| { | |
| "best_metric": 0.8328016996383667, | |
| "best_model_checkpoint": "./vit-base-GTZAN\\checkpoint-550", | |
| "epoch": 16.0, | |
| "eval_steps": 10, | |
| "global_step": 1712, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.0001988317757009346, | |
| "loss": 2.3756, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_accuracy": 0.21164021164021163, | |
| "eval_loss": 2.286055326461792, | |
| "eval_runtime": 3.2931, | |
| "eval_samples_per_second": 57.393, | |
| "eval_steps_per_second": 7.288, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00019766355140186917, | |
| "loss": 2.3051, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "eval_accuracy": 0.3439153439153439, | |
| "eval_loss": 2.1907191276550293, | |
| "eval_runtime": 3.5708, | |
| "eval_samples_per_second": 52.929, | |
| "eval_steps_per_second": 6.721, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.00019649532710280373, | |
| "loss": 2.1219, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_accuracy": 0.31746031746031744, | |
| "eval_loss": 2.021427631378174, | |
| "eval_runtime": 3.5214, | |
| "eval_samples_per_second": 53.671, | |
| "eval_steps_per_second": 6.815, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.00019532710280373834, | |
| "loss": 2.0542, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "eval_accuracy": 0.4074074074074074, | |
| "eval_loss": 1.905888319015503, | |
| "eval_runtime": 3.4441, | |
| "eval_samples_per_second": 54.877, | |
| "eval_steps_per_second": 6.969, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.00019415887850467292, | |
| "loss": 1.8132, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_accuracy": 0.3862433862433862, | |
| "eval_loss": 1.8471989631652832, | |
| "eval_runtime": 3.2687, | |
| "eval_samples_per_second": 57.821, | |
| "eval_steps_per_second": 7.342, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.0001929906542056075, | |
| "loss": 1.8854, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_accuracy": 0.4603174603174603, | |
| "eval_loss": 1.6832294464111328, | |
| "eval_runtime": 3.1893, | |
| "eval_samples_per_second": 59.261, | |
| "eval_steps_per_second": 7.525, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.00019182242990654205, | |
| "loss": 1.6981, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_accuracy": 0.4973544973544973, | |
| "eval_loss": 1.600830078125, | |
| "eval_runtime": 3.1721, | |
| "eval_samples_per_second": 59.583, | |
| "eval_steps_per_second": 7.566, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.00019065420560747664, | |
| "loss": 1.5251, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_accuracy": 0.5026455026455027, | |
| "eval_loss": 1.468518614768982, | |
| "eval_runtime": 3.3583, | |
| "eval_samples_per_second": 56.278, | |
| "eval_steps_per_second": 7.146, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 0.00018948598130841122, | |
| "loss": 1.4463, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "eval_accuracy": 0.6137566137566137, | |
| "eval_loss": 1.3712642192840576, | |
| "eval_runtime": 3.2333, | |
| "eval_samples_per_second": 58.454, | |
| "eval_steps_per_second": 7.423, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.0001883177570093458, | |
| "loss": 1.4335, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_accuracy": 0.4973544973544973, | |
| "eval_loss": 1.4269553422927856, | |
| "eval_runtime": 3.7842, | |
| "eval_samples_per_second": 49.944, | |
| "eval_steps_per_second": 6.342, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 0.00018726635514018693, | |
| "loss": 1.1147, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "eval_accuracy": 0.5925925925925926, | |
| "eval_loss": 1.2793240547180176, | |
| "eval_runtime": 3.3494, | |
| "eval_samples_per_second": 56.427, | |
| "eval_steps_per_second": 7.165, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 0.0001860981308411215, | |
| "loss": 1.3568, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "eval_accuracy": 0.5661375661375662, | |
| "eval_loss": 1.3360047340393066, | |
| "eval_runtime": 3.3593, | |
| "eval_samples_per_second": 56.261, | |
| "eval_steps_per_second": 7.144, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 0.0001849299065420561, | |
| "loss": 1.3077, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "eval_accuracy": 0.5079365079365079, | |
| "eval_loss": 1.452016830444336, | |
| "eval_runtime": 3.1904, | |
| "eval_samples_per_second": 59.241, | |
| "eval_steps_per_second": 7.523, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 0.00018376168224299065, | |
| "loss": 1.2801, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "eval_accuracy": 0.5661375661375662, | |
| "eval_loss": 1.2764976024627686, | |
| "eval_runtime": 3.1251, | |
| "eval_samples_per_second": 60.477, | |
| "eval_steps_per_second": 7.68, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 0.00018259345794392523, | |
| "loss": 1.2894, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "eval_accuracy": 0.6137566137566137, | |
| "eval_loss": 1.194944977760315, | |
| "eval_runtime": 3.3657, | |
| "eval_samples_per_second": 56.154, | |
| "eval_steps_per_second": 7.131, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 0.0001814252336448598, | |
| "loss": 1.2657, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "eval_accuracy": 0.6349206349206349, | |
| "eval_loss": 1.1937017440795898, | |
| "eval_runtime": 3.4004, | |
| "eval_samples_per_second": 55.582, | |
| "eval_steps_per_second": 7.058, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 0.0001802570093457944, | |
| "loss": 0.8784, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "eval_accuracy": 0.6031746031746031, | |
| "eval_loss": 1.2189592123031616, | |
| "eval_runtime": 3.069, | |
| "eval_samples_per_second": 61.583, | |
| "eval_steps_per_second": 7.82, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 0.000179088785046729, | |
| "loss": 1.1575, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "eval_accuracy": 0.6137566137566137, | |
| "eval_loss": 1.2268363237380981, | |
| "eval_runtime": 3.1612, | |
| "eval_samples_per_second": 59.788, | |
| "eval_steps_per_second": 7.592, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 0.00017792056074766356, | |
| "loss": 0.9848, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "eval_accuracy": 0.656084656084656, | |
| "eval_loss": 1.0571767091751099, | |
| "eval_runtime": 3.0146, | |
| "eval_samples_per_second": 62.695, | |
| "eval_steps_per_second": 7.961, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 0.00017675233644859814, | |
| "loss": 0.9409, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "eval_accuracy": 0.6349206349206349, | |
| "eval_loss": 1.160926103591919, | |
| "eval_runtime": 3.1953, | |
| "eval_samples_per_second": 59.149, | |
| "eval_steps_per_second": 7.511, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 0.00017558411214953272, | |
| "loss": 0.9448, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "eval_accuracy": 0.6084656084656085, | |
| "eval_loss": 1.2327442169189453, | |
| "eval_runtime": 3.0705, | |
| "eval_samples_per_second": 61.554, | |
| "eval_steps_per_second": 7.816, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 0.0001744158878504673, | |
| "loss": 1.0819, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "eval_accuracy": 0.582010582010582, | |
| "eval_loss": 1.169877290725708, | |
| "eval_runtime": 3.2052, | |
| "eval_samples_per_second": 58.967, | |
| "eval_steps_per_second": 7.488, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 0.00017324766355140188, | |
| "loss": 0.7485, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "eval_accuracy": 0.6507936507936508, | |
| "eval_loss": 1.1040607690811157, | |
| "eval_runtime": 3.1129, | |
| "eval_samples_per_second": 60.714, | |
| "eval_steps_per_second": 7.71, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 0.00017207943925233644, | |
| "loss": 0.8934, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "eval_accuracy": 0.5873015873015873, | |
| "eval_loss": 1.1672364473342896, | |
| "eval_runtime": 3.2331, | |
| "eval_samples_per_second": 58.458, | |
| "eval_steps_per_second": 7.423, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 0.00017091121495327102, | |
| "loss": 0.8609, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "eval_accuracy": 0.6190476190476191, | |
| "eval_loss": 1.1899827718734741, | |
| "eval_runtime": 3.138, | |
| "eval_samples_per_second": 60.23, | |
| "eval_steps_per_second": 7.648, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 0.00016974299065420563, | |
| "loss": 0.7935, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "eval_accuracy": 0.6402116402116402, | |
| "eval_loss": 1.0623040199279785, | |
| "eval_runtime": 3.1191, | |
| "eval_samples_per_second": 60.594, | |
| "eval_steps_per_second": 7.694, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 0.0001685747663551402, | |
| "loss": 0.8013, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "eval_accuracy": 0.6878306878306878, | |
| "eval_loss": 0.9872872233390808, | |
| "eval_runtime": 3.0196, | |
| "eval_samples_per_second": 62.59, | |
| "eval_steps_per_second": 7.948, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 0.00016740654205607477, | |
| "loss": 0.6669, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "eval_accuracy": 0.656084656084656, | |
| "eval_loss": 1.0078377723693848, | |
| "eval_runtime": 3.0773, | |
| "eval_samples_per_second": 61.418, | |
| "eval_steps_per_second": 7.799, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 0.00016623831775700935, | |
| "loss": 0.7847, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "eval_accuracy": 0.6084656084656085, | |
| "eval_loss": 1.148421049118042, | |
| "eval_runtime": 3.1668, | |
| "eval_samples_per_second": 59.682, | |
| "eval_steps_per_second": 7.579, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 0.00016507009345794393, | |
| "loss": 0.7222, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "eval_accuracy": 0.6243386243386243, | |
| "eval_loss": 1.1295346021652222, | |
| "eval_runtime": 3.1049, | |
| "eval_samples_per_second": 60.871, | |
| "eval_steps_per_second": 7.73, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 0.0001639018691588785, | |
| "loss": 0.7844, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "eval_accuracy": 0.7248677248677249, | |
| "eval_loss": 0.9414218068122864, | |
| "eval_runtime": 3.1524, | |
| "eval_samples_per_second": 59.954, | |
| "eval_steps_per_second": 7.613, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 0.0001627336448598131, | |
| "loss": 0.8057, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "eval_accuracy": 0.6666666666666666, | |
| "eval_loss": 1.050380825996399, | |
| "eval_runtime": 3.1613, | |
| "eval_samples_per_second": 59.785, | |
| "eval_steps_per_second": 7.592, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 0.00016156542056074767, | |
| "loss": 0.4843, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "eval_accuracy": 0.6507936507936508, | |
| "eval_loss": 0.9873789548873901, | |
| "eval_runtime": 3.1677, | |
| "eval_samples_per_second": 59.664, | |
| "eval_steps_per_second": 7.576, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "learning_rate": 0.00016039719626168226, | |
| "loss": 0.6766, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "eval_accuracy": 0.6507936507936508, | |
| "eval_loss": 1.1496278047561646, | |
| "eval_runtime": 3.0545, | |
| "eval_samples_per_second": 61.877, | |
| "eval_steps_per_second": 7.857, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 3.27, | |
| "learning_rate": 0.00015922897196261684, | |
| "loss": 0.4818, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 3.27, | |
| "eval_accuracy": 0.6878306878306878, | |
| "eval_loss": 1.0967848300933838, | |
| "eval_runtime": 3.1038, | |
| "eval_samples_per_second": 60.892, | |
| "eval_steps_per_second": 7.732, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "learning_rate": 0.00015806074766355142, | |
| "loss": 0.5351, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "eval_accuracy": 0.6296296296296297, | |
| "eval_loss": 1.1393951177597046, | |
| "eval_runtime": 3.0544, | |
| "eval_samples_per_second": 61.877, | |
| "eval_steps_per_second": 7.857, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 3.46, | |
| "learning_rate": 0.000156892523364486, | |
| "loss": 0.5035, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 3.46, | |
| "eval_accuracy": 0.708994708994709, | |
| "eval_loss": 0.9814600944519043, | |
| "eval_runtime": 3.6264, | |
| "eval_samples_per_second": 52.118, | |
| "eval_steps_per_second": 6.618, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 3.55, | |
| "learning_rate": 0.00015572429906542056, | |
| "loss": 0.4032, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 3.55, | |
| "eval_accuracy": 0.6402116402116402, | |
| "eval_loss": 1.0881891250610352, | |
| "eval_runtime": 3.1861, | |
| "eval_samples_per_second": 59.32, | |
| "eval_steps_per_second": 7.533, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "learning_rate": 0.00015455607476635514, | |
| "loss": 0.639, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "eval_accuracy": 0.6084656084656085, | |
| "eval_loss": 1.2611372470855713, | |
| "eval_runtime": 3.2278, | |
| "eval_samples_per_second": 58.554, | |
| "eval_steps_per_second": 7.435, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 3.74, | |
| "learning_rate": 0.00015338785046728972, | |
| "loss": 0.5156, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 3.74, | |
| "eval_accuracy": 0.656084656084656, | |
| "eval_loss": 1.037644624710083, | |
| "eval_runtime": 3.6337, | |
| "eval_samples_per_second": 52.013, | |
| "eval_steps_per_second": 6.605, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 3.83, | |
| "learning_rate": 0.00015221962616822433, | |
| "loss": 0.4884, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 3.83, | |
| "eval_accuracy": 0.6984126984126984, | |
| "eval_loss": 0.950617790222168, | |
| "eval_runtime": 3.4889, | |
| "eval_samples_per_second": 54.172, | |
| "eval_steps_per_second": 6.879, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 3.93, | |
| "learning_rate": 0.00015105140186915888, | |
| "loss": 0.5875, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 3.93, | |
| "eval_accuracy": 0.7513227513227513, | |
| "eval_loss": 0.8479233980178833, | |
| "eval_runtime": 3.0768, | |
| "eval_samples_per_second": 61.428, | |
| "eval_steps_per_second": 7.8, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "learning_rate": 0.00014988317757009346, | |
| "loss": 0.6982, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "eval_accuracy": 0.6825396825396826, | |
| "eval_loss": 1.0894999504089355, | |
| "eval_runtime": 3.1014, | |
| "eval_samples_per_second": 60.941, | |
| "eval_steps_per_second": 7.738, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 4.11, | |
| "learning_rate": 0.00014871495327102805, | |
| "loss": 0.3966, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 4.11, | |
| "eval_accuracy": 0.6984126984126984, | |
| "eval_loss": 0.9708942770957947, | |
| "eval_runtime": 3.0279, | |
| "eval_samples_per_second": 62.42, | |
| "eval_steps_per_second": 7.926, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 4.21, | |
| "learning_rate": 0.00014754672897196263, | |
| "loss": 0.377, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 4.21, | |
| "eval_accuracy": 0.6772486772486772, | |
| "eval_loss": 0.9754199385643005, | |
| "eval_runtime": 3.1346, | |
| "eval_samples_per_second": 60.295, | |
| "eval_steps_per_second": 7.657, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 4.3, | |
| "learning_rate": 0.0001463785046728972, | |
| "loss": 0.3417, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 4.3, | |
| "eval_accuracy": 0.6507936507936508, | |
| "eval_loss": 1.1686595678329468, | |
| "eval_runtime": 3.0945, | |
| "eval_samples_per_second": 61.076, | |
| "eval_steps_per_second": 7.756, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 4.39, | |
| "learning_rate": 0.00014521028037383176, | |
| "loss": 0.336, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 4.39, | |
| "eval_accuracy": 0.6984126984126984, | |
| "eval_loss": 0.9825548529624939, | |
| "eval_runtime": 3.1296, | |
| "eval_samples_per_second": 60.39, | |
| "eval_steps_per_second": 7.669, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 4.49, | |
| "learning_rate": 0.00014404205607476635, | |
| "loss": 0.5201, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 4.49, | |
| "eval_accuracy": 0.6613756613756614, | |
| "eval_loss": 1.177049160003662, | |
| "eval_runtime": 3.0811, | |
| "eval_samples_per_second": 61.341, | |
| "eval_steps_per_second": 7.789, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 4.58, | |
| "learning_rate": 0.00014287383177570095, | |
| "loss": 0.1737, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 4.58, | |
| "eval_accuracy": 0.6878306878306878, | |
| "eval_loss": 1.0491447448730469, | |
| "eval_runtime": 3.1745, | |
| "eval_samples_per_second": 59.537, | |
| "eval_steps_per_second": 7.56, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 4.67, | |
| "learning_rate": 0.00014170560747663554, | |
| "loss": 0.2545, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 4.67, | |
| "eval_accuracy": 0.6984126984126984, | |
| "eval_loss": 1.1352397203445435, | |
| "eval_runtime": 3.0543, | |
| "eval_samples_per_second": 61.879, | |
| "eval_steps_per_second": 7.858, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 4.77, | |
| "learning_rate": 0.0001405373831775701, | |
| "loss": 0.3752, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 4.77, | |
| "eval_accuracy": 0.6931216931216931, | |
| "eval_loss": 1.0300217866897583, | |
| "eval_runtime": 3.2562, | |
| "eval_samples_per_second": 58.043, | |
| "eval_steps_per_second": 7.371, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 4.86, | |
| "learning_rate": 0.00013936915887850467, | |
| "loss": 0.3667, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 4.86, | |
| "eval_accuracy": 0.6825396825396826, | |
| "eval_loss": 1.0355250835418701, | |
| "eval_runtime": 3.0388, | |
| "eval_samples_per_second": 62.196, | |
| "eval_steps_per_second": 7.898, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 4.95, | |
| "learning_rate": 0.00013820093457943925, | |
| "loss": 0.2797, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 4.95, | |
| "eval_accuracy": 0.6984126984126984, | |
| "eval_loss": 0.9882386326789856, | |
| "eval_runtime": 3.3521, | |
| "eval_samples_per_second": 56.383, | |
| "eval_steps_per_second": 7.16, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 5.05, | |
| "learning_rate": 0.00013703271028037384, | |
| "loss": 0.1646, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 5.05, | |
| "eval_accuracy": 0.6984126984126984, | |
| "eval_loss": 1.0728471279144287, | |
| "eval_runtime": 3.1345, | |
| "eval_samples_per_second": 60.297, | |
| "eval_steps_per_second": 7.657, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 5.14, | |
| "learning_rate": 0.00013586448598130842, | |
| "loss": 0.2199, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 5.14, | |
| "eval_accuracy": 0.7566137566137566, | |
| "eval_loss": 0.8328016996383667, | |
| "eval_runtime": 3.3035, | |
| "eval_samples_per_second": 57.213, | |
| "eval_steps_per_second": 7.265, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 5.23, | |
| "learning_rate": 0.000134696261682243, | |
| "loss": 0.2191, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 5.23, | |
| "eval_accuracy": 0.746031746031746, | |
| "eval_loss": 0.9280108213424683, | |
| "eval_runtime": 3.0545, | |
| "eval_samples_per_second": 61.876, | |
| "eval_steps_per_second": 7.857, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 5.33, | |
| "learning_rate": 0.00013352803738317758, | |
| "loss": 0.12, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 5.33, | |
| "eval_accuracy": 0.7037037037037037, | |
| "eval_loss": 1.0978211164474487, | |
| "eval_runtime": 3.1612, | |
| "eval_samples_per_second": 59.788, | |
| "eval_steps_per_second": 7.592, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 5.42, | |
| "learning_rate": 0.00013235981308411216, | |
| "loss": 0.2608, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 5.42, | |
| "eval_accuracy": 0.6878306878306878, | |
| "eval_loss": 1.1158148050308228, | |
| "eval_runtime": 3.1212, | |
| "eval_samples_per_second": 60.553, | |
| "eval_steps_per_second": 7.689, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 5.51, | |
| "learning_rate": 0.00013119158878504674, | |
| "loss": 0.2, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 5.51, | |
| "eval_accuracy": 0.7354497354497355, | |
| "eval_loss": 1.087318778038025, | |
| "eval_runtime": 3.0411, | |
| "eval_samples_per_second": 62.148, | |
| "eval_steps_per_second": 7.892, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 5.61, | |
| "learning_rate": 0.00013002336448598133, | |
| "loss": 0.1899, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 5.61, | |
| "eval_accuracy": 0.7142857142857143, | |
| "eval_loss": 1.0559666156768799, | |
| "eval_runtime": 3.1128, | |
| "eval_samples_per_second": 60.718, | |
| "eval_steps_per_second": 7.71, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 5.7, | |
| "learning_rate": 0.00012885514018691588, | |
| "loss": 0.1113, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 5.7, | |
| "eval_accuracy": 0.7037037037037037, | |
| "eval_loss": 1.1143887042999268, | |
| "eval_runtime": 3.038, | |
| "eval_samples_per_second": 62.211, | |
| "eval_steps_per_second": 7.9, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 5.79, | |
| "learning_rate": 0.00012768691588785046, | |
| "loss": 0.2279, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 5.79, | |
| "eval_accuracy": 0.6666666666666666, | |
| "eval_loss": 1.2534881830215454, | |
| "eval_runtime": 3.4146, | |
| "eval_samples_per_second": 55.351, | |
| "eval_steps_per_second": 7.029, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 5.89, | |
| "learning_rate": 0.00012651869158878504, | |
| "loss": 0.1563, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 5.89, | |
| "eval_accuracy": 0.7354497354497355, | |
| "eval_loss": 1.0802773237228394, | |
| "eval_runtime": 3.0678, | |
| "eval_samples_per_second": 61.608, | |
| "eval_steps_per_second": 7.823, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 5.98, | |
| "learning_rate": 0.00012535046728971965, | |
| "loss": 0.2182, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 5.98, | |
| "eval_accuracy": 0.6349206349206349, | |
| "eval_loss": 1.3904473781585693, | |
| "eval_runtime": 3.1818, | |
| "eval_samples_per_second": 59.399, | |
| "eval_steps_per_second": 7.543, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 6.07, | |
| "learning_rate": 0.0001241822429906542, | |
| "loss": 0.1781, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 6.07, | |
| "eval_accuracy": 0.671957671957672, | |
| "eval_loss": 1.3461418151855469, | |
| "eval_runtime": 3.0144, | |
| "eval_samples_per_second": 62.699, | |
| "eval_steps_per_second": 7.962, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 6.17, | |
| "learning_rate": 0.0001230140186915888, | |
| "loss": 0.1395, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 6.17, | |
| "eval_accuracy": 0.6825396825396826, | |
| "eval_loss": 1.276949405670166, | |
| "eval_runtime": 3.1879, | |
| "eval_samples_per_second": 59.287, | |
| "eval_steps_per_second": 7.529, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 6.26, | |
| "learning_rate": 0.00012184579439252337, | |
| "loss": 0.2308, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 6.26, | |
| "eval_accuracy": 0.6931216931216931, | |
| "eval_loss": 1.2213280200958252, | |
| "eval_runtime": 3.1475, | |
| "eval_samples_per_second": 60.047, | |
| "eval_steps_per_second": 7.625, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 6.36, | |
| "learning_rate": 0.00012067757009345795, | |
| "loss": 0.1899, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 6.36, | |
| "eval_accuracy": 0.7142857142857143, | |
| "eval_loss": 1.0947775840759277, | |
| "eval_runtime": 3.3614, | |
| "eval_samples_per_second": 56.226, | |
| "eval_steps_per_second": 7.14, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 6.45, | |
| "learning_rate": 0.00011950934579439252, | |
| "loss": 0.1702, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 6.45, | |
| "eval_accuracy": 0.6931216931216931, | |
| "eval_loss": 1.2383404970169067, | |
| "eval_runtime": 3.5678, | |
| "eval_samples_per_second": 52.974, | |
| "eval_steps_per_second": 6.727, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 6.54, | |
| "learning_rate": 0.0001183411214953271, | |
| "loss": 0.1055, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 6.54, | |
| "eval_accuracy": 0.6349206349206349, | |
| "eval_loss": 1.4009695053100586, | |
| "eval_runtime": 3.1702, | |
| "eval_samples_per_second": 59.618, | |
| "eval_steps_per_second": 7.571, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 6.64, | |
| "learning_rate": 0.00011717289719626168, | |
| "loss": 0.1151, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 6.64, | |
| "eval_accuracy": 0.671957671957672, | |
| "eval_loss": 1.2606865167617798, | |
| "eval_runtime": 3.2176, | |
| "eval_samples_per_second": 58.74, | |
| "eval_steps_per_second": 7.459, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 6.73, | |
| "learning_rate": 0.00011600467289719628, | |
| "loss": 0.2415, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 6.73, | |
| "eval_accuracy": 0.7301587301587301, | |
| "eval_loss": 1.0520366430282593, | |
| "eval_runtime": 3.1343, | |
| "eval_samples_per_second": 60.3, | |
| "eval_steps_per_second": 7.657, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 6.82, | |
| "learning_rate": 0.00011483644859813085, | |
| "loss": 0.117, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 6.82, | |
| "eval_accuracy": 0.7354497354497355, | |
| "eval_loss": 1.0547845363616943, | |
| "eval_runtime": 3.1212, | |
| "eval_samples_per_second": 60.554, | |
| "eval_steps_per_second": 7.689, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 6.92, | |
| "learning_rate": 0.00011366822429906543, | |
| "loss": 0.184, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 6.92, | |
| "eval_accuracy": 0.6984126984126984, | |
| "eval_loss": 1.1872239112854004, | |
| "eval_runtime": 3.2412, | |
| "eval_samples_per_second": 58.311, | |
| "eval_steps_per_second": 7.405, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "learning_rate": 0.00011250000000000001, | |
| "loss": 0.1997, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "eval_accuracy": 0.7248677248677249, | |
| "eval_loss": 1.1127938032150269, | |
| "eval_runtime": 3.2145, | |
| "eval_samples_per_second": 58.796, | |
| "eval_steps_per_second": 7.466, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 7.1, | |
| "learning_rate": 0.00011133177570093458, | |
| "loss": 0.0645, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 7.1, | |
| "eval_accuracy": 0.6984126984126984, | |
| "eval_loss": 1.1514036655426025, | |
| "eval_runtime": 4.5617, | |
| "eval_samples_per_second": 41.432, | |
| "eval_steps_per_second": 5.261, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 7.2, | |
| "learning_rate": 0.00011016355140186916, | |
| "loss": 0.1025, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 7.2, | |
| "eval_accuracy": 0.7037037037037037, | |
| "eval_loss": 1.2251726388931274, | |
| "eval_runtime": 3.3597, | |
| "eval_samples_per_second": 56.255, | |
| "eval_steps_per_second": 7.143, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 7.29, | |
| "learning_rate": 0.00010899532710280373, | |
| "loss": 0.0407, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 7.29, | |
| "eval_accuracy": 0.7513227513227513, | |
| "eval_loss": 1.0571043491363525, | |
| "eval_runtime": 3.3442, | |
| "eval_samples_per_second": 56.516, | |
| "eval_steps_per_second": 7.177, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 7.38, | |
| "learning_rate": 0.00010782710280373834, | |
| "loss": 0.1752, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 7.38, | |
| "eval_accuracy": 0.7354497354497355, | |
| "eval_loss": 1.081169843673706, | |
| "eval_runtime": 3.2833, | |
| "eval_samples_per_second": 57.564, | |
| "eval_steps_per_second": 7.31, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 7.48, | |
| "learning_rate": 0.0001066588785046729, | |
| "loss": 0.1143, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 7.48, | |
| "eval_accuracy": 0.7142857142857143, | |
| "eval_loss": 1.2182053327560425, | |
| "eval_runtime": 3.3002, | |
| "eval_samples_per_second": 57.269, | |
| "eval_steps_per_second": 7.272, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 7.57, | |
| "learning_rate": 0.00010549065420560749, | |
| "loss": 0.1542, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 7.57, | |
| "eval_accuracy": 0.7142857142857143, | |
| "eval_loss": 1.1789014339447021, | |
| "eval_runtime": 3.2576, | |
| "eval_samples_per_second": 58.018, | |
| "eval_steps_per_second": 7.367, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 7.66, | |
| "learning_rate": 0.00010432242990654207, | |
| "loss": 0.0859, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 7.66, | |
| "eval_accuracy": 0.7195767195767195, | |
| "eval_loss": 1.1392204761505127, | |
| "eval_runtime": 3.3449, | |
| "eval_samples_per_second": 56.505, | |
| "eval_steps_per_second": 7.175, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 7.76, | |
| "learning_rate": 0.00010315420560747664, | |
| "loss": 0.119, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 7.76, | |
| "eval_accuracy": 0.7354497354497355, | |
| "eval_loss": 1.1567529439926147, | |
| "eval_runtime": 3.3747, | |
| "eval_samples_per_second": 56.004, | |
| "eval_steps_per_second": 7.112, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 7.85, | |
| "learning_rate": 0.00010198598130841122, | |
| "loss": 0.0913, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 7.85, | |
| "eval_accuracy": 0.6984126984126984, | |
| "eval_loss": 1.109655499458313, | |
| "eval_runtime": 3.3749, | |
| "eval_samples_per_second": 56.001, | |
| "eval_steps_per_second": 7.111, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 7.94, | |
| "learning_rate": 0.00010081775700934579, | |
| "loss": 0.085, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 7.94, | |
| "eval_accuracy": 0.746031746031746, | |
| "eval_loss": 1.118941068649292, | |
| "eval_runtime": 3.2544, | |
| "eval_samples_per_second": 58.076, | |
| "eval_steps_per_second": 7.375, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 8.04, | |
| "learning_rate": 9.964953271028038e-05, | |
| "loss": 0.0201, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 8.04, | |
| "eval_accuracy": 0.7142857142857143, | |
| "eval_loss": 1.1282655000686646, | |
| "eval_runtime": 3.2809, | |
| "eval_samples_per_second": 57.606, | |
| "eval_steps_per_second": 7.315, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 8.13, | |
| "learning_rate": 9.848130841121495e-05, | |
| "loss": 0.0509, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 8.13, | |
| "eval_accuracy": 0.7407407407407407, | |
| "eval_loss": 1.1005280017852783, | |
| "eval_runtime": 3.2115, | |
| "eval_samples_per_second": 58.851, | |
| "eval_steps_per_second": 7.473, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 8.22, | |
| "learning_rate": 9.731308411214953e-05, | |
| "loss": 0.0326, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 8.22, | |
| "eval_accuracy": 0.7301587301587301, | |
| "eval_loss": 1.0489766597747803, | |
| "eval_runtime": 3.6148, | |
| "eval_samples_per_second": 52.285, | |
| "eval_steps_per_second": 6.639, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 8.32, | |
| "learning_rate": 9.614485981308413e-05, | |
| "loss": 0.0728, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 8.32, | |
| "eval_accuracy": 0.7195767195767195, | |
| "eval_loss": 1.2510557174682617, | |
| "eval_runtime": 3.2769, | |
| "eval_samples_per_second": 57.676, | |
| "eval_steps_per_second": 7.324, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 8.41, | |
| "learning_rate": 9.49766355140187e-05, | |
| "loss": 0.0486, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 8.41, | |
| "eval_accuracy": 0.7142857142857143, | |
| "eval_loss": 1.1832597255706787, | |
| "eval_runtime": 3.441, | |
| "eval_samples_per_second": 54.925, | |
| "eval_steps_per_second": 6.975, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 8.5, | |
| "learning_rate": 9.380841121495328e-05, | |
| "loss": 0.0645, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 8.5, | |
| "eval_accuracy": 0.7724867724867724, | |
| "eval_loss": 0.9881472587585449, | |
| "eval_runtime": 3.3474, | |
| "eval_samples_per_second": 56.463, | |
| "eval_steps_per_second": 7.17, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 8.6, | |
| "learning_rate": 9.264018691588785e-05, | |
| "loss": 0.0194, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 8.6, | |
| "eval_accuracy": 0.7566137566137566, | |
| "eval_loss": 1.0412092208862305, | |
| "eval_runtime": 3.305, | |
| "eval_samples_per_second": 57.187, | |
| "eval_steps_per_second": 7.262, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 8.69, | |
| "learning_rate": 9.147196261682244e-05, | |
| "loss": 0.0215, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 8.69, | |
| "eval_accuracy": 0.7195767195767195, | |
| "eval_loss": 1.2484722137451172, | |
| "eval_runtime": 3.5183, | |
| "eval_samples_per_second": 53.719, | |
| "eval_steps_per_second": 6.821, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 8.79, | |
| "learning_rate": 9.030373831775701e-05, | |
| "loss": 0.0853, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 8.79, | |
| "eval_accuracy": 0.7671957671957672, | |
| "eval_loss": 1.0863738059997559, | |
| "eval_runtime": 3.3344, | |
| "eval_samples_per_second": 56.681, | |
| "eval_steps_per_second": 7.198, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 8.88, | |
| "learning_rate": 8.913551401869159e-05, | |
| "loss": 0.0412, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 8.88, | |
| "eval_accuracy": 0.7248677248677249, | |
| "eval_loss": 1.179593801498413, | |
| "eval_runtime": 3.4549, | |
| "eval_samples_per_second": 54.705, | |
| "eval_steps_per_second": 6.947, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 8.97, | |
| "learning_rate": 8.796728971962617e-05, | |
| "loss": 0.0645, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 8.97, | |
| "eval_accuracy": 0.6878306878306878, | |
| "eval_loss": 1.3152216672897339, | |
| "eval_runtime": 3.4461, | |
| "eval_samples_per_second": 54.844, | |
| "eval_steps_per_second": 6.964, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 9.07, | |
| "learning_rate": 8.679906542056075e-05, | |
| "loss": 0.0654, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 9.07, | |
| "eval_accuracy": 0.6931216931216931, | |
| "eval_loss": 1.2788838148117065, | |
| "eval_runtime": 3.1953, | |
| "eval_samples_per_second": 59.15, | |
| "eval_steps_per_second": 7.511, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 9.16, | |
| "learning_rate": 8.563084112149534e-05, | |
| "loss": 0.0352, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 9.16, | |
| "eval_accuracy": 0.7195767195767195, | |
| "eval_loss": 1.1927844285964966, | |
| "eval_runtime": 3.4374, | |
| "eval_samples_per_second": 54.983, | |
| "eval_steps_per_second": 6.982, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 9.25, | |
| "learning_rate": 8.44626168224299e-05, | |
| "loss": 0.0137, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 9.25, | |
| "eval_accuracy": 0.7354497354497355, | |
| "eval_loss": 1.1643190383911133, | |
| "eval_runtime": 3.1879, | |
| "eval_samples_per_second": 59.287, | |
| "eval_steps_per_second": 7.529, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 9.35, | |
| "learning_rate": 8.32943925233645e-05, | |
| "loss": 0.0227, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 9.35, | |
| "eval_accuracy": 0.7142857142857143, | |
| "eval_loss": 1.2255942821502686, | |
| "eval_runtime": 3.4426, | |
| "eval_samples_per_second": 54.901, | |
| "eval_steps_per_second": 6.972, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 9.44, | |
| "learning_rate": 8.212616822429907e-05, | |
| "loss": 0.0391, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 9.44, | |
| "eval_accuracy": 0.7195767195767195, | |
| "eval_loss": 1.2088606357574463, | |
| "eval_runtime": 3.1411, | |
| "eval_samples_per_second": 60.17, | |
| "eval_steps_per_second": 7.641, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 9.53, | |
| "learning_rate": 8.095794392523365e-05, | |
| "loss": 0.0163, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 9.53, | |
| "eval_accuracy": 0.6931216931216931, | |
| "eval_loss": 1.3879644870758057, | |
| "eval_runtime": 3.5148, | |
| "eval_samples_per_second": 53.773, | |
| "eval_steps_per_second": 6.828, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 9.63, | |
| "learning_rate": 7.978971962616823e-05, | |
| "loss": 0.0225, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 9.63, | |
| "eval_accuracy": 0.6931216931216931, | |
| "eval_loss": 1.3944264650344849, | |
| "eval_runtime": 3.2816, | |
| "eval_samples_per_second": 57.594, | |
| "eval_steps_per_second": 7.314, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 9.72, | |
| "learning_rate": 7.862149532710281e-05, | |
| "loss": 0.0348, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 9.72, | |
| "eval_accuracy": 0.7142857142857143, | |
| "eval_loss": 1.3256537914276123, | |
| "eval_runtime": 3.2964, | |
| "eval_samples_per_second": 57.334, | |
| "eval_steps_per_second": 7.281, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 9.81, | |
| "learning_rate": 7.74532710280374e-05, | |
| "loss": 0.0354, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 9.81, | |
| "eval_accuracy": 0.746031746031746, | |
| "eval_loss": 1.1538487672805786, | |
| "eval_runtime": 3.3622, | |
| "eval_samples_per_second": 56.213, | |
| "eval_steps_per_second": 7.138, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 9.91, | |
| "learning_rate": 7.628504672897196e-05, | |
| "loss": 0.0412, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 9.91, | |
| "eval_accuracy": 0.7248677248677249, | |
| "eval_loss": 1.237243890762329, | |
| "eval_runtime": 3.4338, | |
| "eval_samples_per_second": 55.041, | |
| "eval_steps_per_second": 6.989, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 7.511682242990654e-05, | |
| "loss": 0.055, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.708994708994709, | |
| "eval_loss": 1.2265738248825073, | |
| "eval_runtime": 3.4414, | |
| "eval_samples_per_second": 54.919, | |
| "eval_steps_per_second": 6.974, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 10.09, | |
| "learning_rate": 7.394859813084113e-05, | |
| "loss": 0.0115, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 10.09, | |
| "eval_accuracy": 0.7248677248677249, | |
| "eval_loss": 1.235258936882019, | |
| "eval_runtime": 3.3434, | |
| "eval_samples_per_second": 56.53, | |
| "eval_steps_per_second": 7.178, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 10.19, | |
| "learning_rate": 7.278037383177571e-05, | |
| "loss": 0.011, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 10.19, | |
| "eval_accuracy": 0.7248677248677249, | |
| "eval_loss": 1.2655125856399536, | |
| "eval_runtime": 3.2569, | |
| "eval_samples_per_second": 58.031, | |
| "eval_steps_per_second": 7.369, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 10.28, | |
| "learning_rate": 7.161214953271029e-05, | |
| "loss": 0.0105, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 10.28, | |
| "eval_accuracy": 0.7354497354497355, | |
| "eval_loss": 1.2830661535263062, | |
| "eval_runtime": 3.3769, | |
| "eval_samples_per_second": 55.968, | |
| "eval_steps_per_second": 7.107, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 10.37, | |
| "learning_rate": 7.044392523364486e-05, | |
| "loss": 0.0248, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 10.37, | |
| "eval_accuracy": 0.7142857142857143, | |
| "eval_loss": 1.3138365745544434, | |
| "eval_runtime": 3.2282, | |
| "eval_samples_per_second": 58.547, | |
| "eval_steps_per_second": 7.435, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 10.47, | |
| "learning_rate": 6.927570093457945e-05, | |
| "loss": 0.0287, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 10.47, | |
| "eval_accuracy": 0.7195767195767195, | |
| "eval_loss": 1.247241735458374, | |
| "eval_runtime": 3.7473, | |
| "eval_samples_per_second": 50.437, | |
| "eval_steps_per_second": 6.405, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 10.56, | |
| "learning_rate": 6.810747663551402e-05, | |
| "loss": 0.017, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 10.56, | |
| "eval_accuracy": 0.7619047619047619, | |
| "eval_loss": 1.1517435312271118, | |
| "eval_runtime": 3.3479, | |
| "eval_samples_per_second": 56.453, | |
| "eval_steps_per_second": 7.169, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 10.65, | |
| "learning_rate": 6.69392523364486e-05, | |
| "loss": 0.0326, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 10.65, | |
| "eval_accuracy": 0.7513227513227513, | |
| "eval_loss": 1.1729180812835693, | |
| "eval_runtime": 3.563, | |
| "eval_samples_per_second": 53.045, | |
| "eval_steps_per_second": 6.736, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 10.75, | |
| "learning_rate": 6.577102803738317e-05, | |
| "loss": 0.0298, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 10.75, | |
| "eval_accuracy": 0.746031746031746, | |
| "eval_loss": 1.1990931034088135, | |
| "eval_runtime": 3.1999, | |
| "eval_samples_per_second": 59.065, | |
| "eval_steps_per_second": 7.5, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 10.84, | |
| "learning_rate": 6.460280373831777e-05, | |
| "loss": 0.0087, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 10.84, | |
| "eval_accuracy": 0.7195767195767195, | |
| "eval_loss": 1.1964682340621948, | |
| "eval_runtime": 3.3211, | |
| "eval_samples_per_second": 56.908, | |
| "eval_steps_per_second": 7.226, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 10.93, | |
| "learning_rate": 6.343457943925233e-05, | |
| "loss": 0.0104, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 10.93, | |
| "eval_accuracy": 0.7301587301587301, | |
| "eval_loss": 1.200627088546753, | |
| "eval_runtime": 3.2863, | |
| "eval_samples_per_second": 57.511, | |
| "eval_steps_per_second": 7.303, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 11.03, | |
| "learning_rate": 6.226635514018691e-05, | |
| "loss": 0.0176, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 11.03, | |
| "eval_accuracy": 0.7195767195767195, | |
| "eval_loss": 1.2818912267684937, | |
| "eval_runtime": 3.3882, | |
| "eval_samples_per_second": 55.783, | |
| "eval_steps_per_second": 7.083, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 11.12, | |
| "learning_rate": 6.109813084112151e-05, | |
| "loss": 0.0088, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 11.12, | |
| "eval_accuracy": 0.7248677248677249, | |
| "eval_loss": 1.2860090732574463, | |
| "eval_runtime": 3.4546, | |
| "eval_samples_per_second": 54.709, | |
| "eval_steps_per_second": 6.947, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 11.21, | |
| "learning_rate": 5.992990654205608e-05, | |
| "loss": 0.0218, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 11.21, | |
| "eval_accuracy": 0.7407407407407407, | |
| "eval_loss": 1.1996196508407593, | |
| "eval_runtime": 3.4627, | |
| "eval_samples_per_second": 54.582, | |
| "eval_steps_per_second": 6.931, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 11.31, | |
| "learning_rate": 5.876168224299065e-05, | |
| "loss": 0.011, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 11.31, | |
| "eval_accuracy": 0.7407407407407407, | |
| "eval_loss": 1.1904582977294922, | |
| "eval_runtime": 3.6413, | |
| "eval_samples_per_second": 51.905, | |
| "eval_steps_per_second": 6.591, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 11.4, | |
| "learning_rate": 5.7593457943925235e-05, | |
| "loss": 0.0195, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 11.4, | |
| "eval_accuracy": 0.746031746031746, | |
| "eval_loss": 1.1777358055114746, | |
| "eval_runtime": 3.4353, | |
| "eval_samples_per_second": 55.016, | |
| "eval_steps_per_second": 6.986, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 11.5, | |
| "learning_rate": 5.6425233644859823e-05, | |
| "loss": 0.012, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 11.5, | |
| "eval_accuracy": 0.7566137566137566, | |
| "eval_loss": 1.1417244672775269, | |
| "eval_runtime": 3.4149, | |
| "eval_samples_per_second": 55.346, | |
| "eval_steps_per_second": 7.028, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 11.59, | |
| "learning_rate": 5.52570093457944e-05, | |
| "loss": 0.0075, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 11.59, | |
| "eval_accuracy": 0.7619047619047619, | |
| "eval_loss": 1.1428831815719604, | |
| "eval_runtime": 3.4904, | |
| "eval_samples_per_second": 54.148, | |
| "eval_steps_per_second": 6.876, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 11.68, | |
| "learning_rate": 5.408878504672897e-05, | |
| "loss": 0.0131, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 11.68, | |
| "eval_accuracy": 0.7671957671957672, | |
| "eval_loss": 1.1381064653396606, | |
| "eval_runtime": 3.3671, | |
| "eval_samples_per_second": 56.131, | |
| "eval_steps_per_second": 7.128, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 11.78, | |
| "learning_rate": 5.292056074766355e-05, | |
| "loss": 0.0078, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 11.78, | |
| "eval_accuracy": 0.7566137566137566, | |
| "eval_loss": 1.156213641166687, | |
| "eval_runtime": 3.7773, | |
| "eval_samples_per_second": 50.036, | |
| "eval_steps_per_second": 6.354, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 11.87, | |
| "learning_rate": 5.175233644859814e-05, | |
| "loss": 0.0071, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 11.87, | |
| "eval_accuracy": 0.7619047619047619, | |
| "eval_loss": 1.1708426475524902, | |
| "eval_runtime": 3.4015, | |
| "eval_samples_per_second": 55.564, | |
| "eval_steps_per_second": 7.056, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 11.96, | |
| "learning_rate": 5.058411214953271e-05, | |
| "loss": 0.04, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 11.96, | |
| "eval_accuracy": 0.7513227513227513, | |
| "eval_loss": 1.1964821815490723, | |
| "eval_runtime": 3.6594, | |
| "eval_samples_per_second": 51.648, | |
| "eval_steps_per_second": 6.559, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 12.06, | |
| "learning_rate": 4.941588785046729e-05, | |
| "loss": 0.0066, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 12.06, | |
| "eval_accuracy": 0.7354497354497355, | |
| "eval_loss": 1.2294511795043945, | |
| "eval_runtime": 3.2967, | |
| "eval_samples_per_second": 57.329, | |
| "eval_steps_per_second": 7.28, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 12.15, | |
| "learning_rate": 4.8247663551401875e-05, | |
| "loss": 0.0179, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 12.15, | |
| "eval_accuracy": 0.7354497354497355, | |
| "eval_loss": 1.2337099313735962, | |
| "eval_runtime": 3.344, | |
| "eval_samples_per_second": 56.519, | |
| "eval_steps_per_second": 7.177, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 12.24, | |
| "learning_rate": 4.707943925233645e-05, | |
| "loss": 0.0072, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 12.24, | |
| "eval_accuracy": 0.7407407407407407, | |
| "eval_loss": 1.2375584840774536, | |
| "eval_runtime": 3.3433, | |
| "eval_samples_per_second": 56.531, | |
| "eval_steps_per_second": 7.179, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 12.34, | |
| "learning_rate": 4.591121495327103e-05, | |
| "loss": 0.0189, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 12.34, | |
| "eval_accuracy": 0.7354497354497355, | |
| "eval_loss": 1.2402395009994507, | |
| "eval_runtime": 3.4557, | |
| "eval_samples_per_second": 54.692, | |
| "eval_steps_per_second": 6.945, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 12.43, | |
| "learning_rate": 4.4742990654205606e-05, | |
| "loss": 0.0067, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 12.43, | |
| "eval_accuracy": 0.7407407407407407, | |
| "eval_loss": 1.2426130771636963, | |
| "eval_runtime": 3.468, | |
| "eval_samples_per_second": 54.498, | |
| "eval_steps_per_second": 6.92, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 12.52, | |
| "learning_rate": 4.357476635514019e-05, | |
| "loss": 0.014, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 12.52, | |
| "eval_accuracy": 0.746031746031746, | |
| "eval_loss": 1.219921588897705, | |
| "eval_runtime": 3.4683, | |
| "eval_samples_per_second": 54.494, | |
| "eval_steps_per_second": 6.92, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 12.62, | |
| "learning_rate": 4.240654205607476e-05, | |
| "loss": 0.0065, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 12.62, | |
| "eval_accuracy": 0.7513227513227513, | |
| "eval_loss": 1.2070165872573853, | |
| "eval_runtime": 3.3345, | |
| "eval_samples_per_second": 56.68, | |
| "eval_steps_per_second": 7.197, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 12.71, | |
| "learning_rate": 4.123831775700935e-05, | |
| "loss": 0.0119, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 12.71, | |
| "eval_accuracy": 0.7513227513227513, | |
| "eval_loss": 1.2172141075134277, | |
| "eval_runtime": 3.335, | |
| "eval_samples_per_second": 56.672, | |
| "eval_steps_per_second": 7.196, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 12.8, | |
| "learning_rate": 4.0070093457943926e-05, | |
| "loss": 0.0065, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 12.8, | |
| "eval_accuracy": 0.746031746031746, | |
| "eval_loss": 1.2299124002456665, | |
| "eval_runtime": 3.4554, | |
| "eval_samples_per_second": 54.697, | |
| "eval_steps_per_second": 6.946, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 12.9, | |
| "learning_rate": 3.890186915887851e-05, | |
| "loss": 0.0139, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 12.9, | |
| "eval_accuracy": 0.7513227513227513, | |
| "eval_loss": 1.2095272541046143, | |
| "eval_runtime": 3.5215, | |
| "eval_samples_per_second": 53.67, | |
| "eval_steps_per_second": 6.815, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 12.99, | |
| "learning_rate": 3.773364485981308e-05, | |
| "loss": 0.0195, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 12.99, | |
| "eval_accuracy": 0.7513227513227513, | |
| "eval_loss": 1.1914021968841553, | |
| "eval_runtime": 3.3578, | |
| "eval_samples_per_second": 56.287, | |
| "eval_steps_per_second": 7.148, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 13.08, | |
| "learning_rate": 3.6565420560747665e-05, | |
| "loss": 0.0102, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 13.08, | |
| "eval_accuracy": 0.7513227513227513, | |
| "eval_loss": 1.1972215175628662, | |
| "eval_runtime": 3.4283, | |
| "eval_samples_per_second": 55.13, | |
| "eval_steps_per_second": 7.001, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 13.18, | |
| "learning_rate": 3.5397196261682246e-05, | |
| "loss": 0.0162, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 13.18, | |
| "eval_accuracy": 0.7566137566137566, | |
| "eval_loss": 1.2006089687347412, | |
| "eval_runtime": 3.2014, | |
| "eval_samples_per_second": 59.036, | |
| "eval_steps_per_second": 7.497, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 13.27, | |
| "learning_rate": 3.422897196261682e-05, | |
| "loss": 0.0057, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 13.27, | |
| "eval_accuracy": 0.7566137566137566, | |
| "eval_loss": 1.213531494140625, | |
| "eval_runtime": 3.2962, | |
| "eval_samples_per_second": 57.34, | |
| "eval_steps_per_second": 7.281, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 13.36, | |
| "learning_rate": 3.30607476635514e-05, | |
| "loss": 0.0099, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 13.36, | |
| "eval_accuracy": 0.7566137566137566, | |
| "eval_loss": 1.2060108184814453, | |
| "eval_runtime": 3.4059, | |
| "eval_samples_per_second": 55.493, | |
| "eval_steps_per_second": 7.047, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 13.46, | |
| "learning_rate": 3.1892523364485985e-05, | |
| "loss": 0.0092, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 13.46, | |
| "eval_accuracy": 0.7513227513227513, | |
| "eval_loss": 1.209419846534729, | |
| "eval_runtime": 3.3619, | |
| "eval_samples_per_second": 56.218, | |
| "eval_steps_per_second": 7.139, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 13.55, | |
| "learning_rate": 3.0724299065420566e-05, | |
| "loss": 0.0059, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 13.55, | |
| "eval_accuracy": 0.746031746031746, | |
| "eval_loss": 1.21532142162323, | |
| "eval_runtime": 3.4612, | |
| "eval_samples_per_second": 54.605, | |
| "eval_steps_per_second": 6.934, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 13.64, | |
| "learning_rate": 2.955607476635514e-05, | |
| "loss": 0.0132, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 13.64, | |
| "eval_accuracy": 0.7513227513227513, | |
| "eval_loss": 1.2271349430084229, | |
| "eval_runtime": 3.3079, | |
| "eval_samples_per_second": 57.136, | |
| "eval_steps_per_second": 7.255, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 13.74, | |
| "learning_rate": 2.8387850467289723e-05, | |
| "loss": 0.0224, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 13.74, | |
| "eval_accuracy": 0.746031746031746, | |
| "eval_loss": 1.2394039630889893, | |
| "eval_runtime": 3.2507, | |
| "eval_samples_per_second": 58.141, | |
| "eval_steps_per_second": 7.383, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 13.83, | |
| "learning_rate": 2.7219626168224298e-05, | |
| "loss": 0.0116, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 13.83, | |
| "eval_accuracy": 0.746031746031746, | |
| "eval_loss": 1.2353821992874146, | |
| "eval_runtime": 3.2965, | |
| "eval_samples_per_second": 57.333, | |
| "eval_steps_per_second": 7.28, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 13.93, | |
| "learning_rate": 2.605140186915888e-05, | |
| "loss": 0.0096, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 13.93, | |
| "eval_accuracy": 0.746031746031746, | |
| "eval_loss": 1.2316288948059082, | |
| "eval_runtime": 3.263, | |
| "eval_samples_per_second": 57.923, | |
| "eval_steps_per_second": 7.355, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 14.02, | |
| "learning_rate": 2.488317757009346e-05, | |
| "loss": 0.0055, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 14.02, | |
| "eval_accuracy": 0.746031746031746, | |
| "eval_loss": 1.2332398891448975, | |
| "eval_runtime": 3.4255, | |
| "eval_samples_per_second": 55.175, | |
| "eval_steps_per_second": 7.006, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 14.11, | |
| "learning_rate": 2.371495327102804e-05, | |
| "loss": 0.009, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 14.11, | |
| "eval_accuracy": 0.746031746031746, | |
| "eval_loss": 1.2354868650436401, | |
| "eval_runtime": 3.3723, | |
| "eval_samples_per_second": 56.045, | |
| "eval_steps_per_second": 7.117, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 14.21, | |
| "learning_rate": 2.2546728971962618e-05, | |
| "loss": 0.0058, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 14.21, | |
| "eval_accuracy": 0.746031746031746, | |
| "eval_loss": 1.2446562051773071, | |
| "eval_runtime": 3.5668, | |
| "eval_samples_per_second": 52.988, | |
| "eval_steps_per_second": 6.729, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 14.3, | |
| "learning_rate": 2.13785046728972e-05, | |
| "loss": 0.01, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 14.3, | |
| "eval_accuracy": 0.746031746031746, | |
| "eval_loss": 1.2436867952346802, | |
| "eval_runtime": 3.2984, | |
| "eval_samples_per_second": 57.3, | |
| "eval_steps_per_second": 7.276, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 14.39, | |
| "learning_rate": 2.0210280373831778e-05, | |
| "loss": 0.0055, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 14.39, | |
| "eval_accuracy": 0.746031746031746, | |
| "eval_loss": 1.2422124147415161, | |
| "eval_runtime": 3.3462, | |
| "eval_samples_per_second": 56.481, | |
| "eval_steps_per_second": 7.172, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 14.49, | |
| "learning_rate": 1.9042056074766356e-05, | |
| "loss": 0.0187, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 14.49, | |
| "eval_accuracy": 0.7513227513227513, | |
| "eval_loss": 1.221534252166748, | |
| "eval_runtime": 3.4706, | |
| "eval_samples_per_second": 54.457, | |
| "eval_steps_per_second": 6.915, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 14.58, | |
| "learning_rate": 1.7873831775700935e-05, | |
| "loss": 0.0103, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 14.58, | |
| "eval_accuracy": 0.7513227513227513, | |
| "eval_loss": 1.217819333076477, | |
| "eval_runtime": 3.2699, | |
| "eval_samples_per_second": 57.799, | |
| "eval_steps_per_second": 7.34, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 14.67, | |
| "learning_rate": 1.6705607476635516e-05, | |
| "loss": 0.0053, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 14.67, | |
| "eval_accuracy": 0.746031746031746, | |
| "eval_loss": 1.2216895818710327, | |
| "eval_runtime": 3.2903, | |
| "eval_samples_per_second": 57.442, | |
| "eval_steps_per_second": 7.294, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 14.77, | |
| "learning_rate": 1.5537383177570095e-05, | |
| "loss": 0.01, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 14.77, | |
| "eval_accuracy": 0.746031746031746, | |
| "eval_loss": 1.2266777753829956, | |
| "eval_runtime": 3.2812, | |
| "eval_samples_per_second": 57.602, | |
| "eval_steps_per_second": 7.315, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 14.86, | |
| "learning_rate": 1.4369158878504675e-05, | |
| "loss": 0.0238, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 14.86, | |
| "eval_accuracy": 0.746031746031746, | |
| "eval_loss": 1.227875828742981, | |
| "eval_runtime": 3.3613, | |
| "eval_samples_per_second": 56.228, | |
| "eval_steps_per_second": 7.14, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 14.95, | |
| "learning_rate": 1.3200934579439253e-05, | |
| "loss": 0.0091, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 14.95, | |
| "eval_accuracy": 0.746031746031746, | |
| "eval_loss": 1.224220871925354, | |
| "eval_runtime": 3.2469, | |
| "eval_samples_per_second": 58.209, | |
| "eval_steps_per_second": 7.392, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 15.05, | |
| "learning_rate": 1.2032710280373833e-05, | |
| "loss": 0.0053, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 15.05, | |
| "eval_accuracy": 0.7513227513227513, | |
| "eval_loss": 1.2231720685958862, | |
| "eval_runtime": 3.1879, | |
| "eval_samples_per_second": 59.287, | |
| "eval_steps_per_second": 7.528, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 15.14, | |
| "learning_rate": 1.0864485981308411e-05, | |
| "loss": 0.0101, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 15.14, | |
| "eval_accuracy": 0.746031746031746, | |
| "eval_loss": 1.2256537675857544, | |
| "eval_runtime": 3.2787, | |
| "eval_samples_per_second": 57.646, | |
| "eval_steps_per_second": 7.32, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 15.23, | |
| "learning_rate": 9.696261682242991e-06, | |
| "loss": 0.0189, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 15.23, | |
| "eval_accuracy": 0.746031746031746, | |
| "eval_loss": 1.227663278579712, | |
| "eval_runtime": 3.188, | |
| "eval_samples_per_second": 59.286, | |
| "eval_steps_per_second": 7.528, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 15.33, | |
| "learning_rate": 8.52803738317757e-06, | |
| "loss": 0.0056, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 15.33, | |
| "eval_accuracy": 0.746031746031746, | |
| "eval_loss": 1.233586072921753, | |
| "eval_runtime": 3.2945, | |
| "eval_samples_per_second": 57.368, | |
| "eval_steps_per_second": 7.285, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 15.42, | |
| "learning_rate": 7.3598130841121496e-06, | |
| "loss": 0.0052, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 15.42, | |
| "eval_accuracy": 0.746031746031746, | |
| "eval_loss": 1.235275149345398, | |
| "eval_runtime": 3.3479, | |
| "eval_samples_per_second": 56.453, | |
| "eval_steps_per_second": 7.169, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 15.51, | |
| "learning_rate": 6.1915887850467296e-06, | |
| "loss": 0.0054, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 15.51, | |
| "eval_accuracy": 0.746031746031746, | |
| "eval_loss": 1.2359087467193604, | |
| "eval_runtime": 3.3879, | |
| "eval_samples_per_second": 55.786, | |
| "eval_steps_per_second": 7.084, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 15.61, | |
| "learning_rate": 5.023364485981309e-06, | |
| "loss": 0.0054, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 15.61, | |
| "eval_accuracy": 0.746031746031746, | |
| "eval_loss": 1.2361844778060913, | |
| "eval_runtime": 3.1737, | |
| "eval_samples_per_second": 59.551, | |
| "eval_steps_per_second": 7.562, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 15.7, | |
| "learning_rate": 3.855140186915888e-06, | |
| "loss": 0.0102, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 15.7, | |
| "eval_accuracy": 0.7513227513227513, | |
| "eval_loss": 1.2348004579544067, | |
| "eval_runtime": 3.2806, | |
| "eval_samples_per_second": 57.612, | |
| "eval_steps_per_second": 7.316, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 15.79, | |
| "learning_rate": 2.6869158878504674e-06, | |
| "loss": 0.0193, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 15.79, | |
| "eval_accuracy": 0.7513227513227513, | |
| "eval_loss": 1.2326399087905884, | |
| "eval_runtime": 3.2413, | |
| "eval_samples_per_second": 58.309, | |
| "eval_steps_per_second": 7.404, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 15.89, | |
| "learning_rate": 1.5186915887850468e-06, | |
| "loss": 0.0104, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 15.89, | |
| "eval_accuracy": 0.7513227513227513, | |
| "eval_loss": 1.2315497398376465, | |
| "eval_runtime": 3.3871, | |
| "eval_samples_per_second": 55.8, | |
| "eval_steps_per_second": 7.086, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 15.98, | |
| "learning_rate": 3.5046728971962617e-07, | |
| "loss": 0.0095, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 15.98, | |
| "eval_accuracy": 0.7513227513227513, | |
| "eval_loss": 1.2312463521957397, | |
| "eval_runtime": 3.1744, | |
| "eval_samples_per_second": 59.54, | |
| "eval_steps_per_second": 7.561, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "step": 1712, | |
| "total_flos": 2.1042510824822538e+18, | |
| "train_loss": 0.32865437336057146, | |
| "train_runtime": 1354.021, | |
| "train_samples_per_second": 20.053, | |
| "train_steps_per_second": 1.264 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1712, | |
| "num_train_epochs": 16, | |
| "save_steps": 10, | |
| "total_flos": 2.1042510824822538e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |