1575 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 0.0003890559314318959, | |
| "loss": 1.3446, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 0.00038628904456641116, | |
| "loss": 1.3062, | |
| "step": 1585 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 0.00038352582491737547, | |
| "loss": 1.2899, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 0.0003807663615995491, | |
| "loss": 1.2942, | |
| "step": 1595 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 0.0003780107436065498, | |
| "loss": 1.2902, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "eval_loss": 1.379552960395813, | |
| "eval_runtime": 10.6705, | |
| "eval_samples_per_second": 14.057, | |
| "eval_steps_per_second": 1.781, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 0.00037525905980798183, | |
| "loss": 1.3213, | |
| "step": 1605 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 0.0003725113989465705, | |
| "loss": 1.2286, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 0.00036976784963530017, | |
| "loss": 1.3394, | |
| "step": 1615 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 0.0003670285003545564, | |
| "loss": 1.2879, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 0.00036429343944927196, | |
| "loss": 1.3369, | |
| "step": 1625 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 0.0003615627551260785, | |
| "loss": 1.3393, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 0.0003588365354504612, | |
| "loss": 1.3437, | |
| "step": 1635 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 0.00035611486834391894, | |
| "loss": 1.2843, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 0.00035339784158112893, | |
| "loss": 1.3463, | |
| "step": 1645 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 0.00035068554278711494, | |
| "loss": 1.2847, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 0.00034797805943442313, | |
| "loss": 1.2493, | |
| "step": 1655 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 0.0003452754788402996, | |
| "loss": 1.3471, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 0.00034257788816387475, | |
| "loss": 1.2983, | |
| "step": 1665 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 0.0003398853744033529, | |
| "loss": 1.3259, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 0.0003371980243932056, | |
| "loss": 1.333, | |
| "step": 1675 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 0.00033451592480137195, | |
| "loss": 1.3071, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 0.00033183916212646346, | |
| "loss": 1.3238, | |
| "step": 1685 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 0.0003291678226949741, | |
| "loss": 1.3129, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 0.0003265019926584964, | |
| "loss": 1.3235, | |
| "step": 1695 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 0.00032384175799094297, | |
| "loss": 1.3016, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "eval_loss": 1.3693352937698364, | |
| "eval_runtime": 10.6712, | |
| "eval_samples_per_second": 14.057, | |
| "eval_steps_per_second": 1.78, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 0.0003211872044857743, | |
| "loss": 1.2658, | |
| "step": 1705 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 0.00031853841775323103, | |
| "loss": 1.274, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 0.00031589548321757366, | |
| "loss": 1.2629, | |
| "step": 1715 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 0.0003132584861143274, | |
| "loss": 1.3052, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 0.0003106275114875332, | |
| "loss": 1.3099, | |
| "step": 1725 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 0.0003080026441870051, | |
| "loss": 1.2878, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 0.00030538396886559393, | |
| "loss": 1.2815, | |
| "step": 1735 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 0.00030277156997645706, | |
| "loss": 1.2896, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 0.00030016553177033466, | |
| "loss": 1.3545, | |
| "step": 1745 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 0.0002975659382928332, | |
| "loss": 1.29, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 0.00029497287338171385, | |
| "loss": 1.3543, | |
| "step": 1755 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 0.00029238642066418995, | |
| "loss": 1.3202, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 0.0002898066635542288, | |
| "loss": 1.3261, | |
| "step": 1765 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 0.0002872336852498627, | |
| "loss": 1.2256, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 0.0002846675687305045, | |
| "loss": 1.3423, | |
| "step": 1775 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 0.0002821083967542727, | |
| "loss": 1.2896, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 0.00027955625185532217, | |
| "loss": 1.2312, | |
| "step": 1785 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 0.00027701121634118143, | |
| "loss": 1.2822, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 0.00027447337229009937, | |
| "loss": 1.319, | |
| "step": 1795 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 0.00027194280154839824, | |
| "loss": 1.3727, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "eval_loss": 1.3620151281356812, | |
| "eval_runtime": 10.671, | |
| "eval_samples_per_second": 14.057, | |
| "eval_steps_per_second": 1.781, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 0.0002694195857278326, | |
| "loss": 1.251, | |
| "step": 1805 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 0.0002669038062029592, | |
| "loss": 1.2324, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 0.0002643955441085115, | |
| "loss": 1.2644, | |
| "step": 1815 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 0.000261894880336783, | |
| "loss": 1.2582, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 0.0002594018955350191, | |
| "loss": 1.3433, | |
| "step": 1825 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 0.00025691667010281616, | |
| "loss": 1.3069, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 0.00025443928418952724, | |
| "loss": 1.2895, | |
| "step": 1835 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 0.0002519698176916791, | |
| "loss": 1.2799, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.000249508350250395, | |
| "loss": 1.3044, | |
| "step": 1845 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.0002470549612488247, | |
| "loss": 1.2324, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 0.0002446097298095867, | |
| "loss": 1.2357, | |
| "step": 1855 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 0.00024217273479221514, | |
| "loss": 1.2329, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 0.00023974405479061623, | |
| "loss": 1.2486, | |
| "step": 1865 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 0.0002373237681305348, | |
| "loss": 1.1959, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 0.00023491195286702777, | |
| "loss": 1.2485, | |
| "step": 1875 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 0.00023250868678194536, | |
| "loss": 1.2585, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 0.00023011404738142532, | |
| "loss": 1.2108, | |
| "step": 1885 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 0.0002277281118933916, | |
| "loss": 1.188, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 0.00022535095726506344, | |
| "loss": 1.2197, | |
| "step": 1895 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 0.00022298266016047513, | |
| "loss": 1.1352, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "eval_loss": 1.3637186288833618, | |
| "eval_runtime": 10.671, | |
| "eval_samples_per_second": 14.057, | |
| "eval_steps_per_second": 1.781, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 0.0002206232969580027, | |
| "loss": 1.2265, | |
| "step": 1905 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 0.00021827294374790034, | |
| "loss": 1.2631, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 0.00021593167632984756, | |
| "loss": 1.1309, | |
| "step": 1915 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 0.00021359957021050392, | |
| "loss": 1.2877, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 0.00021127670060107362, | |
| "loss": 1.2993, | |
| "step": 1925 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 0.00020896314241488075, | |
| "loss": 1.2244, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 0.0002066589702649529, | |
| "loss": 1.1812, | |
| "step": 1935 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 0.00020436425846161437, | |
| "loss": 1.2113, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 0.00020207908101009054, | |
| "loss": 1.1754, | |
| "step": 1945 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 0.00019980351160812083, | |
| "loss": 1.1897, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 0.0001975376236435813, | |
| "loss": 1.1978, | |
| "step": 1955 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 0.00019528149019211883, | |
| "loss": 1.1937, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 0.00019303518401479414, | |
| "loss": 1.2093, | |
| "step": 1965 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 0.00019079877755573442, | |
| "loss": 1.2119, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 0.0001885723429397983, | |
| "loss": 1.1933, | |
| "step": 1975 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 0.00018635595197024886, | |
| "loss": 1.2046, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 0.00018414967612643814, | |
| "loss": 1.1605, | |
| "step": 1985 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 0.0001819535865615018, | |
| "loss": 1.1764, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 0.00017976775410006508, | |
| "loss": 1.2094, | |
| "step": 1995 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 0.000177592249235958, | |
| "loss": 1.146, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "eval_loss": 1.3614530563354492, | |
| "eval_runtime": 10.6711, | |
| "eval_samples_per_second": 14.057, | |
| "eval_steps_per_second": 1.781, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 0.00017542714212994188, | |
| "loss": 1.2674, | |
| "step": 2005 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 0.00017327250260744698, | |
| "loss": 1.2817, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 0.00017112840015632086, | |
| "loss": 1.2693, | |
| "step": 2015 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 0.00016899490392458628, | |
| "loss": 1.253, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 0.00016687208271821253, | |
| "loss": 1.208, | |
| "step": 2025 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 0.00016476000499889514, | |
| "loss": 1.1818, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 0.0001626587388818491, | |
| "loss": 1.1945, | |
| "step": 2035 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 0.0001605683521336116, | |
| "loss": 1.2225, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 0.00015848891216985596, | |
| "loss": 1.1726, | |
| "step": 2045 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 0.00015642048605321856, | |
| "loss": 1.1651, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 0.0001543631404911356, | |
| "loss": 1.2148, | |
| "step": 2055 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 0.00015231694183369106, | |
| "loss": 1.191, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 0.0001502819560714781, | |
| "loss": 1.2421, | |
| "step": 2065 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 0.00014825824883347018, | |
| "loss": 1.1924, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 0.00014624588538490413, | |
| "loss": 1.1714, | |
| "step": 2075 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 0.00014424493062517623, | |
| "loss": 1.2641, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 0.00014225544908574872, | |
| "loss": 1.2721, | |
| "step": 2085 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 0.00014027750492806817, | |
| "loss": 1.2431, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 0.00013831116194149712, | |
| "loss": 1.2983, | |
| "step": 2095 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 0.00013635648354125662, | |
| "loss": 1.2144, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "eval_loss": 1.3538448810577393, | |
| "eval_runtime": 10.6717, | |
| "eval_samples_per_second": 14.056, | |
| "eval_steps_per_second": 1.78, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 0.0001344135327663804, | |
| "loss": 1.1463, | |
| "step": 2105 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 0.00013248237227768246, | |
| "loss": 1.2751, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 0.00013056306435573633, | |
| "loss": 1.2196, | |
| "step": 2115 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 0.00012865567089886642, | |
| "loss": 1.1964, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 0.00012676025342115105, | |
| "loss": 1.1749, | |
| "step": 2125 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 0.00012487687305043978, | |
| "loss": 1.2615, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 0.00012300559052638122, | |
| "loss": 1.2064, | |
| "step": 2135 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 0.00012114646619846425, | |
| "loss": 1.1642, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 0.00011929956002407194, | |
| "loss": 1.1704, | |
| "step": 2145 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 0.00011746493156654814, | |
| "loss": 1.1668, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 0.00011564263999327546, | |
| "loss": 1.1584, | |
| "step": 2155 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 0.00011383274407376848, | |
| "loss": 1.2412, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 0.0001120353021777778, | |
| "loss": 1.1688, | |
| "step": 2165 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 0.00011025037227340711, | |
| "loss": 1.2097, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 0.00010847801192524454, | |
| "loss": 1.2057, | |
| "step": 2175 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 0.00010671827829250585, | |
| "loss": 1.2296, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 0.00010497122812719068, | |
| "loss": 1.2547, | |
| "step": 2185 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 0.00010323691777225286, | |
| "loss": 1.1746, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 0.00010151540315978314, | |
| "loss": 1.1466, | |
| "step": 2195 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 9.98067398092049e-05, | |
| "loss": 1.1551, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "eval_loss": 1.349250316619873, | |
| "eval_runtime": 10.6708, | |
| "eval_samples_per_second": 14.057, | |
| "eval_steps_per_second": 1.781, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 9.811098282548447e-05, | |
| "loss": 1.158, | |
| "step": 2205 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 9.642818689735305e-05, | |
| "loss": 1.1444, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 9.475840629554394e-05, | |
| "loss": 1.2504, | |
| "step": 2215 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 9.310169487104131e-05, | |
| "loss": 1.1439, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 9.145810605334454e-05, | |
| "loss": 1.2758, | |
| "step": 2225 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 8.982769284874386e-05, | |
| "loss": 1.1992, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 8.821050783861212e-05, | |
| "loss": 1.2177, | |
| "step": 2235 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 8.660660317770841e-05, | |
| "loss": 1.1942, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 8.501603059249563e-05, | |
| "loss": 1.163, | |
| "step": 2245 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 8.343884137947333e-05, | |
| "loss": 1.239, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 8.187508640352265e-05, | |
| "loss": 1.1455, | |
| "step": 2255 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 8.032481609626575e-05, | |
| "loss": 1.2165, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 7.878808045444014e-05, | |
| "loss": 1.1982, | |
| "step": 2265 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 7.726492903828575e-05, | |
| "loss": 1.212, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 7.575541096994637e-05, | |
| "loss": 1.2453, | |
| "step": 2275 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 7.4259574931886e-05, | |
| "loss": 1.2607, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 7.27774691653188e-05, | |
| "loss": 1.1936, | |
| "step": 2285 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 7.130914146865247e-05, | |
| "loss": 1.2702, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 6.985463919594781e-05, | |
| "loss": 1.133, | |
| "step": 2295 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 6.841400925539104e-05, | |
| "loss": 1.2135, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "eval_loss": 1.3470078706741333, | |
| "eval_runtime": 10.6711, | |
| "eval_samples_per_second": 14.057, | |
| "eval_steps_per_second": 1.781, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 6.698729810778065e-05, | |
| "loss": 1.1986, | |
| "step": 2305 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 6.557455176502986e-05, | |
| "loss": 1.2254, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 6.417581578868198e-05, | |
| "loss": 1.212, | |
| "step": 2315 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 6.279113528844127e-05, | |
| "loss": 1.1517, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 6.14205549207184e-05, | |
| "loss": 1.1889, | |
| "step": 2325 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 6.006411888718982e-05, | |
| "loss": 1.2348, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 5.872187093337239e-05, | |
| "loss": 1.1862, | |
| "step": 2335 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 5.739385434721295e-05, | |
| "loss": 1.2143, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 5.608011195769186e-05, | |
| "loss": 1.242, | |
| "step": 2345 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 5.478068613344151e-05, | |
| "loss": 1.1817, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 5.3495618781380764e-05, | |
| "loss": 1.1916, | |
| "step": 2355 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 5.2224951345362703e-05, | |
| "loss": 1.1231, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 5.096872480483816e-05, | |
| "loss": 1.2113, | |
| "step": 2365 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 4.972697967353445e-05, | |
| "loss": 1.164, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 4.8499755998148656e-05, | |
| "loss": 1.1947, | |
| "step": 2375 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 4.728709335705561e-05, | |
| "loss": 1.2219, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 4.6089030859032376e-05, | |
| "loss": 1.2104, | |
| "step": 2385 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 4.490560714199637e-05, | |
| "loss": 1.2077, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 4.373686037175917e-05, | |
| "loss": 1.1758, | |
| "step": 2395 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 4.258282824079618e-05, | |
| "loss": 1.2094, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "eval_loss": 1.3436678647994995, | |
| "eval_runtime": 10.6699, | |
| "eval_samples_per_second": 14.058, | |
| "eval_steps_per_second": 1.781, | |
| "step": 2400 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 2766, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "total_flos": 7.911849987145728e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |