| { |
| "best_global_step": 2891, |
| "best_metric": 0.137603759765625, |
| "best_model_checkpoint": "saves/lntuning/llama-3-8b-instruct/train_mrpc_1753094152/checkpoint-2891", |
| "epoch": 10.0, |
| "eval_steps": 413, |
| "global_step": 8260, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.006053268765133172, |
| "grad_norm": 4.481978893280029, |
| "learning_rate": 2.421307506053269e-07, |
| "loss": 0.2851, |
| "num_input_tokens_seen": 1920, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.012106537530266344, |
| "grad_norm": 4.846698760986328, |
| "learning_rate": 5.447941888619855e-07, |
| "loss": 0.1664, |
| "num_input_tokens_seen": 3808, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.018159806295399514, |
| "grad_norm": 1.9483075141906738, |
| "learning_rate": 8.474576271186441e-07, |
| "loss": 0.2561, |
| "num_input_tokens_seen": 5856, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.024213075060532687, |
| "grad_norm": 10.700196266174316, |
| "learning_rate": 1.1501210653753028e-06, |
| "loss": 0.3437, |
| "num_input_tokens_seen": 7840, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.03026634382566586, |
| "grad_norm": 2.950713872909546, |
| "learning_rate": 1.4527845036319614e-06, |
| "loss": 0.3354, |
| "num_input_tokens_seen": 10080, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.03631961259079903, |
| "grad_norm": 1.4796098470687866, |
| "learning_rate": 1.7554479418886198e-06, |
| "loss": 0.1572, |
| "num_input_tokens_seen": 12064, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.0423728813559322, |
| "grad_norm": 6.562788963317871, |
| "learning_rate": 2.0581113801452785e-06, |
| "loss": 0.2741, |
| "num_input_tokens_seen": 14144, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.048426150121065374, |
| "grad_norm": 2.534764528274536, |
| "learning_rate": 2.3607748184019373e-06, |
| "loss": 0.3235, |
| "num_input_tokens_seen": 16128, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.05447941888619855, |
| "grad_norm": 2.070178508758545, |
| "learning_rate": 2.6634382566585957e-06, |
| "loss": 0.1762, |
| "num_input_tokens_seen": 18112, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.06053268765133172, |
| "grad_norm": 3.431225061416626, |
| "learning_rate": 2.9661016949152545e-06, |
| "loss": 0.1964, |
| "num_input_tokens_seen": 20288, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.06658595641646489, |
| "grad_norm": 2.204240083694458, |
| "learning_rate": 3.268765133171913e-06, |
| "loss": 0.2061, |
| "num_input_tokens_seen": 22368, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.07263922518159806, |
| "grad_norm": 2.7140026092529297, |
| "learning_rate": 3.5714285714285714e-06, |
| "loss": 0.1718, |
| "num_input_tokens_seen": 24256, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.07869249394673124, |
| "grad_norm": 1.759737491607666, |
| "learning_rate": 3.87409200968523e-06, |
| "loss": 0.1738, |
| "num_input_tokens_seen": 26464, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.0847457627118644, |
| "grad_norm": 4.829991340637207, |
| "learning_rate": 4.176755447941889e-06, |
| "loss": 0.2368, |
| "num_input_tokens_seen": 28736, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.09079903147699758, |
| "grad_norm": 2.778394937515259, |
| "learning_rate": 4.479418886198548e-06, |
| "loss": 0.2533, |
| "num_input_tokens_seen": 30848, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.09685230024213075, |
| "grad_norm": 4.135257244110107, |
| "learning_rate": 4.782082324455206e-06, |
| "loss": 0.1632, |
| "num_input_tokens_seen": 32992, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.10290556900726393, |
| "grad_norm": 5.459167957305908, |
| "learning_rate": 5.084745762711865e-06, |
| "loss": 0.2906, |
| "num_input_tokens_seen": 34976, |
| "step": 85 |
| }, |
| { |
| "epoch": 0.1089588377723971, |
| "grad_norm": 2.954826831817627, |
| "learning_rate": 5.3874092009685235e-06, |
| "loss": 0.2841, |
| "num_input_tokens_seen": 36896, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.11501210653753027, |
| "grad_norm": 1.3170984983444214, |
| "learning_rate": 5.6900726392251815e-06, |
| "loss": 0.1628, |
| "num_input_tokens_seen": 38848, |
| "step": 95 |
| }, |
| { |
| "epoch": 0.12106537530266344, |
| "grad_norm": 1.588362455368042, |
| "learning_rate": 5.99273607748184e-06, |
| "loss": 0.1954, |
| "num_input_tokens_seen": 40960, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.1271186440677966, |
| "grad_norm": 2.257688522338867, |
| "learning_rate": 6.295399515738499e-06, |
| "loss": 0.1837, |
| "num_input_tokens_seen": 43008, |
| "step": 105 |
| }, |
| { |
| "epoch": 0.13317191283292978, |
| "grad_norm": 2.7970499992370605, |
| "learning_rate": 6.598062953995157e-06, |
| "loss": 0.213, |
| "num_input_tokens_seen": 44992, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.13922518159806296, |
| "grad_norm": 2.929041862487793, |
| "learning_rate": 6.900726392251816e-06, |
| "loss": 0.2752, |
| "num_input_tokens_seen": 47072, |
| "step": 115 |
| }, |
| { |
| "epoch": 0.14527845036319612, |
| "grad_norm": 5.870335578918457, |
| "learning_rate": 7.203389830508475e-06, |
| "loss": 0.2604, |
| "num_input_tokens_seen": 49152, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.1513317191283293, |
| "grad_norm": 1.5183007717132568, |
| "learning_rate": 7.5060532687651345e-06, |
| "loss": 0.2287, |
| "num_input_tokens_seen": 51232, |
| "step": 125 |
| }, |
| { |
| "epoch": 0.15738498789346247, |
| "grad_norm": 4.100545883178711, |
| "learning_rate": 7.808716707021792e-06, |
| "loss": 0.2572, |
| "num_input_tokens_seen": 53312, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.16343825665859565, |
| "grad_norm": 7.2280168533325195, |
| "learning_rate": 8.111380145278451e-06, |
| "loss": 0.2749, |
| "num_input_tokens_seen": 55520, |
| "step": 135 |
| }, |
| { |
| "epoch": 0.1694915254237288, |
| "grad_norm": 0.9827978014945984, |
| "learning_rate": 8.41404358353511e-06, |
| "loss": 0.1523, |
| "num_input_tokens_seen": 57440, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.17554479418886199, |
| "grad_norm": 1.256384253501892, |
| "learning_rate": 8.716707021791767e-06, |
| "loss": 0.1786, |
| "num_input_tokens_seen": 59584, |
| "step": 145 |
| }, |
| { |
| "epoch": 0.18159806295399517, |
| "grad_norm": 2.8723526000976562, |
| "learning_rate": 9.019370460048427e-06, |
| "loss": 0.199, |
| "num_input_tokens_seen": 61760, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.18765133171912832, |
| "grad_norm": 1.4389151334762573, |
| "learning_rate": 9.322033898305085e-06, |
| "loss": 0.161, |
| "num_input_tokens_seen": 63744, |
| "step": 155 |
| }, |
| { |
| "epoch": 0.1937046004842615, |
| "grad_norm": 5.578898906707764, |
| "learning_rate": 9.624697336561745e-06, |
| "loss": 0.1934, |
| "num_input_tokens_seen": 65856, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.19975786924939468, |
| "grad_norm": 3.256887435913086, |
| "learning_rate": 9.927360774818403e-06, |
| "loss": 0.2321, |
| "num_input_tokens_seen": 67840, |
| "step": 165 |
| }, |
| { |
| "epoch": 0.20581113801452786, |
| "grad_norm": 6.120675086975098, |
| "learning_rate": 1.023002421307506e-05, |
| "loss": 0.242, |
| "num_input_tokens_seen": 69920, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.211864406779661, |
| "grad_norm": 2.3415868282318115, |
| "learning_rate": 1.053268765133172e-05, |
| "loss": 0.2627, |
| "num_input_tokens_seen": 72032, |
| "step": 175 |
| }, |
| { |
| "epoch": 0.2179176755447942, |
| "grad_norm": 2.5677762031555176, |
| "learning_rate": 1.0835351089588378e-05, |
| "loss": 0.1538, |
| "num_input_tokens_seen": 74112, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.22397094430992737, |
| "grad_norm": 3.503406047821045, |
| "learning_rate": 1.1138014527845036e-05, |
| "loss": 0.2057, |
| "num_input_tokens_seen": 76288, |
| "step": 185 |
| }, |
| { |
| "epoch": 0.23002421307506055, |
| "grad_norm": 1.0483795404434204, |
| "learning_rate": 1.1440677966101696e-05, |
| "loss": 0.1511, |
| "num_input_tokens_seen": 78496, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.2360774818401937, |
| "grad_norm": 2.0007925033569336, |
| "learning_rate": 1.1743341404358354e-05, |
| "loss": 0.1411, |
| "num_input_tokens_seen": 80416, |
| "step": 195 |
| }, |
| { |
| "epoch": 0.24213075060532688, |
| "grad_norm": 1.8174257278442383, |
| "learning_rate": 1.2046004842615012e-05, |
| "loss": 0.1116, |
| "num_input_tokens_seen": 82432, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.24818401937046006, |
| "grad_norm": 1.2617318630218506, |
| "learning_rate": 1.2348668280871672e-05, |
| "loss": 0.1715, |
| "num_input_tokens_seen": 84416, |
| "step": 205 |
| }, |
| { |
| "epoch": 0.2542372881355932, |
| "grad_norm": 0.981200635433197, |
| "learning_rate": 1.2651331719128328e-05, |
| "loss": 0.1204, |
| "num_input_tokens_seen": 86336, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.2602905569007264, |
| "grad_norm": 2.5177159309387207, |
| "learning_rate": 1.2953995157384988e-05, |
| "loss": 0.2313, |
| "num_input_tokens_seen": 88352, |
| "step": 215 |
| }, |
| { |
| "epoch": 0.26634382566585957, |
| "grad_norm": 5.912724018096924, |
| "learning_rate": 1.3256658595641647e-05, |
| "loss": 0.1681, |
| "num_input_tokens_seen": 90432, |
| "step": 220 |
| }, |
| { |
| "epoch": 0.27239709443099275, |
| "grad_norm": 1.0392547845840454, |
| "learning_rate": 1.3559322033898305e-05, |
| "loss": 0.1661, |
| "num_input_tokens_seen": 92512, |
| "step": 225 |
| }, |
| { |
| "epoch": 0.2784503631961259, |
| "grad_norm": 1.2187656164169312, |
| "learning_rate": 1.3861985472154965e-05, |
| "loss": 0.1194, |
| "num_input_tokens_seen": 94528, |
| "step": 230 |
| }, |
| { |
| "epoch": 0.2845036319612591, |
| "grad_norm": 2.3299198150634766, |
| "learning_rate": 1.4164648910411623e-05, |
| "loss": 0.1437, |
| "num_input_tokens_seen": 96576, |
| "step": 235 |
| }, |
| { |
| "epoch": 0.29055690072639223, |
| "grad_norm": 1.3196054697036743, |
| "learning_rate": 1.4467312348668283e-05, |
| "loss": 0.2938, |
| "num_input_tokens_seen": 98624, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.2966101694915254, |
| "grad_norm": 1.6813981533050537, |
| "learning_rate": 1.4769975786924939e-05, |
| "loss": 0.2396, |
| "num_input_tokens_seen": 100832, |
| "step": 245 |
| }, |
| { |
| "epoch": 0.3026634382566586, |
| "grad_norm": 6.751827716827393, |
| "learning_rate": 1.5072639225181599e-05, |
| "loss": 0.3256, |
| "num_input_tokens_seen": 102784, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.30871670702179177, |
| "grad_norm": 3.1990904808044434, |
| "learning_rate": 1.5375302663438258e-05, |
| "loss": 0.1266, |
| "num_input_tokens_seen": 104800, |
| "step": 255 |
| }, |
| { |
| "epoch": 0.31476997578692495, |
| "grad_norm": 7.041596412658691, |
| "learning_rate": 1.5677966101694916e-05, |
| "loss": 0.2191, |
| "num_input_tokens_seen": 106880, |
| "step": 260 |
| }, |
| { |
| "epoch": 0.32082324455205813, |
| "grad_norm": 2.598926305770874, |
| "learning_rate": 1.5980629539951574e-05, |
| "loss": 0.2082, |
| "num_input_tokens_seen": 108960, |
| "step": 265 |
| }, |
| { |
| "epoch": 0.3268765133171913, |
| "grad_norm": 1.5992330312728882, |
| "learning_rate": 1.6283292978208232e-05, |
| "loss": 0.1259, |
| "num_input_tokens_seen": 110944, |
| "step": 270 |
| }, |
| { |
| "epoch": 0.33292978208232443, |
| "grad_norm": 2.167006731033325, |
| "learning_rate": 1.6585956416464894e-05, |
| "loss": 0.1686, |
| "num_input_tokens_seen": 113088, |
| "step": 275 |
| }, |
| { |
| "epoch": 0.3389830508474576, |
| "grad_norm": 2.5932061672210693, |
| "learning_rate": 1.6888619854721548e-05, |
| "loss": 0.184, |
| "num_input_tokens_seen": 115072, |
| "step": 280 |
| }, |
| { |
| "epoch": 0.3450363196125908, |
| "grad_norm": 2.1988534927368164, |
| "learning_rate": 1.719128329297821e-05, |
| "loss": 0.1425, |
| "num_input_tokens_seen": 117280, |
| "step": 285 |
| }, |
| { |
| "epoch": 0.35108958837772397, |
| "grad_norm": 1.3688409328460693, |
| "learning_rate": 1.7493946731234868e-05, |
| "loss": 0.2165, |
| "num_input_tokens_seen": 119456, |
| "step": 290 |
| }, |
| { |
| "epoch": 0.35714285714285715, |
| "grad_norm": 2.1994192600250244, |
| "learning_rate": 1.7796610169491526e-05, |
| "loss": 0.1354, |
| "num_input_tokens_seen": 121472, |
| "step": 295 |
| }, |
| { |
| "epoch": 0.36319612590799033, |
| "grad_norm": 2.168099880218506, |
| "learning_rate": 1.8099273607748184e-05, |
| "loss": 0.1149, |
| "num_input_tokens_seen": 123648, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.3692493946731235, |
| "grad_norm": 1.432853102684021, |
| "learning_rate": 1.8401937046004845e-05, |
| "loss": 0.2357, |
| "num_input_tokens_seen": 125632, |
| "step": 305 |
| }, |
| { |
| "epoch": 0.37530266343825663, |
| "grad_norm": 3.39896297454834, |
| "learning_rate": 1.8704600484261503e-05, |
| "loss": 0.1899, |
| "num_input_tokens_seen": 127680, |
| "step": 310 |
| }, |
| { |
| "epoch": 0.3813559322033898, |
| "grad_norm": 3.7564778327941895, |
| "learning_rate": 1.900726392251816e-05, |
| "loss": 0.1355, |
| "num_input_tokens_seen": 129856, |
| "step": 315 |
| }, |
| { |
| "epoch": 0.387409200968523, |
| "grad_norm": 3.254880905151367, |
| "learning_rate": 1.930992736077482e-05, |
| "loss": 0.1704, |
| "num_input_tokens_seen": 131872, |
| "step": 320 |
| }, |
| { |
| "epoch": 0.3934624697336562, |
| "grad_norm": 1.0621639490127563, |
| "learning_rate": 1.9612590799031477e-05, |
| "loss": 0.262, |
| "num_input_tokens_seen": 133984, |
| "step": 325 |
| }, |
| { |
| "epoch": 0.39951573849878935, |
| "grad_norm": 4.072643280029297, |
| "learning_rate": 1.9915254237288135e-05, |
| "loss": 0.155, |
| "num_input_tokens_seen": 136128, |
| "step": 330 |
| }, |
| { |
| "epoch": 0.40556900726392253, |
| "grad_norm": 1.1124200820922852, |
| "learning_rate": 2.0217917675544796e-05, |
| "loss": 0.179, |
| "num_input_tokens_seen": 138208, |
| "step": 335 |
| }, |
| { |
| "epoch": 0.4116222760290557, |
| "grad_norm": 2.559614896774292, |
| "learning_rate": 2.0520581113801454e-05, |
| "loss": 0.1799, |
| "num_input_tokens_seen": 140288, |
| "step": 340 |
| }, |
| { |
| "epoch": 0.41767554479418884, |
| "grad_norm": 5.550265789031982, |
| "learning_rate": 2.0823244552058112e-05, |
| "loss": 0.212, |
| "num_input_tokens_seen": 142336, |
| "step": 345 |
| }, |
| { |
| "epoch": 0.423728813559322, |
| "grad_norm": 4.045815944671631, |
| "learning_rate": 2.1125907990314774e-05, |
| "loss": 0.1164, |
| "num_input_tokens_seen": 144448, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.4297820823244552, |
| "grad_norm": 2.1211326122283936, |
| "learning_rate": 2.1428571428571428e-05, |
| "loss": 0.2411, |
| "num_input_tokens_seen": 146464, |
| "step": 355 |
| }, |
| { |
| "epoch": 0.4358353510895884, |
| "grad_norm": 0.916531503200531, |
| "learning_rate": 2.1731234866828086e-05, |
| "loss": 0.1893, |
| "num_input_tokens_seen": 148512, |
| "step": 360 |
| }, |
| { |
| "epoch": 0.44188861985472155, |
| "grad_norm": 1.21219003200531, |
| "learning_rate": 2.2033898305084748e-05, |
| "loss": 0.1485, |
| "num_input_tokens_seen": 150496, |
| "step": 365 |
| }, |
| { |
| "epoch": 0.44794188861985473, |
| "grad_norm": 1.8068974018096924, |
| "learning_rate": 2.2336561743341405e-05, |
| "loss": 0.2618, |
| "num_input_tokens_seen": 152608, |
| "step": 370 |
| }, |
| { |
| "epoch": 0.4539951573849879, |
| "grad_norm": 2.374595880508423, |
| "learning_rate": 2.2639225181598063e-05, |
| "loss": 0.2532, |
| "num_input_tokens_seen": 154624, |
| "step": 375 |
| }, |
| { |
| "epoch": 0.4600484261501211, |
| "grad_norm": 0.7082160711288452, |
| "learning_rate": 2.2941888619854725e-05, |
| "loss": 0.1748, |
| "num_input_tokens_seen": 156608, |
| "step": 380 |
| }, |
| { |
| "epoch": 0.4661016949152542, |
| "grad_norm": 2.4511871337890625, |
| "learning_rate": 2.3244552058111383e-05, |
| "loss": 0.2267, |
| "num_input_tokens_seen": 158560, |
| "step": 385 |
| }, |
| { |
| "epoch": 0.4721549636803874, |
| "grad_norm": 5.554380416870117, |
| "learning_rate": 2.3547215496368037e-05, |
| "loss": 0.1376, |
| "num_input_tokens_seen": 160640, |
| "step": 390 |
| }, |
| { |
| "epoch": 0.4782082324455206, |
| "grad_norm": 2.231539011001587, |
| "learning_rate": 2.38498789346247e-05, |
| "loss": 0.1913, |
| "num_input_tokens_seen": 162784, |
| "step": 395 |
| }, |
| { |
| "epoch": 0.48426150121065376, |
| "grad_norm": 1.5285236835479736, |
| "learning_rate": 2.4152542372881357e-05, |
| "loss": 0.1789, |
| "num_input_tokens_seen": 164832, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.49031476997578693, |
| "grad_norm": 3.0688276290893555, |
| "learning_rate": 2.4455205811138015e-05, |
| "loss": 0.1788, |
| "num_input_tokens_seen": 166880, |
| "step": 405 |
| }, |
| { |
| "epoch": 0.4963680387409201, |
| "grad_norm": 1.0780361890792847, |
| "learning_rate": 2.4757869249394676e-05, |
| "loss": 0.1648, |
| "num_input_tokens_seen": 169088, |
| "step": 410 |
| }, |
| { |
| "epoch": 0.5, |
| "eval_loss": 0.17582012712955475, |
| "eval_runtime": 4.5985, |
| "eval_samples_per_second": 79.808, |
| "eval_steps_per_second": 20.006, |
| "num_input_tokens_seen": 170336, |
| "step": 413 |
| }, |
| { |
| "epoch": 0.5024213075060533, |
| "grad_norm": 2.741290330886841, |
| "learning_rate": 2.5060532687651334e-05, |
| "loss": 0.1725, |
| "num_input_tokens_seen": 171232, |
| "step": 415 |
| }, |
| { |
| "epoch": 0.5084745762711864, |
| "grad_norm": 1.3940932750701904, |
| "learning_rate": 2.536319612590799e-05, |
| "loss": 0.2014, |
| "num_input_tokens_seen": 173376, |
| "step": 420 |
| }, |
| { |
| "epoch": 0.5145278450363197, |
| "grad_norm": 1.2796820402145386, |
| "learning_rate": 2.566585956416465e-05, |
| "loss": 0.1241, |
| "num_input_tokens_seen": 175424, |
| "step": 425 |
| }, |
| { |
| "epoch": 0.5205811138014528, |
| "grad_norm": 3.262789487838745, |
| "learning_rate": 2.5968523002421308e-05, |
| "loss": 0.1782, |
| "num_input_tokens_seen": 177664, |
| "step": 430 |
| }, |
| { |
| "epoch": 0.5266343825665859, |
| "grad_norm": 3.2393486499786377, |
| "learning_rate": 2.627118644067797e-05, |
| "loss": 0.2036, |
| "num_input_tokens_seen": 179648, |
| "step": 435 |
| }, |
| { |
| "epoch": 0.5326876513317191, |
| "grad_norm": 2.748382329940796, |
| "learning_rate": 2.6573849878934624e-05, |
| "loss": 0.2153, |
| "num_input_tokens_seen": 181664, |
| "step": 440 |
| }, |
| { |
| "epoch": 0.5387409200968523, |
| "grad_norm": 1.3553707599639893, |
| "learning_rate": 2.6876513317191282e-05, |
| "loss": 0.2238, |
| "num_input_tokens_seen": 183840, |
| "step": 445 |
| }, |
| { |
| "epoch": 0.5447941888619855, |
| "grad_norm": 0.9500827789306641, |
| "learning_rate": 2.7179176755447943e-05, |
| "loss": 0.1729, |
| "num_input_tokens_seen": 185696, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.5508474576271186, |
| "grad_norm": 1.636928677558899, |
| "learning_rate": 2.74818401937046e-05, |
| "loss": 0.1541, |
| "num_input_tokens_seen": 187712, |
| "step": 455 |
| }, |
| { |
| "epoch": 0.5569007263922519, |
| "grad_norm": 1.2328100204467773, |
| "learning_rate": 2.7784503631961263e-05, |
| "loss": 0.172, |
| "num_input_tokens_seen": 189728, |
| "step": 460 |
| }, |
| { |
| "epoch": 0.562953995157385, |
| "grad_norm": 1.4917689561843872, |
| "learning_rate": 2.8087167070217917e-05, |
| "loss": 0.1796, |
| "num_input_tokens_seen": 191744, |
| "step": 465 |
| }, |
| { |
| "epoch": 0.5690072639225182, |
| "grad_norm": 1.818116307258606, |
| "learning_rate": 2.838983050847458e-05, |
| "loss": 0.1308, |
| "num_input_tokens_seen": 193888, |
| "step": 470 |
| }, |
| { |
| "epoch": 0.5750605326876513, |
| "grad_norm": 2.183380126953125, |
| "learning_rate": 2.8692493946731237e-05, |
| "loss": 0.2065, |
| "num_input_tokens_seen": 195904, |
| "step": 475 |
| }, |
| { |
| "epoch": 0.5811138014527845, |
| "grad_norm": 2.1599833965301514, |
| "learning_rate": 2.899515738498789e-05, |
| "loss": 0.2173, |
| "num_input_tokens_seen": 197952, |
| "step": 480 |
| }, |
| { |
| "epoch": 0.5871670702179177, |
| "grad_norm": 3.2142691612243652, |
| "learning_rate": 2.9297820823244553e-05, |
| "loss": 0.1674, |
| "num_input_tokens_seen": 199968, |
| "step": 485 |
| }, |
| { |
| "epoch": 0.5932203389830508, |
| "grad_norm": 9.413737297058105, |
| "learning_rate": 2.960048426150121e-05, |
| "loss": 0.2289, |
| "num_input_tokens_seen": 201984, |
| "step": 490 |
| }, |
| { |
| "epoch": 0.5992736077481841, |
| "grad_norm": 2.025810956954956, |
| "learning_rate": 2.9903147699757872e-05, |
| "loss": 0.1412, |
| "num_input_tokens_seen": 204000, |
| "step": 495 |
| }, |
| { |
| "epoch": 0.6053268765133172, |
| "grad_norm": 3.99399471282959, |
| "learning_rate": 3.0205811138014527e-05, |
| "loss": 0.168, |
| "num_input_tokens_seen": 206080, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.6113801452784504, |
| "grad_norm": 3.777092933654785, |
| "learning_rate": 3.050847457627119e-05, |
| "loss": 0.1914, |
| "num_input_tokens_seen": 208000, |
| "step": 505 |
| }, |
| { |
| "epoch": 0.6174334140435835, |
| "grad_norm": 1.1595715284347534, |
| "learning_rate": 3.0811138014527846e-05, |
| "loss": 0.1263, |
| "num_input_tokens_seen": 210208, |
| "step": 510 |
| }, |
| { |
| "epoch": 0.6234866828087167, |
| "grad_norm": 2.891212224960327, |
| "learning_rate": 3.111380145278451e-05, |
| "loss": 0.1541, |
| "num_input_tokens_seen": 212288, |
| "step": 515 |
| }, |
| { |
| "epoch": 0.6295399515738499, |
| "grad_norm": 2.809659957885742, |
| "learning_rate": 3.141646489104116e-05, |
| "loss": 0.1527, |
| "num_input_tokens_seen": 214400, |
| "step": 520 |
| }, |
| { |
| "epoch": 0.635593220338983, |
| "grad_norm": 2.3840301036834717, |
| "learning_rate": 3.1719128329297823e-05, |
| "loss": 0.1366, |
| "num_input_tokens_seen": 216512, |
| "step": 525 |
| }, |
| { |
| "epoch": 0.6416464891041163, |
| "grad_norm": 1.3832828998565674, |
| "learning_rate": 3.2021791767554485e-05, |
| "loss": 0.1665, |
| "num_input_tokens_seen": 218496, |
| "step": 530 |
| }, |
| { |
| "epoch": 0.6476997578692494, |
| "grad_norm": 2.0845787525177, |
| "learning_rate": 3.232445520581114e-05, |
| "loss": 0.1143, |
| "num_input_tokens_seen": 220512, |
| "step": 535 |
| }, |
| { |
| "epoch": 0.6537530266343826, |
| "grad_norm": 1.3605108261108398, |
| "learning_rate": 3.26271186440678e-05, |
| "loss": 0.1541, |
| "num_input_tokens_seen": 222560, |
| "step": 540 |
| }, |
| { |
| "epoch": 0.6598062953995157, |
| "grad_norm": 2.2927634716033936, |
| "learning_rate": 3.2929782082324455e-05, |
| "loss": 0.1235, |
| "num_input_tokens_seen": 224480, |
| "step": 545 |
| }, |
| { |
| "epoch": 0.6658595641646489, |
| "grad_norm": 7.201409339904785, |
| "learning_rate": 3.323244552058112e-05, |
| "loss": 0.2002, |
| "num_input_tokens_seen": 226560, |
| "step": 550 |
| }, |
| { |
| "epoch": 0.6719128329297821, |
| "grad_norm": 2.5615785121917725, |
| "learning_rate": 3.353510895883777e-05, |
| "loss": 0.1185, |
| "num_input_tokens_seen": 228512, |
| "step": 555 |
| }, |
| { |
| "epoch": 0.6779661016949152, |
| "grad_norm": 5.765679359436035, |
| "learning_rate": 3.383777239709443e-05, |
| "loss": 0.1894, |
| "num_input_tokens_seen": 230528, |
| "step": 560 |
| }, |
| { |
| "epoch": 0.6840193704600485, |
| "grad_norm": 1.7863295078277588, |
| "learning_rate": 3.4140435835351094e-05, |
| "loss": 0.1473, |
| "num_input_tokens_seen": 232768, |
| "step": 565 |
| }, |
| { |
| "epoch": 0.6900726392251816, |
| "grad_norm": 3.400667428970337, |
| "learning_rate": 3.444309927360775e-05, |
| "loss": 0.1475, |
| "num_input_tokens_seen": 234784, |
| "step": 570 |
| }, |
| { |
| "epoch": 0.6961259079903148, |
| "grad_norm": 3.5374653339385986, |
| "learning_rate": 3.474576271186441e-05, |
| "loss": 0.3046, |
| "num_input_tokens_seen": 236832, |
| "step": 575 |
| }, |
| { |
| "epoch": 0.7021791767554479, |
| "grad_norm": 2.3441779613494873, |
| "learning_rate": 3.5048426150121065e-05, |
| "loss": 0.1825, |
| "num_input_tokens_seen": 238784, |
| "step": 580 |
| }, |
| { |
| "epoch": 0.7082324455205811, |
| "grad_norm": 3.510235071182251, |
| "learning_rate": 3.5351089588377726e-05, |
| "loss": 0.236, |
| "num_input_tokens_seen": 240768, |
| "step": 585 |
| }, |
| { |
| "epoch": 0.7142857142857143, |
| "grad_norm": 3.022887706756592, |
| "learning_rate": 3.565375302663439e-05, |
| "loss": 0.205, |
| "num_input_tokens_seen": 242848, |
| "step": 590 |
| }, |
| { |
| "epoch": 0.7203389830508474, |
| "grad_norm": 5.518234729766846, |
| "learning_rate": 3.595641646489104e-05, |
| "loss": 0.1348, |
| "num_input_tokens_seen": 244992, |
| "step": 595 |
| }, |
| { |
| "epoch": 0.7263922518159807, |
| "grad_norm": 4.24160623550415, |
| "learning_rate": 3.62590799031477e-05, |
| "loss": 0.1509, |
| "num_input_tokens_seen": 247040, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.7324455205811138, |
| "grad_norm": 4.148669242858887, |
| "learning_rate": 3.656174334140436e-05, |
| "loss": 0.2164, |
| "num_input_tokens_seen": 249184, |
| "step": 605 |
| }, |
| { |
| "epoch": 0.738498789346247, |
| "grad_norm": 3.636296033859253, |
| "learning_rate": 3.686440677966102e-05, |
| "loss": 0.1869, |
| "num_input_tokens_seen": 251104, |
| "step": 610 |
| }, |
| { |
| "epoch": 0.7445520581113801, |
| "grad_norm": 4.738290786743164, |
| "learning_rate": 3.7167070217917674e-05, |
| "loss": 0.2009, |
| "num_input_tokens_seen": 253056, |
| "step": 615 |
| }, |
| { |
| "epoch": 0.7506053268765133, |
| "grad_norm": 1.276099443435669, |
| "learning_rate": 3.7469733656174335e-05, |
| "loss": 0.1407, |
| "num_input_tokens_seen": 255008, |
| "step": 620 |
| }, |
| { |
| "epoch": 0.7566585956416465, |
| "grad_norm": 6.177402973175049, |
| "learning_rate": 3.7772397094431e-05, |
| "loss": 0.1873, |
| "num_input_tokens_seen": 257120, |
| "step": 625 |
| }, |
| { |
| "epoch": 0.7627118644067796, |
| "grad_norm": 1.6612720489501953, |
| "learning_rate": 3.807506053268765e-05, |
| "loss": 0.1251, |
| "num_input_tokens_seen": 259168, |
| "step": 630 |
| }, |
| { |
| "epoch": 0.7687651331719129, |
| "grad_norm": 4.596778392791748, |
| "learning_rate": 3.837772397094431e-05, |
| "loss": 0.1175, |
| "num_input_tokens_seen": 261216, |
| "step": 635 |
| }, |
| { |
| "epoch": 0.774818401937046, |
| "grad_norm": 5.147200584411621, |
| "learning_rate": 3.868038740920097e-05, |
| "loss": 0.1912, |
| "num_input_tokens_seen": 263136, |
| "step": 640 |
| }, |
| { |
| "epoch": 0.7808716707021792, |
| "grad_norm": 3.2150142192840576, |
| "learning_rate": 3.898305084745763e-05, |
| "loss": 0.2389, |
| "num_input_tokens_seen": 265184, |
| "step": 645 |
| }, |
| { |
| "epoch": 0.7869249394673123, |
| "grad_norm": 1.7957394123077393, |
| "learning_rate": 3.928571428571429e-05, |
| "loss": 0.156, |
| "num_input_tokens_seen": 267264, |
| "step": 650 |
| }, |
| { |
| "epoch": 0.7929782082324455, |
| "grad_norm": 1.8125636577606201, |
| "learning_rate": 3.958837772397095e-05, |
| "loss": 0.3316, |
| "num_input_tokens_seen": 269216, |
| "step": 655 |
| }, |
| { |
| "epoch": 0.7990314769975787, |
| "grad_norm": 1.157749056816101, |
| "learning_rate": 3.9891041162227606e-05, |
| "loss": 0.1813, |
| "num_input_tokens_seen": 271264, |
| "step": 660 |
| }, |
| { |
| "epoch": 0.8050847457627118, |
| "grad_norm": 1.4555474519729614, |
| "learning_rate": 4.019370460048426e-05, |
| "loss": 0.1342, |
| "num_input_tokens_seen": 273280, |
| "step": 665 |
| }, |
| { |
| "epoch": 0.8111380145278451, |
| "grad_norm": 1.5828756093978882, |
| "learning_rate": 4.049636803874092e-05, |
| "loss": 0.1223, |
| "num_input_tokens_seen": 275392, |
| "step": 670 |
| }, |
| { |
| "epoch": 0.8171912832929782, |
| "grad_norm": 3.629384994506836, |
| "learning_rate": 4.0799031476997577e-05, |
| "loss": 0.1947, |
| "num_input_tokens_seen": 277440, |
| "step": 675 |
| }, |
| { |
| "epoch": 0.8232445520581114, |
| "grad_norm": 2.305537223815918, |
| "learning_rate": 4.110169491525424e-05, |
| "loss": 0.2098, |
| "num_input_tokens_seen": 279456, |
| "step": 680 |
| }, |
| { |
| "epoch": 0.8292978208232445, |
| "grad_norm": 1.5820642709732056, |
| "learning_rate": 4.14043583535109e-05, |
| "loss": 0.1602, |
| "num_input_tokens_seen": 281632, |
| "step": 685 |
| }, |
| { |
| "epoch": 0.8353510895883777, |
| "grad_norm": 3.7225077152252197, |
| "learning_rate": 4.170702179176756e-05, |
| "loss": 0.2414, |
| "num_input_tokens_seen": 283680, |
| "step": 690 |
| }, |
| { |
| "epoch": 0.8414043583535109, |
| "grad_norm": 2.8825156688690186, |
| "learning_rate": 4.2009685230024215e-05, |
| "loss": 0.1334, |
| "num_input_tokens_seen": 285760, |
| "step": 695 |
| }, |
| { |
| "epoch": 0.847457627118644, |
| "grad_norm": 6.222320556640625, |
| "learning_rate": 4.231234866828087e-05, |
| "loss": 0.1221, |
| "num_input_tokens_seen": 287904, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.8535108958837773, |
| "grad_norm": 1.3990041017532349, |
| "learning_rate": 4.261501210653753e-05, |
| "loss": 0.1937, |
| "num_input_tokens_seen": 289952, |
| "step": 705 |
| }, |
| { |
| "epoch": 0.8595641646489104, |
| "grad_norm": 3.03328800201416, |
| "learning_rate": 4.2917675544794186e-05, |
| "loss": 0.129, |
| "num_input_tokens_seen": 291968, |
| "step": 710 |
| }, |
| { |
| "epoch": 0.8656174334140436, |
| "grad_norm": 2.7313449382781982, |
| "learning_rate": 4.3220338983050854e-05, |
| "loss": 0.2106, |
| "num_input_tokens_seen": 293952, |
| "step": 715 |
| }, |
| { |
| "epoch": 0.8716707021791767, |
| "grad_norm": 9.207576751708984, |
| "learning_rate": 4.352300242130751e-05, |
| "loss": 0.2177, |
| "num_input_tokens_seen": 296192, |
| "step": 720 |
| }, |
| { |
| "epoch": 0.8777239709443099, |
| "grad_norm": 2.5809319019317627, |
| "learning_rate": 4.382566585956417e-05, |
| "loss": 0.1338, |
| "num_input_tokens_seen": 298336, |
| "step": 725 |
| }, |
| { |
| "epoch": 0.8837772397094431, |
| "grad_norm": 1.9844462871551514, |
| "learning_rate": 4.4128329297820825e-05, |
| "loss": 0.1614, |
| "num_input_tokens_seen": 300352, |
| "step": 730 |
| }, |
| { |
| "epoch": 0.8898305084745762, |
| "grad_norm": 3.2159414291381836, |
| "learning_rate": 4.443099273607748e-05, |
| "loss": 0.1122, |
| "num_input_tokens_seen": 302432, |
| "step": 735 |
| }, |
| { |
| "epoch": 0.8958837772397095, |
| "grad_norm": 9.370662689208984, |
| "learning_rate": 4.473365617433414e-05, |
| "loss": 0.1848, |
| "num_input_tokens_seen": 304544, |
| "step": 740 |
| }, |
| { |
| "epoch": 0.9019370460048426, |
| "grad_norm": 0.8076304197311401, |
| "learning_rate": 4.50363196125908e-05, |
| "loss": 0.1298, |
| "num_input_tokens_seen": 306592, |
| "step": 745 |
| }, |
| { |
| "epoch": 0.9079903147699758, |
| "grad_norm": 4.535274982452393, |
| "learning_rate": 4.533898305084746e-05, |
| "loss": 0.16, |
| "num_input_tokens_seen": 308672, |
| "step": 750 |
| }, |
| { |
| "epoch": 0.914043583535109, |
| "grad_norm": 0.7559286952018738, |
| "learning_rate": 4.564164648910412e-05, |
| "loss": 0.0545, |
| "num_input_tokens_seen": 310656, |
| "step": 755 |
| }, |
| { |
| "epoch": 0.9200968523002422, |
| "grad_norm": 2.4823074340820312, |
| "learning_rate": 4.594430992736078e-05, |
| "loss": 0.2359, |
| "num_input_tokens_seen": 312768, |
| "step": 760 |
| }, |
| { |
| "epoch": 0.9261501210653753, |
| "grad_norm": 0.8833109736442566, |
| "learning_rate": 4.6246973365617434e-05, |
| "loss": 0.0402, |
| "num_input_tokens_seen": 314880, |
| "step": 765 |
| }, |
| { |
| "epoch": 0.9322033898305084, |
| "grad_norm": 2.477018117904663, |
| "learning_rate": 4.654963680387409e-05, |
| "loss": 0.0613, |
| "num_input_tokens_seen": 316960, |
| "step": 770 |
| }, |
| { |
| "epoch": 0.9382566585956417, |
| "grad_norm": 5.7945685386657715, |
| "learning_rate": 4.685230024213076e-05, |
| "loss": 0.1336, |
| "num_input_tokens_seen": 319072, |
| "step": 775 |
| }, |
| { |
| "epoch": 0.9443099273607748, |
| "grad_norm": 1.619981050491333, |
| "learning_rate": 4.715496368038741e-05, |
| "loss": 0.1738, |
| "num_input_tokens_seen": 321248, |
| "step": 780 |
| }, |
| { |
| "epoch": 0.950363196125908, |
| "grad_norm": 1.6304205656051636, |
| "learning_rate": 4.745762711864407e-05, |
| "loss": 0.2943, |
| "num_input_tokens_seen": 323168, |
| "step": 785 |
| }, |
| { |
| "epoch": 0.9564164648910412, |
| "grad_norm": 1.6372556686401367, |
| "learning_rate": 4.776029055690073e-05, |
| "loss": 0.1316, |
| "num_input_tokens_seen": 325280, |
| "step": 790 |
| }, |
| { |
| "epoch": 0.9624697336561744, |
| "grad_norm": 2.625636339187622, |
| "learning_rate": 4.806295399515739e-05, |
| "loss": 0.1265, |
| "num_input_tokens_seen": 327264, |
| "step": 795 |
| }, |
| { |
| "epoch": 0.9685230024213075, |
| "grad_norm": 2.179762363433838, |
| "learning_rate": 4.836561743341404e-05, |
| "loss": 0.1583, |
| "num_input_tokens_seen": 329312, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.9745762711864406, |
| "grad_norm": 0.8714865446090698, |
| "learning_rate": 4.8668280871670705e-05, |
| "loss": 0.1965, |
| "num_input_tokens_seen": 331296, |
| "step": 805 |
| }, |
| { |
| "epoch": 0.9806295399515739, |
| "grad_norm": 0.9597650766372681, |
| "learning_rate": 4.8970944309927366e-05, |
| "loss": 0.0882, |
| "num_input_tokens_seen": 333280, |
| "step": 810 |
| }, |
| { |
| "epoch": 0.986682808716707, |
| "grad_norm": 1.2910470962524414, |
| "learning_rate": 4.927360774818402e-05, |
| "loss": 0.1259, |
| "num_input_tokens_seen": 335392, |
| "step": 815 |
| }, |
| { |
| "epoch": 0.9927360774818402, |
| "grad_norm": 1.1439247131347656, |
| "learning_rate": 4.957627118644068e-05, |
| "loss": 0.2821, |
| "num_input_tokens_seen": 337504, |
| "step": 820 |
| }, |
| { |
| "epoch": 0.9987893462469734, |
| "grad_norm": 1.6988706588745117, |
| "learning_rate": 4.9878934624697336e-05, |
| "loss": 0.1132, |
| "num_input_tokens_seen": 339488, |
| "step": 825 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.17887082695960999, |
| "eval_runtime": 4.5703, |
| "eval_samples_per_second": 80.302, |
| "eval_steps_per_second": 20.13, |
| "num_input_tokens_seen": 339568, |
| "step": 826 |
| }, |
| { |
| "epoch": 1.0048426150121066, |
| "grad_norm": 0.8017047643661499, |
| "learning_rate": 4.99999799087436e-05, |
| "loss": 0.1615, |
| "num_input_tokens_seen": 341168, |
| "step": 830 |
| }, |
| { |
| "epoch": 1.0108958837772397, |
| "grad_norm": 0.8913490772247314, |
| "learning_rate": 4.999985712896029e-05, |
| "loss": 0.072, |
| "num_input_tokens_seen": 343216, |
| "step": 835 |
| }, |
| { |
| "epoch": 1.0169491525423728, |
| "grad_norm": 4.105673313140869, |
| "learning_rate": 4.9999622731750315e-05, |
| "loss": 0.1312, |
| "num_input_tokens_seen": 345200, |
| "step": 840 |
| }, |
| { |
| "epoch": 1.023002421307506, |
| "grad_norm": 0.4698481559753418, |
| "learning_rate": 4.999927671816018e-05, |
| "loss": 0.0782, |
| "num_input_tokens_seen": 347408, |
| "step": 845 |
| }, |
| { |
| "epoch": 1.0290556900726393, |
| "grad_norm": 4.901593208312988, |
| "learning_rate": 4.999881908973474e-05, |
| "loss": 0.219, |
| "num_input_tokens_seen": 349488, |
| "step": 850 |
| }, |
| { |
| "epoch": 1.0351089588377724, |
| "grad_norm": 3.6952834129333496, |
| "learning_rate": 4.9998249848517185e-05, |
| "loss": 0.3065, |
| "num_input_tokens_seen": 351536, |
| "step": 855 |
| }, |
| { |
| "epoch": 1.0411622276029056, |
| "grad_norm": 2.738077402114868, |
| "learning_rate": 4.999756899704902e-05, |
| "loss": 0.2376, |
| "num_input_tokens_seen": 353488, |
| "step": 860 |
| }, |
| { |
| "epoch": 1.0472154963680387, |
| "grad_norm": 3.399280071258545, |
| "learning_rate": 4.999677653837004e-05, |
| "loss": 0.0926, |
| "num_input_tokens_seen": 355504, |
| "step": 865 |
| }, |
| { |
| "epoch": 1.053268765133172, |
| "grad_norm": 9.515294075012207, |
| "learning_rate": 4.999587247601837e-05, |
| "loss": 0.2354, |
| "num_input_tokens_seen": 357456, |
| "step": 870 |
| }, |
| { |
| "epoch": 1.0593220338983051, |
| "grad_norm": 2.640784502029419, |
| "learning_rate": 4.99948568140304e-05, |
| "loss": 0.201, |
| "num_input_tokens_seen": 359568, |
| "step": 875 |
| }, |
| { |
| "epoch": 1.0653753026634383, |
| "grad_norm": 1.2339344024658203, |
| "learning_rate": 4.999372955694077e-05, |
| "loss": 0.2238, |
| "num_input_tokens_seen": 361616, |
| "step": 880 |
| }, |
| { |
| "epoch": 1.0714285714285714, |
| "grad_norm": 2.403195381164551, |
| "learning_rate": 4.999249070978237e-05, |
| "loss": 0.1327, |
| "num_input_tokens_seen": 363696, |
| "step": 885 |
| }, |
| { |
| "epoch": 1.0774818401937045, |
| "grad_norm": 2.847059965133667, |
| "learning_rate": 4.9991140278086316e-05, |
| "loss": 0.1774, |
| "num_input_tokens_seen": 365712, |
| "step": 890 |
| }, |
| { |
| "epoch": 1.0835351089588379, |
| "grad_norm": 0.30369001626968384, |
| "learning_rate": 4.998967826788191e-05, |
| "loss": 0.0374, |
| "num_input_tokens_seen": 367824, |
| "step": 895 |
| }, |
| { |
| "epoch": 1.089588377723971, |
| "grad_norm": 2.6305861473083496, |
| "learning_rate": 4.998810468569661e-05, |
| "loss": 0.1665, |
| "num_input_tokens_seen": 369840, |
| "step": 900 |
| }, |
| { |
| "epoch": 1.0956416464891041, |
| "grad_norm": 0.4452836513519287, |
| "learning_rate": 4.998641953855604e-05, |
| "loss": 0.1515, |
| "num_input_tokens_seen": 371952, |
| "step": 905 |
| }, |
| { |
| "epoch": 1.1016949152542372, |
| "grad_norm": 1.6030263900756836, |
| "learning_rate": 4.9984622833983906e-05, |
| "loss": 0.136, |
| "num_input_tokens_seen": 374032, |
| "step": 910 |
| }, |
| { |
| "epoch": 1.1077481840193704, |
| "grad_norm": 3.4988062381744385, |
| "learning_rate": 4.9982714580002e-05, |
| "loss": 0.1357, |
| "num_input_tokens_seen": 376176, |
| "step": 915 |
| }, |
| { |
| "epoch": 1.1138014527845037, |
| "grad_norm": 3.163297653198242, |
| "learning_rate": 4.998069478513013e-05, |
| "loss": 0.1427, |
| "num_input_tokens_seen": 378224, |
| "step": 920 |
| }, |
| { |
| "epoch": 1.1198547215496368, |
| "grad_norm": 1.0224205255508423, |
| "learning_rate": 4.997856345838615e-05, |
| "loss": 0.1399, |
| "num_input_tokens_seen": 380304, |
| "step": 925 |
| }, |
| { |
| "epoch": 1.12590799031477, |
| "grad_norm": 1.4912834167480469, |
| "learning_rate": 4.997632060928582e-05, |
| "loss": 0.0602, |
| "num_input_tokens_seen": 382416, |
| "step": 930 |
| }, |
| { |
| "epoch": 1.131961259079903, |
| "grad_norm": 1.3977404832839966, |
| "learning_rate": 4.997396624784284e-05, |
| "loss": 0.1835, |
| "num_input_tokens_seen": 384592, |
| "step": 935 |
| }, |
| { |
| "epoch": 1.1380145278450362, |
| "grad_norm": 0.7628365755081177, |
| "learning_rate": 4.9971500384568795e-05, |
| "loss": 0.1278, |
| "num_input_tokens_seen": 386640, |
| "step": 940 |
| }, |
| { |
| "epoch": 1.1440677966101696, |
| "grad_norm": 1.2870368957519531, |
| "learning_rate": 4.996892303047306e-05, |
| "loss": 0.13, |
| "num_input_tokens_seen": 388752, |
| "step": 945 |
| }, |
| { |
| "epoch": 1.1501210653753027, |
| "grad_norm": 12.154106140136719, |
| "learning_rate": 4.996623419706282e-05, |
| "loss": 0.225, |
| "num_input_tokens_seen": 390928, |
| "step": 950 |
| }, |
| { |
| "epoch": 1.1561743341404358, |
| "grad_norm": 0.07500404119491577, |
| "learning_rate": 4.996343389634298e-05, |
| "loss": 0.0603, |
| "num_input_tokens_seen": 393104, |
| "step": 955 |
| }, |
| { |
| "epoch": 1.162227602905569, |
| "grad_norm": 2.0933313369750977, |
| "learning_rate": 4.996052214081608e-05, |
| "loss": 0.1878, |
| "num_input_tokens_seen": 395184, |
| "step": 960 |
| }, |
| { |
| "epoch": 1.1682808716707023, |
| "grad_norm": 7.35886812210083, |
| "learning_rate": 4.995749894348232e-05, |
| "loss": 0.1715, |
| "num_input_tokens_seen": 397264, |
| "step": 965 |
| }, |
| { |
| "epoch": 1.1743341404358354, |
| "grad_norm": 4.131441593170166, |
| "learning_rate": 4.995436431783942e-05, |
| "loss": 0.1233, |
| "num_input_tokens_seen": 399376, |
| "step": 970 |
| }, |
| { |
| "epoch": 1.1803874092009685, |
| "grad_norm": 2.0855846405029297, |
| "learning_rate": 4.9951118277882636e-05, |
| "loss": 0.1681, |
| "num_input_tokens_seen": 401296, |
| "step": 975 |
| }, |
| { |
| "epoch": 1.1864406779661016, |
| "grad_norm": 4.022651672363281, |
| "learning_rate": 4.994776083810463e-05, |
| "loss": 0.1455, |
| "num_input_tokens_seen": 403344, |
| "step": 980 |
| }, |
| { |
| "epoch": 1.192493946731235, |
| "grad_norm": 2.833282709121704, |
| "learning_rate": 4.994429201349542e-05, |
| "loss": 0.1993, |
| "num_input_tokens_seen": 405328, |
| "step": 985 |
| }, |
| { |
| "epoch": 1.1985472154963681, |
| "grad_norm": 3.453665256500244, |
| "learning_rate": 4.994071181954237e-05, |
| "loss": 0.1205, |
| "num_input_tokens_seen": 407344, |
| "step": 990 |
| }, |
| { |
| "epoch": 1.2046004842615012, |
| "grad_norm": 4.6256422996521, |
| "learning_rate": 4.993702027223004e-05, |
| "loss": 0.142, |
| "num_input_tokens_seen": 409296, |
| "step": 995 |
| }, |
| { |
| "epoch": 1.2106537530266344, |
| "grad_norm": 2.930302381515503, |
| "learning_rate": 4.9933217388040164e-05, |
| "loss": 0.2749, |
| "num_input_tokens_seen": 411536, |
| "step": 1000 |
| }, |
| { |
| "epoch": 1.2167070217917675, |
| "grad_norm": 7.9702043533325195, |
| "learning_rate": 4.992930318395157e-05, |
| "loss": 0.0887, |
| "num_input_tokens_seen": 413712, |
| "step": 1005 |
| }, |
| { |
| "epoch": 1.2227602905569008, |
| "grad_norm": 8.404480934143066, |
| "learning_rate": 4.99252776774401e-05, |
| "loss": 0.1615, |
| "num_input_tokens_seen": 415856, |
| "step": 1010 |
| }, |
| { |
| "epoch": 1.228813559322034, |
| "grad_norm": 3.982208728790283, |
| "learning_rate": 4.99211408864785e-05, |
| "loss": 0.2316, |
| "num_input_tokens_seen": 417808, |
| "step": 1015 |
| }, |
| { |
| "epoch": 1.234866828087167, |
| "grad_norm": 0.8618561625480652, |
| "learning_rate": 4.991689282953642e-05, |
| "loss": 0.0428, |
| "num_input_tokens_seen": 419760, |
| "step": 1020 |
| }, |
| { |
| "epoch": 1.2409200968523002, |
| "grad_norm": 3.26019287109375, |
| "learning_rate": 4.991253352558025e-05, |
| "loss": 0.3529, |
| "num_input_tokens_seen": 421840, |
| "step": 1025 |
| }, |
| { |
| "epoch": 1.2469733656174333, |
| "grad_norm": 7.507120609283447, |
| "learning_rate": 4.9908062994073056e-05, |
| "loss": 0.2839, |
| "num_input_tokens_seen": 424112, |
| "step": 1030 |
| }, |
| { |
| "epoch": 1.2530266343825667, |
| "grad_norm": 2.8803584575653076, |
| "learning_rate": 4.990348125497454e-05, |
| "loss": 0.1223, |
| "num_input_tokens_seen": 426128, |
| "step": 1035 |
| }, |
| { |
| "epoch": 1.2590799031476998, |
| "grad_norm": 0.847564697265625, |
| "learning_rate": 4.9898788328740884e-05, |
| "loss": 0.118, |
| "num_input_tokens_seen": 428272, |
| "step": 1040 |
| }, |
| { |
| "epoch": 1.265133171912833, |
| "grad_norm": 0.8926573395729065, |
| "learning_rate": 4.989398423632471e-05, |
| "loss": 0.2175, |
| "num_input_tokens_seen": 430320, |
| "step": 1045 |
| }, |
| { |
| "epoch": 1.271186440677966, |
| "grad_norm": 1.0349339246749878, |
| "learning_rate": 4.988906899917496e-05, |
| "loss": 0.1073, |
| "num_input_tokens_seen": 432272, |
| "step": 1050 |
| }, |
| { |
| "epoch": 1.2772397094430992, |
| "grad_norm": 1.2034751176834106, |
| "learning_rate": 4.988404263923679e-05, |
| "loss": 0.0985, |
| "num_input_tokens_seen": 434384, |
| "step": 1055 |
| }, |
| { |
| "epoch": 1.2832929782082325, |
| "grad_norm": 3.1568541526794434, |
| "learning_rate": 4.987890517895152e-05, |
| "loss": 0.1696, |
| "num_input_tokens_seen": 436336, |
| "step": 1060 |
| }, |
| { |
| "epoch": 1.2893462469733656, |
| "grad_norm": 4.365025520324707, |
| "learning_rate": 4.987365664125647e-05, |
| "loss": 0.1524, |
| "num_input_tokens_seen": 438352, |
| "step": 1065 |
| }, |
| { |
| "epoch": 1.2953995157384988, |
| "grad_norm": 1.4751983880996704, |
| "learning_rate": 4.986829704958491e-05, |
| "loss": 0.1576, |
| "num_input_tokens_seen": 440336, |
| "step": 1070 |
| }, |
| { |
| "epoch": 1.3014527845036319, |
| "grad_norm": 2.4118525981903076, |
| "learning_rate": 4.986282642786594e-05, |
| "loss": 0.1163, |
| "num_input_tokens_seen": 442352, |
| "step": 1075 |
| }, |
| { |
| "epoch": 1.307506053268765, |
| "grad_norm": 0.789813756942749, |
| "learning_rate": 4.985724480052435e-05, |
| "loss": 0.0842, |
| "num_input_tokens_seen": 444496, |
| "step": 1080 |
| }, |
| { |
| "epoch": 1.3135593220338984, |
| "grad_norm": 1.4542982578277588, |
| "learning_rate": 4.985155219248057e-05, |
| "loss": 0.105, |
| "num_input_tokens_seen": 446576, |
| "step": 1085 |
| }, |
| { |
| "epoch": 1.3196125907990315, |
| "grad_norm": 6.07450532913208, |
| "learning_rate": 4.9845748629150514e-05, |
| "loss": 0.1469, |
| "num_input_tokens_seen": 448656, |
| "step": 1090 |
| }, |
| { |
| "epoch": 1.3256658595641646, |
| "grad_norm": 1.8046495914459229, |
| "learning_rate": 4.9839834136445485e-05, |
| "loss": 0.1416, |
| "num_input_tokens_seen": 450672, |
| "step": 1095 |
| }, |
| { |
| "epoch": 1.331719128329298, |
| "grad_norm": 1.6317821741104126, |
| "learning_rate": 4.983380874077204e-05, |
| "loss": 0.1155, |
| "num_input_tokens_seen": 452784, |
| "step": 1100 |
| }, |
| { |
| "epoch": 1.3377723970944309, |
| "grad_norm": 0.9619260430335999, |
| "learning_rate": 4.982767246903192e-05, |
| "loss": 0.1092, |
| "num_input_tokens_seen": 454864, |
| "step": 1105 |
| }, |
| { |
| "epoch": 1.3438256658595642, |
| "grad_norm": 4.070939540863037, |
| "learning_rate": 4.982142534862185e-05, |
| "loss": 0.2142, |
| "num_input_tokens_seen": 457072, |
| "step": 1110 |
| }, |
| { |
| "epoch": 1.3498789346246973, |
| "grad_norm": 10.078119277954102, |
| "learning_rate": 4.981506740743351e-05, |
| "loss": 0.1481, |
| "num_input_tokens_seen": 459184, |
| "step": 1115 |
| }, |
| { |
| "epoch": 1.3559322033898304, |
| "grad_norm": 5.898523330688477, |
| "learning_rate": 4.980859867385334e-05, |
| "loss": 0.1137, |
| "num_input_tokens_seen": 461136, |
| "step": 1120 |
| }, |
| { |
| "epoch": 1.3619854721549638, |
| "grad_norm": 5.684123516082764, |
| "learning_rate": 4.9802019176762434e-05, |
| "loss": 0.1881, |
| "num_input_tokens_seen": 463152, |
| "step": 1125 |
| }, |
| { |
| "epoch": 1.368038740920097, |
| "grad_norm": 2.8209903240203857, |
| "learning_rate": 4.9795328945536425e-05, |
| "loss": 0.1448, |
| "num_input_tokens_seen": 465232, |
| "step": 1130 |
| }, |
| { |
| "epoch": 1.37409200968523, |
| "grad_norm": 1.7147382497787476, |
| "learning_rate": 4.978852801004534e-05, |
| "loss": 0.1441, |
| "num_input_tokens_seen": 467248, |
| "step": 1135 |
| }, |
| { |
| "epoch": 1.3801452784503632, |
| "grad_norm": 3.1413381099700928, |
| "learning_rate": 4.9781616400653464e-05, |
| "loss": 0.1192, |
| "num_input_tokens_seen": 469424, |
| "step": 1140 |
| }, |
| { |
| "epoch": 1.3861985472154963, |
| "grad_norm": 6.792686462402344, |
| "learning_rate": 4.9774594148219225e-05, |
| "loss": 0.2559, |
| "num_input_tokens_seen": 471344, |
| "step": 1145 |
| }, |
| { |
| "epoch": 1.3922518159806296, |
| "grad_norm": 1.0777902603149414, |
| "learning_rate": 4.976746128409502e-05, |
| "loss": 0.1163, |
| "num_input_tokens_seen": 473296, |
| "step": 1150 |
| }, |
| { |
| "epoch": 1.3983050847457628, |
| "grad_norm": 5.556042194366455, |
| "learning_rate": 4.9760217840127126e-05, |
| "loss": 0.1898, |
| "num_input_tokens_seen": 475312, |
| "step": 1155 |
| }, |
| { |
| "epoch": 1.4043583535108959, |
| "grad_norm": 5.81771993637085, |
| "learning_rate": 4.97528638486555e-05, |
| "loss": 0.154, |
| "num_input_tokens_seen": 477360, |
| "step": 1160 |
| }, |
| { |
| "epoch": 1.410411622276029, |
| "grad_norm": 0.9776678681373596, |
| "learning_rate": 4.9745399342513666e-05, |
| "loss": 0.1191, |
| "num_input_tokens_seen": 479376, |
| "step": 1165 |
| }, |
| { |
| "epoch": 1.4164648910411621, |
| "grad_norm": 2.5209102630615234, |
| "learning_rate": 4.9737824355028584e-05, |
| "loss": 0.1837, |
| "num_input_tokens_seen": 481456, |
| "step": 1170 |
| }, |
| { |
| "epoch": 1.4225181598062955, |
| "grad_norm": 0.49560511112213135, |
| "learning_rate": 4.973013892002047e-05, |
| "loss": 0.1288, |
| "num_input_tokens_seen": 483632, |
| "step": 1175 |
| }, |
| { |
| "epoch": 1.4285714285714286, |
| "grad_norm": 7.962185859680176, |
| "learning_rate": 4.9722343071802665e-05, |
| "loss": 0.1998, |
| "num_input_tokens_seen": 485680, |
| "step": 1180 |
| }, |
| { |
| "epoch": 1.4346246973365617, |
| "grad_norm": 2.495086908340454, |
| "learning_rate": 4.971443684518145e-05, |
| "loss": 0.1084, |
| "num_input_tokens_seen": 487792, |
| "step": 1185 |
| }, |
| { |
| "epoch": 1.4406779661016949, |
| "grad_norm": 3.3710200786590576, |
| "learning_rate": 4.970642027545596e-05, |
| "loss": 0.2048, |
| "num_input_tokens_seen": 489840, |
| "step": 1190 |
| }, |
| { |
| "epoch": 1.446731234866828, |
| "grad_norm": 1.2718791961669922, |
| "learning_rate": 4.969829339841793e-05, |
| "loss": 0.0573, |
| "num_input_tokens_seen": 491824, |
| "step": 1195 |
| }, |
| { |
| "epoch": 1.4527845036319613, |
| "grad_norm": 3.988370180130005, |
| "learning_rate": 4.9690056250351626e-05, |
| "loss": 0.1191, |
| "num_input_tokens_seen": 493872, |
| "step": 1200 |
| }, |
| { |
| "epoch": 1.4588377723970944, |
| "grad_norm": 2.300257921218872, |
| "learning_rate": 4.9681708868033616e-05, |
| "loss": 0.1173, |
| "num_input_tokens_seen": 495952, |
| "step": 1205 |
| }, |
| { |
| "epoch": 1.4648910411622276, |
| "grad_norm": 1.824439287185669, |
| "learning_rate": 4.967325128873266e-05, |
| "loss": 0.25, |
| "num_input_tokens_seen": 497936, |
| "step": 1210 |
| }, |
| { |
| "epoch": 1.4709443099273607, |
| "grad_norm": 0.630806565284729, |
| "learning_rate": 4.96646835502095e-05, |
| "loss": 0.1407, |
| "num_input_tokens_seen": 499856, |
| "step": 1215 |
| }, |
| { |
| "epoch": 1.4769975786924938, |
| "grad_norm": 2.253023147583008, |
| "learning_rate": 4.965600569071671e-05, |
| "loss": 0.1138, |
| "num_input_tokens_seen": 501840, |
| "step": 1220 |
| }, |
| { |
| "epoch": 1.4830508474576272, |
| "grad_norm": 1.211021065711975, |
| "learning_rate": 4.9647217748998534e-05, |
| "loss": 0.0632, |
| "num_input_tokens_seen": 503952, |
| "step": 1225 |
| }, |
| { |
| "epoch": 1.4891041162227603, |
| "grad_norm": 4.336838722229004, |
| "learning_rate": 4.963831976429067e-05, |
| "loss": 0.1787, |
| "num_input_tokens_seen": 505936, |
| "step": 1230 |
| }, |
| { |
| "epoch": 1.4951573849878934, |
| "grad_norm": 4.364633560180664, |
| "learning_rate": 4.9629311776320176e-05, |
| "loss": 0.144, |
| "num_input_tokens_seen": 507984, |
| "step": 1235 |
| }, |
| { |
| "epoch": 1.5, |
| "eval_loss": 0.1783103495836258, |
| "eval_runtime": 4.5928, |
| "eval_samples_per_second": 79.908, |
| "eval_steps_per_second": 20.031, |
| "num_input_tokens_seen": 509456, |
| "step": 1239 |
| }, |
| { |
| "epoch": 1.5012106537530268, |
| "grad_norm": 0.9117156863212585, |
| "learning_rate": 4.962019382530521e-05, |
| "loss": 0.2137, |
| "num_input_tokens_seen": 509840, |
| "step": 1240 |
| }, |
| { |
| "epoch": 1.5072639225181597, |
| "grad_norm": 1.2304811477661133, |
| "learning_rate": 4.9610965951954885e-05, |
| "loss": 0.169, |
| "num_input_tokens_seen": 511856, |
| "step": 1245 |
| }, |
| { |
| "epoch": 1.513317191283293, |
| "grad_norm": 2.3721790313720703, |
| "learning_rate": 4.960162819746911e-05, |
| "loss": 0.211, |
| "num_input_tokens_seen": 513904, |
| "step": 1250 |
| }, |
| { |
| "epoch": 1.5193704600484261, |
| "grad_norm": 4.308636665344238, |
| "learning_rate": 4.9592180603538366e-05, |
| "loss": 0.1163, |
| "num_input_tokens_seen": 515824, |
| "step": 1255 |
| }, |
| { |
| "epoch": 1.5254237288135593, |
| "grad_norm": 3.0907084941864014, |
| "learning_rate": 4.958262321234353e-05, |
| "loss": 0.0857, |
| "num_input_tokens_seen": 517744, |
| "step": 1260 |
| }, |
| { |
| "epoch": 1.5314769975786926, |
| "grad_norm": 0.9459354877471924, |
| "learning_rate": 4.95729560665557e-05, |
| "loss": 0.1442, |
| "num_input_tokens_seen": 519824, |
| "step": 1265 |
| }, |
| { |
| "epoch": 1.5375302663438255, |
| "grad_norm": 4.082531452178955, |
| "learning_rate": 4.956317920933602e-05, |
| "loss": 0.1981, |
| "num_input_tokens_seen": 521936, |
| "step": 1270 |
| }, |
| { |
| "epoch": 1.5435835351089588, |
| "grad_norm": 3.863461971282959, |
| "learning_rate": 4.955329268433543e-05, |
| "loss": 0.1058, |
| "num_input_tokens_seen": 524176, |
| "step": 1275 |
| }, |
| { |
| "epoch": 1.549636803874092, |
| "grad_norm": 6.776220321655273, |
| "learning_rate": 4.954329653569452e-05, |
| "loss": 0.1502, |
| "num_input_tokens_seen": 526256, |
| "step": 1280 |
| }, |
| { |
| "epoch": 1.555690072639225, |
| "grad_norm": 3.519094467163086, |
| "learning_rate": 4.953319080804333e-05, |
| "loss": 0.1133, |
| "num_input_tokens_seen": 528304, |
| "step": 1285 |
| }, |
| { |
| "epoch": 1.5617433414043584, |
| "grad_norm": 4.169881820678711, |
| "learning_rate": 4.952297554650113e-05, |
| "loss": 0.2624, |
| "num_input_tokens_seen": 530320, |
| "step": 1290 |
| }, |
| { |
| "epoch": 1.5677966101694916, |
| "grad_norm": 1.6443334817886353, |
| "learning_rate": 4.9512650796676216e-05, |
| "loss": 0.0577, |
| "num_input_tokens_seen": 532400, |
| "step": 1295 |
| }, |
| { |
| "epoch": 1.5738498789346247, |
| "grad_norm": 0.9508858323097229, |
| "learning_rate": 4.9502216604665744e-05, |
| "loss": 0.1549, |
| "num_input_tokens_seen": 534416, |
| "step": 1300 |
| }, |
| { |
| "epoch": 1.5799031476997578, |
| "grad_norm": 2.909374952316284, |
| "learning_rate": 4.949167301705548e-05, |
| "loss": 0.1042, |
| "num_input_tokens_seen": 536592, |
| "step": 1305 |
| }, |
| { |
| "epoch": 1.585956416464891, |
| "grad_norm": 0.7363409996032715, |
| "learning_rate": 4.948102008091962e-05, |
| "loss": 0.0307, |
| "num_input_tokens_seen": 538704, |
| "step": 1310 |
| }, |
| { |
| "epoch": 1.5920096852300243, |
| "grad_norm": 5.999347686767578, |
| "learning_rate": 4.947025784382057e-05, |
| "loss": 0.2497, |
| "num_input_tokens_seen": 540912, |
| "step": 1315 |
| }, |
| { |
| "epoch": 1.5980629539951574, |
| "grad_norm": 4.051459789276123, |
| "learning_rate": 4.9459386353808736e-05, |
| "loss": 0.2243, |
| "num_input_tokens_seen": 542864, |
| "step": 1320 |
| }, |
| { |
| "epoch": 1.6041162227602905, |
| "grad_norm": 9.532818794250488, |
| "learning_rate": 4.944840565942229e-05, |
| "loss": 0.3938, |
| "num_input_tokens_seen": 544816, |
| "step": 1325 |
| }, |
| { |
| "epoch": 1.6101694915254239, |
| "grad_norm": 7.469811916351318, |
| "learning_rate": 4.943731580968701e-05, |
| "loss": 0.2847, |
| "num_input_tokens_seen": 546864, |
| "step": 1330 |
| }, |
| { |
| "epoch": 1.6162227602905568, |
| "grad_norm": 3.413723945617676, |
| "learning_rate": 4.942611685411598e-05, |
| "loss": 0.2188, |
| "num_input_tokens_seen": 548912, |
| "step": 1335 |
| }, |
| { |
| "epoch": 1.6222760290556901, |
| "grad_norm": 4.4016432762146, |
| "learning_rate": 4.9414808842709435e-05, |
| "loss": 0.2475, |
| "num_input_tokens_seen": 551056, |
| "step": 1340 |
| }, |
| { |
| "epoch": 1.6283292978208233, |
| "grad_norm": 1.3102144002914429, |
| "learning_rate": 4.940339182595451e-05, |
| "loss": 0.0887, |
| "num_input_tokens_seen": 553072, |
| "step": 1345 |
| }, |
| { |
| "epoch": 1.6343825665859564, |
| "grad_norm": 1.6671048402786255, |
| "learning_rate": 4.9391865854825015e-05, |
| "loss": 0.1674, |
| "num_input_tokens_seen": 555248, |
| "step": 1350 |
| }, |
| { |
| "epoch": 1.6404358353510897, |
| "grad_norm": 1.2309081554412842, |
| "learning_rate": 4.938023098078122e-05, |
| "loss": 0.0685, |
| "num_input_tokens_seen": 557360, |
| "step": 1355 |
| }, |
| { |
| "epoch": 1.6464891041162226, |
| "grad_norm": 3.3514671325683594, |
| "learning_rate": 4.93684872557696e-05, |
| "loss": 0.0737, |
| "num_input_tokens_seen": 559376, |
| "step": 1360 |
| }, |
| { |
| "epoch": 1.652542372881356, |
| "grad_norm": 4.470357418060303, |
| "learning_rate": 4.935663473222264e-05, |
| "loss": 0.1702, |
| "num_input_tokens_seen": 561296, |
| "step": 1365 |
| }, |
| { |
| "epoch": 1.658595641646489, |
| "grad_norm": 1.129664421081543, |
| "learning_rate": 4.934467346305856e-05, |
| "loss": 0.1448, |
| "num_input_tokens_seen": 563376, |
| "step": 1370 |
| }, |
| { |
| "epoch": 1.6646489104116222, |
| "grad_norm": 0.7362378835678101, |
| "learning_rate": 4.933260350168112e-05, |
| "loss": 0.0589, |
| "num_input_tokens_seen": 565424, |
| "step": 1375 |
| }, |
| { |
| "epoch": 1.6707021791767556, |
| "grad_norm": 0.631158173084259, |
| "learning_rate": 4.932042490197933e-05, |
| "loss": 0.0482, |
| "num_input_tokens_seen": 567504, |
| "step": 1380 |
| }, |
| { |
| "epoch": 1.6767554479418885, |
| "grad_norm": 3.6880412101745605, |
| "learning_rate": 4.930813771832728e-05, |
| "loss": 0.2682, |
| "num_input_tokens_seen": 569744, |
| "step": 1385 |
| }, |
| { |
| "epoch": 1.6828087167070218, |
| "grad_norm": 1.3964409828186035, |
| "learning_rate": 4.929574200558382e-05, |
| "loss": 0.1129, |
| "num_input_tokens_seen": 571888, |
| "step": 1390 |
| }, |
| { |
| "epoch": 1.688861985472155, |
| "grad_norm": 2.9864020347595215, |
| "learning_rate": 4.928323781909239e-05, |
| "loss": 0.1442, |
| "num_input_tokens_seen": 574000, |
| "step": 1395 |
| }, |
| { |
| "epoch": 1.694915254237288, |
| "grad_norm": 4.279382705688477, |
| "learning_rate": 4.927062521468068e-05, |
| "loss": 0.212, |
| "num_input_tokens_seen": 575984, |
| "step": 1400 |
| }, |
| { |
| "epoch": 1.7009685230024214, |
| "grad_norm": 1.5373003482818604, |
| "learning_rate": 4.92579042486605e-05, |
| "loss": 0.0917, |
| "num_input_tokens_seen": 577968, |
| "step": 1405 |
| }, |
| { |
| "epoch": 1.7070217917675545, |
| "grad_norm": 1.7001993656158447, |
| "learning_rate": 4.924507497782743e-05, |
| "loss": 0.137, |
| "num_input_tokens_seen": 580112, |
| "step": 1410 |
| }, |
| { |
| "epoch": 1.7130750605326877, |
| "grad_norm": 1.1870551109313965, |
| "learning_rate": 4.923213745946059e-05, |
| "loss": 0.1927, |
| "num_input_tokens_seen": 582160, |
| "step": 1415 |
| }, |
| { |
| "epoch": 1.7191283292978208, |
| "grad_norm": 0.5280523300170898, |
| "learning_rate": 4.921909175132242e-05, |
| "loss": 0.1633, |
| "num_input_tokens_seen": 584304, |
| "step": 1420 |
| }, |
| { |
| "epoch": 1.725181598062954, |
| "grad_norm": 1.6161837577819824, |
| "learning_rate": 4.920593791165839e-05, |
| "loss": 0.1462, |
| "num_input_tokens_seen": 586096, |
| "step": 1425 |
| }, |
| { |
| "epoch": 1.7312348668280872, |
| "grad_norm": 3.1209022998809814, |
| "learning_rate": 4.919267599919674e-05, |
| "loss": 0.1477, |
| "num_input_tokens_seen": 588240, |
| "step": 1430 |
| }, |
| { |
| "epoch": 1.7372881355932204, |
| "grad_norm": 1.9811747074127197, |
| "learning_rate": 4.917930607314823e-05, |
| "loss": 0.2459, |
| "num_input_tokens_seen": 590480, |
| "step": 1435 |
| }, |
| { |
| "epoch": 1.7433414043583535, |
| "grad_norm": 1.1726977825164795, |
| "learning_rate": 4.916582819320588e-05, |
| "loss": 0.1896, |
| "num_input_tokens_seen": 592528, |
| "step": 1440 |
| }, |
| { |
| "epoch": 1.7493946731234868, |
| "grad_norm": 3.542783737182617, |
| "learning_rate": 4.915224241954467e-05, |
| "loss": 0.2088, |
| "num_input_tokens_seen": 594416, |
| "step": 1445 |
| }, |
| { |
| "epoch": 1.7554479418886197, |
| "grad_norm": 1.4151628017425537, |
| "learning_rate": 4.9138548812821316e-05, |
| "loss": 0.1804, |
| "num_input_tokens_seen": 596432, |
| "step": 1450 |
| }, |
| { |
| "epoch": 1.761501210653753, |
| "grad_norm": 1.6290380954742432, |
| "learning_rate": 4.912474743417399e-05, |
| "loss": 0.0787, |
| "num_input_tokens_seen": 598352, |
| "step": 1455 |
| }, |
| { |
| "epoch": 1.7675544794188862, |
| "grad_norm": 1.6579142808914185, |
| "learning_rate": 4.911083834522199e-05, |
| "loss": 0.0636, |
| "num_input_tokens_seen": 600432, |
| "step": 1460 |
| }, |
| { |
| "epoch": 1.7736077481840193, |
| "grad_norm": 5.867772579193115, |
| "learning_rate": 4.909682160806556e-05, |
| "loss": 0.2342, |
| "num_input_tokens_seen": 602480, |
| "step": 1465 |
| }, |
| { |
| "epoch": 1.7796610169491527, |
| "grad_norm": 4.180382251739502, |
| "learning_rate": 4.908269728528553e-05, |
| "loss": 0.1955, |
| "num_input_tokens_seen": 604496, |
| "step": 1470 |
| }, |
| { |
| "epoch": 1.7857142857142856, |
| "grad_norm": 3.5099289417266846, |
| "learning_rate": 4.90684654399431e-05, |
| "loss": 0.1021, |
| "num_input_tokens_seen": 606672, |
| "step": 1475 |
| }, |
| { |
| "epoch": 1.791767554479419, |
| "grad_norm": 0.4963616728782654, |
| "learning_rate": 4.9054126135579495e-05, |
| "loss": 0.1071, |
| "num_input_tokens_seen": 608752, |
| "step": 1480 |
| }, |
| { |
| "epoch": 1.797820823244552, |
| "grad_norm": 2.4257378578186035, |
| "learning_rate": 4.9039679436215734e-05, |
| "loss": 0.129, |
| "num_input_tokens_seen": 610608, |
| "step": 1485 |
| }, |
| { |
| "epoch": 1.8038740920096852, |
| "grad_norm": 3.747525215148926, |
| "learning_rate": 4.9025125406352335e-05, |
| "loss": 0.2842, |
| "num_input_tokens_seen": 612688, |
| "step": 1490 |
| }, |
| { |
| "epoch": 1.8099273607748185, |
| "grad_norm": 0.5966554880142212, |
| "learning_rate": 4.9010464110968976e-05, |
| "loss": 0.0584, |
| "num_input_tokens_seen": 614704, |
| "step": 1495 |
| }, |
| { |
| "epoch": 1.8159806295399514, |
| "grad_norm": 2.613186836242676, |
| "learning_rate": 4.89956956155243e-05, |
| "loss": 0.1314, |
| "num_input_tokens_seen": 616784, |
| "step": 1500 |
| }, |
| { |
| "epoch": 1.8220338983050848, |
| "grad_norm": 3.0699353218078613, |
| "learning_rate": 4.898081998595555e-05, |
| "loss": 0.1275, |
| "num_input_tokens_seen": 618736, |
| "step": 1505 |
| }, |
| { |
| "epoch": 1.828087167070218, |
| "grad_norm": 2.9778733253479004, |
| "learning_rate": 4.8965837288678253e-05, |
| "loss": 0.1038, |
| "num_input_tokens_seen": 620944, |
| "step": 1510 |
| }, |
| { |
| "epoch": 1.834140435835351, |
| "grad_norm": 2.6867446899414062, |
| "learning_rate": 4.895074759058601e-05, |
| "loss": 0.1367, |
| "num_input_tokens_seen": 623120, |
| "step": 1515 |
| }, |
| { |
| "epoch": 1.8401937046004844, |
| "grad_norm": 1.885842204093933, |
| "learning_rate": 4.893555095905014e-05, |
| "loss": 0.074, |
| "num_input_tokens_seen": 625136, |
| "step": 1520 |
| }, |
| { |
| "epoch": 1.8462469733656173, |
| "grad_norm": 4.191492557525635, |
| "learning_rate": 4.892024746191939e-05, |
| "loss": 0.1355, |
| "num_input_tokens_seen": 627216, |
| "step": 1525 |
| }, |
| { |
| "epoch": 1.8523002421307506, |
| "grad_norm": 0.14360515773296356, |
| "learning_rate": 4.890483716751961e-05, |
| "loss": 0.0959, |
| "num_input_tokens_seen": 629136, |
| "step": 1530 |
| }, |
| { |
| "epoch": 1.8583535108958837, |
| "grad_norm": 2.302429676055908, |
| "learning_rate": 4.888932014465352e-05, |
| "loss": 0.1219, |
| "num_input_tokens_seen": 631216, |
| "step": 1535 |
| }, |
| { |
| "epoch": 1.8644067796610169, |
| "grad_norm": 2.125596046447754, |
| "learning_rate": 4.8873696462600303e-05, |
| "loss": 0.0763, |
| "num_input_tokens_seen": 633328, |
| "step": 1540 |
| }, |
| { |
| "epoch": 1.8704600484261502, |
| "grad_norm": 5.019554615020752, |
| "learning_rate": 4.8857966191115365e-05, |
| "loss": 0.2288, |
| "num_input_tokens_seen": 635440, |
| "step": 1545 |
| }, |
| { |
| "epoch": 1.8765133171912833, |
| "grad_norm": 0.8047354221343994, |
| "learning_rate": 4.884212940043001e-05, |
| "loss": 0.132, |
| "num_input_tokens_seen": 637360, |
| "step": 1550 |
| }, |
| { |
| "epoch": 1.8825665859564165, |
| "grad_norm": 2.835331678390503, |
| "learning_rate": 4.882618616125111e-05, |
| "loss": 0.243, |
| "num_input_tokens_seen": 639280, |
| "step": 1555 |
| }, |
| { |
| "epoch": 1.8886198547215496, |
| "grad_norm": 0.7895589470863342, |
| "learning_rate": 4.881013654476081e-05, |
| "loss": 0.1762, |
| "num_input_tokens_seen": 641328, |
| "step": 1560 |
| }, |
| { |
| "epoch": 1.8946731234866827, |
| "grad_norm": 1.5545868873596191, |
| "learning_rate": 4.8793980622616195e-05, |
| "loss": 0.2117, |
| "num_input_tokens_seen": 643376, |
| "step": 1565 |
| }, |
| { |
| "epoch": 1.900726392251816, |
| "grad_norm": 1.4125303030014038, |
| "learning_rate": 4.877771846694897e-05, |
| "loss": 0.0568, |
| "num_input_tokens_seen": 645488, |
| "step": 1570 |
| }, |
| { |
| "epoch": 1.9067796610169492, |
| "grad_norm": 4.356451988220215, |
| "learning_rate": 4.876135015036515e-05, |
| "loss": 0.1828, |
| "num_input_tokens_seen": 647600, |
| "step": 1575 |
| }, |
| { |
| "epoch": 1.9128329297820823, |
| "grad_norm": 0.882681667804718, |
| "learning_rate": 4.874487574594473e-05, |
| "loss": 0.1048, |
| "num_input_tokens_seen": 649648, |
| "step": 1580 |
| }, |
| { |
| "epoch": 1.9188861985472156, |
| "grad_norm": 2.282263994216919, |
| "learning_rate": 4.872829532724136e-05, |
| "loss": 0.1744, |
| "num_input_tokens_seen": 651760, |
| "step": 1585 |
| }, |
| { |
| "epoch": 1.9249394673123486, |
| "grad_norm": 1.4083192348480225, |
| "learning_rate": 4.8711608968282e-05, |
| "loss": 0.2004, |
| "num_input_tokens_seen": 653840, |
| "step": 1590 |
| }, |
| { |
| "epoch": 1.930992736077482, |
| "grad_norm": 3.696666955947876, |
| "learning_rate": 4.8694816743566616e-05, |
| "loss": 0.2136, |
| "num_input_tokens_seen": 655888, |
| "step": 1595 |
| }, |
| { |
| "epoch": 1.937046004842615, |
| "grad_norm": 0.2428300827741623, |
| "learning_rate": 4.867791872806785e-05, |
| "loss": 0.0729, |
| "num_input_tokens_seen": 657776, |
| "step": 1600 |
| }, |
| { |
| "epoch": 1.9430992736077481, |
| "grad_norm": 1.8835179805755615, |
| "learning_rate": 4.8660914997230624e-05, |
| "loss": 0.1833, |
| "num_input_tokens_seen": 659952, |
| "step": 1605 |
| }, |
| { |
| "epoch": 1.9491525423728815, |
| "grad_norm": 5.549609184265137, |
| "learning_rate": 4.8643805626971894e-05, |
| "loss": 0.1643, |
| "num_input_tokens_seen": 661968, |
| "step": 1610 |
| }, |
| { |
| "epoch": 1.9552058111380144, |
| "grad_norm": 0.962121844291687, |
| "learning_rate": 4.862659069368026e-05, |
| "loss": 0.1775, |
| "num_input_tokens_seen": 664048, |
| "step": 1615 |
| }, |
| { |
| "epoch": 1.9612590799031477, |
| "grad_norm": 0.7466434836387634, |
| "learning_rate": 4.8609270274215614e-05, |
| "loss": 0.2465, |
| "num_input_tokens_seen": 665968, |
| "step": 1620 |
| }, |
| { |
| "epoch": 1.9673123486682809, |
| "grad_norm": 1.28084135055542, |
| "learning_rate": 4.859184444590882e-05, |
| "loss": 0.1881, |
| "num_input_tokens_seen": 667920, |
| "step": 1625 |
| }, |
| { |
| "epoch": 1.973365617433414, |
| "grad_norm": 0.41623222827911377, |
| "learning_rate": 4.857431328656137e-05, |
| "loss": 0.0832, |
| "num_input_tokens_seen": 669968, |
| "step": 1630 |
| }, |
| { |
| "epoch": 1.9794188861985473, |
| "grad_norm": 1.7877904176712036, |
| "learning_rate": 4.855667687444504e-05, |
| "loss": 0.1038, |
| "num_input_tokens_seen": 672016, |
| "step": 1635 |
| }, |
| { |
| "epoch": 1.9854721549636802, |
| "grad_norm": 0.9274682402610779, |
| "learning_rate": 4.85389352883015e-05, |
| "loss": 0.0918, |
| "num_input_tokens_seen": 674096, |
| "step": 1640 |
| }, |
| { |
| "epoch": 1.9915254237288136, |
| "grad_norm": 2.654660940170288, |
| "learning_rate": 4.8521088607342016e-05, |
| "loss": 0.123, |
| "num_input_tokens_seen": 676208, |
| "step": 1645 |
| }, |
| { |
| "epoch": 1.9975786924939467, |
| "grad_norm": 0.8411111235618591, |
| "learning_rate": 4.850313691124707e-05, |
| "loss": 0.0424, |
| "num_input_tokens_seen": 678256, |
| "step": 1650 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 0.1412314772605896, |
| "eval_runtime": 4.5644, |
| "eval_samples_per_second": 80.404, |
| "eval_steps_per_second": 20.156, |
| "num_input_tokens_seen": 678688, |
| "step": 1652 |
| }, |
| { |
| "epoch": 2.00363196125908, |
| "grad_norm": 2.427675485610962, |
| "learning_rate": 4.8485080280166006e-05, |
| "loss": 0.1351, |
| "num_input_tokens_seen": 679936, |
| "step": 1655 |
| }, |
| { |
| "epoch": 2.009685230024213, |
| "grad_norm": 3.1601905822753906, |
| "learning_rate": 4.8466918794716666e-05, |
| "loss": 0.1074, |
| "num_input_tokens_seen": 681984, |
| "step": 1660 |
| }, |
| { |
| "epoch": 2.015738498789346, |
| "grad_norm": 2.2332310676574707, |
| "learning_rate": 4.8448652535985045e-05, |
| "loss": 0.0816, |
| "num_input_tokens_seen": 684096, |
| "step": 1665 |
| }, |
| { |
| "epoch": 2.0217917675544794, |
| "grad_norm": 1.4707834720611572, |
| "learning_rate": 4.8430281585524926e-05, |
| "loss": 0.0863, |
| "num_input_tokens_seen": 686016, |
| "step": 1670 |
| }, |
| { |
| "epoch": 2.0278450363196128, |
| "grad_norm": 3.2379772663116455, |
| "learning_rate": 4.841180602535751e-05, |
| "loss": 0.0878, |
| "num_input_tokens_seen": 687904, |
| "step": 1675 |
| }, |
| { |
| "epoch": 2.0338983050847457, |
| "grad_norm": 5.141901969909668, |
| "learning_rate": 4.839322593797104e-05, |
| "loss": 0.2172, |
| "num_input_tokens_seen": 689888, |
| "step": 1680 |
| }, |
| { |
| "epoch": 2.039951573849879, |
| "grad_norm": 3.7298524379730225, |
| "learning_rate": 4.837454140632045e-05, |
| "loss": 0.1119, |
| "num_input_tokens_seen": 691808, |
| "step": 1685 |
| }, |
| { |
| "epoch": 2.046004842615012, |
| "grad_norm": 1.6675068140029907, |
| "learning_rate": 4.8355752513826995e-05, |
| "loss": 0.2492, |
| "num_input_tokens_seen": 693856, |
| "step": 1690 |
| }, |
| { |
| "epoch": 2.0520581113801453, |
| "grad_norm": 2.8532845973968506, |
| "learning_rate": 4.833685934437787e-05, |
| "loss": 0.1375, |
| "num_input_tokens_seen": 695680, |
| "step": 1695 |
| }, |
| { |
| "epoch": 2.0581113801452786, |
| "grad_norm": 1.0494747161865234, |
| "learning_rate": 4.831786198232583e-05, |
| "loss": 0.0764, |
| "num_input_tokens_seen": 697792, |
| "step": 1700 |
| }, |
| { |
| "epoch": 2.0641646489104115, |
| "grad_norm": 3.190880537033081, |
| "learning_rate": 4.8298760512488824e-05, |
| "loss": 0.155, |
| "num_input_tokens_seen": 699712, |
| "step": 1705 |
| }, |
| { |
| "epoch": 2.070217917675545, |
| "grad_norm": 2.6185317039489746, |
| "learning_rate": 4.827955502014963e-05, |
| "loss": 0.1041, |
| "num_input_tokens_seen": 701792, |
| "step": 1710 |
| }, |
| { |
| "epoch": 2.0762711864406778, |
| "grad_norm": 2.9850172996520996, |
| "learning_rate": 4.826024559105542e-05, |
| "loss": 0.206, |
| "num_input_tokens_seen": 703936, |
| "step": 1715 |
| }, |
| { |
| "epoch": 2.082324455205811, |
| "grad_norm": 3.1610946655273438, |
| "learning_rate": 4.8240832311417465e-05, |
| "loss": 0.092, |
| "num_input_tokens_seen": 705952, |
| "step": 1720 |
| }, |
| { |
| "epoch": 2.0883777239709445, |
| "grad_norm": 3.6915476322174072, |
| "learning_rate": 4.822131526791065e-05, |
| "loss": 0.1464, |
| "num_input_tokens_seen": 708064, |
| "step": 1725 |
| }, |
| { |
| "epoch": 2.0944309927360774, |
| "grad_norm": 3.869178056716919, |
| "learning_rate": 4.820169454767318e-05, |
| "loss": 0.092, |
| "num_input_tokens_seen": 709952, |
| "step": 1730 |
| }, |
| { |
| "epoch": 2.1004842615012107, |
| "grad_norm": 3.4117565155029297, |
| "learning_rate": 4.8181970238306104e-05, |
| "loss": 0.127, |
| "num_input_tokens_seen": 712032, |
| "step": 1735 |
| }, |
| { |
| "epoch": 2.106537530266344, |
| "grad_norm": 1.2668098211288452, |
| "learning_rate": 4.816214242787302e-05, |
| "loss": 0.0634, |
| "num_input_tokens_seen": 714048, |
| "step": 1740 |
| }, |
| { |
| "epoch": 2.112590799031477, |
| "grad_norm": 1.9988105297088623, |
| "learning_rate": 4.814221120489958e-05, |
| "loss": 0.1309, |
| "num_input_tokens_seen": 716224, |
| "step": 1745 |
| }, |
| { |
| "epoch": 2.1186440677966103, |
| "grad_norm": 5.828415870666504, |
| "learning_rate": 4.812217665837316e-05, |
| "loss": 0.149, |
| "num_input_tokens_seen": 718144, |
| "step": 1750 |
| }, |
| { |
| "epoch": 2.124697336561743, |
| "grad_norm": 1.041694164276123, |
| "learning_rate": 4.810203887774247e-05, |
| "loss": 0.1105, |
| "num_input_tokens_seen": 720288, |
| "step": 1755 |
| }, |
| { |
| "epoch": 2.1307506053268765, |
| "grad_norm": 2.428319215774536, |
| "learning_rate": 4.808179795291712e-05, |
| "loss": 0.2155, |
| "num_input_tokens_seen": 722368, |
| "step": 1760 |
| }, |
| { |
| "epoch": 2.13680387409201, |
| "grad_norm": 2.7118420600891113, |
| "learning_rate": 4.8061453974267195e-05, |
| "loss": 0.1619, |
| "num_input_tokens_seen": 724480, |
| "step": 1765 |
| }, |
| { |
| "epoch": 2.142857142857143, |
| "grad_norm": 1.4349424839019775, |
| "learning_rate": 4.804100703262294e-05, |
| "loss": 0.1896, |
| "num_input_tokens_seen": 726784, |
| "step": 1770 |
| }, |
| { |
| "epoch": 2.148910411622276, |
| "grad_norm": 3.1386163234710693, |
| "learning_rate": 4.8020457219274266e-05, |
| "loss": 0.1684, |
| "num_input_tokens_seen": 728768, |
| "step": 1775 |
| }, |
| { |
| "epoch": 2.154963680387409, |
| "grad_norm": 5.631900310516357, |
| "learning_rate": 4.799980462597039e-05, |
| "loss": 0.2013, |
| "num_input_tokens_seen": 730816, |
| "step": 1780 |
| }, |
| { |
| "epoch": 2.1610169491525424, |
| "grad_norm": 1.2051900625228882, |
| "learning_rate": 4.7979049344919416e-05, |
| "loss": 0.0672, |
| "num_input_tokens_seen": 732896, |
| "step": 1785 |
| }, |
| { |
| "epoch": 2.1670702179176757, |
| "grad_norm": 0.28911882638931274, |
| "learning_rate": 4.795819146878792e-05, |
| "loss": 0.1565, |
| "num_input_tokens_seen": 734816, |
| "step": 1790 |
| }, |
| { |
| "epoch": 2.1731234866828086, |
| "grad_norm": 6.5837788581848145, |
| "learning_rate": 4.7937231090700516e-05, |
| "loss": 0.2135, |
| "num_input_tokens_seen": 736800, |
| "step": 1795 |
| }, |
| { |
| "epoch": 2.179176755447942, |
| "grad_norm": 0.9957193732261658, |
| "learning_rate": 4.7916168304239496e-05, |
| "loss": 0.1847, |
| "num_input_tokens_seen": 738944, |
| "step": 1800 |
| }, |
| { |
| "epoch": 2.185230024213075, |
| "grad_norm": 0.9871184229850769, |
| "learning_rate": 4.789500320344435e-05, |
| "loss": 0.0843, |
| "num_input_tokens_seen": 741184, |
| "step": 1805 |
| }, |
| { |
| "epoch": 2.1912832929782082, |
| "grad_norm": 2.35097599029541, |
| "learning_rate": 4.787373588281138e-05, |
| "loss": 0.0992, |
| "num_input_tokens_seen": 743136, |
| "step": 1810 |
| }, |
| { |
| "epoch": 2.1973365617433416, |
| "grad_norm": 4.3666181564331055, |
| "learning_rate": 4.785236643729327e-05, |
| "loss": 0.1001, |
| "num_input_tokens_seen": 745152, |
| "step": 1815 |
| }, |
| { |
| "epoch": 2.2033898305084745, |
| "grad_norm": 2.161907196044922, |
| "learning_rate": 4.7830894962298675e-05, |
| "loss": 0.3108, |
| "num_input_tokens_seen": 747200, |
| "step": 1820 |
| }, |
| { |
| "epoch": 2.209443099273608, |
| "grad_norm": 3.8931241035461426, |
| "learning_rate": 4.7809321553691764e-05, |
| "loss": 0.2053, |
| "num_input_tokens_seen": 749344, |
| "step": 1825 |
| }, |
| { |
| "epoch": 2.2154963680387407, |
| "grad_norm": 0.4339629113674164, |
| "learning_rate": 4.778764630779183e-05, |
| "loss": 0.0899, |
| "num_input_tokens_seen": 751360, |
| "step": 1830 |
| }, |
| { |
| "epoch": 2.221549636803874, |
| "grad_norm": 3.072408676147461, |
| "learning_rate": 4.7765869321372836e-05, |
| "loss": 0.1655, |
| "num_input_tokens_seen": 753408, |
| "step": 1835 |
| }, |
| { |
| "epoch": 2.2276029055690074, |
| "grad_norm": 2.9156787395477295, |
| "learning_rate": 4.774399069166296e-05, |
| "loss": 0.1509, |
| "num_input_tokens_seen": 755456, |
| "step": 1840 |
| }, |
| { |
| "epoch": 2.2336561743341403, |
| "grad_norm": 2.098881244659424, |
| "learning_rate": 4.772201051634426e-05, |
| "loss": 0.1335, |
| "num_input_tokens_seen": 757504, |
| "step": 1845 |
| }, |
| { |
| "epoch": 2.2397094430992737, |
| "grad_norm": 0.5506150126457214, |
| "learning_rate": 4.769992889355208e-05, |
| "loss": 0.1555, |
| "num_input_tokens_seen": 759584, |
| "step": 1850 |
| }, |
| { |
| "epoch": 2.2457627118644066, |
| "grad_norm": 1.9892140626907349, |
| "learning_rate": 4.767774592187475e-05, |
| "loss": 0.11, |
| "num_input_tokens_seen": 761632, |
| "step": 1855 |
| }, |
| { |
| "epoch": 2.25181598062954, |
| "grad_norm": 3.1103200912475586, |
| "learning_rate": 4.76554617003531e-05, |
| "loss": 0.1216, |
| "num_input_tokens_seen": 763648, |
| "step": 1860 |
| }, |
| { |
| "epoch": 2.2578692493946733, |
| "grad_norm": 3.333366632461548, |
| "learning_rate": 4.763307632847998e-05, |
| "loss": 0.1664, |
| "num_input_tokens_seen": 765696, |
| "step": 1865 |
| }, |
| { |
| "epoch": 2.263922518159806, |
| "grad_norm": 5.307172775268555, |
| "learning_rate": 4.761058990619986e-05, |
| "loss": 0.1662, |
| "num_input_tokens_seen": 767776, |
| "step": 1870 |
| }, |
| { |
| "epoch": 2.2699757869249395, |
| "grad_norm": 3.0664305686950684, |
| "learning_rate": 4.7588002533908405e-05, |
| "loss": 0.1085, |
| "num_input_tokens_seen": 769856, |
| "step": 1875 |
| }, |
| { |
| "epoch": 2.2760290556900724, |
| "grad_norm": 3.5791735649108887, |
| "learning_rate": 4.756531431245195e-05, |
| "loss": 0.1527, |
| "num_input_tokens_seen": 771904, |
| "step": 1880 |
| }, |
| { |
| "epoch": 2.2820823244552058, |
| "grad_norm": 1.5854547023773193, |
| "learning_rate": 4.75425253431271e-05, |
| "loss": 0.1064, |
| "num_input_tokens_seen": 774016, |
| "step": 1885 |
| }, |
| { |
| "epoch": 2.288135593220339, |
| "grad_norm": 1.7430024147033691, |
| "learning_rate": 4.7519635727680286e-05, |
| "loss": 0.215, |
| "num_input_tokens_seen": 776000, |
| "step": 1890 |
| }, |
| { |
| "epoch": 2.294188861985472, |
| "grad_norm": 2.2312424182891846, |
| "learning_rate": 4.749664556830731e-05, |
| "loss": 0.1338, |
| "num_input_tokens_seen": 778208, |
| "step": 1895 |
| }, |
| { |
| "epoch": 2.3002421307506054, |
| "grad_norm": 2.4188883304595947, |
| "learning_rate": 4.747355496765283e-05, |
| "loss": 0.1155, |
| "num_input_tokens_seen": 780128, |
| "step": 1900 |
| }, |
| { |
| "epoch": 2.3062953995157383, |
| "grad_norm": 1.0266026258468628, |
| "learning_rate": 4.745036402880999e-05, |
| "loss": 0.0778, |
| "num_input_tokens_seen": 782112, |
| "step": 1905 |
| }, |
| { |
| "epoch": 2.3123486682808716, |
| "grad_norm": 1.269418478012085, |
| "learning_rate": 4.7427072855319886e-05, |
| "loss": 0.1447, |
| "num_input_tokens_seen": 784256, |
| "step": 1910 |
| }, |
| { |
| "epoch": 2.318401937046005, |
| "grad_norm": 2.8256311416625977, |
| "learning_rate": 4.740368155117116e-05, |
| "loss": 0.1182, |
| "num_input_tokens_seen": 786272, |
| "step": 1915 |
| }, |
| { |
| "epoch": 2.324455205811138, |
| "grad_norm": 2.589238166809082, |
| "learning_rate": 4.7380190220799484e-05, |
| "loss": 0.045, |
| "num_input_tokens_seen": 788352, |
| "step": 1920 |
| }, |
| { |
| "epoch": 2.330508474576271, |
| "grad_norm": 0.9821070432662964, |
| "learning_rate": 4.735659896908713e-05, |
| "loss": 0.1627, |
| "num_input_tokens_seen": 790368, |
| "step": 1925 |
| }, |
| { |
| "epoch": 2.3365617433414045, |
| "grad_norm": 0.7688742876052856, |
| "learning_rate": 4.73329079013625e-05, |
| "loss": 0.1664, |
| "num_input_tokens_seen": 792320, |
| "step": 1930 |
| }, |
| { |
| "epoch": 2.3426150121065374, |
| "grad_norm": 0.5684288740158081, |
| "learning_rate": 4.730911712339964e-05, |
| "loss": 0.0689, |
| "num_input_tokens_seen": 794272, |
| "step": 1935 |
| }, |
| { |
| "epoch": 2.348668280871671, |
| "grad_norm": 4.761138439178467, |
| "learning_rate": 4.728522674141776e-05, |
| "loss": 0.2063, |
| "num_input_tokens_seen": 796416, |
| "step": 1940 |
| }, |
| { |
| "epoch": 2.3547215496368037, |
| "grad_norm": 1.1905338764190674, |
| "learning_rate": 4.7261236862080805e-05, |
| "loss": 0.0513, |
| "num_input_tokens_seen": 798432, |
| "step": 1945 |
| }, |
| { |
| "epoch": 2.360774818401937, |
| "grad_norm": 3.9322619438171387, |
| "learning_rate": 4.723714759249692e-05, |
| "loss": 0.15, |
| "num_input_tokens_seen": 800480, |
| "step": 1950 |
| }, |
| { |
| "epoch": 2.3668280871670704, |
| "grad_norm": 4.847472667694092, |
| "learning_rate": 4.721295904021802e-05, |
| "loss": 0.1752, |
| "num_input_tokens_seen": 802432, |
| "step": 1955 |
| }, |
| { |
| "epoch": 2.3728813559322033, |
| "grad_norm": 0.6638381481170654, |
| "learning_rate": 4.718867131323927e-05, |
| "loss": 0.1272, |
| "num_input_tokens_seen": 804352, |
| "step": 1960 |
| }, |
| { |
| "epoch": 2.3789346246973366, |
| "grad_norm": 3.257404327392578, |
| "learning_rate": 4.7164284519998644e-05, |
| "loss": 0.1885, |
| "num_input_tokens_seen": 806272, |
| "step": 1965 |
| }, |
| { |
| "epoch": 2.38498789346247, |
| "grad_norm": 1.8241240978240967, |
| "learning_rate": 4.71397987693764e-05, |
| "loss": 0.1153, |
| "num_input_tokens_seen": 808352, |
| "step": 1970 |
| }, |
| { |
| "epoch": 2.391041162227603, |
| "grad_norm": 1.4032349586486816, |
| "learning_rate": 4.711521417069462e-05, |
| "loss": 0.1143, |
| "num_input_tokens_seen": 810304, |
| "step": 1975 |
| }, |
| { |
| "epoch": 2.3970944309927362, |
| "grad_norm": 0.7167484760284424, |
| "learning_rate": 4.709053083371672e-05, |
| "loss": 0.0683, |
| "num_input_tokens_seen": 812384, |
| "step": 1980 |
| }, |
| { |
| "epoch": 2.403147699757869, |
| "grad_norm": 1.5216193199157715, |
| "learning_rate": 4.706574886864696e-05, |
| "loss": 0.1331, |
| "num_input_tokens_seen": 814400, |
| "step": 1985 |
| }, |
| { |
| "epoch": 2.4092009685230025, |
| "grad_norm": 0.35691097378730774, |
| "learning_rate": 4.7040868386129935e-05, |
| "loss": 0.0971, |
| "num_input_tokens_seen": 816448, |
| "step": 1990 |
| }, |
| { |
| "epoch": 2.415254237288136, |
| "grad_norm": 0.27627068758010864, |
| "learning_rate": 4.701588949725009e-05, |
| "loss": 0.1488, |
| "num_input_tokens_seen": 818624, |
| "step": 1995 |
| }, |
| { |
| "epoch": 2.4213075060532687, |
| "grad_norm": 3.6620829105377197, |
| "learning_rate": 4.699081231353124e-05, |
| "loss": 0.1598, |
| "num_input_tokens_seen": 820640, |
| "step": 2000 |
| }, |
| { |
| "epoch": 2.427360774818402, |
| "grad_norm": 4.2808837890625, |
| "learning_rate": 4.696563694693605e-05, |
| "loss": 0.2381, |
| "num_input_tokens_seen": 822752, |
| "step": 2005 |
| }, |
| { |
| "epoch": 2.433414043583535, |
| "grad_norm": 4.718568325042725, |
| "learning_rate": 4.694036350986556e-05, |
| "loss": 0.1828, |
| "num_input_tokens_seen": 824832, |
| "step": 2010 |
| }, |
| { |
| "epoch": 2.4394673123486683, |
| "grad_norm": 2.1222352981567383, |
| "learning_rate": 4.6914992115158634e-05, |
| "loss": 0.1231, |
| "num_input_tokens_seen": 826816, |
| "step": 2015 |
| }, |
| { |
| "epoch": 2.4455205811138017, |
| "grad_norm": 3.19950270652771, |
| "learning_rate": 4.688952287609152e-05, |
| "loss": 0.1957, |
| "num_input_tokens_seen": 828672, |
| "step": 2020 |
| }, |
| { |
| "epoch": 2.4515738498789346, |
| "grad_norm": 1.1805663108825684, |
| "learning_rate": 4.686395590637732e-05, |
| "loss": 0.1136, |
| "num_input_tokens_seen": 830752, |
| "step": 2025 |
| }, |
| { |
| "epoch": 2.457627118644068, |
| "grad_norm": 4.136936187744141, |
| "learning_rate": 4.683829132016544e-05, |
| "loss": 0.1257, |
| "num_input_tokens_seen": 832832, |
| "step": 2030 |
| }, |
| { |
| "epoch": 2.463680387409201, |
| "grad_norm": 1.4625964164733887, |
| "learning_rate": 4.6812529232041144e-05, |
| "loss": 0.129, |
| "num_input_tokens_seen": 834848, |
| "step": 2035 |
| }, |
| { |
| "epoch": 2.469733656174334, |
| "grad_norm": 1.1322230100631714, |
| "learning_rate": 4.6786669757025016e-05, |
| "loss": 0.0553, |
| "num_input_tokens_seen": 836864, |
| "step": 2040 |
| }, |
| { |
| "epoch": 2.4757869249394675, |
| "grad_norm": 3.3223824501037598, |
| "learning_rate": 4.676071301057243e-05, |
| "loss": 0.1469, |
| "num_input_tokens_seen": 838784, |
| "step": 2045 |
| }, |
| { |
| "epoch": 2.4818401937046004, |
| "grad_norm": 2.883943796157837, |
| "learning_rate": 4.673465910857306e-05, |
| "loss": 0.0844, |
| "num_input_tokens_seen": 840832, |
| "step": 2050 |
| }, |
| { |
| "epoch": 2.4878934624697338, |
| "grad_norm": 0.32013097405433655, |
| "learning_rate": 4.670850816735035e-05, |
| "loss": 0.1226, |
| "num_input_tokens_seen": 842752, |
| "step": 2055 |
| }, |
| { |
| "epoch": 2.4939467312348667, |
| "grad_norm": 3.8903720378875732, |
| "learning_rate": 4.668226030366101e-05, |
| "loss": 0.2109, |
| "num_input_tokens_seen": 844928, |
| "step": 2060 |
| }, |
| { |
| "epoch": 2.5, |
| "grad_norm": 1.0813623666763306, |
| "learning_rate": 4.665591563469445e-05, |
| "loss": 0.1393, |
| "num_input_tokens_seen": 847104, |
| "step": 2065 |
| }, |
| { |
| "epoch": 2.5, |
| "eval_loss": 0.1389196813106537, |
| "eval_runtime": 4.5634, |
| "eval_samples_per_second": 80.422, |
| "eval_steps_per_second": 20.16, |
| "num_input_tokens_seen": 847104, |
| "step": 2065 |
| }, |
| { |
| "epoch": 2.5060532687651333, |
| "grad_norm": 0.8157436847686768, |
| "learning_rate": 4.662947427807231e-05, |
| "loss": 0.0783, |
| "num_input_tokens_seen": 849120, |
| "step": 2070 |
| }, |
| { |
| "epoch": 2.5121065375302662, |
| "grad_norm": 3.726567268371582, |
| "learning_rate": 4.6602936351847924e-05, |
| "loss": 0.0737, |
| "num_input_tokens_seen": 851296, |
| "step": 2075 |
| }, |
| { |
| "epoch": 2.5181598062953996, |
| "grad_norm": 6.2762603759765625, |
| "learning_rate": 4.657630197450577e-05, |
| "loss": 0.2042, |
| "num_input_tokens_seen": 853344, |
| "step": 2080 |
| }, |
| { |
| "epoch": 2.5242130750605325, |
| "grad_norm": 2.1367788314819336, |
| "learning_rate": 4.6549571264960945e-05, |
| "loss": 0.1232, |
| "num_input_tokens_seen": 855264, |
| "step": 2085 |
| }, |
| { |
| "epoch": 2.530266343825666, |
| "grad_norm": 1.8090111017227173, |
| "learning_rate": 4.652274434255866e-05, |
| "loss": 0.1651, |
| "num_input_tokens_seen": 857152, |
| "step": 2090 |
| }, |
| { |
| "epoch": 2.536319612590799, |
| "grad_norm": 2.769136667251587, |
| "learning_rate": 4.6495821327073675e-05, |
| "loss": 0.162, |
| "num_input_tokens_seen": 859232, |
| "step": 2095 |
| }, |
| { |
| "epoch": 2.542372881355932, |
| "grad_norm": 4.568650722503662, |
| "learning_rate": 4.6468802338709783e-05, |
| "loss": 0.1262, |
| "num_input_tokens_seen": 861312, |
| "step": 2100 |
| }, |
| { |
| "epoch": 2.5484261501210654, |
| "grad_norm": 4.672850131988525, |
| "learning_rate": 4.644168749809929e-05, |
| "loss": 0.1883, |
| "num_input_tokens_seen": 863552, |
| "step": 2105 |
| }, |
| { |
| "epoch": 2.5544794188861983, |
| "grad_norm": 0.21458782255649567, |
| "learning_rate": 4.6414476926302406e-05, |
| "loss": 0.118, |
| "num_input_tokens_seen": 865568, |
| "step": 2110 |
| }, |
| { |
| "epoch": 2.5605326876513317, |
| "grad_norm": 3.470489501953125, |
| "learning_rate": 4.638717074480682e-05, |
| "loss": 0.1168, |
| "num_input_tokens_seen": 867488, |
| "step": 2115 |
| }, |
| { |
| "epoch": 2.566585956416465, |
| "grad_norm": 2.928154468536377, |
| "learning_rate": 4.6359769075527026e-05, |
| "loss": 0.0644, |
| "num_input_tokens_seen": 869504, |
| "step": 2120 |
| }, |
| { |
| "epoch": 2.572639225181598, |
| "grad_norm": 1.570302963256836, |
| "learning_rate": 4.6332272040803895e-05, |
| "loss": 0.0429, |
| "num_input_tokens_seen": 871680, |
| "step": 2125 |
| }, |
| { |
| "epoch": 2.5786924939467313, |
| "grad_norm": 1.8090287446975708, |
| "learning_rate": 4.630467976340405e-05, |
| "loss": 0.0671, |
| "num_input_tokens_seen": 873856, |
| "step": 2130 |
| }, |
| { |
| "epoch": 2.584745762711864, |
| "grad_norm": 3.67999005317688, |
| "learning_rate": 4.6276992366519365e-05, |
| "loss": 0.1545, |
| "num_input_tokens_seen": 875968, |
| "step": 2135 |
| }, |
| { |
| "epoch": 2.5907990314769975, |
| "grad_norm": 5.59567403793335, |
| "learning_rate": 4.624920997376637e-05, |
| "loss": 0.1714, |
| "num_input_tokens_seen": 878144, |
| "step": 2140 |
| }, |
| { |
| "epoch": 2.596852300242131, |
| "grad_norm": 3.0647568702697754, |
| "learning_rate": 4.622133270918576e-05, |
| "loss": 0.1627, |
| "num_input_tokens_seen": 880320, |
| "step": 2145 |
| }, |
| { |
| "epoch": 2.6029055690072638, |
| "grad_norm": 1.2152265310287476, |
| "learning_rate": 4.619336069724177e-05, |
| "loss": 0.1276, |
| "num_input_tokens_seen": 882400, |
| "step": 2150 |
| }, |
| { |
| "epoch": 2.608958837772397, |
| "grad_norm": 2.7467970848083496, |
| "learning_rate": 4.6165294062821696e-05, |
| "loss": 0.3168, |
| "num_input_tokens_seen": 884512, |
| "step": 2155 |
| }, |
| { |
| "epoch": 2.61501210653753, |
| "grad_norm": 1.246924638748169, |
| "learning_rate": 4.613713293123525e-05, |
| "loss": 0.0729, |
| "num_input_tokens_seen": 886592, |
| "step": 2160 |
| }, |
| { |
| "epoch": 2.6210653753026634, |
| "grad_norm": 3.9440741539001465, |
| "learning_rate": 4.610887742821408e-05, |
| "loss": 0.1066, |
| "num_input_tokens_seen": 888640, |
| "step": 2165 |
| }, |
| { |
| "epoch": 2.6271186440677967, |
| "grad_norm": 2.369666814804077, |
| "learning_rate": 4.608052767991118e-05, |
| "loss": 0.0523, |
| "num_input_tokens_seen": 890880, |
| "step": 2170 |
| }, |
| { |
| "epoch": 2.6331719128329296, |
| "grad_norm": 2.7659249305725098, |
| "learning_rate": 4.605208381290029e-05, |
| "loss": 0.0824, |
| "num_input_tokens_seen": 892832, |
| "step": 2175 |
| }, |
| { |
| "epoch": 2.639225181598063, |
| "grad_norm": 4.095376491546631, |
| "learning_rate": 4.6023545954175406e-05, |
| "loss": 0.1441, |
| "num_input_tokens_seen": 894912, |
| "step": 2180 |
| }, |
| { |
| "epoch": 2.645278450363196, |
| "grad_norm": 4.215013027191162, |
| "learning_rate": 4.599491423115014e-05, |
| "loss": 0.1021, |
| "num_input_tokens_seen": 896960, |
| "step": 2185 |
| }, |
| { |
| "epoch": 2.651331719128329, |
| "grad_norm": 0.6620141863822937, |
| "learning_rate": 4.59661887716572e-05, |
| "loss": 0.0891, |
| "num_input_tokens_seen": 898816, |
| "step": 2190 |
| }, |
| { |
| "epoch": 2.6573849878934626, |
| "grad_norm": 0.9556487798690796, |
| "learning_rate": 4.5937369703947785e-05, |
| "loss": 0.0992, |
| "num_input_tokens_seen": 900832, |
| "step": 2195 |
| }, |
| { |
| "epoch": 2.663438256658596, |
| "grad_norm": 1.2059531211853027, |
| "learning_rate": 4.590845715669104e-05, |
| "loss": 0.0924, |
| "num_input_tokens_seen": 902944, |
| "step": 2200 |
| }, |
| { |
| "epoch": 2.669491525423729, |
| "grad_norm": 1.3572944402694702, |
| "learning_rate": 4.5879451258973465e-05, |
| "loss": 0.1106, |
| "num_input_tokens_seen": 905056, |
| "step": 2205 |
| }, |
| { |
| "epoch": 2.6755447941888617, |
| "grad_norm": 3.2731289863586426, |
| "learning_rate": 4.5850352140298356e-05, |
| "loss": 0.1858, |
| "num_input_tokens_seen": 907232, |
| "step": 2210 |
| }, |
| { |
| "epoch": 2.681598062953995, |
| "grad_norm": 4.388832092285156, |
| "learning_rate": 4.582115993058519e-05, |
| "loss": 0.1382, |
| "num_input_tokens_seen": 909248, |
| "step": 2215 |
| }, |
| { |
| "epoch": 2.6876513317191284, |
| "grad_norm": 0.5173718333244324, |
| "learning_rate": 4.5791874760169095e-05, |
| "loss": 0.0703, |
| "num_input_tokens_seen": 911264, |
| "step": 2220 |
| }, |
| { |
| "epoch": 2.6937046004842617, |
| "grad_norm": 0.8536763191223145, |
| "learning_rate": 4.5762496759800246e-05, |
| "loss": 0.1439, |
| "num_input_tokens_seen": 913216, |
| "step": 2225 |
| }, |
| { |
| "epoch": 2.6997578692493946, |
| "grad_norm": 0.34403684735298157, |
| "learning_rate": 4.573302606064324e-05, |
| "loss": 0.1254, |
| "num_input_tokens_seen": 915328, |
| "step": 2230 |
| }, |
| { |
| "epoch": 2.705811138014528, |
| "grad_norm": 5.366670608520508, |
| "learning_rate": 4.5703462794276574e-05, |
| "loss": 0.1947, |
| "num_input_tokens_seen": 917568, |
| "step": 2235 |
| }, |
| { |
| "epoch": 2.711864406779661, |
| "grad_norm": 1.7030010223388672, |
| "learning_rate": 4.567380709269205e-05, |
| "loss": 0.1793, |
| "num_input_tokens_seen": 919424, |
| "step": 2240 |
| }, |
| { |
| "epoch": 2.7179176755447942, |
| "grad_norm": 4.686395645141602, |
| "learning_rate": 4.5644059088294145e-05, |
| "loss": 0.0785, |
| "num_input_tokens_seen": 921376, |
| "step": 2245 |
| }, |
| { |
| "epoch": 2.7239709443099276, |
| "grad_norm": 3.0779364109039307, |
| "learning_rate": 4.561421891389943e-05, |
| "loss": 0.0824, |
| "num_input_tokens_seen": 923456, |
| "step": 2250 |
| }, |
| { |
| "epoch": 2.7300242130750605, |
| "grad_norm": 5.996677875518799, |
| "learning_rate": 4.558428670273601e-05, |
| "loss": 0.1826, |
| "num_input_tokens_seen": 925504, |
| "step": 2255 |
| }, |
| { |
| "epoch": 2.736077481840194, |
| "grad_norm": 3.9204232692718506, |
| "learning_rate": 4.555426258844292e-05, |
| "loss": 0.1157, |
| "num_input_tokens_seen": 927456, |
| "step": 2260 |
| }, |
| { |
| "epoch": 2.7421307506053267, |
| "grad_norm": 3.752305507659912, |
| "learning_rate": 4.552414670506949e-05, |
| "loss": 0.0627, |
| "num_input_tokens_seen": 929440, |
| "step": 2265 |
| }, |
| { |
| "epoch": 2.74818401937046, |
| "grad_norm": 2.5699219703674316, |
| "learning_rate": 4.5493939187074784e-05, |
| "loss": 0.1061, |
| "num_input_tokens_seen": 931712, |
| "step": 2270 |
| }, |
| { |
| "epoch": 2.7542372881355934, |
| "grad_norm": 3.8020174503326416, |
| "learning_rate": 4.5463640169326994e-05, |
| "loss": 0.246, |
| "num_input_tokens_seen": 933664, |
| "step": 2275 |
| }, |
| { |
| "epoch": 2.7602905569007263, |
| "grad_norm": 2.4262406826019287, |
| "learning_rate": 4.5433249787102816e-05, |
| "loss": 0.1468, |
| "num_input_tokens_seen": 935840, |
| "step": 2280 |
| }, |
| { |
| "epoch": 2.7663438256658597, |
| "grad_norm": 2.018612861633301, |
| "learning_rate": 4.54027681760869e-05, |
| "loss": 0.1444, |
| "num_input_tokens_seen": 937920, |
| "step": 2285 |
| }, |
| { |
| "epoch": 2.7723970944309926, |
| "grad_norm": 4.552961349487305, |
| "learning_rate": 4.537219547237115e-05, |
| "loss": 0.1195, |
| "num_input_tokens_seen": 940160, |
| "step": 2290 |
| }, |
| { |
| "epoch": 2.778450363196126, |
| "grad_norm": 1.2480086088180542, |
| "learning_rate": 4.5341531812454234e-05, |
| "loss": 0.0581, |
| "num_input_tokens_seen": 942304, |
| "step": 2295 |
| }, |
| { |
| "epoch": 2.7845036319612593, |
| "grad_norm": 4.706632137298584, |
| "learning_rate": 4.5310777333240885e-05, |
| "loss": 0.128, |
| "num_input_tokens_seen": 944288, |
| "step": 2300 |
| }, |
| { |
| "epoch": 2.790556900726392, |
| "grad_norm": 3.13391375541687, |
| "learning_rate": 4.52799321720413e-05, |
| "loss": 0.1094, |
| "num_input_tokens_seen": 946368, |
| "step": 2305 |
| }, |
| { |
| "epoch": 2.7966101694915255, |
| "grad_norm": 0.19843530654907227, |
| "learning_rate": 4.524899646657059e-05, |
| "loss": 0.1588, |
| "num_input_tokens_seen": 948512, |
| "step": 2310 |
| }, |
| { |
| "epoch": 2.8026634382566584, |
| "grad_norm": 5.570863246917725, |
| "learning_rate": 4.521797035494809e-05, |
| "loss": 0.1722, |
| "num_input_tokens_seen": 950624, |
| "step": 2315 |
| }, |
| { |
| "epoch": 2.8087167070217918, |
| "grad_norm": 0.583500862121582, |
| "learning_rate": 4.5186853975696775e-05, |
| "loss": 0.0668, |
| "num_input_tokens_seen": 952640, |
| "step": 2320 |
| }, |
| { |
| "epoch": 2.814769975786925, |
| "grad_norm": 7.228137016296387, |
| "learning_rate": 4.515564746774265e-05, |
| "loss": 0.191, |
| "num_input_tokens_seen": 954656, |
| "step": 2325 |
| }, |
| { |
| "epoch": 2.820823244552058, |
| "grad_norm": 6.490035057067871, |
| "learning_rate": 4.512435097041412e-05, |
| "loss": 0.0892, |
| "num_input_tokens_seen": 956736, |
| "step": 2330 |
| }, |
| { |
| "epoch": 2.8268765133171914, |
| "grad_norm": 3.498931407928467, |
| "learning_rate": 4.509296462344136e-05, |
| "loss": 0.0698, |
| "num_input_tokens_seen": 958816, |
| "step": 2335 |
| }, |
| { |
| "epoch": 2.8329297820823243, |
| "grad_norm": 5.152684211730957, |
| "learning_rate": 4.50614885669557e-05, |
| "loss": 0.2331, |
| "num_input_tokens_seen": 960800, |
| "step": 2340 |
| }, |
| { |
| "epoch": 2.8389830508474576, |
| "grad_norm": 4.12315559387207, |
| "learning_rate": 4.5029922941489e-05, |
| "loss": 0.1327, |
| "num_input_tokens_seen": 962976, |
| "step": 2345 |
| }, |
| { |
| "epoch": 2.845036319612591, |
| "grad_norm": 3.800520896911621, |
| "learning_rate": 4.499826788797302e-05, |
| "loss": 0.1845, |
| "num_input_tokens_seen": 965088, |
| "step": 2350 |
| }, |
| { |
| "epoch": 2.851089588377724, |
| "grad_norm": 3.0858726501464844, |
| "learning_rate": 4.49665235477388e-05, |
| "loss": 0.1429, |
| "num_input_tokens_seen": 967136, |
| "step": 2355 |
| }, |
| { |
| "epoch": 2.857142857142857, |
| "grad_norm": 3.461909055709839, |
| "learning_rate": 4.493469006251601e-05, |
| "loss": 0.1257, |
| "num_input_tokens_seen": 969248, |
| "step": 2360 |
| }, |
| { |
| "epoch": 2.86319612590799, |
| "grad_norm": 0.6151326298713684, |
| "learning_rate": 4.490276757443233e-05, |
| "loss": 0.1448, |
| "num_input_tokens_seen": 971360, |
| "step": 2365 |
| }, |
| { |
| "epoch": 2.8692493946731235, |
| "grad_norm": 0.8009752035140991, |
| "learning_rate": 4.487075622601281e-05, |
| "loss": 0.0933, |
| "num_input_tokens_seen": 973408, |
| "step": 2370 |
| }, |
| { |
| "epoch": 2.875302663438257, |
| "grad_norm": 0.28616681694984436, |
| "learning_rate": 4.483865616017924e-05, |
| "loss": 0.1037, |
| "num_input_tokens_seen": 975392, |
| "step": 2375 |
| }, |
| { |
| "epoch": 2.8813559322033897, |
| "grad_norm": 2.447929859161377, |
| "learning_rate": 4.480646752024951e-05, |
| "loss": 0.0563, |
| "num_input_tokens_seen": 977376, |
| "step": 2380 |
| }, |
| { |
| "epoch": 2.887409200968523, |
| "grad_norm": 0.7191622853279114, |
| "learning_rate": 4.477419044993697e-05, |
| "loss": 0.1621, |
| "num_input_tokens_seen": 979328, |
| "step": 2385 |
| }, |
| { |
| "epoch": 2.893462469733656, |
| "grad_norm": 4.25314474105835, |
| "learning_rate": 4.474182509334978e-05, |
| "loss": 0.1238, |
| "num_input_tokens_seen": 981376, |
| "step": 2390 |
| }, |
| { |
| "epoch": 2.8995157384987893, |
| "grad_norm": 1.7415614128112793, |
| "learning_rate": 4.470937159499029e-05, |
| "loss": 0.0546, |
| "num_input_tokens_seen": 983360, |
| "step": 2395 |
| }, |
| { |
| "epoch": 2.9055690072639226, |
| "grad_norm": 1.0595369338989258, |
| "learning_rate": 4.467683009975435e-05, |
| "loss": 0.1113, |
| "num_input_tokens_seen": 985408, |
| "step": 2400 |
| }, |
| { |
| "epoch": 2.9116222760290555, |
| "grad_norm": 5.065093994140625, |
| "learning_rate": 4.464420075293072e-05, |
| "loss": 0.1293, |
| "num_input_tokens_seen": 987584, |
| "step": 2405 |
| }, |
| { |
| "epoch": 2.917675544794189, |
| "grad_norm": 2.5174288749694824, |
| "learning_rate": 4.4611483700200374e-05, |
| "loss": 0.1081, |
| "num_input_tokens_seen": 989632, |
| "step": 2410 |
| }, |
| { |
| "epoch": 2.923728813559322, |
| "grad_norm": 0.578865110874176, |
| "learning_rate": 4.457867908763589e-05, |
| "loss": 0.0653, |
| "num_input_tokens_seen": 991680, |
| "step": 2415 |
| }, |
| { |
| "epoch": 2.929782082324455, |
| "grad_norm": 0.7825148701667786, |
| "learning_rate": 4.454578706170075e-05, |
| "loss": 0.0944, |
| "num_input_tokens_seen": 993824, |
| "step": 2420 |
| }, |
| { |
| "epoch": 2.9358353510895885, |
| "grad_norm": 0.21404187381267548, |
| "learning_rate": 4.4512807769248723e-05, |
| "loss": 0.0885, |
| "num_input_tokens_seen": 995904, |
| "step": 2425 |
| }, |
| { |
| "epoch": 2.9418886198547214, |
| "grad_norm": 0.4999610483646393, |
| "learning_rate": 4.447974135752321e-05, |
| "loss": 0.0637, |
| "num_input_tokens_seen": 998080, |
| "step": 2430 |
| }, |
| { |
| "epoch": 2.9479418886198547, |
| "grad_norm": 5.155250072479248, |
| "learning_rate": 4.444658797415656e-05, |
| "loss": 0.1987, |
| "num_input_tokens_seen": 1000160, |
| "step": 2435 |
| }, |
| { |
| "epoch": 2.9539951573849876, |
| "grad_norm": 0.5416507124900818, |
| "learning_rate": 4.441334776716944e-05, |
| "loss": 0.1704, |
| "num_input_tokens_seen": 1002368, |
| "step": 2440 |
| }, |
| { |
| "epoch": 2.960048426150121, |
| "grad_norm": 5.383670806884766, |
| "learning_rate": 4.438002088497015e-05, |
| "loss": 0.1466, |
| "num_input_tokens_seen": 1004448, |
| "step": 2445 |
| }, |
| { |
| "epoch": 2.9661016949152543, |
| "grad_norm": 3.468714475631714, |
| "learning_rate": 4.434660747635396e-05, |
| "loss": 0.0692, |
| "num_input_tokens_seen": 1006336, |
| "step": 2450 |
| }, |
| { |
| "epoch": 2.9721549636803877, |
| "grad_norm": 0.6584161520004272, |
| "learning_rate": 4.4313107690502485e-05, |
| "loss": 0.1368, |
| "num_input_tokens_seen": 1008416, |
| "step": 2455 |
| }, |
| { |
| "epoch": 2.9782082324455206, |
| "grad_norm": 0.13571301102638245, |
| "learning_rate": 4.427952167698298e-05, |
| "loss": 0.1044, |
| "num_input_tokens_seen": 1010400, |
| "step": 2460 |
| }, |
| { |
| "epoch": 2.9842615012106535, |
| "grad_norm": 0.7680113315582275, |
| "learning_rate": 4.4245849585747654e-05, |
| "loss": 0.1064, |
| "num_input_tokens_seen": 1012320, |
| "step": 2465 |
| }, |
| { |
| "epoch": 2.990314769975787, |
| "grad_norm": 0.6504201889038086, |
| "learning_rate": 4.4212091567133083e-05, |
| "loss": 0.1309, |
| "num_input_tokens_seen": 1014400, |
| "step": 2470 |
| }, |
| { |
| "epoch": 2.99636803874092, |
| "grad_norm": 0.6503428220748901, |
| "learning_rate": 4.417824777185943e-05, |
| "loss": 0.0702, |
| "num_input_tokens_seen": 1016480, |
| "step": 2475 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 0.14438338577747345, |
| "eval_runtime": 4.5701, |
| "eval_samples_per_second": 80.305, |
| "eval_steps_per_second": 20.131, |
| "num_input_tokens_seen": 1017368, |
| "step": 2478 |
| }, |
| { |
| "epoch": 3.002421307506053, |
| "grad_norm": 2.1441495418548584, |
| "learning_rate": 4.414431835102987e-05, |
| "loss": 0.0468, |
| "num_input_tokens_seen": 1018232, |
| "step": 2480 |
| }, |
| { |
| "epoch": 3.0084745762711864, |
| "grad_norm": 0.11217233538627625, |
| "learning_rate": 4.411030345612984e-05, |
| "loss": 0.1225, |
| "num_input_tokens_seen": 1020280, |
| "step": 2485 |
| }, |
| { |
| "epoch": 3.0145278450363198, |
| "grad_norm": 0.7029927372932434, |
| "learning_rate": 4.407620323902643e-05, |
| "loss": 0.0755, |
| "num_input_tokens_seen": 1022328, |
| "step": 2490 |
| }, |
| { |
| "epoch": 3.0205811138014527, |
| "grad_norm": 3.3221864700317383, |
| "learning_rate": 4.404201785196762e-05, |
| "loss": 0.1046, |
| "num_input_tokens_seen": 1024312, |
| "step": 2495 |
| }, |
| { |
| "epoch": 3.026634382566586, |
| "grad_norm": 1.9272534847259521, |
| "learning_rate": 4.400774744758171e-05, |
| "loss": 0.094, |
| "num_input_tokens_seen": 1026392, |
| "step": 2500 |
| }, |
| { |
| "epoch": 3.032687651331719, |
| "grad_norm": 6.2990899085998535, |
| "learning_rate": 4.397339217887652e-05, |
| "loss": 0.0966, |
| "num_input_tokens_seen": 1028344, |
| "step": 2505 |
| }, |
| { |
| "epoch": 3.0387409200968523, |
| "grad_norm": 6.206118583679199, |
| "learning_rate": 4.393895219923881e-05, |
| "loss": 0.2425, |
| "num_input_tokens_seen": 1030520, |
| "step": 2510 |
| }, |
| { |
| "epoch": 3.0447941888619856, |
| "grad_norm": 1.4443256855010986, |
| "learning_rate": 4.3904427662433534e-05, |
| "loss": 0.1987, |
| "num_input_tokens_seen": 1032728, |
| "step": 2515 |
| }, |
| { |
| "epoch": 3.0508474576271185, |
| "grad_norm": 3.545659303665161, |
| "learning_rate": 4.386981872260317e-05, |
| "loss": 0.0737, |
| "num_input_tokens_seen": 1034808, |
| "step": 2520 |
| }, |
| { |
| "epoch": 3.056900726392252, |
| "grad_norm": 3.7366652488708496, |
| "learning_rate": 4.383512553426703e-05, |
| "loss": 0.1712, |
| "num_input_tokens_seen": 1036888, |
| "step": 2525 |
| }, |
| { |
| "epoch": 3.062953995157385, |
| "grad_norm": 3.9347126483917236, |
| "learning_rate": 4.380034825232059e-05, |
| "loss": 0.11, |
| "num_input_tokens_seen": 1039000, |
| "step": 2530 |
| }, |
| { |
| "epoch": 3.069007263922518, |
| "grad_norm": 3.4273524284362793, |
| "learning_rate": 4.376548703203474e-05, |
| "loss": 0.1139, |
| "num_input_tokens_seen": 1040984, |
| "step": 2535 |
| }, |
| { |
| "epoch": 3.0750605326876514, |
| "grad_norm": 1.0495061874389648, |
| "learning_rate": 4.3730542029055174e-05, |
| "loss": 0.0579, |
| "num_input_tokens_seen": 1043000, |
| "step": 2540 |
| }, |
| { |
| "epoch": 3.0811138014527844, |
| "grad_norm": 1.4927022457122803, |
| "learning_rate": 4.3695513399401646e-05, |
| "loss": 0.1328, |
| "num_input_tokens_seen": 1044984, |
| "step": 2545 |
| }, |
| { |
| "epoch": 3.0871670702179177, |
| "grad_norm": 1.1897157430648804, |
| "learning_rate": 4.366040129946725e-05, |
| "loss": 0.1041, |
| "num_input_tokens_seen": 1047096, |
| "step": 2550 |
| }, |
| { |
| "epoch": 3.093220338983051, |
| "grad_norm": 1.3103008270263672, |
| "learning_rate": 4.362520588601777e-05, |
| "loss": 0.1656, |
| "num_input_tokens_seen": 1049208, |
| "step": 2555 |
| }, |
| { |
| "epoch": 3.099273607748184, |
| "grad_norm": 4.3546223640441895, |
| "learning_rate": 4.3589927316190983e-05, |
| "loss": 0.2196, |
| "num_input_tokens_seen": 1051192, |
| "step": 2560 |
| }, |
| { |
| "epoch": 3.1053268765133173, |
| "grad_norm": 2.591219186782837, |
| "learning_rate": 4.35545657474959e-05, |
| "loss": 0.1287, |
| "num_input_tokens_seen": 1053240, |
| "step": 2565 |
| }, |
| { |
| "epoch": 3.11138014527845, |
| "grad_norm": 2.16152024269104, |
| "learning_rate": 4.351912133781213e-05, |
| "loss": 0.0659, |
| "num_input_tokens_seen": 1055384, |
| "step": 2570 |
| }, |
| { |
| "epoch": 3.1174334140435835, |
| "grad_norm": 0.5291240811347961, |
| "learning_rate": 4.3483594245389106e-05, |
| "loss": 0.1992, |
| "num_input_tokens_seen": 1057464, |
| "step": 2575 |
| }, |
| { |
| "epoch": 3.123486682808717, |
| "grad_norm": 3.001479148864746, |
| "learning_rate": 4.3447984628845464e-05, |
| "loss": 0.0759, |
| "num_input_tokens_seen": 1059736, |
| "step": 2580 |
| }, |
| { |
| "epoch": 3.12953995157385, |
| "grad_norm": 2.1946427822113037, |
| "learning_rate": 4.341229264716825e-05, |
| "loss": 0.1369, |
| "num_input_tokens_seen": 1061656, |
| "step": 2585 |
| }, |
| { |
| "epoch": 3.135593220338983, |
| "grad_norm": 3.4312591552734375, |
| "learning_rate": 4.337651845971227e-05, |
| "loss": 0.0533, |
| "num_input_tokens_seen": 1063736, |
| "step": 2590 |
| }, |
| { |
| "epoch": 3.141646489104116, |
| "grad_norm": 0.5884976387023926, |
| "learning_rate": 4.334066222619933e-05, |
| "loss": 0.1154, |
| "num_input_tokens_seen": 1065720, |
| "step": 2595 |
| }, |
| { |
| "epoch": 3.1476997578692494, |
| "grad_norm": 4.081981658935547, |
| "learning_rate": 4.3304724106717584e-05, |
| "loss": 0.1374, |
| "num_input_tokens_seen": 1067736, |
| "step": 2600 |
| }, |
| { |
| "epoch": 3.1537530266343827, |
| "grad_norm": 0.2492610514163971, |
| "learning_rate": 4.326870426172075e-05, |
| "loss": 0.0978, |
| "num_input_tokens_seen": 1069848, |
| "step": 2605 |
| }, |
| { |
| "epoch": 3.1598062953995156, |
| "grad_norm": 1.401228427886963, |
| "learning_rate": 4.323260285202746e-05, |
| "loss": 0.0858, |
| "num_input_tokens_seen": 1071960, |
| "step": 2610 |
| }, |
| { |
| "epoch": 3.165859564164649, |
| "grad_norm": 3.4008891582489014, |
| "learning_rate": 4.3196420038820475e-05, |
| "loss": 0.0843, |
| "num_input_tokens_seen": 1074072, |
| "step": 2615 |
| }, |
| { |
| "epoch": 3.171912832929782, |
| "grad_norm": 3.2857916355133057, |
| "learning_rate": 4.316015598364603e-05, |
| "loss": 0.1736, |
| "num_input_tokens_seen": 1076184, |
| "step": 2620 |
| }, |
| { |
| "epoch": 3.1779661016949152, |
| "grad_norm": 1.1122257709503174, |
| "learning_rate": 4.312381084841307e-05, |
| "loss": 0.1213, |
| "num_input_tokens_seen": 1078360, |
| "step": 2625 |
| }, |
| { |
| "epoch": 3.1840193704600486, |
| "grad_norm": 1.347262978553772, |
| "learning_rate": 4.308738479539254e-05, |
| "loss": 0.125, |
| "num_input_tokens_seen": 1080440, |
| "step": 2630 |
| }, |
| { |
| "epoch": 3.1900726392251815, |
| "grad_norm": 0.6629340052604675, |
| "learning_rate": 4.305087798721665e-05, |
| "loss": 0.11, |
| "num_input_tokens_seen": 1082520, |
| "step": 2635 |
| }, |
| { |
| "epoch": 3.196125907990315, |
| "grad_norm": 4.0958170890808105, |
| "learning_rate": 4.30142905868782e-05, |
| "loss": 0.1791, |
| "num_input_tokens_seen": 1084408, |
| "step": 2640 |
| }, |
| { |
| "epoch": 3.2021791767554477, |
| "grad_norm": 2.998307943344116, |
| "learning_rate": 4.297762275772975e-05, |
| "loss": 0.0911, |
| "num_input_tokens_seen": 1086424, |
| "step": 2645 |
| }, |
| { |
| "epoch": 3.208232445520581, |
| "grad_norm": 3.835343360900879, |
| "learning_rate": 4.2940874663483005e-05, |
| "loss": 0.1416, |
| "num_input_tokens_seen": 1088440, |
| "step": 2650 |
| }, |
| { |
| "epoch": 3.2142857142857144, |
| "grad_norm": 0.17636780440807343, |
| "learning_rate": 4.2904046468208006e-05, |
| "loss": 0.1582, |
| "num_input_tokens_seen": 1090648, |
| "step": 2655 |
| }, |
| { |
| "epoch": 3.2203389830508473, |
| "grad_norm": 5.161961555480957, |
| "learning_rate": 4.286713833633242e-05, |
| "loss": 0.1795, |
| "num_input_tokens_seen": 1092632, |
| "step": 2660 |
| }, |
| { |
| "epoch": 3.2263922518159807, |
| "grad_norm": 0.3390583097934723, |
| "learning_rate": 4.283015043264084e-05, |
| "loss": 0.0862, |
| "num_input_tokens_seen": 1094648, |
| "step": 2665 |
| }, |
| { |
| "epoch": 3.232445520581114, |
| "grad_norm": 2.341804265975952, |
| "learning_rate": 4.279308292227396e-05, |
| "loss": 0.1128, |
| "num_input_tokens_seen": 1096728, |
| "step": 2670 |
| }, |
| { |
| "epoch": 3.238498789346247, |
| "grad_norm": 1.2374261617660522, |
| "learning_rate": 4.275593597072796e-05, |
| "loss": 0.0901, |
| "num_input_tokens_seen": 1098872, |
| "step": 2675 |
| }, |
| { |
| "epoch": 3.2445520581113803, |
| "grad_norm": 3.755679130554199, |
| "learning_rate": 4.2718709743853654e-05, |
| "loss": 0.0633, |
| "num_input_tokens_seen": 1101048, |
| "step": 2680 |
| }, |
| { |
| "epoch": 3.250605326876513, |
| "grad_norm": 4.655717372894287, |
| "learning_rate": 4.268140440785584e-05, |
| "loss": 0.1257, |
| "num_input_tokens_seen": 1103320, |
| "step": 2685 |
| }, |
| { |
| "epoch": 3.2566585956416465, |
| "grad_norm": 2.0559744834899902, |
| "learning_rate": 4.264402012929247e-05, |
| "loss": 0.0598, |
| "num_input_tokens_seen": 1105336, |
| "step": 2690 |
| }, |
| { |
| "epoch": 3.26271186440678, |
| "grad_norm": 2.825394868850708, |
| "learning_rate": 4.2606557075073996e-05, |
| "loss": 0.1262, |
| "num_input_tokens_seen": 1107288, |
| "step": 2695 |
| }, |
| { |
| "epoch": 3.2687651331719128, |
| "grad_norm": 1.9354199171066284, |
| "learning_rate": 4.256901541246255e-05, |
| "loss": 0.0741, |
| "num_input_tokens_seen": 1109368, |
| "step": 2700 |
| }, |
| { |
| "epoch": 3.274818401937046, |
| "grad_norm": 4.32333517074585, |
| "learning_rate": 4.253139530907124e-05, |
| "loss": 0.1098, |
| "num_input_tokens_seen": 1111576, |
| "step": 2705 |
| }, |
| { |
| "epoch": 3.280871670702179, |
| "grad_norm": 0.3646182417869568, |
| "learning_rate": 4.249369693286341e-05, |
| "loss": 0.1509, |
| "num_input_tokens_seen": 1113624, |
| "step": 2710 |
| }, |
| { |
| "epoch": 3.2869249394673123, |
| "grad_norm": 3.2211687564849854, |
| "learning_rate": 4.245592045215182e-05, |
| "loss": 0.1527, |
| "num_input_tokens_seen": 1115512, |
| "step": 2715 |
| }, |
| { |
| "epoch": 3.2929782082324457, |
| "grad_norm": 1.915663242340088, |
| "learning_rate": 4.2418066035598e-05, |
| "loss": 0.0569, |
| "num_input_tokens_seen": 1117464, |
| "step": 2720 |
| }, |
| { |
| "epoch": 3.2990314769975786, |
| "grad_norm": 4.4511590003967285, |
| "learning_rate": 4.238013385221142e-05, |
| "loss": 0.1169, |
| "num_input_tokens_seen": 1119480, |
| "step": 2725 |
| }, |
| { |
| "epoch": 3.305084745762712, |
| "grad_norm": 0.2371293008327484, |
| "learning_rate": 4.2342124071348744e-05, |
| "loss": 0.0296, |
| "num_input_tokens_seen": 1121496, |
| "step": 2730 |
| }, |
| { |
| "epoch": 3.3111380145278453, |
| "grad_norm": 2.90073561668396, |
| "learning_rate": 4.230403686271309e-05, |
| "loss": 0.0977, |
| "num_input_tokens_seen": 1123480, |
| "step": 2735 |
| }, |
| { |
| "epoch": 3.317191283292978, |
| "grad_norm": 6.4930500984191895, |
| "learning_rate": 4.2265872396353314e-05, |
| "loss": 0.2057, |
| "num_input_tokens_seen": 1125528, |
| "step": 2740 |
| }, |
| { |
| "epoch": 3.3232445520581115, |
| "grad_norm": 2.2125489711761475, |
| "learning_rate": 4.2227630842663136e-05, |
| "loss": 0.0457, |
| "num_input_tokens_seen": 1127512, |
| "step": 2745 |
| }, |
| { |
| "epoch": 3.3292978208232444, |
| "grad_norm": 0.3942786455154419, |
| "learning_rate": 4.21893123723805e-05, |
| "loss": 0.0164, |
| "num_input_tokens_seen": 1129592, |
| "step": 2750 |
| }, |
| { |
| "epoch": 3.335351089588378, |
| "grad_norm": 6.583146095275879, |
| "learning_rate": 4.2150917156586735e-05, |
| "loss": 0.1122, |
| "num_input_tokens_seen": 1131576, |
| "step": 2755 |
| }, |
| { |
| "epoch": 3.341404358353511, |
| "grad_norm": 1.0589375495910645, |
| "learning_rate": 4.211244536670584e-05, |
| "loss": 0.0896, |
| "num_input_tokens_seen": 1133784, |
| "step": 2760 |
| }, |
| { |
| "epoch": 3.347457627118644, |
| "grad_norm": 3.002046585083008, |
| "learning_rate": 4.207389717450368e-05, |
| "loss": 0.2762, |
| "num_input_tokens_seen": 1135800, |
| "step": 2765 |
| }, |
| { |
| "epoch": 3.3535108958837774, |
| "grad_norm": 4.337278366088867, |
| "learning_rate": 4.203527275208723e-05, |
| "loss": 0.1217, |
| "num_input_tokens_seen": 1137784, |
| "step": 2770 |
| }, |
| { |
| "epoch": 3.3595641646489103, |
| "grad_norm": 1.5810871124267578, |
| "learning_rate": 4.199657227190384e-05, |
| "loss": 0.1831, |
| "num_input_tokens_seen": 1139896, |
| "step": 2775 |
| }, |
| { |
| "epoch": 3.3656174334140436, |
| "grad_norm": 1.9263957738876343, |
| "learning_rate": 4.195779590674041e-05, |
| "loss": 0.0314, |
| "num_input_tokens_seen": 1142040, |
| "step": 2780 |
| }, |
| { |
| "epoch": 3.371670702179177, |
| "grad_norm": 3.1378190517425537, |
| "learning_rate": 4.191894382972264e-05, |
| "loss": 0.083, |
| "num_input_tokens_seen": 1144088, |
| "step": 2785 |
| }, |
| { |
| "epoch": 3.37772397094431, |
| "grad_norm": 0.04914064332842827, |
| "learning_rate": 4.188001621431429e-05, |
| "loss": 0.1129, |
| "num_input_tokens_seen": 1146232, |
| "step": 2790 |
| }, |
| { |
| "epoch": 3.383777239709443, |
| "grad_norm": 5.580847263336182, |
| "learning_rate": 4.184101323431636e-05, |
| "loss": 0.3408, |
| "num_input_tokens_seen": 1148344, |
| "step": 2795 |
| }, |
| { |
| "epoch": 3.389830508474576, |
| "grad_norm": 4.590537071228027, |
| "learning_rate": 4.180193506386634e-05, |
| "loss": 0.1085, |
| "num_input_tokens_seen": 1150360, |
| "step": 2800 |
| }, |
| { |
| "epoch": 3.3958837772397095, |
| "grad_norm": 2.900740146636963, |
| "learning_rate": 4.1762781877437406e-05, |
| "loss": 0.0514, |
| "num_input_tokens_seen": 1152376, |
| "step": 2805 |
| }, |
| { |
| "epoch": 3.401937046004843, |
| "grad_norm": 4.106755256652832, |
| "learning_rate": 4.172355384983769e-05, |
| "loss": 0.2247, |
| "num_input_tokens_seen": 1154424, |
| "step": 2810 |
| }, |
| { |
| "epoch": 3.4079903147699757, |
| "grad_norm": 4.872042179107666, |
| "learning_rate": 4.168425115620944e-05, |
| "loss": 0.1178, |
| "num_input_tokens_seen": 1156472, |
| "step": 2815 |
| }, |
| { |
| "epoch": 3.414043583535109, |
| "grad_norm": 4.917882442474365, |
| "learning_rate": 4.164487397202829e-05, |
| "loss": 0.2427, |
| "num_input_tokens_seen": 1158552, |
| "step": 2820 |
| }, |
| { |
| "epoch": 3.420096852300242, |
| "grad_norm": 4.278311729431152, |
| "learning_rate": 4.160542247310244e-05, |
| "loss": 0.1525, |
| "num_input_tokens_seen": 1160696, |
| "step": 2825 |
| }, |
| { |
| "epoch": 3.4261501210653753, |
| "grad_norm": 5.004565715789795, |
| "learning_rate": 4.156589683557189e-05, |
| "loss": 0.1883, |
| "num_input_tokens_seen": 1162808, |
| "step": 2830 |
| }, |
| { |
| "epoch": 3.4322033898305087, |
| "grad_norm": 3.080528736114502, |
| "learning_rate": 4.1526297235907635e-05, |
| "loss": 0.0894, |
| "num_input_tokens_seen": 1164728, |
| "step": 2835 |
| }, |
| { |
| "epoch": 3.4382566585956416, |
| "grad_norm": 0.4325386881828308, |
| "learning_rate": 4.148662385091091e-05, |
| "loss": 0.1208, |
| "num_input_tokens_seen": 1166808, |
| "step": 2840 |
| }, |
| { |
| "epoch": 3.444309927360775, |
| "grad_norm": 1.3167212009429932, |
| "learning_rate": 4.144687685771238e-05, |
| "loss": 0.0684, |
| "num_input_tokens_seen": 1168888, |
| "step": 2845 |
| }, |
| { |
| "epoch": 3.450363196125908, |
| "grad_norm": 2.3370537757873535, |
| "learning_rate": 4.140705643377133e-05, |
| "loss": 0.1124, |
| "num_input_tokens_seen": 1170872, |
| "step": 2850 |
| }, |
| { |
| "epoch": 3.456416464891041, |
| "grad_norm": 4.785461902618408, |
| "learning_rate": 4.1367162756874925e-05, |
| "loss": 0.1198, |
| "num_input_tokens_seen": 1172984, |
| "step": 2855 |
| }, |
| { |
| "epoch": 3.4624697336561745, |
| "grad_norm": 5.924464702606201, |
| "learning_rate": 4.132719600513734e-05, |
| "loss": 0.092, |
| "num_input_tokens_seen": 1175032, |
| "step": 2860 |
| }, |
| { |
| "epoch": 3.4685230024213074, |
| "grad_norm": 3.9813077449798584, |
| "learning_rate": 4.128715635699905e-05, |
| "loss": 0.1867, |
| "num_input_tokens_seen": 1177240, |
| "step": 2865 |
| }, |
| { |
| "epoch": 3.4745762711864407, |
| "grad_norm": 0.31910327076911926, |
| "learning_rate": 4.124704399122597e-05, |
| "loss": 0.1416, |
| "num_input_tokens_seen": 1179192, |
| "step": 2870 |
| }, |
| { |
| "epoch": 3.4806295399515736, |
| "grad_norm": 0.5019274950027466, |
| "learning_rate": 4.120685908690869e-05, |
| "loss": 0.1544, |
| "num_input_tokens_seen": 1181112, |
| "step": 2875 |
| }, |
| { |
| "epoch": 3.486682808716707, |
| "grad_norm": 6.107857704162598, |
| "learning_rate": 4.1166601823461656e-05, |
| "loss": 0.1366, |
| "num_input_tokens_seen": 1183128, |
| "step": 2880 |
| }, |
| { |
| "epoch": 3.4927360774818403, |
| "grad_norm": 2.1856138706207275, |
| "learning_rate": 4.112627238062239e-05, |
| "loss": 0.0745, |
| "num_input_tokens_seen": 1185240, |
| "step": 2885 |
| }, |
| { |
| "epoch": 3.4987893462469732, |
| "grad_norm": 0.27053192257881165, |
| "learning_rate": 4.1085870938450656e-05, |
| "loss": 0.1314, |
| "num_input_tokens_seen": 1187320, |
| "step": 2890 |
| }, |
| { |
| "epoch": 3.5, |
| "eval_loss": 0.137603759765625, |
| "eval_runtime": 4.5756, |
| "eval_samples_per_second": 80.208, |
| "eval_steps_per_second": 20.107, |
| "num_input_tokens_seen": 1187704, |
| "step": 2891 |
| }, |
| { |
| "epoch": 3.5048426150121066, |
| "grad_norm": 1.7873985767364502, |
| "learning_rate": 4.1045397677327684e-05, |
| "loss": 0.0986, |
| "num_input_tokens_seen": 1189400, |
| "step": 2895 |
| }, |
| { |
| "epoch": 3.5108958837772395, |
| "grad_norm": 1.725449562072754, |
| "learning_rate": 4.1004852777955364e-05, |
| "loss": 0.1157, |
| "num_input_tokens_seen": 1191384, |
| "step": 2900 |
| }, |
| { |
| "epoch": 3.516949152542373, |
| "grad_norm": 4.23082160949707, |
| "learning_rate": 4.096423642135543e-05, |
| "loss": 0.0537, |
| "num_input_tokens_seen": 1193368, |
| "step": 2905 |
| }, |
| { |
| "epoch": 3.523002421307506, |
| "grad_norm": 0.3017522692680359, |
| "learning_rate": 4.0923548788868625e-05, |
| "loss": 0.0296, |
| "num_input_tokens_seen": 1195512, |
| "step": 2910 |
| }, |
| { |
| "epoch": 3.529055690072639, |
| "grad_norm": 0.3969971239566803, |
| "learning_rate": 4.0882790062153957e-05, |
| "loss": 0.1352, |
| "num_input_tokens_seen": 1197560, |
| "step": 2915 |
| }, |
| { |
| "epoch": 3.5351089588377724, |
| "grad_norm": 0.6447391510009766, |
| "learning_rate": 4.084196042318783e-05, |
| "loss": 0.063, |
| "num_input_tokens_seen": 1199768, |
| "step": 2920 |
| }, |
| { |
| "epoch": 3.5411622276029053, |
| "grad_norm": 5.6643877029418945, |
| "learning_rate": 4.080106005426326e-05, |
| "loss": 0.2772, |
| "num_input_tokens_seen": 1201848, |
| "step": 2925 |
| }, |
| { |
| "epoch": 3.5472154963680387, |
| "grad_norm": 4.083348751068115, |
| "learning_rate": 4.076008913798903e-05, |
| "loss": 0.1208, |
| "num_input_tokens_seen": 1203896, |
| "step": 2930 |
| }, |
| { |
| "epoch": 3.553268765133172, |
| "grad_norm": 3.979558229446411, |
| "learning_rate": 4.071904785728894e-05, |
| "loss": 0.1456, |
| "num_input_tokens_seen": 1205880, |
| "step": 2935 |
| }, |
| { |
| "epoch": 3.559322033898305, |
| "grad_norm": 8.00076961517334, |
| "learning_rate": 4.0677936395400906e-05, |
| "loss": 0.1744, |
| "num_input_tokens_seen": 1207896, |
| "step": 2940 |
| }, |
| { |
| "epoch": 3.5653753026634383, |
| "grad_norm": 3.3506362438201904, |
| "learning_rate": 4.063675493587621e-05, |
| "loss": 0.199, |
| "num_input_tokens_seen": 1210008, |
| "step": 2945 |
| }, |
| { |
| "epoch": 3.571428571428571, |
| "grad_norm": 6.1021881103515625, |
| "learning_rate": 4.059550366257864e-05, |
| "loss": 0.0986, |
| "num_input_tokens_seen": 1212024, |
| "step": 2950 |
| }, |
| { |
| "epoch": 3.5774818401937045, |
| "grad_norm": 0.7336778044700623, |
| "learning_rate": 4.055418275968368e-05, |
| "loss": 0.0768, |
| "num_input_tokens_seen": 1214040, |
| "step": 2955 |
| }, |
| { |
| "epoch": 3.583535108958838, |
| "grad_norm": 2.5828888416290283, |
| "learning_rate": 4.0512792411677705e-05, |
| "loss": 0.0929, |
| "num_input_tokens_seen": 1216088, |
| "step": 2960 |
| }, |
| { |
| "epoch": 3.589588377723971, |
| "grad_norm": 3.6418821811676025, |
| "learning_rate": 4.047133280335713e-05, |
| "loss": 0.1131, |
| "num_input_tokens_seen": 1218136, |
| "step": 2965 |
| }, |
| { |
| "epoch": 3.595641646489104, |
| "grad_norm": 0.2827266454696655, |
| "learning_rate": 4.042980411982762e-05, |
| "loss": 0.092, |
| "num_input_tokens_seen": 1220248, |
| "step": 2970 |
| }, |
| { |
| "epoch": 3.601694915254237, |
| "grad_norm": 4.693321228027344, |
| "learning_rate": 4.0388206546503215e-05, |
| "loss": 0.2923, |
| "num_input_tokens_seen": 1222360, |
| "step": 2975 |
| }, |
| { |
| "epoch": 3.6077481840193704, |
| "grad_norm": 2.132143020629883, |
| "learning_rate": 4.0346540269105546e-05, |
| "loss": 0.1654, |
| "num_input_tokens_seen": 1224568, |
| "step": 2980 |
| }, |
| { |
| "epoch": 3.6138014527845037, |
| "grad_norm": 2.10683274269104, |
| "learning_rate": 4.030480547366297e-05, |
| "loss": 0.1568, |
| "num_input_tokens_seen": 1226648, |
| "step": 2985 |
| }, |
| { |
| "epoch": 3.619854721549637, |
| "grad_norm": 3.6658689975738525, |
| "learning_rate": 4.026300234650979e-05, |
| "loss": 0.1603, |
| "num_input_tokens_seen": 1228600, |
| "step": 2990 |
| }, |
| { |
| "epoch": 3.62590799031477, |
| "grad_norm": 2.4331119060516357, |
| "learning_rate": 4.022113107428536e-05, |
| "loss": 0.0855, |
| "num_input_tokens_seen": 1230616, |
| "step": 2995 |
| }, |
| { |
| "epoch": 3.6319612590799033, |
| "grad_norm": 3.701345443725586, |
| "learning_rate": 4.0179191843933286e-05, |
| "loss": 0.1095, |
| "num_input_tokens_seen": 1232632, |
| "step": 3000 |
| }, |
| { |
| "epoch": 3.638014527845036, |
| "grad_norm": 1.2965837717056274, |
| "learning_rate": 4.013718484270061e-05, |
| "loss": 0.0896, |
| "num_input_tokens_seen": 1234552, |
| "step": 3005 |
| }, |
| { |
| "epoch": 3.6440677966101696, |
| "grad_norm": 1.7559748888015747, |
| "learning_rate": 4.009511025813694e-05, |
| "loss": 0.0422, |
| "num_input_tokens_seen": 1236728, |
| "step": 3010 |
| }, |
| { |
| "epoch": 3.650121065375303, |
| "grad_norm": 3.9477643966674805, |
| "learning_rate": 4.005296827809362e-05, |
| "loss": 0.2595, |
| "num_input_tokens_seen": 1238776, |
| "step": 3015 |
| }, |
| { |
| "epoch": 3.656174334140436, |
| "grad_norm": 1.9731038808822632, |
| "learning_rate": 4.001075909072289e-05, |
| "loss": 0.1161, |
| "num_input_tokens_seen": 1240856, |
| "step": 3020 |
| }, |
| { |
| "epoch": 3.662227602905569, |
| "grad_norm": 0.5970947742462158, |
| "learning_rate": 3.9968482884477075e-05, |
| "loss": 0.0828, |
| "num_input_tokens_seen": 1242936, |
| "step": 3025 |
| }, |
| { |
| "epoch": 3.668280871670702, |
| "grad_norm": 2.401581048965454, |
| "learning_rate": 3.992613984810771e-05, |
| "loss": 0.1905, |
| "num_input_tokens_seen": 1245080, |
| "step": 3030 |
| }, |
| { |
| "epoch": 3.6743341404358354, |
| "grad_norm": 1.213310956954956, |
| "learning_rate": 3.988373017066469e-05, |
| "loss": 0.0652, |
| "num_input_tokens_seen": 1247192, |
| "step": 3035 |
| }, |
| { |
| "epoch": 3.6803874092009687, |
| "grad_norm": 3.343557119369507, |
| "learning_rate": 3.984125404149548e-05, |
| "loss": 0.0579, |
| "num_input_tokens_seen": 1249240, |
| "step": 3040 |
| }, |
| { |
| "epoch": 3.6864406779661016, |
| "grad_norm": 0.24004943668842316, |
| "learning_rate": 3.9798711650244194e-05, |
| "loss": 0.1836, |
| "num_input_tokens_seen": 1251320, |
| "step": 3045 |
| }, |
| { |
| "epoch": 3.692493946731235, |
| "grad_norm": 6.831732749938965, |
| "learning_rate": 3.9756103186850825e-05, |
| "loss": 0.2021, |
| "num_input_tokens_seen": 1253336, |
| "step": 3050 |
| }, |
| { |
| "epoch": 3.698547215496368, |
| "grad_norm": 3.7986762523651123, |
| "learning_rate": 3.971342884155033e-05, |
| "loss": 0.1354, |
| "num_input_tokens_seen": 1255352, |
| "step": 3055 |
| }, |
| { |
| "epoch": 3.7046004842615012, |
| "grad_norm": 0.4976424276828766, |
| "learning_rate": 3.9670688804871815e-05, |
| "loss": 0.0733, |
| "num_input_tokens_seen": 1257272, |
| "step": 3060 |
| }, |
| { |
| "epoch": 3.7106537530266346, |
| "grad_norm": 1.6615444421768188, |
| "learning_rate": 3.96278832676377e-05, |
| "loss": 0.1375, |
| "num_input_tokens_seen": 1259416, |
| "step": 3065 |
| }, |
| { |
| "epoch": 3.7167070217917675, |
| "grad_norm": 0.4979148209095001, |
| "learning_rate": 3.958501242096283e-05, |
| "loss": 0.1439, |
| "num_input_tokens_seen": 1261496, |
| "step": 3070 |
| }, |
| { |
| "epoch": 3.722760290556901, |
| "grad_norm": 1.3393867015838623, |
| "learning_rate": 3.954207645625365e-05, |
| "loss": 0.0512, |
| "num_input_tokens_seen": 1263480, |
| "step": 3075 |
| }, |
| { |
| "epoch": 3.7288135593220337, |
| "grad_norm": 1.7195483446121216, |
| "learning_rate": 3.949907556520731e-05, |
| "loss": 0.1391, |
| "num_input_tokens_seen": 1265528, |
| "step": 3080 |
| }, |
| { |
| "epoch": 3.734866828087167, |
| "grad_norm": 0.9343760013580322, |
| "learning_rate": 3.9456009939810886e-05, |
| "loss": 0.0898, |
| "num_input_tokens_seen": 1267512, |
| "step": 3085 |
| }, |
| { |
| "epoch": 3.7409200968523004, |
| "grad_norm": 4.527099609375, |
| "learning_rate": 3.941287977234043e-05, |
| "loss": 0.1332, |
| "num_input_tokens_seen": 1269560, |
| "step": 3090 |
| }, |
| { |
| "epoch": 3.7469733656174333, |
| "grad_norm": 2.255335807800293, |
| "learning_rate": 3.9369685255360175e-05, |
| "loss": 0.0676, |
| "num_input_tokens_seen": 1271640, |
| "step": 3095 |
| }, |
| { |
| "epoch": 3.7530266343825667, |
| "grad_norm": 1.6302518844604492, |
| "learning_rate": 3.9326426581721663e-05, |
| "loss": 0.0341, |
| "num_input_tokens_seen": 1273688, |
| "step": 3100 |
| }, |
| { |
| "epoch": 3.7590799031476996, |
| "grad_norm": 0.33657604455947876, |
| "learning_rate": 3.9283103944562874e-05, |
| "loss": 0.0306, |
| "num_input_tokens_seen": 1275768, |
| "step": 3105 |
| }, |
| { |
| "epoch": 3.765133171912833, |
| "grad_norm": 0.6542962193489075, |
| "learning_rate": 3.923971753730735e-05, |
| "loss": 0.0519, |
| "num_input_tokens_seen": 1277752, |
| "step": 3110 |
| }, |
| { |
| "epoch": 3.7711864406779663, |
| "grad_norm": 2.5565290451049805, |
| "learning_rate": 3.919626755366338e-05, |
| "loss": 0.1122, |
| "num_input_tokens_seen": 1279864, |
| "step": 3115 |
| }, |
| { |
| "epoch": 3.777239709443099, |
| "grad_norm": 0.5348601937294006, |
| "learning_rate": 3.9152754187623086e-05, |
| "loss": 0.1073, |
| "num_input_tokens_seen": 1281880, |
| "step": 3120 |
| }, |
| { |
| "epoch": 3.7832929782082325, |
| "grad_norm": 3.66865611076355, |
| "learning_rate": 3.910917763346156e-05, |
| "loss": 0.0425, |
| "num_input_tokens_seen": 1283928, |
| "step": 3125 |
| }, |
| { |
| "epoch": 3.7893462469733654, |
| "grad_norm": 2.6302590370178223, |
| "learning_rate": 3.906553808573604e-05, |
| "loss": 0.2901, |
| "num_input_tokens_seen": 1285944, |
| "step": 3130 |
| }, |
| { |
| "epoch": 3.7953995157384988, |
| "grad_norm": 2.9969611167907715, |
| "learning_rate": 3.9021835739285e-05, |
| "loss": 0.1615, |
| "num_input_tokens_seen": 1287928, |
| "step": 3135 |
| }, |
| { |
| "epoch": 3.801452784503632, |
| "grad_norm": 4.440647602081299, |
| "learning_rate": 3.897807078922728e-05, |
| "loss": 0.1891, |
| "num_input_tokens_seen": 1290008, |
| "step": 3140 |
| }, |
| { |
| "epoch": 3.807506053268765, |
| "grad_norm": 6.937892913818359, |
| "learning_rate": 3.8934243430961265e-05, |
| "loss": 0.0881, |
| "num_input_tokens_seen": 1292120, |
| "step": 3145 |
| }, |
| { |
| "epoch": 3.8135593220338984, |
| "grad_norm": 2.623624086380005, |
| "learning_rate": 3.889035386016393e-05, |
| "loss": 0.1615, |
| "num_input_tokens_seen": 1294040, |
| "step": 3150 |
| }, |
| { |
| "epoch": 3.8196125907990313, |
| "grad_norm": 5.344344615936279, |
| "learning_rate": 3.8846402272790044e-05, |
| "loss": 0.1284, |
| "num_input_tokens_seen": 1296024, |
| "step": 3155 |
| }, |
| { |
| "epoch": 3.8256658595641646, |
| "grad_norm": 3.985133409500122, |
| "learning_rate": 3.8802388865071246e-05, |
| "loss": 0.1705, |
| "num_input_tokens_seen": 1298104, |
| "step": 3160 |
| }, |
| { |
| "epoch": 3.831719128329298, |
| "grad_norm": 1.2340222597122192, |
| "learning_rate": 3.875831383351519e-05, |
| "loss": 0.0358, |
| "num_input_tokens_seen": 1300248, |
| "step": 3165 |
| }, |
| { |
| "epoch": 3.837772397094431, |
| "grad_norm": 2.6467792987823486, |
| "learning_rate": 3.8714177374904683e-05, |
| "loss": 0.1947, |
| "num_input_tokens_seen": 1302104, |
| "step": 3170 |
| }, |
| { |
| "epoch": 3.843825665859564, |
| "grad_norm": 0.4315508306026459, |
| "learning_rate": 3.866997968629674e-05, |
| "loss": 0.0413, |
| "num_input_tokens_seen": 1304056, |
| "step": 3175 |
| }, |
| { |
| "epoch": 3.849878934624697, |
| "grad_norm": 3.8331992626190186, |
| "learning_rate": 3.86257209650218e-05, |
| "loss": 0.0932, |
| "num_input_tokens_seen": 1306104, |
| "step": 3180 |
| }, |
| { |
| "epoch": 3.8559322033898304, |
| "grad_norm": 1.633231282234192, |
| "learning_rate": 3.858140140868276e-05, |
| "loss": 0.1438, |
| "num_input_tokens_seen": 1308056, |
| "step": 3185 |
| }, |
| { |
| "epoch": 3.861985472154964, |
| "grad_norm": 3.581052780151367, |
| "learning_rate": 3.853702121515416e-05, |
| "loss": 0.1224, |
| "num_input_tokens_seen": 1310104, |
| "step": 3190 |
| }, |
| { |
| "epoch": 3.8680387409200967, |
| "grad_norm": 3.2716169357299805, |
| "learning_rate": 3.849258058258124e-05, |
| "loss": 0.0858, |
| "num_input_tokens_seen": 1312152, |
| "step": 3195 |
| }, |
| { |
| "epoch": 3.87409200968523, |
| "grad_norm": 6.2645368576049805, |
| "learning_rate": 3.84480797093791e-05, |
| "loss": 0.0981, |
| "num_input_tokens_seen": 1314328, |
| "step": 3200 |
| }, |
| { |
| "epoch": 3.880145278450363, |
| "grad_norm": 3.6259467601776123, |
| "learning_rate": 3.8403518794231795e-05, |
| "loss": 0.0788, |
| "num_input_tokens_seen": 1316344, |
| "step": 3205 |
| }, |
| { |
| "epoch": 3.8861985472154963, |
| "grad_norm": 2.101606845855713, |
| "learning_rate": 3.835889803609145e-05, |
| "loss": 0.0663, |
| "num_input_tokens_seen": 1318360, |
| "step": 3210 |
| }, |
| { |
| "epoch": 3.8922518159806296, |
| "grad_norm": 0.37834468483924866, |
| "learning_rate": 3.8314217634177376e-05, |
| "loss": 0.0548, |
| "num_input_tokens_seen": 1320376, |
| "step": 3215 |
| }, |
| { |
| "epoch": 3.898305084745763, |
| "grad_norm": 0.7180870771408081, |
| "learning_rate": 3.826947778797516e-05, |
| "loss": 0.0425, |
| "num_input_tokens_seen": 1322616, |
| "step": 3220 |
| }, |
| { |
| "epoch": 3.904358353510896, |
| "grad_norm": 1.2626093626022339, |
| "learning_rate": 3.822467869723581e-05, |
| "loss": 0.2914, |
| "num_input_tokens_seen": 1324664, |
| "step": 3225 |
| }, |
| { |
| "epoch": 3.910411622276029, |
| "grad_norm": 5.424513339996338, |
| "learning_rate": 3.8179820561974835e-05, |
| "loss": 0.1202, |
| "num_input_tokens_seen": 1326616, |
| "step": 3230 |
| }, |
| { |
| "epoch": 3.916464891041162, |
| "grad_norm": 3.26811146736145, |
| "learning_rate": 3.813490358247137e-05, |
| "loss": 0.0692, |
| "num_input_tokens_seen": 1328760, |
| "step": 3235 |
| }, |
| { |
| "epoch": 3.9225181598062955, |
| "grad_norm": 2.555222511291504, |
| "learning_rate": 3.8089927959267255e-05, |
| "loss": 0.1256, |
| "num_input_tokens_seen": 1330968, |
| "step": 3240 |
| }, |
| { |
| "epoch": 3.928571428571429, |
| "grad_norm": 3.6134443283081055, |
| "learning_rate": 3.8044893893166203e-05, |
| "loss": 0.1744, |
| "num_input_tokens_seen": 1332952, |
| "step": 3245 |
| }, |
| { |
| "epoch": 3.9346246973365617, |
| "grad_norm": 3.7331314086914062, |
| "learning_rate": 3.799980158523279e-05, |
| "loss": 0.1684, |
| "num_input_tokens_seen": 1335064, |
| "step": 3250 |
| }, |
| { |
| "epoch": 3.940677966101695, |
| "grad_norm": 5.901867389678955, |
| "learning_rate": 3.795465123679167e-05, |
| "loss": 0.1036, |
| "num_input_tokens_seen": 1337080, |
| "step": 3255 |
| }, |
| { |
| "epoch": 3.946731234866828, |
| "grad_norm": 3.149181365966797, |
| "learning_rate": 3.790944304942664e-05, |
| "loss": 0.1296, |
| "num_input_tokens_seen": 1339096, |
| "step": 3260 |
| }, |
| { |
| "epoch": 3.9527845036319613, |
| "grad_norm": 0.9098186492919922, |
| "learning_rate": 3.7864177224979696e-05, |
| "loss": 0.0825, |
| "num_input_tokens_seen": 1341048, |
| "step": 3265 |
| }, |
| { |
| "epoch": 3.9588377723970947, |
| "grad_norm": 5.158130168914795, |
| "learning_rate": 3.781885396555019e-05, |
| "loss": 0.1029, |
| "num_input_tokens_seen": 1343224, |
| "step": 3270 |
| }, |
| { |
| "epoch": 3.9648910411622276, |
| "grad_norm": 0.13243332505226135, |
| "learning_rate": 3.777347347349392e-05, |
| "loss": 0.1416, |
| "num_input_tokens_seen": 1345272, |
| "step": 3275 |
| }, |
| { |
| "epoch": 3.970944309927361, |
| "grad_norm": 9.198348045349121, |
| "learning_rate": 3.7728035951422166e-05, |
| "loss": 0.2062, |
| "num_input_tokens_seen": 1347416, |
| "step": 3280 |
| }, |
| { |
| "epoch": 3.976997578692494, |
| "grad_norm": 0.32454535365104675, |
| "learning_rate": 3.7682541602200875e-05, |
| "loss": 0.0542, |
| "num_input_tokens_seen": 1349464, |
| "step": 3285 |
| }, |
| { |
| "epoch": 3.983050847457627, |
| "grad_norm": 0.24111558496952057, |
| "learning_rate": 3.76369906289497e-05, |
| "loss": 0.1584, |
| "num_input_tokens_seen": 1351352, |
| "step": 3290 |
| }, |
| { |
| "epoch": 3.9891041162227605, |
| "grad_norm": 1.5734061002731323, |
| "learning_rate": 3.7591383235041086e-05, |
| "loss": 0.0471, |
| "num_input_tokens_seen": 1353368, |
| "step": 3295 |
| }, |
| { |
| "epoch": 3.9951573849878934, |
| "grad_norm": 0.10585124790668488, |
| "learning_rate": 3.75457196240994e-05, |
| "loss": 0.1547, |
| "num_input_tokens_seen": 1355416, |
| "step": 3300 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_loss": 0.13813835382461548, |
| "eval_runtime": 4.5782, |
| "eval_samples_per_second": 80.162, |
| "eval_steps_per_second": 20.095, |
| "num_input_tokens_seen": 1356744, |
| "step": 3304 |
| }, |
| { |
| "epoch": 4.001210653753026, |
| "grad_norm": 0.9487738609313965, |
| "learning_rate": 3.7500000000000003e-05, |
| "loss": 0.1349, |
| "num_input_tokens_seen": 1357192, |
| "step": 3305 |
| }, |
| { |
| "epoch": 4.00726392251816, |
| "grad_norm": 3.7472715377807617, |
| "learning_rate": 3.7454224566868327e-05, |
| "loss": 0.1112, |
| "num_input_tokens_seen": 1359272, |
| "step": 3310 |
| }, |
| { |
| "epoch": 4.013317191283293, |
| "grad_norm": 4.9403886795043945, |
| "learning_rate": 3.7408393529078985e-05, |
| "loss": 0.1103, |
| "num_input_tokens_seen": 1361480, |
| "step": 3315 |
| }, |
| { |
| "epoch": 4.019370460048426, |
| "grad_norm": 0.8156682848930359, |
| "learning_rate": 3.7362507091254836e-05, |
| "loss": 0.1043, |
| "num_input_tokens_seen": 1363560, |
| "step": 3320 |
| }, |
| { |
| "epoch": 4.02542372881356, |
| "grad_norm": 4.155811786651611, |
| "learning_rate": 3.7316565458266114e-05, |
| "loss": 0.241, |
| "num_input_tokens_seen": 1365640, |
| "step": 3325 |
| }, |
| { |
| "epoch": 4.031476997578692, |
| "grad_norm": 1.49620521068573, |
| "learning_rate": 3.727056883522945e-05, |
| "loss": 0.0996, |
| "num_input_tokens_seen": 1367720, |
| "step": 3330 |
| }, |
| { |
| "epoch": 4.0375302663438255, |
| "grad_norm": 4.452794551849365, |
| "learning_rate": 3.722451742750701e-05, |
| "loss": 0.1678, |
| "num_input_tokens_seen": 1369704, |
| "step": 3335 |
| }, |
| { |
| "epoch": 4.043583535108959, |
| "grad_norm": 4.364172458648682, |
| "learning_rate": 3.717841144070556e-05, |
| "loss": 0.1008, |
| "num_input_tokens_seen": 1371816, |
| "step": 3340 |
| }, |
| { |
| "epoch": 4.049636803874092, |
| "grad_norm": 0.06378893554210663, |
| "learning_rate": 3.713225108067553e-05, |
| "loss": 0.0347, |
| "num_input_tokens_seen": 1373800, |
| "step": 3345 |
| }, |
| { |
| "epoch": 4.0556900726392255, |
| "grad_norm": 0.38104724884033203, |
| "learning_rate": 3.708603655351012e-05, |
| "loss": 0.0651, |
| "num_input_tokens_seen": 1375752, |
| "step": 3350 |
| }, |
| { |
| "epoch": 4.061743341404358, |
| "grad_norm": 4.189276695251465, |
| "learning_rate": 3.7039768065544395e-05, |
| "loss": 0.1629, |
| "num_input_tokens_seen": 1377896, |
| "step": 3355 |
| }, |
| { |
| "epoch": 4.067796610169491, |
| "grad_norm": 1.064452052116394, |
| "learning_rate": 3.69934458233543e-05, |
| "loss": 0.0949, |
| "num_input_tokens_seen": 1379912, |
| "step": 3360 |
| }, |
| { |
| "epoch": 4.073849878934625, |
| "grad_norm": 2.7440671920776367, |
| "learning_rate": 3.694707003375579e-05, |
| "loss": 0.1777, |
| "num_input_tokens_seen": 1381960, |
| "step": 3365 |
| }, |
| { |
| "epoch": 4.079903147699758, |
| "grad_norm": 3.948115825653076, |
| "learning_rate": 3.690064090380392e-05, |
| "loss": 0.1963, |
| "num_input_tokens_seen": 1384072, |
| "step": 3370 |
| }, |
| { |
| "epoch": 4.085956416464891, |
| "grad_norm": 2.6125643253326416, |
| "learning_rate": 3.685415864079185e-05, |
| "loss": 0.1138, |
| "num_input_tokens_seen": 1386152, |
| "step": 3375 |
| }, |
| { |
| "epoch": 4.092009685230024, |
| "grad_norm": 2.7647571563720703, |
| "learning_rate": 3.680762345225001e-05, |
| "loss": 0.0476, |
| "num_input_tokens_seen": 1388168, |
| "step": 3380 |
| }, |
| { |
| "epoch": 4.098062953995157, |
| "grad_norm": 2.3222060203552246, |
| "learning_rate": 3.676103554594511e-05, |
| "loss": 0.0609, |
| "num_input_tokens_seen": 1390152, |
| "step": 3385 |
| }, |
| { |
| "epoch": 4.1041162227602905, |
| "grad_norm": 6.68032693862915, |
| "learning_rate": 3.671439512987921e-05, |
| "loss": 0.1748, |
| "num_input_tokens_seen": 1392168, |
| "step": 3390 |
| }, |
| { |
| "epoch": 4.110169491525424, |
| "grad_norm": 2.3445775508880615, |
| "learning_rate": 3.666770241228883e-05, |
| "loss": 0.07, |
| "num_input_tokens_seen": 1394376, |
| "step": 3395 |
| }, |
| { |
| "epoch": 4.116222760290557, |
| "grad_norm": 0.17334812879562378, |
| "learning_rate": 3.6620957601644016e-05, |
| "loss": 0.0244, |
| "num_input_tokens_seen": 1396520, |
| "step": 3400 |
| }, |
| { |
| "epoch": 4.12227602905569, |
| "grad_norm": 0.5321148037910461, |
| "learning_rate": 3.657416090664737e-05, |
| "loss": 0.0809, |
| "num_input_tokens_seen": 1398600, |
| "step": 3405 |
| }, |
| { |
| "epoch": 4.128329297820823, |
| "grad_norm": 1.0061872005462646, |
| "learning_rate": 3.652731253623315e-05, |
| "loss": 0.1107, |
| "num_input_tokens_seen": 1400584, |
| "step": 3410 |
| }, |
| { |
| "epoch": 4.134382566585956, |
| "grad_norm": 0.31218233704566956, |
| "learning_rate": 3.648041269956634e-05, |
| "loss": 0.0652, |
| "num_input_tokens_seen": 1402760, |
| "step": 3415 |
| }, |
| { |
| "epoch": 4.14043583535109, |
| "grad_norm": 2.9069929122924805, |
| "learning_rate": 3.6433461606041695e-05, |
| "loss": 0.1431, |
| "num_input_tokens_seen": 1404936, |
| "step": 3420 |
| }, |
| { |
| "epoch": 4.146489104116223, |
| "grad_norm": 5.1606926918029785, |
| "learning_rate": 3.6386459465282824e-05, |
| "loss": 0.0984, |
| "num_input_tokens_seen": 1406920, |
| "step": 3425 |
| }, |
| { |
| "epoch": 4.1525423728813555, |
| "grad_norm": 5.275994777679443, |
| "learning_rate": 3.6339406487141255e-05, |
| "loss": 0.0691, |
| "num_input_tokens_seen": 1408840, |
| "step": 3430 |
| }, |
| { |
| "epoch": 4.158595641646489, |
| "grad_norm": 2.359971284866333, |
| "learning_rate": 3.6292302881695464e-05, |
| "loss": 0.1333, |
| "num_input_tokens_seen": 1410696, |
| "step": 3435 |
| }, |
| { |
| "epoch": 4.164648910411622, |
| "grad_norm": 1.0342682600021362, |
| "learning_rate": 3.6245148859249996e-05, |
| "loss": 0.1415, |
| "num_input_tokens_seen": 1412680, |
| "step": 3440 |
| }, |
| { |
| "epoch": 4.170702179176756, |
| "grad_norm": 1.001820683479309, |
| "learning_rate": 3.619794463033447e-05, |
| "loss": 0.0941, |
| "num_input_tokens_seen": 1414728, |
| "step": 3445 |
| }, |
| { |
| "epoch": 4.176755447941889, |
| "grad_norm": 0.8069421052932739, |
| "learning_rate": 3.6150690405702685e-05, |
| "loss": 0.0293, |
| "num_input_tokens_seen": 1416712, |
| "step": 3450 |
| }, |
| { |
| "epoch": 4.182808716707021, |
| "grad_norm": 4.724492073059082, |
| "learning_rate": 3.6103386396331635e-05, |
| "loss": 0.0611, |
| "num_input_tokens_seen": 1418952, |
| "step": 3455 |
| }, |
| { |
| "epoch": 4.188861985472155, |
| "grad_norm": 6.935494422912598, |
| "learning_rate": 3.605603281342061e-05, |
| "loss": 0.1149, |
| "num_input_tokens_seen": 1421032, |
| "step": 3460 |
| }, |
| { |
| "epoch": 4.194915254237288, |
| "grad_norm": 0.4098648130893707, |
| "learning_rate": 3.6008629868390204e-05, |
| "loss": 0.1266, |
| "num_input_tokens_seen": 1423048, |
| "step": 3465 |
| }, |
| { |
| "epoch": 4.200968523002421, |
| "grad_norm": 5.3340020179748535, |
| "learning_rate": 3.5961177772881434e-05, |
| "loss": 0.2302, |
| "num_input_tokens_seen": 1425192, |
| "step": 3470 |
| }, |
| { |
| "epoch": 4.207021791767555, |
| "grad_norm": 0.06073416396975517, |
| "learning_rate": 3.591367673875472e-05, |
| "loss": 0.1065, |
| "num_input_tokens_seen": 1427304, |
| "step": 3475 |
| }, |
| { |
| "epoch": 4.213075060532688, |
| "grad_norm": 3.5133183002471924, |
| "learning_rate": 3.5866126978089025e-05, |
| "loss": 0.2221, |
| "num_input_tokens_seen": 1429288, |
| "step": 3480 |
| }, |
| { |
| "epoch": 4.219128329297821, |
| "grad_norm": 6.023957252502441, |
| "learning_rate": 3.5818528703180826e-05, |
| "loss": 0.0864, |
| "num_input_tokens_seen": 1431400, |
| "step": 3485 |
| }, |
| { |
| "epoch": 4.225181598062954, |
| "grad_norm": 3.456350803375244, |
| "learning_rate": 3.577088212654322e-05, |
| "loss": 0.137, |
| "num_input_tokens_seen": 1433576, |
| "step": 3490 |
| }, |
| { |
| "epoch": 4.231234866828087, |
| "grad_norm": 1.2072936296463013, |
| "learning_rate": 3.572318746090496e-05, |
| "loss": 0.0733, |
| "num_input_tokens_seen": 1435560, |
| "step": 3495 |
| }, |
| { |
| "epoch": 4.237288135593221, |
| "grad_norm": 6.404455184936523, |
| "learning_rate": 3.5675444919209486e-05, |
| "loss": 0.1385, |
| "num_input_tokens_seen": 1437672, |
| "step": 3500 |
| }, |
| { |
| "epoch": 4.243341404358354, |
| "grad_norm": 4.31003999710083, |
| "learning_rate": 3.5627654714614e-05, |
| "loss": 0.1378, |
| "num_input_tokens_seen": 1439656, |
| "step": 3505 |
| }, |
| { |
| "epoch": 4.249394673123486, |
| "grad_norm": 1.0932585000991821, |
| "learning_rate": 3.557981706048852e-05, |
| "loss": 0.0267, |
| "num_input_tokens_seen": 1441608, |
| "step": 3510 |
| }, |
| { |
| "epoch": 4.25544794188862, |
| "grad_norm": 3.007089138031006, |
| "learning_rate": 3.5531932170414896e-05, |
| "loss": 0.0983, |
| "num_input_tokens_seen": 1443624, |
| "step": 3515 |
| }, |
| { |
| "epoch": 4.261501210653753, |
| "grad_norm": 0.3836453855037689, |
| "learning_rate": 3.5484000258185876e-05, |
| "loss": 0.0431, |
| "num_input_tokens_seen": 1445736, |
| "step": 3520 |
| }, |
| { |
| "epoch": 4.267554479418886, |
| "grad_norm": 2.0524728298187256, |
| "learning_rate": 3.5436021537804144e-05, |
| "loss": 0.1157, |
| "num_input_tokens_seen": 1447880, |
| "step": 3525 |
| }, |
| { |
| "epoch": 4.27360774818402, |
| "grad_norm": 4.9584479331970215, |
| "learning_rate": 3.538799622348139e-05, |
| "loss": 0.2273, |
| "num_input_tokens_seen": 1449896, |
| "step": 3530 |
| }, |
| { |
| "epoch": 4.279661016949152, |
| "grad_norm": 0.3631916642189026, |
| "learning_rate": 3.5339924529637304e-05, |
| "loss": 0.0961, |
| "num_input_tokens_seen": 1451880, |
| "step": 3535 |
| }, |
| { |
| "epoch": 4.285714285714286, |
| "grad_norm": 0.1526634246110916, |
| "learning_rate": 3.529180667089868e-05, |
| "loss": 0.0849, |
| "num_input_tokens_seen": 1453992, |
| "step": 3540 |
| }, |
| { |
| "epoch": 4.291767554479419, |
| "grad_norm": 0.08341622352600098, |
| "learning_rate": 3.52436428620984e-05, |
| "loss": 0.1471, |
| "num_input_tokens_seen": 1455912, |
| "step": 3545 |
| }, |
| { |
| "epoch": 4.297820823244552, |
| "grad_norm": 1.2977865934371948, |
| "learning_rate": 3.5195433318274516e-05, |
| "loss": 0.1623, |
| "num_input_tokens_seen": 1458024, |
| "step": 3550 |
| }, |
| { |
| "epoch": 4.303874092009686, |
| "grad_norm": 0.30896905064582825, |
| "learning_rate": 3.514717825466925e-05, |
| "loss": 0.0768, |
| "num_input_tokens_seen": 1459976, |
| "step": 3555 |
| }, |
| { |
| "epoch": 4.309927360774818, |
| "grad_norm": 4.159477710723877, |
| "learning_rate": 3.509887788672809e-05, |
| "loss": 0.1655, |
| "num_input_tokens_seen": 1462120, |
| "step": 3560 |
| }, |
| { |
| "epoch": 4.315980629539951, |
| "grad_norm": 4.378042221069336, |
| "learning_rate": 3.5050532430098774e-05, |
| "loss": 0.1571, |
| "num_input_tokens_seen": 1464104, |
| "step": 3565 |
| }, |
| { |
| "epoch": 4.322033898305085, |
| "grad_norm": 4.206084728240967, |
| "learning_rate": 3.500214210063035e-05, |
| "loss": 0.1301, |
| "num_input_tokens_seen": 1466216, |
| "step": 3570 |
| }, |
| { |
| "epoch": 4.328087167070218, |
| "grad_norm": 3.4586846828460693, |
| "learning_rate": 3.495370711437221e-05, |
| "loss": 0.0902, |
| "num_input_tokens_seen": 1468264, |
| "step": 3575 |
| }, |
| { |
| "epoch": 4.3341404358353515, |
| "grad_norm": 0.12353920936584473, |
| "learning_rate": 3.490522768757316e-05, |
| "loss": 0.1492, |
| "num_input_tokens_seen": 1470408, |
| "step": 3580 |
| }, |
| { |
| "epoch": 4.340193704600484, |
| "grad_norm": 0.6406307220458984, |
| "learning_rate": 3.485670403668036e-05, |
| "loss": 0.0404, |
| "num_input_tokens_seen": 1472392, |
| "step": 3585 |
| }, |
| { |
| "epoch": 4.346246973365617, |
| "grad_norm": 0.753180742263794, |
| "learning_rate": 3.480813637833846e-05, |
| "loss": 0.0436, |
| "num_input_tokens_seen": 1474504, |
| "step": 3590 |
| }, |
| { |
| "epoch": 4.352300242130751, |
| "grad_norm": 0.8588903546333313, |
| "learning_rate": 3.475952492938859e-05, |
| "loss": 0.1417, |
| "num_input_tokens_seen": 1476616, |
| "step": 3595 |
| }, |
| { |
| "epoch": 4.358353510895884, |
| "grad_norm": 2.96315336227417, |
| "learning_rate": 3.471086990686737e-05, |
| "loss": 0.0421, |
| "num_input_tokens_seen": 1478664, |
| "step": 3600 |
| }, |
| { |
| "epoch": 4.364406779661017, |
| "grad_norm": 1.0311739444732666, |
| "learning_rate": 3.466217152800598e-05, |
| "loss": 0.2103, |
| "num_input_tokens_seen": 1480648, |
| "step": 3605 |
| }, |
| { |
| "epoch": 4.37046004842615, |
| "grad_norm": 0.5896651744842529, |
| "learning_rate": 3.461343001022919e-05, |
| "loss": 0.0813, |
| "num_input_tokens_seen": 1482760, |
| "step": 3610 |
| }, |
| { |
| "epoch": 4.376513317191283, |
| "grad_norm": 2.433903932571411, |
| "learning_rate": 3.456464557115433e-05, |
| "loss": 0.1196, |
| "num_input_tokens_seen": 1484744, |
| "step": 3615 |
| }, |
| { |
| "epoch": 4.3825665859564165, |
| "grad_norm": 3.2190709114074707, |
| "learning_rate": 3.45158184285904e-05, |
| "loss": 0.0418, |
| "num_input_tokens_seen": 1486728, |
| "step": 3620 |
| }, |
| { |
| "epoch": 4.38861985472155, |
| "grad_norm": 2.588831663131714, |
| "learning_rate": 3.446694880053704e-05, |
| "loss": 0.051, |
| "num_input_tokens_seen": 1488808, |
| "step": 3625 |
| }, |
| { |
| "epoch": 4.394673123486683, |
| "grad_norm": 4.543102264404297, |
| "learning_rate": 3.441803690518359e-05, |
| "loss": 0.1555, |
| "num_input_tokens_seen": 1490984, |
| "step": 3630 |
| }, |
| { |
| "epoch": 4.400726392251816, |
| "grad_norm": 3.894247055053711, |
| "learning_rate": 3.4369082960908084e-05, |
| "loss": 0.1524, |
| "num_input_tokens_seen": 1493000, |
| "step": 3635 |
| }, |
| { |
| "epoch": 4.406779661016949, |
| "grad_norm": 2.111471176147461, |
| "learning_rate": 3.432008718627631e-05, |
| "loss": 0.2373, |
| "num_input_tokens_seen": 1494920, |
| "step": 3640 |
| }, |
| { |
| "epoch": 4.412832929782082, |
| "grad_norm": 5.577587604522705, |
| "learning_rate": 3.4271049800040805e-05, |
| "loss": 0.1239, |
| "num_input_tokens_seen": 1496904, |
| "step": 3645 |
| }, |
| { |
| "epoch": 4.418886198547216, |
| "grad_norm": 2.5321731567382812, |
| "learning_rate": 3.42219710211399e-05, |
| "loss": 0.0717, |
| "num_input_tokens_seen": 1498792, |
| "step": 3650 |
| }, |
| { |
| "epoch": 4.424939467312349, |
| "grad_norm": 0.10607433319091797, |
| "learning_rate": 3.417285106869673e-05, |
| "loss": 0.0888, |
| "num_input_tokens_seen": 1500840, |
| "step": 3655 |
| }, |
| { |
| "epoch": 4.4309927360774815, |
| "grad_norm": 3.724353551864624, |
| "learning_rate": 3.4123690162018246e-05, |
| "loss": 0.0908, |
| "num_input_tokens_seen": 1502888, |
| "step": 3660 |
| }, |
| { |
| "epoch": 4.437046004842615, |
| "grad_norm": 5.9483208656311035, |
| "learning_rate": 3.407448852059426e-05, |
| "loss": 0.0772, |
| "num_input_tokens_seen": 1504904, |
| "step": 3665 |
| }, |
| { |
| "epoch": 4.443099273607748, |
| "grad_norm": 3.859468936920166, |
| "learning_rate": 3.4025246364096455e-05, |
| "loss": 0.1303, |
| "num_input_tokens_seen": 1506824, |
| "step": 3670 |
| }, |
| { |
| "epoch": 4.4491525423728815, |
| "grad_norm": 1.015526294708252, |
| "learning_rate": 3.397596391237739e-05, |
| "loss": 0.141, |
| "num_input_tokens_seen": 1508872, |
| "step": 3675 |
| }, |
| { |
| "epoch": 4.455205811138015, |
| "grad_norm": 3.720564126968384, |
| "learning_rate": 3.3926641385469556e-05, |
| "loss": 0.1819, |
| "num_input_tokens_seen": 1510824, |
| "step": 3680 |
| }, |
| { |
| "epoch": 4.461259079903147, |
| "grad_norm": 3.61460542678833, |
| "learning_rate": 3.387727900358435e-05, |
| "loss": 0.1805, |
| "num_input_tokens_seen": 1512968, |
| "step": 3685 |
| }, |
| { |
| "epoch": 4.467312348668281, |
| "grad_norm": 5.1266889572143555, |
| "learning_rate": 3.38278769871111e-05, |
| "loss": 0.1072, |
| "num_input_tokens_seen": 1515144, |
| "step": 3690 |
| }, |
| { |
| "epoch": 4.473365617433414, |
| "grad_norm": 2.495168685913086, |
| "learning_rate": 3.377843555661612e-05, |
| "loss": 0.064, |
| "num_input_tokens_seen": 1517192, |
| "step": 3695 |
| }, |
| { |
| "epoch": 4.479418886198547, |
| "grad_norm": 1.2742055654525757, |
| "learning_rate": 3.372895493284167e-05, |
| "loss": 0.0776, |
| "num_input_tokens_seen": 1519400, |
| "step": 3700 |
| }, |
| { |
| "epoch": 4.485472154963681, |
| "grad_norm": 0.7095040678977966, |
| "learning_rate": 3.367943533670501e-05, |
| "loss": 0.0758, |
| "num_input_tokens_seen": 1521416, |
| "step": 3705 |
| }, |
| { |
| "epoch": 4.491525423728813, |
| "grad_norm": 2.5754213333129883, |
| "learning_rate": 3.3629876989297405e-05, |
| "loss": 0.1493, |
| "num_input_tokens_seen": 1523240, |
| "step": 3710 |
| }, |
| { |
| "epoch": 4.4975786924939465, |
| "grad_norm": 1.1021342277526855, |
| "learning_rate": 3.3580280111883125e-05, |
| "loss": 0.1357, |
| "num_input_tokens_seen": 1525288, |
| "step": 3715 |
| }, |
| { |
| "epoch": 4.5, |
| "eval_loss": 0.1436297744512558, |
| "eval_runtime": 4.6052, |
| "eval_samples_per_second": 79.693, |
| "eval_steps_per_second": 19.978, |
| "num_input_tokens_seen": 1526088, |
| "step": 3717 |
| }, |
| { |
| "epoch": 4.50363196125908, |
| "grad_norm": 1.27449631690979, |
| "learning_rate": 3.3530644925898465e-05, |
| "loss": 0.1015, |
| "num_input_tokens_seen": 1527304, |
| "step": 3720 |
| }, |
| { |
| "epoch": 4.509685230024213, |
| "grad_norm": 4.025327205657959, |
| "learning_rate": 3.348097165295076e-05, |
| "loss": 0.1539, |
| "num_input_tokens_seen": 1529384, |
| "step": 3725 |
| }, |
| { |
| "epoch": 4.5157384987893465, |
| "grad_norm": 0.13018469512462616, |
| "learning_rate": 3.34312605148174e-05, |
| "loss": 0.0881, |
| "num_input_tokens_seen": 1531464, |
| "step": 3730 |
| }, |
| { |
| "epoch": 4.521791767554479, |
| "grad_norm": 5.49751091003418, |
| "learning_rate": 3.338151173344483e-05, |
| "loss": 0.1117, |
| "num_input_tokens_seen": 1533608, |
| "step": 3735 |
| }, |
| { |
| "epoch": 4.527845036319612, |
| "grad_norm": 0.5280150175094604, |
| "learning_rate": 3.333172553094754e-05, |
| "loss": 0.0613, |
| "num_input_tokens_seen": 1535656, |
| "step": 3740 |
| }, |
| { |
| "epoch": 4.533898305084746, |
| "grad_norm": 4.4329986572265625, |
| "learning_rate": 3.328190212960712e-05, |
| "loss": 0.1342, |
| "num_input_tokens_seen": 1537640, |
| "step": 3745 |
| }, |
| { |
| "epoch": 4.539951573849879, |
| "grad_norm": 2.851104974746704, |
| "learning_rate": 3.323204175187125e-05, |
| "loss": 0.1218, |
| "num_input_tokens_seen": 1539592, |
| "step": 3750 |
| }, |
| { |
| "epoch": 4.546004842615012, |
| "grad_norm": 1.7534023523330688, |
| "learning_rate": 3.318214462035266e-05, |
| "loss": 0.0491, |
| "num_input_tokens_seen": 1541576, |
| "step": 3755 |
| }, |
| { |
| "epoch": 4.552058111380145, |
| "grad_norm": 3.9379611015319824, |
| "learning_rate": 3.3132210957828226e-05, |
| "loss": 0.1587, |
| "num_input_tokens_seen": 1543464, |
| "step": 3760 |
| }, |
| { |
| "epoch": 4.558111380145278, |
| "grad_norm": 2.7358548641204834, |
| "learning_rate": 3.3082240987237875e-05, |
| "loss": 0.0942, |
| "num_input_tokens_seen": 1545416, |
| "step": 3765 |
| }, |
| { |
| "epoch": 4.5641646489104115, |
| "grad_norm": 1.8120285272598267, |
| "learning_rate": 3.3032234931683684e-05, |
| "loss": 0.045, |
| "num_input_tokens_seen": 1547432, |
| "step": 3770 |
| }, |
| { |
| "epoch": 4.570217917675545, |
| "grad_norm": 0.10306795686483383, |
| "learning_rate": 3.2982193014428805e-05, |
| "loss": 0.0788, |
| "num_input_tokens_seen": 1549576, |
| "step": 3775 |
| }, |
| { |
| "epoch": 4.576271186440678, |
| "grad_norm": 1.0330625772476196, |
| "learning_rate": 3.2932115458896515e-05, |
| "loss": 0.1055, |
| "num_input_tokens_seen": 1551688, |
| "step": 3780 |
| }, |
| { |
| "epoch": 4.582324455205811, |
| "grad_norm": 0.3044089078903198, |
| "learning_rate": 3.2882002488669204e-05, |
| "loss": 0.1335, |
| "num_input_tokens_seen": 1553672, |
| "step": 3785 |
| }, |
| { |
| "epoch": 4.588377723970944, |
| "grad_norm": 1.4460806846618652, |
| "learning_rate": 3.28318543274874e-05, |
| "loss": 0.0837, |
| "num_input_tokens_seen": 1555720, |
| "step": 3790 |
| }, |
| { |
| "epoch": 4.594430992736077, |
| "grad_norm": 3.097297191619873, |
| "learning_rate": 3.278167119924872e-05, |
| "loss": 0.1103, |
| "num_input_tokens_seen": 1557672, |
| "step": 3795 |
| }, |
| { |
| "epoch": 4.600484261501211, |
| "grad_norm": 0.30317577719688416, |
| "learning_rate": 3.27314533280069e-05, |
| "loss": 0.1134, |
| "num_input_tokens_seen": 1559880, |
| "step": 3800 |
| }, |
| { |
| "epoch": 4.606537530266344, |
| "grad_norm": 3.337770700454712, |
| "learning_rate": 3.268120093797082e-05, |
| "loss": 0.1148, |
| "num_input_tokens_seen": 1561960, |
| "step": 3805 |
| }, |
| { |
| "epoch": 4.6125907990314765, |
| "grad_norm": 4.097595691680908, |
| "learning_rate": 3.263091425350345e-05, |
| "loss": 0.0856, |
| "num_input_tokens_seen": 1563880, |
| "step": 3810 |
| }, |
| { |
| "epoch": 4.61864406779661, |
| "grad_norm": 0.2643558979034424, |
| "learning_rate": 3.258059349912089e-05, |
| "loss": 0.098, |
| "num_input_tokens_seen": 1565896, |
| "step": 3815 |
| }, |
| { |
| "epoch": 4.624697336561743, |
| "grad_norm": 2.8181965351104736, |
| "learning_rate": 3.253023889949135e-05, |
| "loss": 0.1251, |
| "num_input_tokens_seen": 1568040, |
| "step": 3820 |
| }, |
| { |
| "epoch": 4.6307506053268765, |
| "grad_norm": 3.229228973388672, |
| "learning_rate": 3.247985067943414e-05, |
| "loss": 0.1232, |
| "num_input_tokens_seen": 1570056, |
| "step": 3825 |
| }, |
| { |
| "epoch": 4.63680387409201, |
| "grad_norm": 4.2846999168396, |
| "learning_rate": 3.2429429063918696e-05, |
| "loss": 0.1687, |
| "num_input_tokens_seen": 1572168, |
| "step": 3830 |
| }, |
| { |
| "epoch": 4.642857142857143, |
| "grad_norm": 0.9762236475944519, |
| "learning_rate": 3.2378974278063534e-05, |
| "loss": 0.0517, |
| "num_input_tokens_seen": 1574216, |
| "step": 3835 |
| }, |
| { |
| "epoch": 4.648910411622276, |
| "grad_norm": 0.32010525465011597, |
| "learning_rate": 3.232848654713528e-05, |
| "loss": 0.0454, |
| "num_input_tokens_seen": 1576168, |
| "step": 3840 |
| }, |
| { |
| "epoch": 4.654963680387409, |
| "grad_norm": 1.3530986309051514, |
| "learning_rate": 3.227796609654765e-05, |
| "loss": 0.157, |
| "num_input_tokens_seen": 1578152, |
| "step": 3845 |
| }, |
| { |
| "epoch": 4.661016949152542, |
| "grad_norm": 0.9239023327827454, |
| "learning_rate": 3.222741315186043e-05, |
| "loss": 0.0574, |
| "num_input_tokens_seen": 1580104, |
| "step": 3850 |
| }, |
| { |
| "epoch": 4.667070217917676, |
| "grad_norm": 0.5891803503036499, |
| "learning_rate": 3.217682793877851e-05, |
| "loss": 0.1585, |
| "num_input_tokens_seen": 1582056, |
| "step": 3855 |
| }, |
| { |
| "epoch": 4.673123486682809, |
| "grad_norm": 2.4281816482543945, |
| "learning_rate": 3.212621068315081e-05, |
| "loss": 0.0981, |
| "num_input_tokens_seen": 1584136, |
| "step": 3860 |
| }, |
| { |
| "epoch": 4.6791767554479415, |
| "grad_norm": 1.570319652557373, |
| "learning_rate": 3.207556161096935e-05, |
| "loss": 0.0666, |
| "num_input_tokens_seen": 1586184, |
| "step": 3865 |
| }, |
| { |
| "epoch": 4.685230024213075, |
| "grad_norm": 0.6124736070632935, |
| "learning_rate": 3.202488094836819e-05, |
| "loss": 0.1518, |
| "num_input_tokens_seen": 1588296, |
| "step": 3870 |
| }, |
| { |
| "epoch": 4.691283292978208, |
| "grad_norm": 0.177334725856781, |
| "learning_rate": 3.197416892162242e-05, |
| "loss": 0.1367, |
| "num_input_tokens_seen": 1590504, |
| "step": 3875 |
| }, |
| { |
| "epoch": 4.697336561743342, |
| "grad_norm": 3.659196376800537, |
| "learning_rate": 3.1923425757147175e-05, |
| "loss": 0.1299, |
| "num_input_tokens_seen": 1592584, |
| "step": 3880 |
| }, |
| { |
| "epoch": 4.703389830508475, |
| "grad_norm": 2.184091806411743, |
| "learning_rate": 3.1872651681496604e-05, |
| "loss": 0.1015, |
| "num_input_tokens_seen": 1594728, |
| "step": 3885 |
| }, |
| { |
| "epoch": 4.709443099273607, |
| "grad_norm": 3.05389404296875, |
| "learning_rate": 3.182184692136287e-05, |
| "loss": 0.0826, |
| "num_input_tokens_seen": 1596776, |
| "step": 3890 |
| }, |
| { |
| "epoch": 4.715496368038741, |
| "grad_norm": 3.5935373306274414, |
| "learning_rate": 3.177101170357513e-05, |
| "loss": 0.1999, |
| "num_input_tokens_seen": 1598984, |
| "step": 3895 |
| }, |
| { |
| "epoch": 4.721549636803874, |
| "grad_norm": 4.548536777496338, |
| "learning_rate": 3.1720146255098535e-05, |
| "loss": 0.0944, |
| "num_input_tokens_seen": 1601096, |
| "step": 3900 |
| }, |
| { |
| "epoch": 4.727602905569007, |
| "grad_norm": 0.9657927751541138, |
| "learning_rate": 3.16692508030332e-05, |
| "loss": 0.1482, |
| "num_input_tokens_seen": 1603336, |
| "step": 3905 |
| }, |
| { |
| "epoch": 4.733656174334141, |
| "grad_norm": 2.0334603786468506, |
| "learning_rate": 3.16183255746132e-05, |
| "loss": 0.0449, |
| "num_input_tokens_seen": 1605320, |
| "step": 3910 |
| }, |
| { |
| "epoch": 4.739709443099273, |
| "grad_norm": 6.739678859710693, |
| "learning_rate": 3.156737079720555e-05, |
| "loss": 0.0969, |
| "num_input_tokens_seen": 1607304, |
| "step": 3915 |
| }, |
| { |
| "epoch": 4.745762711864407, |
| "grad_norm": 0.7341704964637756, |
| "learning_rate": 3.151638669830919e-05, |
| "loss": 0.1329, |
| "num_input_tokens_seen": 1609384, |
| "step": 3920 |
| }, |
| { |
| "epoch": 4.75181598062954, |
| "grad_norm": 4.675315856933594, |
| "learning_rate": 3.1465373505554e-05, |
| "loss": 0.1591, |
| "num_input_tokens_seen": 1611304, |
| "step": 3925 |
| }, |
| { |
| "epoch": 4.757869249394673, |
| "grad_norm": 1.1919448375701904, |
| "learning_rate": 3.14143314466997e-05, |
| "loss": 0.1263, |
| "num_input_tokens_seen": 1613192, |
| "step": 3930 |
| }, |
| { |
| "epoch": 4.763922518159807, |
| "grad_norm": 2.328058958053589, |
| "learning_rate": 3.136326074963494e-05, |
| "loss": 0.0304, |
| "num_input_tokens_seen": 1615304, |
| "step": 3935 |
| }, |
| { |
| "epoch": 4.76997578692494, |
| "grad_norm": 0.7319985628128052, |
| "learning_rate": 3.131216164237622e-05, |
| "loss": 0.1002, |
| "num_input_tokens_seen": 1617288, |
| "step": 3940 |
| }, |
| { |
| "epoch": 4.776029055690072, |
| "grad_norm": 4.388686180114746, |
| "learning_rate": 3.1261034353066884e-05, |
| "loss": 0.1414, |
| "num_input_tokens_seen": 1619336, |
| "step": 3945 |
| }, |
| { |
| "epoch": 4.782082324455206, |
| "grad_norm": 3.907365322113037, |
| "learning_rate": 3.1209879109976064e-05, |
| "loss": 0.0695, |
| "num_input_tokens_seen": 1621416, |
| "step": 3950 |
| }, |
| { |
| "epoch": 4.788135593220339, |
| "grad_norm": 4.539724349975586, |
| "learning_rate": 3.115869614149776e-05, |
| "loss": 0.1006, |
| "num_input_tokens_seen": 1623432, |
| "step": 3955 |
| }, |
| { |
| "epoch": 4.7941888619854724, |
| "grad_norm": 4.285974979400635, |
| "learning_rate": 3.1107485676149714e-05, |
| "loss": 0.2159, |
| "num_input_tokens_seen": 1625448, |
| "step": 3960 |
| }, |
| { |
| "epoch": 4.800242130750606, |
| "grad_norm": 5.8608551025390625, |
| "learning_rate": 3.105624794257245e-05, |
| "loss": 0.1279, |
| "num_input_tokens_seen": 1627624, |
| "step": 3965 |
| }, |
| { |
| "epoch": 4.806295399515738, |
| "grad_norm": 0.8381302952766418, |
| "learning_rate": 3.100498316952823e-05, |
| "loss": 0.1144, |
| "num_input_tokens_seen": 1629800, |
| "step": 3970 |
| }, |
| { |
| "epoch": 4.812348668280872, |
| "grad_norm": 3.4423251152038574, |
| "learning_rate": 3.095369158590006e-05, |
| "loss": 0.0671, |
| "num_input_tokens_seen": 1631720, |
| "step": 3975 |
| }, |
| { |
| "epoch": 4.818401937046005, |
| "grad_norm": 1.0596593618392944, |
| "learning_rate": 3.09023734206906e-05, |
| "loss": 0.1878, |
| "num_input_tokens_seen": 1633704, |
| "step": 3980 |
| }, |
| { |
| "epoch": 4.824455205811138, |
| "grad_norm": 4.54054069519043, |
| "learning_rate": 3.085102890302125e-05, |
| "loss": 0.1463, |
| "num_input_tokens_seen": 1635656, |
| "step": 3985 |
| }, |
| { |
| "epoch": 4.830508474576272, |
| "grad_norm": 1.3257328271865845, |
| "learning_rate": 3.079965826213102e-05, |
| "loss": 0.1182, |
| "num_input_tokens_seen": 1637736, |
| "step": 3990 |
| }, |
| { |
| "epoch": 4.836561743341404, |
| "grad_norm": 1.2008308172225952, |
| "learning_rate": 3.074826172737559e-05, |
| "loss": 0.1531, |
| "num_input_tokens_seen": 1639816, |
| "step": 3995 |
| }, |
| { |
| "epoch": 4.842615012106537, |
| "grad_norm": 5.070513725280762, |
| "learning_rate": 3.0696839528226206e-05, |
| "loss": 0.1027, |
| "num_input_tokens_seen": 1641736, |
| "step": 4000 |
| }, |
| { |
| "epoch": 4.848668280871671, |
| "grad_norm": 1.366325855255127, |
| "learning_rate": 3.064539189426874e-05, |
| "loss": 0.144, |
| "num_input_tokens_seen": 1643656, |
| "step": 4005 |
| }, |
| { |
| "epoch": 4.854721549636804, |
| "grad_norm": 5.837193489074707, |
| "learning_rate": 3.059391905520259e-05, |
| "loss": 0.1821, |
| "num_input_tokens_seen": 1645736, |
| "step": 4010 |
| }, |
| { |
| "epoch": 4.8607748184019375, |
| "grad_norm": 1.7730399370193481, |
| "learning_rate": 3.054242124083972e-05, |
| "loss": 0.0776, |
| "num_input_tokens_seen": 1647688, |
| "step": 4015 |
| }, |
| { |
| "epoch": 4.86682808716707, |
| "grad_norm": 4.303905487060547, |
| "learning_rate": 3.0490898681103575e-05, |
| "loss": 0.1172, |
| "num_input_tokens_seen": 1649768, |
| "step": 4020 |
| }, |
| { |
| "epoch": 4.872881355932203, |
| "grad_norm": 6.675983905792236, |
| "learning_rate": 3.0439351606028094e-05, |
| "loss": 0.1297, |
| "num_input_tokens_seen": 1651688, |
| "step": 4025 |
| }, |
| { |
| "epoch": 4.878934624697337, |
| "grad_norm": 2.1775729656219482, |
| "learning_rate": 3.0387780245756655e-05, |
| "loss": 0.0857, |
| "num_input_tokens_seen": 1653896, |
| "step": 4030 |
| }, |
| { |
| "epoch": 4.88498789346247, |
| "grad_norm": 0.18741416931152344, |
| "learning_rate": 3.0336184830541093e-05, |
| "loss": 0.0326, |
| "num_input_tokens_seen": 1656008, |
| "step": 4035 |
| }, |
| { |
| "epoch": 4.891041162227603, |
| "grad_norm": 0.9524343013763428, |
| "learning_rate": 3.028456559074061e-05, |
| "loss": 0.1001, |
| "num_input_tokens_seen": 1658088, |
| "step": 4040 |
| }, |
| { |
| "epoch": 4.897094430992736, |
| "grad_norm": 1.6602981090545654, |
| "learning_rate": 3.0232922756820804e-05, |
| "loss": 0.0551, |
| "num_input_tokens_seen": 1660200, |
| "step": 4045 |
| }, |
| { |
| "epoch": 4.903147699757869, |
| "grad_norm": 4.7026262283325195, |
| "learning_rate": 3.0181256559352587e-05, |
| "loss": 0.1072, |
| "num_input_tokens_seen": 1662440, |
| "step": 4050 |
| }, |
| { |
| "epoch": 4.9092009685230025, |
| "grad_norm": 0.43130701780319214, |
| "learning_rate": 3.0129567229011214e-05, |
| "loss": 0.0924, |
| "num_input_tokens_seen": 1664552, |
| "step": 4055 |
| }, |
| { |
| "epoch": 4.915254237288136, |
| "grad_norm": 1.2491116523742676, |
| "learning_rate": 3.0077854996575184e-05, |
| "loss": 0.081, |
| "num_input_tokens_seen": 1666600, |
| "step": 4060 |
| }, |
| { |
| "epoch": 4.921307506053269, |
| "grad_norm": 0.4165017902851105, |
| "learning_rate": 3.0026120092925293e-05, |
| "loss": 0.1173, |
| "num_input_tokens_seen": 1668776, |
| "step": 4065 |
| }, |
| { |
| "epoch": 4.927360774818402, |
| "grad_norm": 2.2347145080566406, |
| "learning_rate": 2.9974362749043512e-05, |
| "loss": 0.0687, |
| "num_input_tokens_seen": 1670952, |
| "step": 4070 |
| }, |
| { |
| "epoch": 4.933414043583535, |
| "grad_norm": 0.06528237462043762, |
| "learning_rate": 2.9922583196012037e-05, |
| "loss": 0.0733, |
| "num_input_tokens_seen": 1673128, |
| "step": 4075 |
| }, |
| { |
| "epoch": 4.939467312348668, |
| "grad_norm": 3.1934924125671387, |
| "learning_rate": 2.9870781665012204e-05, |
| "loss": 0.0489, |
| "num_input_tokens_seen": 1675112, |
| "step": 4080 |
| }, |
| { |
| "epoch": 4.945520581113802, |
| "grad_norm": 3.640748977661133, |
| "learning_rate": 2.981895838732348e-05, |
| "loss": 0.1047, |
| "num_input_tokens_seen": 1677096, |
| "step": 4085 |
| }, |
| { |
| "epoch": 4.951573849878935, |
| "grad_norm": 0.3172272741794586, |
| "learning_rate": 2.9767113594322426e-05, |
| "loss": 0.1, |
| "num_input_tokens_seen": 1679080, |
| "step": 4090 |
| }, |
| { |
| "epoch": 4.9576271186440675, |
| "grad_norm": 3.484344959259033, |
| "learning_rate": 2.9715247517481655e-05, |
| "loss": 0.067, |
| "num_input_tokens_seen": 1681000, |
| "step": 4095 |
| }, |
| { |
| "epoch": 4.963680387409201, |
| "grad_norm": 2.876481294631958, |
| "learning_rate": 2.96633603883688e-05, |
| "loss": 0.247, |
| "num_input_tokens_seen": 1683048, |
| "step": 4100 |
| }, |
| { |
| "epoch": 4.969733656174334, |
| "grad_norm": 2.505605697631836, |
| "learning_rate": 2.961145243864552e-05, |
| "loss": 0.0494, |
| "num_input_tokens_seen": 1685160, |
| "step": 4105 |
| }, |
| { |
| "epoch": 4.9757869249394675, |
| "grad_norm": 9.4348783493042, |
| "learning_rate": 2.9559523900066395e-05, |
| "loss": 0.2144, |
| "num_input_tokens_seen": 1687048, |
| "step": 4110 |
| }, |
| { |
| "epoch": 4.981840193704601, |
| "grad_norm": 2.766404390335083, |
| "learning_rate": 2.9507575004477955e-05, |
| "loss": 0.1706, |
| "num_input_tokens_seen": 1689000, |
| "step": 4115 |
| }, |
| { |
| "epoch": 4.987893462469733, |
| "grad_norm": 3.0030455589294434, |
| "learning_rate": 2.9455605983817598e-05, |
| "loss": 0.0957, |
| "num_input_tokens_seen": 1691112, |
| "step": 4120 |
| }, |
| { |
| "epoch": 4.993946731234867, |
| "grad_norm": 0.21309371292591095, |
| "learning_rate": 2.9403617070112587e-05, |
| "loss": 0.122, |
| "num_input_tokens_seen": 1693160, |
| "step": 4125 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 11.627579689025879, |
| "learning_rate": 2.9351608495479004e-05, |
| "loss": 0.069, |
| "num_input_tokens_seen": 1694912, |
| "step": 4130 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_loss": 0.14715999364852905, |
| "eval_runtime": 4.5922, |
| "eval_samples_per_second": 79.919, |
| "eval_steps_per_second": 20.034, |
| "num_input_tokens_seen": 1694912, |
| "step": 4130 |
| }, |
| { |
| "epoch": 5.006053268765133, |
| "grad_norm": 8.168224334716797, |
| "learning_rate": 2.92995804921207e-05, |
| "loss": 0.0962, |
| "num_input_tokens_seen": 1697056, |
| "step": 4135 |
| }, |
| { |
| "epoch": 5.012106537530267, |
| "grad_norm": 4.525173187255859, |
| "learning_rate": 2.9247533292328273e-05, |
| "loss": 0.1041, |
| "num_input_tokens_seen": 1699168, |
| "step": 4140 |
| }, |
| { |
| "epoch": 5.018159806295399, |
| "grad_norm": 0.5518445372581482, |
| "learning_rate": 2.9195467128478044e-05, |
| "loss": 0.0151, |
| "num_input_tokens_seen": 1701152, |
| "step": 4145 |
| }, |
| { |
| "epoch": 5.0242130750605325, |
| "grad_norm": 0.14739976823329926, |
| "learning_rate": 2.914338223303098e-05, |
| "loss": 0.1272, |
| "num_input_tokens_seen": 1703168, |
| "step": 4150 |
| }, |
| { |
| "epoch": 5.030266343825666, |
| "grad_norm": 1.3362171649932861, |
| "learning_rate": 2.9091278838531695e-05, |
| "loss": 0.0119, |
| "num_input_tokens_seen": 1705120, |
| "step": 4155 |
| }, |
| { |
| "epoch": 5.036319612590799, |
| "grad_norm": 2.4070515632629395, |
| "learning_rate": 2.9039157177607383e-05, |
| "loss": 0.0939, |
| "num_input_tokens_seen": 1707200, |
| "step": 4160 |
| }, |
| { |
| "epoch": 5.0423728813559325, |
| "grad_norm": 4.166516304016113, |
| "learning_rate": 2.8987017482966815e-05, |
| "loss": 0.1308, |
| "num_input_tokens_seen": 1709120, |
| "step": 4165 |
| }, |
| { |
| "epoch": 5.048426150121065, |
| "grad_norm": 4.306673526763916, |
| "learning_rate": 2.893485998739926e-05, |
| "loss": 0.0451, |
| "num_input_tokens_seen": 1711200, |
| "step": 4170 |
| }, |
| { |
| "epoch": 5.054479418886198, |
| "grad_norm": 7.965576171875, |
| "learning_rate": 2.8882684923773458e-05, |
| "loss": 0.2002, |
| "num_input_tokens_seen": 1713248, |
| "step": 4175 |
| }, |
| { |
| "epoch": 5.060532687651332, |
| "grad_norm": 2.435213327407837, |
| "learning_rate": 2.883049252503659e-05, |
| "loss": 0.0611, |
| "num_input_tokens_seen": 1715296, |
| "step": 4180 |
| }, |
| { |
| "epoch": 5.066585956416465, |
| "grad_norm": 0.1197163313627243, |
| "learning_rate": 2.877828302421325e-05, |
| "loss": 0.1464, |
| "num_input_tokens_seen": 1717280, |
| "step": 4185 |
| }, |
| { |
| "epoch": 5.072639225181598, |
| "grad_norm": 5.31384801864624, |
| "learning_rate": 2.872605665440436e-05, |
| "loss": 0.1242, |
| "num_input_tokens_seen": 1719136, |
| "step": 4190 |
| }, |
| { |
| "epoch": 5.078692493946731, |
| "grad_norm": 0.12134741991758347, |
| "learning_rate": 2.8673813648786196e-05, |
| "loss": 0.1163, |
| "num_input_tokens_seen": 1721152, |
| "step": 4195 |
| }, |
| { |
| "epoch": 5.084745762711864, |
| "grad_norm": 5.05936861038208, |
| "learning_rate": 2.862155424060926e-05, |
| "loss": 0.0711, |
| "num_input_tokens_seen": 1723328, |
| "step": 4200 |
| }, |
| { |
| "epoch": 5.0907990314769975, |
| "grad_norm": 0.19684794545173645, |
| "learning_rate": 2.856927866319733e-05, |
| "loss": 0.0897, |
| "num_input_tokens_seen": 1725280, |
| "step": 4205 |
| }, |
| { |
| "epoch": 5.096852300242131, |
| "grad_norm": 0.09383846819400787, |
| "learning_rate": 2.851698714994635e-05, |
| "loss": 0.0437, |
| "num_input_tokens_seen": 1727328, |
| "step": 4210 |
| }, |
| { |
| "epoch": 5.102905569007264, |
| "grad_norm": 7.017461776733398, |
| "learning_rate": 2.8464679934323424e-05, |
| "loss": 0.0987, |
| "num_input_tokens_seen": 1729472, |
| "step": 4215 |
| }, |
| { |
| "epoch": 5.108958837772397, |
| "grad_norm": 0.7437957525253296, |
| "learning_rate": 2.841235724986575e-05, |
| "loss": 0.0985, |
| "num_input_tokens_seen": 1731392, |
| "step": 4220 |
| }, |
| { |
| "epoch": 5.11501210653753, |
| "grad_norm": 7.1092705726623535, |
| "learning_rate": 2.8360019330179604e-05, |
| "loss": 0.188, |
| "num_input_tokens_seen": 1733472, |
| "step": 4225 |
| }, |
| { |
| "epoch": 5.121065375302663, |
| "grad_norm": 0.43915751576423645, |
| "learning_rate": 2.8307666408939278e-05, |
| "loss": 0.107, |
| "num_input_tokens_seen": 1735520, |
| "step": 4230 |
| }, |
| { |
| "epoch": 5.127118644067797, |
| "grad_norm": 0.4318813979625702, |
| "learning_rate": 2.8255298719886043e-05, |
| "loss": 0.1732, |
| "num_input_tokens_seen": 1737536, |
| "step": 4235 |
| }, |
| { |
| "epoch": 5.13317191283293, |
| "grad_norm": 4.211883544921875, |
| "learning_rate": 2.820291649682709e-05, |
| "loss": 0.1299, |
| "num_input_tokens_seen": 1739424, |
| "step": 4240 |
| }, |
| { |
| "epoch": 5.1392251815980625, |
| "grad_norm": 0.5891851186752319, |
| "learning_rate": 2.8150519973634543e-05, |
| "loss": 0.0775, |
| "num_input_tokens_seen": 1741536, |
| "step": 4245 |
| }, |
| { |
| "epoch": 5.145278450363196, |
| "grad_norm": 4.266312122344971, |
| "learning_rate": 2.809810938424432e-05, |
| "loss": 0.1593, |
| "num_input_tokens_seen": 1743488, |
| "step": 4250 |
| }, |
| { |
| "epoch": 5.151331719128329, |
| "grad_norm": 2.173311710357666, |
| "learning_rate": 2.804568496265516e-05, |
| "loss": 0.1045, |
| "num_input_tokens_seen": 1745728, |
| "step": 4255 |
| }, |
| { |
| "epoch": 5.157384987893463, |
| "grad_norm": 3.343336820602417, |
| "learning_rate": 2.799324694292757e-05, |
| "loss": 0.0858, |
| "num_input_tokens_seen": 1747808, |
| "step": 4260 |
| }, |
| { |
| "epoch": 5.163438256658596, |
| "grad_norm": 0.05580740049481392, |
| "learning_rate": 2.7940795559182764e-05, |
| "loss": 0.0505, |
| "num_input_tokens_seen": 1749856, |
| "step": 4265 |
| }, |
| { |
| "epoch": 5.169491525423728, |
| "grad_norm": 4.62854528427124, |
| "learning_rate": 2.788833104560161e-05, |
| "loss": 0.1006, |
| "num_input_tokens_seen": 1751904, |
| "step": 4270 |
| }, |
| { |
| "epoch": 5.175544794188862, |
| "grad_norm": 0.49617746472358704, |
| "learning_rate": 2.7835853636423616e-05, |
| "loss": 0.0892, |
| "num_input_tokens_seen": 1753984, |
| "step": 4275 |
| }, |
| { |
| "epoch": 5.181598062953995, |
| "grad_norm": 2.32796311378479, |
| "learning_rate": 2.7783363565945847e-05, |
| "loss": 0.0829, |
| "num_input_tokens_seen": 1756000, |
| "step": 4280 |
| }, |
| { |
| "epoch": 5.187651331719128, |
| "grad_norm": 0.8803606033325195, |
| "learning_rate": 2.773086106852192e-05, |
| "loss": 0.0805, |
| "num_input_tokens_seen": 1758080, |
| "step": 4285 |
| }, |
| { |
| "epoch": 5.193704600484262, |
| "grad_norm": 1.4200032949447632, |
| "learning_rate": 2.7678346378560903e-05, |
| "loss": 0.0972, |
| "num_input_tokens_seen": 1760224, |
| "step": 4290 |
| }, |
| { |
| "epoch": 5.199757869249395, |
| "grad_norm": 5.253544807434082, |
| "learning_rate": 2.762581973052633e-05, |
| "loss": 0.0848, |
| "num_input_tokens_seen": 1762176, |
| "step": 4295 |
| }, |
| { |
| "epoch": 5.2058111380145276, |
| "grad_norm": 0.5915831923484802, |
| "learning_rate": 2.7573281358935104e-05, |
| "loss": 0.0243, |
| "num_input_tokens_seen": 1764352, |
| "step": 4300 |
| }, |
| { |
| "epoch": 5.211864406779661, |
| "grad_norm": 5.024724960327148, |
| "learning_rate": 2.7520731498356494e-05, |
| "loss": 0.0917, |
| "num_input_tokens_seen": 1766432, |
| "step": 4305 |
| }, |
| { |
| "epoch": 5.217917675544794, |
| "grad_norm": 1.844663143157959, |
| "learning_rate": 2.746817038341103e-05, |
| "loss": 0.2167, |
| "num_input_tokens_seen": 1768608, |
| "step": 4310 |
| }, |
| { |
| "epoch": 5.223970944309928, |
| "grad_norm": 0.30476701259613037, |
| "learning_rate": 2.7415598248769524e-05, |
| "loss": 0.0132, |
| "num_input_tokens_seen": 1770752, |
| "step": 4315 |
| }, |
| { |
| "epoch": 5.230024213075061, |
| "grad_norm": 2.587169885635376, |
| "learning_rate": 2.7363015329151965e-05, |
| "loss": 0.0206, |
| "num_input_tokens_seen": 1772832, |
| "step": 4320 |
| }, |
| { |
| "epoch": 5.236077481840193, |
| "grad_norm": 0.4779854118824005, |
| "learning_rate": 2.73104218593265e-05, |
| "loss": 0.1323, |
| "num_input_tokens_seen": 1774912, |
| "step": 4325 |
| }, |
| { |
| "epoch": 5.242130750605327, |
| "grad_norm": 1.2622554302215576, |
| "learning_rate": 2.7257818074108394e-05, |
| "loss": 0.2511, |
| "num_input_tokens_seen": 1777024, |
| "step": 4330 |
| }, |
| { |
| "epoch": 5.24818401937046, |
| "grad_norm": 1.7752158641815186, |
| "learning_rate": 2.7205204208358947e-05, |
| "loss": 0.1289, |
| "num_input_tokens_seen": 1779008, |
| "step": 4335 |
| }, |
| { |
| "epoch": 5.254237288135593, |
| "grad_norm": 6.4176836013793945, |
| "learning_rate": 2.715258049698446e-05, |
| "loss": 0.0524, |
| "num_input_tokens_seen": 1780896, |
| "step": 4340 |
| }, |
| { |
| "epoch": 5.260290556900727, |
| "grad_norm": 3.9696273803710938, |
| "learning_rate": 2.709994717493523e-05, |
| "loss": 0.1406, |
| "num_input_tokens_seen": 1783008, |
| "step": 4345 |
| }, |
| { |
| "epoch": 5.266343825665859, |
| "grad_norm": 0.1831623762845993, |
| "learning_rate": 2.7047304477204416e-05, |
| "loss": 0.0092, |
| "num_input_tokens_seen": 1784992, |
| "step": 4350 |
| }, |
| { |
| "epoch": 5.272397094430993, |
| "grad_norm": 11.523201942443848, |
| "learning_rate": 2.6994652638827078e-05, |
| "loss": 0.3058, |
| "num_input_tokens_seen": 1787008, |
| "step": 4355 |
| }, |
| { |
| "epoch": 5.278450363196126, |
| "grad_norm": 3.319190502166748, |
| "learning_rate": 2.694199189487906e-05, |
| "loss": 0.1035, |
| "num_input_tokens_seen": 1789120, |
| "step": 4360 |
| }, |
| { |
| "epoch": 5.284503631961259, |
| "grad_norm": 4.413753509521484, |
| "learning_rate": 2.688932248047597e-05, |
| "loss": 0.1166, |
| "num_input_tokens_seen": 1791232, |
| "step": 4365 |
| }, |
| { |
| "epoch": 5.290556900726393, |
| "grad_norm": 5.708840370178223, |
| "learning_rate": 2.683664463077214e-05, |
| "loss": 0.0982, |
| "num_input_tokens_seen": 1793440, |
| "step": 4370 |
| }, |
| { |
| "epoch": 5.296610169491525, |
| "grad_norm": 4.179380893707275, |
| "learning_rate": 2.678395858095955e-05, |
| "loss": 0.0611, |
| "num_input_tokens_seen": 1795488, |
| "step": 4375 |
| }, |
| { |
| "epoch": 5.302663438256658, |
| "grad_norm": 4.286114692687988, |
| "learning_rate": 2.6731264566266795e-05, |
| "loss": 0.0886, |
| "num_input_tokens_seen": 1797600, |
| "step": 4380 |
| }, |
| { |
| "epoch": 5.308716707021792, |
| "grad_norm": 4.661886215209961, |
| "learning_rate": 2.6678562821958043e-05, |
| "loss": 0.1656, |
| "num_input_tokens_seen": 1799584, |
| "step": 4385 |
| }, |
| { |
| "epoch": 5.314769975786925, |
| "grad_norm": 0.09037864208221436, |
| "learning_rate": 2.6625853583331943e-05, |
| "loss": 0.1248, |
| "num_input_tokens_seen": 1801440, |
| "step": 4390 |
| }, |
| { |
| "epoch": 5.3208232445520585, |
| "grad_norm": 3.2096681594848633, |
| "learning_rate": 2.6573137085720638e-05, |
| "loss": 0.0649, |
| "num_input_tokens_seen": 1803456, |
| "step": 4395 |
| }, |
| { |
| "epoch": 5.326876513317191, |
| "grad_norm": 1.737039566040039, |
| "learning_rate": 2.6520413564488672e-05, |
| "loss": 0.1877, |
| "num_input_tokens_seen": 1805440, |
| "step": 4400 |
| }, |
| { |
| "epoch": 5.332929782082324, |
| "grad_norm": 3.13798451423645, |
| "learning_rate": 2.6467683255031918e-05, |
| "loss": 0.0848, |
| "num_input_tokens_seen": 1807360, |
| "step": 4405 |
| }, |
| { |
| "epoch": 5.338983050847458, |
| "grad_norm": 3.5494918823242188, |
| "learning_rate": 2.6414946392776597e-05, |
| "loss": 0.0934, |
| "num_input_tokens_seen": 1809344, |
| "step": 4410 |
| }, |
| { |
| "epoch": 5.345036319612591, |
| "grad_norm": 0.5050595998764038, |
| "learning_rate": 2.636220321317816e-05, |
| "loss": 0.073, |
| "num_input_tokens_seen": 1811456, |
| "step": 4415 |
| }, |
| { |
| "epoch": 5.351089588377724, |
| "grad_norm": 3.0784072875976562, |
| "learning_rate": 2.6309453951720274e-05, |
| "loss": 0.048, |
| "num_input_tokens_seen": 1813600, |
| "step": 4420 |
| }, |
| { |
| "epoch": 5.357142857142857, |
| "grad_norm": 5.797350883483887, |
| "learning_rate": 2.625669884391377e-05, |
| "loss": 0.2233, |
| "num_input_tokens_seen": 1815424, |
| "step": 4425 |
| }, |
| { |
| "epoch": 5.36319612590799, |
| "grad_norm": 9.18054485321045, |
| "learning_rate": 2.6203938125295552e-05, |
| "loss": 0.1113, |
| "num_input_tokens_seen": 1817600, |
| "step": 4430 |
| }, |
| { |
| "epoch": 5.3692493946731235, |
| "grad_norm": 5.451303482055664, |
| "learning_rate": 2.6151172031427597e-05, |
| "loss": 0.0575, |
| "num_input_tokens_seen": 1819648, |
| "step": 4435 |
| }, |
| { |
| "epoch": 5.375302663438257, |
| "grad_norm": 0.7396259903907776, |
| "learning_rate": 2.609840079789588e-05, |
| "loss": 0.1025, |
| "num_input_tokens_seen": 1821728, |
| "step": 4440 |
| }, |
| { |
| "epoch": 5.38135593220339, |
| "grad_norm": 5.703775882720947, |
| "learning_rate": 2.604562466030931e-05, |
| "loss": 0.0703, |
| "num_input_tokens_seen": 1823776, |
| "step": 4445 |
| }, |
| { |
| "epoch": 5.387409200968523, |
| "grad_norm": 0.9737942218780518, |
| "learning_rate": 2.599284385429871e-05, |
| "loss": 0.0886, |
| "num_input_tokens_seen": 1825856, |
| "step": 4450 |
| }, |
| { |
| "epoch": 5.393462469733656, |
| "grad_norm": 6.848929405212402, |
| "learning_rate": 2.594005861551574e-05, |
| "loss": 0.0506, |
| "num_input_tokens_seen": 1827936, |
| "step": 4455 |
| }, |
| { |
| "epoch": 5.399515738498789, |
| "grad_norm": 0.08520136773586273, |
| "learning_rate": 2.588726917963183e-05, |
| "loss": 0.087, |
| "num_input_tokens_seen": 1829824, |
| "step": 4460 |
| }, |
| { |
| "epoch": 5.405569007263923, |
| "grad_norm": 0.5107972621917725, |
| "learning_rate": 2.5834475782337187e-05, |
| "loss": 0.0144, |
| "num_input_tokens_seen": 1831936, |
| "step": 4465 |
| }, |
| { |
| "epoch": 5.411622276029056, |
| "grad_norm": 1.4982185363769531, |
| "learning_rate": 2.578167865933967e-05, |
| "loss": 0.0483, |
| "num_input_tokens_seen": 1834048, |
| "step": 4470 |
| }, |
| { |
| "epoch": 5.4176755447941884, |
| "grad_norm": 0.8156539797782898, |
| "learning_rate": 2.5728878046363785e-05, |
| "loss": 0.0896, |
| "num_input_tokens_seen": 1836192, |
| "step": 4475 |
| }, |
| { |
| "epoch": 5.423728813559322, |
| "grad_norm": 4.080778121948242, |
| "learning_rate": 2.5676074179149635e-05, |
| "loss": 0.0587, |
| "num_input_tokens_seen": 1838432, |
| "step": 4480 |
| }, |
| { |
| "epoch": 5.429782082324455, |
| "grad_norm": 6.264119625091553, |
| "learning_rate": 2.5623267293451826e-05, |
| "loss": 0.1014, |
| "num_input_tokens_seen": 1840576, |
| "step": 4485 |
| }, |
| { |
| "epoch": 5.4358353510895885, |
| "grad_norm": 0.09231238812208176, |
| "learning_rate": 2.5570457625038457e-05, |
| "loss": 0.0556, |
| "num_input_tokens_seen": 1842624, |
| "step": 4490 |
| }, |
| { |
| "epoch": 5.441888619854722, |
| "grad_norm": 6.133981704711914, |
| "learning_rate": 2.551764540969005e-05, |
| "loss": 0.1426, |
| "num_input_tokens_seen": 1844576, |
| "step": 4495 |
| }, |
| { |
| "epoch": 5.447941888619855, |
| "grad_norm": 1.5127137899398804, |
| "learning_rate": 2.5464830883198492e-05, |
| "loss": 0.119, |
| "num_input_tokens_seen": 1846560, |
| "step": 4500 |
| }, |
| { |
| "epoch": 5.453995157384988, |
| "grad_norm": 5.255079746246338, |
| "learning_rate": 2.5412014281365986e-05, |
| "loss": 0.1274, |
| "num_input_tokens_seen": 1848576, |
| "step": 4505 |
| }, |
| { |
| "epoch": 5.460048426150121, |
| "grad_norm": 5.694177627563477, |
| "learning_rate": 2.5359195840004023e-05, |
| "loss": 0.0501, |
| "num_input_tokens_seen": 1850688, |
| "step": 4510 |
| }, |
| { |
| "epoch": 5.466101694915254, |
| "grad_norm": 2.639869451522827, |
| "learning_rate": 2.5306375794932273e-05, |
| "loss": 0.0547, |
| "num_input_tokens_seen": 1852800, |
| "step": 4515 |
| }, |
| { |
| "epoch": 5.472154963680388, |
| "grad_norm": 1.6186069250106812, |
| "learning_rate": 2.52535543819776e-05, |
| "loss": 0.1454, |
| "num_input_tokens_seen": 1854720, |
| "step": 4520 |
| }, |
| { |
| "epoch": 5.478208232445521, |
| "grad_norm": 4.176394939422607, |
| "learning_rate": 2.5200731836972956e-05, |
| "loss": 0.2223, |
| "num_input_tokens_seen": 1856768, |
| "step": 4525 |
| }, |
| { |
| "epoch": 5.4842615012106535, |
| "grad_norm": 0.455463171005249, |
| "learning_rate": 2.5147908395756343e-05, |
| "loss": 0.033, |
| "num_input_tokens_seen": 1858848, |
| "step": 4530 |
| }, |
| { |
| "epoch": 5.490314769975787, |
| "grad_norm": 3.566337823867798, |
| "learning_rate": 2.5095084294169768e-05, |
| "loss": 0.0516, |
| "num_input_tokens_seen": 1860896, |
| "step": 4535 |
| }, |
| { |
| "epoch": 5.49636803874092, |
| "grad_norm": 4.8022894859313965, |
| "learning_rate": 2.5042259768058208e-05, |
| "loss": 0.2009, |
| "num_input_tokens_seen": 1862816, |
| "step": 4540 |
| }, |
| { |
| "epoch": 5.5, |
| "eval_loss": 0.15775655210018158, |
| "eval_runtime": 4.5824, |
| "eval_samples_per_second": 80.089, |
| "eval_steps_per_second": 20.077, |
| "num_input_tokens_seen": 1864000, |
| "step": 4543 |
| }, |
| { |
| "epoch": 5.5024213075060535, |
| "grad_norm": 4.100371360778809, |
| "learning_rate": 2.4989435053268497e-05, |
| "loss": 0.1968, |
| "num_input_tokens_seen": 1864832, |
| "step": 4545 |
| }, |
| { |
| "epoch": 5.508474576271187, |
| "grad_norm": 5.8973541259765625, |
| "learning_rate": 2.493661038564835e-05, |
| "loss": 0.1107, |
| "num_input_tokens_seen": 1866752, |
| "step": 4550 |
| }, |
| { |
| "epoch": 5.514527845036319, |
| "grad_norm": 0.15794266760349274, |
| "learning_rate": 2.4883786001045238e-05, |
| "loss": 0.0457, |
| "num_input_tokens_seen": 1868928, |
| "step": 4555 |
| }, |
| { |
| "epoch": 5.520581113801453, |
| "grad_norm": 3.9451935291290283, |
| "learning_rate": 2.4830962135305398e-05, |
| "loss": 0.1607, |
| "num_input_tokens_seen": 1871072, |
| "step": 4560 |
| }, |
| { |
| "epoch": 5.526634382566586, |
| "grad_norm": 1.0250242948532104, |
| "learning_rate": 2.4778139024272724e-05, |
| "loss": 0.0756, |
| "num_input_tokens_seen": 1873152, |
| "step": 4565 |
| }, |
| { |
| "epoch": 5.532687651331719, |
| "grad_norm": 5.201865196228027, |
| "learning_rate": 2.4725316903787765e-05, |
| "loss": 0.1061, |
| "num_input_tokens_seen": 1875040, |
| "step": 4570 |
| }, |
| { |
| "epoch": 5.538740920096853, |
| "grad_norm": 0.0985790342092514, |
| "learning_rate": 2.4672496009686622e-05, |
| "loss": 0.0073, |
| "num_input_tokens_seen": 1877184, |
| "step": 4575 |
| }, |
| { |
| "epoch": 5.544794188861985, |
| "grad_norm": 2.5414302349090576, |
| "learning_rate": 2.4619676577799946e-05, |
| "loss": 0.1435, |
| "num_input_tokens_seen": 1879232, |
| "step": 4580 |
| }, |
| { |
| "epoch": 5.5508474576271185, |
| "grad_norm": 4.586217403411865, |
| "learning_rate": 2.4566858843951847e-05, |
| "loss": 0.1246, |
| "num_input_tokens_seen": 1881312, |
| "step": 4585 |
| }, |
| { |
| "epoch": 5.556900726392252, |
| "grad_norm": 6.781052589416504, |
| "learning_rate": 2.451404304395884e-05, |
| "loss": 0.2671, |
| "num_input_tokens_seen": 1883328, |
| "step": 4590 |
| }, |
| { |
| "epoch": 5.562953995157385, |
| "grad_norm": 10.360923767089844, |
| "learning_rate": 2.446122941362883e-05, |
| "loss": 0.1366, |
| "num_input_tokens_seen": 1885248, |
| "step": 4595 |
| }, |
| { |
| "epoch": 5.5690072639225185, |
| "grad_norm": 3.757084608078003, |
| "learning_rate": 2.4408418188760026e-05, |
| "loss": 0.1358, |
| "num_input_tokens_seen": 1887328, |
| "step": 4600 |
| }, |
| { |
| "epoch": 5.575060532687651, |
| "grad_norm": 3.5405287742614746, |
| "learning_rate": 2.435560960513989e-05, |
| "loss": 0.1358, |
| "num_input_tokens_seen": 1889408, |
| "step": 4605 |
| }, |
| { |
| "epoch": 5.581113801452784, |
| "grad_norm": 1.0986759662628174, |
| "learning_rate": 2.4302803898544106e-05, |
| "loss": 0.1262, |
| "num_input_tokens_seen": 1891456, |
| "step": 4610 |
| }, |
| { |
| "epoch": 5.587167070217918, |
| "grad_norm": 3.6903698444366455, |
| "learning_rate": 2.425000130473549e-05, |
| "loss": 0.0779, |
| "num_input_tokens_seen": 1893696, |
| "step": 4615 |
| }, |
| { |
| "epoch": 5.593220338983051, |
| "grad_norm": 0.8637160658836365, |
| "learning_rate": 2.4197202059463e-05, |
| "loss": 0.1851, |
| "num_input_tokens_seen": 1895616, |
| "step": 4620 |
| }, |
| { |
| "epoch": 5.599273607748184, |
| "grad_norm": 4.0059895515441895, |
| "learning_rate": 2.4144406398460594e-05, |
| "loss": 0.1229, |
| "num_input_tokens_seen": 1897600, |
| "step": 4625 |
| }, |
| { |
| "epoch": 5.605326876513317, |
| "grad_norm": 5.283796787261963, |
| "learning_rate": 2.4091614557446267e-05, |
| "loss": 0.2567, |
| "num_input_tokens_seen": 1899616, |
| "step": 4630 |
| }, |
| { |
| "epoch": 5.61138014527845, |
| "grad_norm": 0.3470328450202942, |
| "learning_rate": 2.4038826772120932e-05, |
| "loss": 0.0737, |
| "num_input_tokens_seen": 1901568, |
| "step": 4635 |
| }, |
| { |
| "epoch": 5.6174334140435835, |
| "grad_norm": 4.049567222595215, |
| "learning_rate": 2.398604327816742e-05, |
| "loss": 0.1776, |
| "num_input_tokens_seen": 1903616, |
| "step": 4640 |
| }, |
| { |
| "epoch": 5.623486682808717, |
| "grad_norm": 3.8298497200012207, |
| "learning_rate": 2.3933264311249377e-05, |
| "loss": 0.1617, |
| "num_input_tokens_seen": 1905504, |
| "step": 4645 |
| }, |
| { |
| "epoch": 5.62953995157385, |
| "grad_norm": 2.1219868659973145, |
| "learning_rate": 2.3880490107010255e-05, |
| "loss": 0.0557, |
| "num_input_tokens_seen": 1907456, |
| "step": 4650 |
| }, |
| { |
| "epoch": 5.635593220338983, |
| "grad_norm": 2.666740894317627, |
| "learning_rate": 2.382772090107223e-05, |
| "loss": 0.0658, |
| "num_input_tokens_seen": 1909568, |
| "step": 4655 |
| }, |
| { |
| "epoch": 5.641646489104116, |
| "grad_norm": 2.493098258972168, |
| "learning_rate": 2.3774956929035177e-05, |
| "loss": 0.0427, |
| "num_input_tokens_seen": 1911840, |
| "step": 4660 |
| }, |
| { |
| "epoch": 5.647699757869249, |
| "grad_norm": 0.14598090946674347, |
| "learning_rate": 2.3722198426475593e-05, |
| "loss": 0.1101, |
| "num_input_tokens_seen": 1913952, |
| "step": 4665 |
| }, |
| { |
| "epoch": 5.653753026634383, |
| "grad_norm": 4.130605220794678, |
| "learning_rate": 2.3669445628945542e-05, |
| "loss": 0.0634, |
| "num_input_tokens_seen": 1916160, |
| "step": 4670 |
| }, |
| { |
| "epoch": 5.659806295399516, |
| "grad_norm": 1.1681698560714722, |
| "learning_rate": 2.3616698771971633e-05, |
| "loss": 0.0881, |
| "num_input_tokens_seen": 1918144, |
| "step": 4675 |
| }, |
| { |
| "epoch": 5.6658595641646485, |
| "grad_norm": 6.252587795257568, |
| "learning_rate": 2.356395809105396e-05, |
| "loss": 0.1455, |
| "num_input_tokens_seen": 1920160, |
| "step": 4680 |
| }, |
| { |
| "epoch": 5.671912832929782, |
| "grad_norm": 1.4607112407684326, |
| "learning_rate": 2.3511223821665028e-05, |
| "loss": 0.1253, |
| "num_input_tokens_seen": 1922368, |
| "step": 4685 |
| }, |
| { |
| "epoch": 5.677966101694915, |
| "grad_norm": 3.692471742630005, |
| "learning_rate": 2.3458496199248717e-05, |
| "loss": 0.1402, |
| "num_input_tokens_seen": 1924448, |
| "step": 4690 |
| }, |
| { |
| "epoch": 5.684019370460049, |
| "grad_norm": 5.765774726867676, |
| "learning_rate": 2.340577545921923e-05, |
| "loss": 0.2013, |
| "num_input_tokens_seen": 1926592, |
| "step": 4695 |
| }, |
| { |
| "epoch": 5.690072639225182, |
| "grad_norm": 2.151799440383911, |
| "learning_rate": 2.335306183696006e-05, |
| "loss": 0.0668, |
| "num_input_tokens_seen": 1928672, |
| "step": 4700 |
| }, |
| { |
| "epoch": 5.696125907990314, |
| "grad_norm": 4.2460222244262695, |
| "learning_rate": 2.3300355567822897e-05, |
| "loss": 0.157, |
| "num_input_tokens_seen": 1930816, |
| "step": 4705 |
| }, |
| { |
| "epoch": 5.702179176755448, |
| "grad_norm": 1.2913779020309448, |
| "learning_rate": 2.324765688712661e-05, |
| "loss": 0.1019, |
| "num_input_tokens_seen": 1932896, |
| "step": 4710 |
| }, |
| { |
| "epoch": 5.708232445520581, |
| "grad_norm": 0.1220802515745163, |
| "learning_rate": 2.3194966030156187e-05, |
| "loss": 0.0852, |
| "num_input_tokens_seen": 1934944, |
| "step": 4715 |
| }, |
| { |
| "epoch": 5.714285714285714, |
| "grad_norm": 0.9283545017242432, |
| "learning_rate": 2.31422832321617e-05, |
| "loss": 0.1064, |
| "num_input_tokens_seen": 1937152, |
| "step": 4720 |
| }, |
| { |
| "epoch": 5.720338983050848, |
| "grad_norm": 0.4256783723831177, |
| "learning_rate": 2.308960872835721e-05, |
| "loss": 0.063, |
| "num_input_tokens_seen": 1939328, |
| "step": 4725 |
| }, |
| { |
| "epoch": 5.72639225181598, |
| "grad_norm": 1.6901894807815552, |
| "learning_rate": 2.3036942753919775e-05, |
| "loss": 0.1151, |
| "num_input_tokens_seen": 1941312, |
| "step": 4730 |
| }, |
| { |
| "epoch": 5.732445520581114, |
| "grad_norm": 5.385450839996338, |
| "learning_rate": 2.2984285543988352e-05, |
| "loss": 0.0663, |
| "num_input_tokens_seen": 1943264, |
| "step": 4735 |
| }, |
| { |
| "epoch": 5.738498789346247, |
| "grad_norm": 0.5914505124092102, |
| "learning_rate": 2.2931637333662785e-05, |
| "loss": 0.0648, |
| "num_input_tokens_seen": 1945312, |
| "step": 4740 |
| }, |
| { |
| "epoch": 5.74455205811138, |
| "grad_norm": 0.29477110505104065, |
| "learning_rate": 2.287899835800273e-05, |
| "loss": 0.0784, |
| "num_input_tokens_seen": 1947328, |
| "step": 4745 |
| }, |
| { |
| "epoch": 5.750605326876514, |
| "grad_norm": 3.8047056198120117, |
| "learning_rate": 2.2826368852026597e-05, |
| "loss": 0.0983, |
| "num_input_tokens_seen": 1949376, |
| "step": 4750 |
| }, |
| { |
| "epoch": 5.756658595641646, |
| "grad_norm": 3.759469509124756, |
| "learning_rate": 2.277374905071053e-05, |
| "loss": 0.2523, |
| "num_input_tokens_seen": 1951456, |
| "step": 4755 |
| }, |
| { |
| "epoch": 5.762711864406779, |
| "grad_norm": 3.657890796661377, |
| "learning_rate": 2.2721139188987357e-05, |
| "loss": 0.0834, |
| "num_input_tokens_seen": 1953536, |
| "step": 4760 |
| }, |
| { |
| "epoch": 5.768765133171913, |
| "grad_norm": 7.039313316345215, |
| "learning_rate": 2.26685395017455e-05, |
| "loss": 0.1593, |
| "num_input_tokens_seen": 1955744, |
| "step": 4765 |
| }, |
| { |
| "epoch": 5.774818401937046, |
| "grad_norm": 5.334690093994141, |
| "learning_rate": 2.261595022382799e-05, |
| "loss": 0.1404, |
| "num_input_tokens_seen": 1957824, |
| "step": 4770 |
| }, |
| { |
| "epoch": 5.780871670702179, |
| "grad_norm": 2.440227508544922, |
| "learning_rate": 2.256337159003134e-05, |
| "loss": 0.0983, |
| "num_input_tokens_seen": 1960000, |
| "step": 4775 |
| }, |
| { |
| "epoch": 5.786924939467312, |
| "grad_norm": 0.9316068291664124, |
| "learning_rate": 2.251080383510459e-05, |
| "loss": 0.0422, |
| "num_input_tokens_seen": 1962144, |
| "step": 4780 |
| }, |
| { |
| "epoch": 5.792978208232445, |
| "grad_norm": 2.1307058334350586, |
| "learning_rate": 2.2458247193748155e-05, |
| "loss": 0.1192, |
| "num_input_tokens_seen": 1964192, |
| "step": 4785 |
| }, |
| { |
| "epoch": 5.799031476997579, |
| "grad_norm": 4.095328330993652, |
| "learning_rate": 2.240570190061288e-05, |
| "loss": 0.1351, |
| "num_input_tokens_seen": 1966240, |
| "step": 4790 |
| }, |
| { |
| "epoch": 5.805084745762712, |
| "grad_norm": 3.0268330574035645, |
| "learning_rate": 2.2353168190298915e-05, |
| "loss": 0.1107, |
| "num_input_tokens_seen": 1968320, |
| "step": 4795 |
| }, |
| { |
| "epoch": 5.811138014527845, |
| "grad_norm": 0.37829795479774475, |
| "learning_rate": 2.2300646297354704e-05, |
| "loss": 0.0993, |
| "num_input_tokens_seen": 1970304, |
| "step": 4800 |
| }, |
| { |
| "epoch": 5.817191283292978, |
| "grad_norm": 2.7740402221679688, |
| "learning_rate": 2.224813645627592e-05, |
| "loss": 0.0937, |
| "num_input_tokens_seen": 1972320, |
| "step": 4805 |
| }, |
| { |
| "epoch": 5.823244552058111, |
| "grad_norm": 2.5438811779022217, |
| "learning_rate": 2.2195638901504452e-05, |
| "loss": 0.0555, |
| "num_input_tokens_seen": 1974432, |
| "step": 4810 |
| }, |
| { |
| "epoch": 5.829297820823244, |
| "grad_norm": 0.15112103521823883, |
| "learning_rate": 2.2143153867427305e-05, |
| "loss": 0.0675, |
| "num_input_tokens_seen": 1976480, |
| "step": 4815 |
| }, |
| { |
| "epoch": 5.835351089588378, |
| "grad_norm": 4.919175148010254, |
| "learning_rate": 2.2090681588375594e-05, |
| "loss": 0.1833, |
| "num_input_tokens_seen": 1978624, |
| "step": 4820 |
| }, |
| { |
| "epoch": 5.841404358353511, |
| "grad_norm": 0.0790180116891861, |
| "learning_rate": 2.2038222298623507e-05, |
| "loss": 0.0329, |
| "num_input_tokens_seen": 1980736, |
| "step": 4825 |
| }, |
| { |
| "epoch": 5.847457627118644, |
| "grad_norm": 0.06224536895751953, |
| "learning_rate": 2.1985776232387202e-05, |
| "loss": 0.0506, |
| "num_input_tokens_seen": 1982656, |
| "step": 4830 |
| }, |
| { |
| "epoch": 5.853510895883777, |
| "grad_norm": 0.7474290132522583, |
| "learning_rate": 2.1933343623823814e-05, |
| "loss": 0.1328, |
| "num_input_tokens_seen": 1984832, |
| "step": 4835 |
| }, |
| { |
| "epoch": 5.85956416464891, |
| "grad_norm": 4.492368698120117, |
| "learning_rate": 2.1880924707030407e-05, |
| "loss": 0.1015, |
| "num_input_tokens_seen": 1986848, |
| "step": 4840 |
| }, |
| { |
| "epoch": 5.865617433414044, |
| "grad_norm": 1.0196672677993774, |
| "learning_rate": 2.1828519716042888e-05, |
| "loss": 0.1972, |
| "num_input_tokens_seen": 1988992, |
| "step": 4845 |
| }, |
| { |
| "epoch": 5.871670702179177, |
| "grad_norm": 0.20354236662387848, |
| "learning_rate": 2.177612888483502e-05, |
| "loss": 0.1323, |
| "num_input_tokens_seen": 1990976, |
| "step": 4850 |
| }, |
| { |
| "epoch": 5.877723970944309, |
| "grad_norm": 0.2845112681388855, |
| "learning_rate": 2.1723752447317312e-05, |
| "loss": 0.0714, |
| "num_input_tokens_seen": 1992928, |
| "step": 4855 |
| }, |
| { |
| "epoch": 5.883777239709443, |
| "grad_norm": 3.6729049682617188, |
| "learning_rate": 2.167139063733605e-05, |
| "loss": 0.2155, |
| "num_input_tokens_seen": 1995104, |
| "step": 4860 |
| }, |
| { |
| "epoch": 5.889830508474576, |
| "grad_norm": 5.529604434967041, |
| "learning_rate": 2.161904368867217e-05, |
| "loss": 0.0664, |
| "num_input_tokens_seen": 1997312, |
| "step": 4865 |
| }, |
| { |
| "epoch": 5.8958837772397095, |
| "grad_norm": 4.269104957580566, |
| "learning_rate": 2.1566711835040284e-05, |
| "loss": 0.0805, |
| "num_input_tokens_seen": 1999232, |
| "step": 4870 |
| }, |
| { |
| "epoch": 5.901937046004843, |
| "grad_norm": 0.41338273882865906, |
| "learning_rate": 2.1514395310087596e-05, |
| "loss": 0.1931, |
| "num_input_tokens_seen": 2001088, |
| "step": 4875 |
| }, |
| { |
| "epoch": 5.907990314769976, |
| "grad_norm": 0.3836718797683716, |
| "learning_rate": 2.1462094347392887e-05, |
| "loss": 0.0544, |
| "num_input_tokens_seen": 2003232, |
| "step": 4880 |
| }, |
| { |
| "epoch": 5.914043583535109, |
| "grad_norm": 4.488040447235107, |
| "learning_rate": 2.1409809180465436e-05, |
| "loss": 0.1114, |
| "num_input_tokens_seen": 2005312, |
| "step": 4885 |
| }, |
| { |
| "epoch": 5.920096852300242, |
| "grad_norm": 5.718064308166504, |
| "learning_rate": 2.1357540042744006e-05, |
| "loss": 0.1378, |
| "num_input_tokens_seen": 2007392, |
| "step": 4890 |
| }, |
| { |
| "epoch": 5.926150121065375, |
| "grad_norm": 0.7707825899124146, |
| "learning_rate": 2.1305287167595808e-05, |
| "loss": 0.1329, |
| "num_input_tokens_seen": 2009568, |
| "step": 4895 |
| }, |
| { |
| "epoch": 5.932203389830509, |
| "grad_norm": 4.785271644592285, |
| "learning_rate": 2.1253050788315436e-05, |
| "loss": 0.0762, |
| "num_input_tokens_seen": 2011424, |
| "step": 4900 |
| }, |
| { |
| "epoch": 5.938256658595642, |
| "grad_norm": 4.0082783699035645, |
| "learning_rate": 2.120083113812381e-05, |
| "loss": 0.0583, |
| "num_input_tokens_seen": 2013504, |
| "step": 4905 |
| }, |
| { |
| "epoch": 5.9443099273607745, |
| "grad_norm": 7.899497985839844, |
| "learning_rate": 2.1148628450167203e-05, |
| "loss": 0.1401, |
| "num_input_tokens_seen": 2015872, |
| "step": 4910 |
| }, |
| { |
| "epoch": 5.950363196125908, |
| "grad_norm": 3.8147408962249756, |
| "learning_rate": 2.109644295751612e-05, |
| "loss": 0.1231, |
| "num_input_tokens_seen": 2017888, |
| "step": 4915 |
| }, |
| { |
| "epoch": 5.956416464891041, |
| "grad_norm": 4.809561252593994, |
| "learning_rate": 2.1044274893164316e-05, |
| "loss": 0.149, |
| "num_input_tokens_seen": 2019904, |
| "step": 4920 |
| }, |
| { |
| "epoch": 5.9624697336561745, |
| "grad_norm": 1.246935486793518, |
| "learning_rate": 2.0992124490027727e-05, |
| "loss": 0.1612, |
| "num_input_tokens_seen": 2022016, |
| "step": 4925 |
| }, |
| { |
| "epoch": 5.968523002421308, |
| "grad_norm": 3.2453746795654297, |
| "learning_rate": 2.0939991980943437e-05, |
| "loss": 0.1673, |
| "num_input_tokens_seen": 2023936, |
| "step": 4930 |
| }, |
| { |
| "epoch": 5.97457627118644, |
| "grad_norm": 4.5902204513549805, |
| "learning_rate": 2.088787759866863e-05, |
| "loss": 0.1408, |
| "num_input_tokens_seen": 2026080, |
| "step": 4935 |
| }, |
| { |
| "epoch": 5.980629539951574, |
| "grad_norm": 3.014443874359131, |
| "learning_rate": 2.0835781575879574e-05, |
| "loss": 0.0181, |
| "num_input_tokens_seen": 2028064, |
| "step": 4940 |
| }, |
| { |
| "epoch": 5.986682808716707, |
| "grad_norm": 4.182370185852051, |
| "learning_rate": 2.0783704145170547e-05, |
| "loss": 0.0733, |
| "num_input_tokens_seen": 2029920, |
| "step": 4945 |
| }, |
| { |
| "epoch": 5.99273607748184, |
| "grad_norm": 4.959621429443359, |
| "learning_rate": 2.0731645539052845e-05, |
| "loss": 0.1935, |
| "num_input_tokens_seen": 2031776, |
| "step": 4950 |
| }, |
| { |
| "epoch": 5.998789346246974, |
| "grad_norm": 3.4146416187286377, |
| "learning_rate": 2.067960598995369e-05, |
| "loss": 0.043, |
| "num_input_tokens_seen": 2033888, |
| "step": 4955 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_loss": 0.1471845954656601, |
| "eval_runtime": 4.5703, |
| "eval_samples_per_second": 80.301, |
| "eval_steps_per_second": 20.13, |
| "num_input_tokens_seen": 2033992, |
| "step": 4956 |
| }, |
| { |
| "epoch": 6.004842615012106, |
| "grad_norm": 1.2523798942565918, |
| "learning_rate": 2.062758573021523e-05, |
| "loss": 0.1246, |
| "num_input_tokens_seen": 2035752, |
| "step": 4960 |
| }, |
| { |
| "epoch": 6.0108958837772395, |
| "grad_norm": 1.3420109748840332, |
| "learning_rate": 2.0575584992093505e-05, |
| "loss": 0.1767, |
| "num_input_tokens_seen": 2037896, |
| "step": 4965 |
| }, |
| { |
| "epoch": 6.016949152542373, |
| "grad_norm": 3.164762020111084, |
| "learning_rate": 2.0523604007757374e-05, |
| "loss": 0.1195, |
| "num_input_tokens_seen": 2040008, |
| "step": 4970 |
| }, |
| { |
| "epoch": 6.023002421307506, |
| "grad_norm": 3.989443302154541, |
| "learning_rate": 2.0471643009287523e-05, |
| "loss": 0.0898, |
| "num_input_tokens_seen": 2042056, |
| "step": 4975 |
| }, |
| { |
| "epoch": 6.0290556900726395, |
| "grad_norm": 0.10141967236995697, |
| "learning_rate": 2.0419702228675395e-05, |
| "loss": 0.2044, |
| "num_input_tokens_seen": 2044040, |
| "step": 4980 |
| }, |
| { |
| "epoch": 6.035108958837772, |
| "grad_norm": 0.23426412045955658, |
| "learning_rate": 2.0367781897822147e-05, |
| "loss": 0.1074, |
| "num_input_tokens_seen": 2046056, |
| "step": 4985 |
| }, |
| { |
| "epoch": 6.041162227602905, |
| "grad_norm": 1.5576239824295044, |
| "learning_rate": 2.031588224853767e-05, |
| "loss": 0.1107, |
| "num_input_tokens_seen": 2047944, |
| "step": 4990 |
| }, |
| { |
| "epoch": 6.047215496368039, |
| "grad_norm": 1.8153196573257446, |
| "learning_rate": 2.0264003512539493e-05, |
| "loss": 0.0688, |
| "num_input_tokens_seen": 2050024, |
| "step": 4995 |
| }, |
| { |
| "epoch": 6.053268765133172, |
| "grad_norm": 2.0969276428222656, |
| "learning_rate": 2.0212145921451787e-05, |
| "loss": 0.1391, |
| "num_input_tokens_seen": 2052040, |
| "step": 5000 |
| }, |
| { |
| "epoch": 6.059322033898305, |
| "grad_norm": 0.1364622712135315, |
| "learning_rate": 2.01603097068043e-05, |
| "loss": 0.0444, |
| "num_input_tokens_seen": 2054120, |
| "step": 5005 |
| }, |
| { |
| "epoch": 6.065375302663438, |
| "grad_norm": 3.0799670219421387, |
| "learning_rate": 2.0108495100031364e-05, |
| "loss": 0.0513, |
| "num_input_tokens_seen": 2056296, |
| "step": 5010 |
| }, |
| { |
| "epoch": 6.071428571428571, |
| "grad_norm": 2.7169783115386963, |
| "learning_rate": 2.0056702332470806e-05, |
| "loss": 0.0249, |
| "num_input_tokens_seen": 2058408, |
| "step": 5015 |
| }, |
| { |
| "epoch": 6.0774818401937045, |
| "grad_norm": 5.1847991943359375, |
| "learning_rate": 2.0004931635362982e-05, |
| "loss": 0.1118, |
| "num_input_tokens_seen": 2060456, |
| "step": 5020 |
| }, |
| { |
| "epoch": 6.083535108958838, |
| "grad_norm": 0.45843198895454407, |
| "learning_rate": 1.995318323984969e-05, |
| "loss": 0.0542, |
| "num_input_tokens_seen": 2062408, |
| "step": 5025 |
| }, |
| { |
| "epoch": 6.089588377723971, |
| "grad_norm": 2.184920310974121, |
| "learning_rate": 1.9901457376973143e-05, |
| "loss": 0.1114, |
| "num_input_tokens_seen": 2064392, |
| "step": 5030 |
| }, |
| { |
| "epoch": 6.095641646489105, |
| "grad_norm": 1.2919806241989136, |
| "learning_rate": 1.9849754277674993e-05, |
| "loss": 0.0539, |
| "num_input_tokens_seen": 2066504, |
| "step": 5035 |
| }, |
| { |
| "epoch": 6.101694915254237, |
| "grad_norm": 0.44648459553718567, |
| "learning_rate": 1.979807417279521e-05, |
| "loss": 0.0888, |
| "num_input_tokens_seen": 2068584, |
| "step": 5040 |
| }, |
| { |
| "epoch": 6.10774818401937, |
| "grad_norm": 0.25474312901496887, |
| "learning_rate": 1.974641729307115e-05, |
| "loss": 0.0106, |
| "num_input_tokens_seen": 2070696, |
| "step": 5045 |
| }, |
| { |
| "epoch": 6.113801452784504, |
| "grad_norm": 1.318625807762146, |
| "learning_rate": 1.9694783869136435e-05, |
| "loss": 0.1124, |
| "num_input_tokens_seen": 2072872, |
| "step": 5050 |
| }, |
| { |
| "epoch": 6.119854721549637, |
| "grad_norm": 3.6301968097686768, |
| "learning_rate": 1.9643174131519986e-05, |
| "loss": 0.0856, |
| "num_input_tokens_seen": 2074824, |
| "step": 5055 |
| }, |
| { |
| "epoch": 6.12590799031477, |
| "grad_norm": 2.665332317352295, |
| "learning_rate": 1.9591588310644967e-05, |
| "loss": 0.0809, |
| "num_input_tokens_seen": 2076808, |
| "step": 5060 |
| }, |
| { |
| "epoch": 6.131961259079903, |
| "grad_norm": 1.1560572385787964, |
| "learning_rate": 1.9540026636827742e-05, |
| "loss": 0.0592, |
| "num_input_tokens_seen": 2078856, |
| "step": 5065 |
| }, |
| { |
| "epoch": 6.138014527845036, |
| "grad_norm": 8.742777824401855, |
| "learning_rate": 1.948848934027689e-05, |
| "loss": 0.0858, |
| "num_input_tokens_seen": 2081096, |
| "step": 5070 |
| }, |
| { |
| "epoch": 6.1440677966101696, |
| "grad_norm": 2.756279945373535, |
| "learning_rate": 1.9436976651092144e-05, |
| "loss": 0.074, |
| "num_input_tokens_seen": 2083144, |
| "step": 5075 |
| }, |
| { |
| "epoch": 6.150121065375303, |
| "grad_norm": 0.6714470386505127, |
| "learning_rate": 1.9385488799263372e-05, |
| "loss": 0.1086, |
| "num_input_tokens_seen": 2085096, |
| "step": 5080 |
| }, |
| { |
| "epoch": 6.156174334140436, |
| "grad_norm": 0.19403041899204254, |
| "learning_rate": 1.9334026014669543e-05, |
| "loss": 0.0633, |
| "num_input_tokens_seen": 2087272, |
| "step": 5085 |
| }, |
| { |
| "epoch": 6.162227602905569, |
| "grad_norm": 6.13324499130249, |
| "learning_rate": 1.9282588527077715e-05, |
| "loss": 0.2309, |
| "num_input_tokens_seen": 2089224, |
| "step": 5090 |
| }, |
| { |
| "epoch": 6.168280871670702, |
| "grad_norm": 4.615688323974609, |
| "learning_rate": 1.9231176566142006e-05, |
| "loss": 0.1434, |
| "num_input_tokens_seen": 2091432, |
| "step": 5095 |
| }, |
| { |
| "epoch": 6.174334140435835, |
| "grad_norm": 0.10968305915594101, |
| "learning_rate": 1.917979036140255e-05, |
| "loss": 0.0737, |
| "num_input_tokens_seen": 2093384, |
| "step": 5100 |
| }, |
| { |
| "epoch": 6.180387409200969, |
| "grad_norm": 0.185858353972435, |
| "learning_rate": 1.9128430142284503e-05, |
| "loss": 0.1049, |
| "num_input_tokens_seen": 2095528, |
| "step": 5105 |
| }, |
| { |
| "epoch": 6.186440677966102, |
| "grad_norm": 1.6614528894424438, |
| "learning_rate": 1.9077096138096992e-05, |
| "loss": 0.0492, |
| "num_input_tokens_seen": 2097544, |
| "step": 5110 |
| }, |
| { |
| "epoch": 6.1924939467312345, |
| "grad_norm": 2.876973867416382, |
| "learning_rate": 1.9025788578032113e-05, |
| "loss": 0.1631, |
| "num_input_tokens_seen": 2099592, |
| "step": 5115 |
| }, |
| { |
| "epoch": 6.198547215496368, |
| "grad_norm": 0.698144793510437, |
| "learning_rate": 1.8974507691163867e-05, |
| "loss": 0.0246, |
| "num_input_tokens_seen": 2101448, |
| "step": 5120 |
| }, |
| { |
| "epoch": 6.204600484261501, |
| "grad_norm": 0.8185459971427917, |
| "learning_rate": 1.892325370644721e-05, |
| "loss": 0.0946, |
| "num_input_tokens_seen": 2103528, |
| "step": 5125 |
| }, |
| { |
| "epoch": 6.210653753026635, |
| "grad_norm": 2.75486421585083, |
| "learning_rate": 1.8872026852716954e-05, |
| "loss": 0.0369, |
| "num_input_tokens_seen": 2105640, |
| "step": 5130 |
| }, |
| { |
| "epoch": 6.216707021791768, |
| "grad_norm": 1.2081927061080933, |
| "learning_rate": 1.8820827358686793e-05, |
| "loss": 0.0666, |
| "num_input_tokens_seen": 2107688, |
| "step": 5135 |
| }, |
| { |
| "epoch": 6.2227602905569, |
| "grad_norm": 2.066209316253662, |
| "learning_rate": 1.8769655452948274e-05, |
| "loss": 0.1806, |
| "num_input_tokens_seen": 2109608, |
| "step": 5140 |
| }, |
| { |
| "epoch": 6.228813559322034, |
| "grad_norm": 0.48250189423561096, |
| "learning_rate": 1.8718511363969733e-05, |
| "loss": 0.0996, |
| "num_input_tokens_seen": 2111752, |
| "step": 5145 |
| }, |
| { |
| "epoch": 6.234866828087167, |
| "grad_norm": 2.2784717082977295, |
| "learning_rate": 1.8667395320095367e-05, |
| "loss": 0.0652, |
| "num_input_tokens_seen": 2113928, |
| "step": 5150 |
| }, |
| { |
| "epoch": 6.2409200968523, |
| "grad_norm": 0.3844600319862366, |
| "learning_rate": 1.8616307549544113e-05, |
| "loss": 0.1524, |
| "num_input_tokens_seen": 2115944, |
| "step": 5155 |
| }, |
| { |
| "epoch": 6.246973365617434, |
| "grad_norm": 8.31705093383789, |
| "learning_rate": 1.85652482804087e-05, |
| "loss": 0.1151, |
| "num_input_tokens_seen": 2118120, |
| "step": 5160 |
| }, |
| { |
| "epoch": 6.253026634382566, |
| "grad_norm": 2.3616673946380615, |
| "learning_rate": 1.85142177406546e-05, |
| "loss": 0.1494, |
| "num_input_tokens_seen": 2120136, |
| "step": 5165 |
| }, |
| { |
| "epoch": 6.2590799031477, |
| "grad_norm": 3.0859901905059814, |
| "learning_rate": 1.8463216158119015e-05, |
| "loss": 0.1174, |
| "num_input_tokens_seen": 2122184, |
| "step": 5170 |
| }, |
| { |
| "epoch": 6.265133171912833, |
| "grad_norm": 0.7617553472518921, |
| "learning_rate": 1.8412243760509867e-05, |
| "loss": 0.1346, |
| "num_input_tokens_seen": 2124200, |
| "step": 5175 |
| }, |
| { |
| "epoch": 6.271186440677966, |
| "grad_norm": 6.6624298095703125, |
| "learning_rate": 1.8361300775404765e-05, |
| "loss": 0.0971, |
| "num_input_tokens_seen": 2126280, |
| "step": 5180 |
| }, |
| { |
| "epoch": 6.2772397094431, |
| "grad_norm": 3.2902045249938965, |
| "learning_rate": 1.8310387430250014e-05, |
| "loss": 0.0593, |
| "num_input_tokens_seen": 2128360, |
| "step": 5185 |
| }, |
| { |
| "epoch": 6.283292978208232, |
| "grad_norm": 0.7124584913253784, |
| "learning_rate": 1.825950395235956e-05, |
| "loss": 0.1357, |
| "num_input_tokens_seen": 2130248, |
| "step": 5190 |
| }, |
| { |
| "epoch": 6.289346246973365, |
| "grad_norm": 2.4646220207214355, |
| "learning_rate": 1.8208650568914033e-05, |
| "loss": 0.1265, |
| "num_input_tokens_seen": 2132200, |
| "step": 5195 |
| }, |
| { |
| "epoch": 6.295399515738499, |
| "grad_norm": 4.314565181732178, |
| "learning_rate": 1.815782750695967e-05, |
| "loss": 0.1629, |
| "num_input_tokens_seen": 2134216, |
| "step": 5200 |
| }, |
| { |
| "epoch": 6.301452784503632, |
| "grad_norm": 2.004688262939453, |
| "learning_rate": 1.810703499340735e-05, |
| "loss": 0.0434, |
| "num_input_tokens_seen": 2136392, |
| "step": 5205 |
| }, |
| { |
| "epoch": 6.3075060532687655, |
| "grad_norm": 2.316528558731079, |
| "learning_rate": 1.8056273255031552e-05, |
| "loss": 0.1194, |
| "num_input_tokens_seen": 2138504, |
| "step": 5210 |
| }, |
| { |
| "epoch": 6.313559322033898, |
| "grad_norm": 2.124305248260498, |
| "learning_rate": 1.8005542518469366e-05, |
| "loss": 0.0821, |
| "num_input_tokens_seen": 2140616, |
| "step": 5215 |
| }, |
| { |
| "epoch": 6.319612590799031, |
| "grad_norm": 1.2579299211502075, |
| "learning_rate": 1.7954843010219446e-05, |
| "loss": 0.1001, |
| "num_input_tokens_seen": 2142664, |
| "step": 5220 |
| }, |
| { |
| "epoch": 6.325665859564165, |
| "grad_norm": 4.945680141448975, |
| "learning_rate": 1.790417495664103e-05, |
| "loss": 0.0734, |
| "num_input_tokens_seen": 2144744, |
| "step": 5225 |
| }, |
| { |
| "epoch": 6.331719128329298, |
| "grad_norm": 5.6669206619262695, |
| "learning_rate": 1.785353858395292e-05, |
| "loss": 0.3636, |
| "num_input_tokens_seen": 2146760, |
| "step": 5230 |
| }, |
| { |
| "epoch": 6.337772397094431, |
| "grad_norm": 5.804713726043701, |
| "learning_rate": 1.7802934118232482e-05, |
| "loss": 0.0949, |
| "num_input_tokens_seen": 2148904, |
| "step": 5235 |
| }, |
| { |
| "epoch": 6.343825665859564, |
| "grad_norm": 1.7007763385772705, |
| "learning_rate": 1.775236178541461e-05, |
| "loss": 0.0563, |
| "num_input_tokens_seen": 2151080, |
| "step": 5240 |
| }, |
| { |
| "epoch": 6.349878934624697, |
| "grad_norm": 9.71132755279541, |
| "learning_rate": 1.7701821811290743e-05, |
| "loss": 0.1433, |
| "num_input_tokens_seen": 2153032, |
| "step": 5245 |
| }, |
| { |
| "epoch": 6.3559322033898304, |
| "grad_norm": 4.293256759643555, |
| "learning_rate": 1.7651314421507843e-05, |
| "loss": 0.1557, |
| "num_input_tokens_seen": 2155080, |
| "step": 5250 |
| }, |
| { |
| "epoch": 6.361985472154964, |
| "grad_norm": 5.381481647491455, |
| "learning_rate": 1.7600839841567395e-05, |
| "loss": 0.18, |
| "num_input_tokens_seen": 2157064, |
| "step": 5255 |
| }, |
| { |
| "epoch": 6.368038740920097, |
| "grad_norm": 0.4548739790916443, |
| "learning_rate": 1.7550398296824395e-05, |
| "loss": 0.1216, |
| "num_input_tokens_seen": 2159208, |
| "step": 5260 |
| }, |
| { |
| "epoch": 6.37409200968523, |
| "grad_norm": 6.4153923988342285, |
| "learning_rate": 1.749999001248635e-05, |
| "loss": 0.0475, |
| "num_input_tokens_seen": 2161384, |
| "step": 5265 |
| }, |
| { |
| "epoch": 6.380145278450363, |
| "grad_norm": 2.944775342941284, |
| "learning_rate": 1.7449615213612264e-05, |
| "loss": 0.1253, |
| "num_input_tokens_seen": 2163432, |
| "step": 5270 |
| }, |
| { |
| "epoch": 6.386198547215496, |
| "grad_norm": 1.4213374853134155, |
| "learning_rate": 1.7399274125111635e-05, |
| "loss": 0.0373, |
| "num_input_tokens_seen": 2165640, |
| "step": 5275 |
| }, |
| { |
| "epoch": 6.39225181598063, |
| "grad_norm": 4.871456146240234, |
| "learning_rate": 1.7348966971743465e-05, |
| "loss": 0.0991, |
| "num_input_tokens_seen": 2167656, |
| "step": 5280 |
| }, |
| { |
| "epoch": 6.398305084745763, |
| "grad_norm": 1.1972601413726807, |
| "learning_rate": 1.729869397811523e-05, |
| "loss": 0.0719, |
| "num_input_tokens_seen": 2169672, |
| "step": 5285 |
| }, |
| { |
| "epoch": 6.404358353510895, |
| "grad_norm": 3.45843768119812, |
| "learning_rate": 1.72484553686819e-05, |
| "loss": 0.0967, |
| "num_input_tokens_seen": 2171592, |
| "step": 5290 |
| }, |
| { |
| "epoch": 6.410411622276029, |
| "grad_norm": 2.6961007118225098, |
| "learning_rate": 1.719825136774494e-05, |
| "loss": 0.047, |
| "num_input_tokens_seen": 2173576, |
| "step": 5295 |
| }, |
| { |
| "epoch": 6.416464891041162, |
| "grad_norm": 0.6391634345054626, |
| "learning_rate": 1.714808219945129e-05, |
| "loss": 0.0287, |
| "num_input_tokens_seen": 2175592, |
| "step": 5300 |
| }, |
| { |
| "epoch": 6.4225181598062955, |
| "grad_norm": 0.5544232130050659, |
| "learning_rate": 1.709794808779234e-05, |
| "loss": 0.1309, |
| "num_input_tokens_seen": 2177512, |
| "step": 5305 |
| }, |
| { |
| "epoch": 6.428571428571429, |
| "grad_norm": 5.888014316558838, |
| "learning_rate": 1.704784925660301e-05, |
| "loss": 0.0952, |
| "num_input_tokens_seen": 2179560, |
| "step": 5310 |
| }, |
| { |
| "epoch": 6.434624697336561, |
| "grad_norm": 1.9635401964187622, |
| "learning_rate": 1.699778592956069e-05, |
| "loss": 0.1128, |
| "num_input_tokens_seen": 2181608, |
| "step": 5315 |
| }, |
| { |
| "epoch": 6.440677966101695, |
| "grad_norm": 6.4271240234375, |
| "learning_rate": 1.6947758330184226e-05, |
| "loss": 0.0603, |
| "num_input_tokens_seen": 2183656, |
| "step": 5320 |
| }, |
| { |
| "epoch": 6.446731234866828, |
| "grad_norm": 0.48759642243385315, |
| "learning_rate": 1.689776668183299e-05, |
| "loss": 0.0778, |
| "num_input_tokens_seen": 2185576, |
| "step": 5325 |
| }, |
| { |
| "epoch": 6.452784503631961, |
| "grad_norm": 6.219998836517334, |
| "learning_rate": 1.6847811207705813e-05, |
| "loss": 0.0543, |
| "num_input_tokens_seen": 2187592, |
| "step": 5330 |
| }, |
| { |
| "epoch": 6.458837772397095, |
| "grad_norm": 0.6584652066230774, |
| "learning_rate": 1.6797892130840036e-05, |
| "loss": 0.0478, |
| "num_input_tokens_seen": 2189544, |
| "step": 5335 |
| }, |
| { |
| "epoch": 6.464891041162228, |
| "grad_norm": 0.11968863755464554, |
| "learning_rate": 1.6748009674110477e-05, |
| "loss": 0.0868, |
| "num_input_tokens_seen": 2191496, |
| "step": 5340 |
| }, |
| { |
| "epoch": 6.4709443099273605, |
| "grad_norm": 0.749453604221344, |
| "learning_rate": 1.669816406022848e-05, |
| "loss": 0.0866, |
| "num_input_tokens_seen": 2193416, |
| "step": 5345 |
| }, |
| { |
| "epoch": 6.476997578692494, |
| "grad_norm": 4.262302398681641, |
| "learning_rate": 1.6648355511740876e-05, |
| "loss": 0.0848, |
| "num_input_tokens_seen": 2195432, |
| "step": 5350 |
| }, |
| { |
| "epoch": 6.483050847457627, |
| "grad_norm": 2.831707000732422, |
| "learning_rate": 1.659858425102902e-05, |
| "loss": 0.0165, |
| "num_input_tokens_seen": 2197288, |
| "step": 5355 |
| }, |
| { |
| "epoch": 6.4891041162227605, |
| "grad_norm": 7.086419105529785, |
| "learning_rate": 1.6548850500307772e-05, |
| "loss": 0.0853, |
| "num_input_tokens_seen": 2199368, |
| "step": 5360 |
| }, |
| { |
| "epoch": 6.495157384987894, |
| "grad_norm": 2.674248695373535, |
| "learning_rate": 1.649915448162455e-05, |
| "loss": 0.0217, |
| "num_input_tokens_seen": 2201640, |
| "step": 5365 |
| }, |
| { |
| "epoch": 6.5, |
| "eval_loss": 0.15626245737075806, |
| "eval_runtime": 4.5725, |
| "eval_samples_per_second": 80.262, |
| "eval_steps_per_second": 20.12, |
| "num_input_tokens_seen": 2203208, |
| "step": 5369 |
| }, |
| { |
| "epoch": 6.501210653753026, |
| "grad_norm": 0.10960067063570023, |
| "learning_rate": 1.6449496416858284e-05, |
| "loss": 0.0489, |
| "num_input_tokens_seen": 2203592, |
| "step": 5370 |
| }, |
| { |
| "epoch": 6.50726392251816, |
| "grad_norm": 0.3896951377391815, |
| "learning_rate": 1.6399876527718456e-05, |
| "loss": 0.1401, |
| "num_input_tokens_seen": 2205640, |
| "step": 5375 |
| }, |
| { |
| "epoch": 6.513317191283293, |
| "grad_norm": 4.460085391998291, |
| "learning_rate": 1.6350295035744094e-05, |
| "loss": 0.1424, |
| "num_input_tokens_seen": 2207752, |
| "step": 5380 |
| }, |
| { |
| "epoch": 6.519370460048426, |
| "grad_norm": 0.08996804803609848, |
| "learning_rate": 1.6300752162302822e-05, |
| "loss": 0.0192, |
| "num_input_tokens_seen": 2209864, |
| "step": 5385 |
| }, |
| { |
| "epoch": 6.52542372881356, |
| "grad_norm": 10.497203826904297, |
| "learning_rate": 1.625124812858982e-05, |
| "loss": 0.1851, |
| "num_input_tokens_seen": 2211944, |
| "step": 5390 |
| }, |
| { |
| "epoch": 6.531476997578692, |
| "grad_norm": 4.926606178283691, |
| "learning_rate": 1.6201783155626862e-05, |
| "loss": 0.113, |
| "num_input_tokens_seen": 2213928, |
| "step": 5395 |
| }, |
| { |
| "epoch": 6.5375302663438255, |
| "grad_norm": 0.7235932946205139, |
| "learning_rate": 1.615235746426133e-05, |
| "loss": 0.0963, |
| "num_input_tokens_seen": 2215944, |
| "step": 5400 |
| }, |
| { |
| "epoch": 6.543583535108959, |
| "grad_norm": 3.8486897945404053, |
| "learning_rate": 1.6102971275165228e-05, |
| "loss": 0.0764, |
| "num_input_tokens_seen": 2217960, |
| "step": 5405 |
| }, |
| { |
| "epoch": 6.549636803874092, |
| "grad_norm": 3.5995168685913086, |
| "learning_rate": 1.6053624808834188e-05, |
| "loss": 0.1895, |
| "num_input_tokens_seen": 2219976, |
| "step": 5410 |
| }, |
| { |
| "epoch": 6.5556900726392255, |
| "grad_norm": 5.618495941162109, |
| "learning_rate": 1.6004318285586497e-05, |
| "loss": 0.1285, |
| "num_input_tokens_seen": 2221992, |
| "step": 5415 |
| }, |
| { |
| "epoch": 6.561743341404358, |
| "grad_norm": 4.392757415771484, |
| "learning_rate": 1.5955051925562092e-05, |
| "loss": 0.0823, |
| "num_input_tokens_seen": 2223976, |
| "step": 5420 |
| }, |
| { |
| "epoch": 6.567796610169491, |
| "grad_norm": 1.3197625875473022, |
| "learning_rate": 1.590582594872162e-05, |
| "loss": 0.0533, |
| "num_input_tokens_seen": 2226088, |
| "step": 5425 |
| }, |
| { |
| "epoch": 6.573849878934625, |
| "grad_norm": 4.43609094619751, |
| "learning_rate": 1.585664057484539e-05, |
| "loss": 0.1339, |
| "num_input_tokens_seen": 2228008, |
| "step": 5430 |
| }, |
| { |
| "epoch": 6.579903147699758, |
| "grad_norm": 0.7666565775871277, |
| "learning_rate": 1.5807496023532472e-05, |
| "loss": 0.2157, |
| "num_input_tokens_seen": 2229928, |
| "step": 5435 |
| }, |
| { |
| "epoch": 6.585956416464891, |
| "grad_norm": 0.46131646633148193, |
| "learning_rate": 1.5758392514199644e-05, |
| "loss": 0.0424, |
| "num_input_tokens_seen": 2231912, |
| "step": 5440 |
| }, |
| { |
| "epoch": 6.592009685230024, |
| "grad_norm": 4.645249843597412, |
| "learning_rate": 1.5709330266080446e-05, |
| "loss": 0.0594, |
| "num_input_tokens_seen": 2233992, |
| "step": 5445 |
| }, |
| { |
| "epoch": 6.598062953995157, |
| "grad_norm": 0.14227555692195892, |
| "learning_rate": 1.5660309498224225e-05, |
| "loss": 0.0124, |
| "num_input_tokens_seen": 2235976, |
| "step": 5450 |
| }, |
| { |
| "epoch": 6.6041162227602905, |
| "grad_norm": 1.6020721197128296, |
| "learning_rate": 1.5611330429495096e-05, |
| "loss": 0.0878, |
| "num_input_tokens_seen": 2238088, |
| "step": 5455 |
| }, |
| { |
| "epoch": 6.610169491525424, |
| "grad_norm": 10.044299125671387, |
| "learning_rate": 1.556239327857101e-05, |
| "loss": 0.1516, |
| "num_input_tokens_seen": 2240136, |
| "step": 5460 |
| }, |
| { |
| "epoch": 6.616222760290557, |
| "grad_norm": 0.4725329875946045, |
| "learning_rate": 1.551349826394278e-05, |
| "loss": 0.173, |
| "num_input_tokens_seen": 2242280, |
| "step": 5465 |
| }, |
| { |
| "epoch": 6.622276029055691, |
| "grad_norm": 5.6281890869140625, |
| "learning_rate": 1.5464645603913066e-05, |
| "loss": 0.1576, |
| "num_input_tokens_seen": 2244360, |
| "step": 5470 |
| }, |
| { |
| "epoch": 6.628329297820823, |
| "grad_norm": 3.5972378253936768, |
| "learning_rate": 1.5415835516595465e-05, |
| "loss": 0.0579, |
| "num_input_tokens_seen": 2246536, |
| "step": 5475 |
| }, |
| { |
| "epoch": 6.634382566585956, |
| "grad_norm": 1.099054217338562, |
| "learning_rate": 1.5367068219913456e-05, |
| "loss": 0.1159, |
| "num_input_tokens_seen": 2248616, |
| "step": 5480 |
| }, |
| { |
| "epoch": 6.64043583535109, |
| "grad_norm": 0.566524863243103, |
| "learning_rate": 1.5318343931599503e-05, |
| "loss": 0.0055, |
| "num_input_tokens_seen": 2250664, |
| "step": 5485 |
| }, |
| { |
| "epoch": 6.646489104116223, |
| "grad_norm": 6.453625202178955, |
| "learning_rate": 1.5269662869194036e-05, |
| "loss": 0.0432, |
| "num_input_tokens_seen": 2252808, |
| "step": 5490 |
| }, |
| { |
| "epoch": 6.652542372881356, |
| "grad_norm": 5.013184070587158, |
| "learning_rate": 1.5221025250044486e-05, |
| "loss": 0.0926, |
| "num_input_tokens_seen": 2254984, |
| "step": 5495 |
| }, |
| { |
| "epoch": 6.658595641646489, |
| "grad_norm": 3.822239875793457, |
| "learning_rate": 1.517243129130433e-05, |
| "loss": 0.0233, |
| "num_input_tokens_seen": 2257064, |
| "step": 5500 |
| }, |
| { |
| "epoch": 6.664648910411622, |
| "grad_norm": 6.671678066253662, |
| "learning_rate": 1.512388120993212e-05, |
| "loss": 0.092, |
| "num_input_tokens_seen": 2259112, |
| "step": 5505 |
| }, |
| { |
| "epoch": 6.670702179176756, |
| "grad_norm": 0.08668724447488785, |
| "learning_rate": 1.5075375222690496e-05, |
| "loss": 0.0619, |
| "num_input_tokens_seen": 2261224, |
| "step": 5510 |
| }, |
| { |
| "epoch": 6.676755447941889, |
| "grad_norm": 3.928685188293457, |
| "learning_rate": 1.5026913546145232e-05, |
| "loss": 0.1003, |
| "num_input_tokens_seen": 2263400, |
| "step": 5515 |
| }, |
| { |
| "epoch": 6.682808716707022, |
| "grad_norm": 0.28091078996658325, |
| "learning_rate": 1.4978496396664279e-05, |
| "loss": 0.0754, |
| "num_input_tokens_seen": 2265416, |
| "step": 5520 |
| }, |
| { |
| "epoch": 6.688861985472155, |
| "grad_norm": 0.40043458342552185, |
| "learning_rate": 1.4930123990416766e-05, |
| "loss": 0.122, |
| "num_input_tokens_seen": 2267560, |
| "step": 5525 |
| }, |
| { |
| "epoch": 6.694915254237288, |
| "grad_norm": 0.0906248465180397, |
| "learning_rate": 1.4881796543372079e-05, |
| "loss": 0.0766, |
| "num_input_tokens_seen": 2269544, |
| "step": 5530 |
| }, |
| { |
| "epoch": 6.700968523002421, |
| "grad_norm": 5.206305027008057, |
| "learning_rate": 1.4833514271298859e-05, |
| "loss": 0.0786, |
| "num_input_tokens_seen": 2271720, |
| "step": 5535 |
| }, |
| { |
| "epoch": 6.707021791767555, |
| "grad_norm": 1.6504778861999512, |
| "learning_rate": 1.4785277389764046e-05, |
| "loss": 0.0286, |
| "num_input_tokens_seen": 2273928, |
| "step": 5540 |
| }, |
| { |
| "epoch": 6.713075060532688, |
| "grad_norm": 7.289839267730713, |
| "learning_rate": 1.4737086114131943e-05, |
| "loss": 0.0607, |
| "num_input_tokens_seen": 2275912, |
| "step": 5545 |
| }, |
| { |
| "epoch": 6.719128329297821, |
| "grad_norm": 3.971864938735962, |
| "learning_rate": 1.4688940659563225e-05, |
| "loss": 0.0885, |
| "num_input_tokens_seen": 2278024, |
| "step": 5550 |
| }, |
| { |
| "epoch": 6.725181598062954, |
| "grad_norm": 0.6193917393684387, |
| "learning_rate": 1.4640841241013995e-05, |
| "loss": 0.007, |
| "num_input_tokens_seen": 2280136, |
| "step": 5555 |
| }, |
| { |
| "epoch": 6.731234866828087, |
| "grad_norm": 1.3996975421905518, |
| "learning_rate": 1.4592788073234803e-05, |
| "loss": 0.0323, |
| "num_input_tokens_seen": 2282248, |
| "step": 5560 |
| }, |
| { |
| "epoch": 6.737288135593221, |
| "grad_norm": 0.15475653111934662, |
| "learning_rate": 1.4544781370769723e-05, |
| "loss": 0.0204, |
| "num_input_tokens_seen": 2284424, |
| "step": 5565 |
| }, |
| { |
| "epoch": 6.743341404358354, |
| "grad_norm": 0.561587929725647, |
| "learning_rate": 1.4496821347955359e-05, |
| "loss": 0.144, |
| "num_input_tokens_seen": 2286344, |
| "step": 5570 |
| }, |
| { |
| "epoch": 6.749394673123486, |
| "grad_norm": 0.6858986020088196, |
| "learning_rate": 1.444890821891991e-05, |
| "loss": 0.1286, |
| "num_input_tokens_seen": 2288456, |
| "step": 5575 |
| }, |
| { |
| "epoch": 6.75544794188862, |
| "grad_norm": 0.9666218161582947, |
| "learning_rate": 1.4401042197582193e-05, |
| "loss": 0.0445, |
| "num_input_tokens_seen": 2290312, |
| "step": 5580 |
| }, |
| { |
| "epoch": 6.761501210653753, |
| "grad_norm": 0.7301199436187744, |
| "learning_rate": 1.4353223497650731e-05, |
| "loss": 0.0131, |
| "num_input_tokens_seen": 2292392, |
| "step": 5585 |
| }, |
| { |
| "epoch": 6.767554479418886, |
| "grad_norm": 3.5780975818634033, |
| "learning_rate": 1.4305452332622748e-05, |
| "loss": 0.1459, |
| "num_input_tokens_seen": 2294472, |
| "step": 5590 |
| }, |
| { |
| "epoch": 6.77360774818402, |
| "grad_norm": 5.3841938972473145, |
| "learning_rate": 1.4257728915783244e-05, |
| "loss": 0.0683, |
| "num_input_tokens_seen": 2296616, |
| "step": 5595 |
| }, |
| { |
| "epoch": 6.779661016949152, |
| "grad_norm": 2.9884018898010254, |
| "learning_rate": 1.4210053460204023e-05, |
| "loss": 0.1095, |
| "num_input_tokens_seen": 2298856, |
| "step": 5600 |
| }, |
| { |
| "epoch": 6.785714285714286, |
| "grad_norm": 5.287160396575928, |
| "learning_rate": 1.4162426178742788e-05, |
| "loss": 0.2111, |
| "num_input_tokens_seen": 2301064, |
| "step": 5605 |
| }, |
| { |
| "epoch": 6.791767554479419, |
| "grad_norm": 5.867886543273926, |
| "learning_rate": 1.4114847284042132e-05, |
| "loss": 0.2521, |
| "num_input_tokens_seen": 2303208, |
| "step": 5610 |
| }, |
| { |
| "epoch": 6.797820823244552, |
| "grad_norm": 6.757856845855713, |
| "learning_rate": 1.4067316988528617e-05, |
| "loss": 0.0968, |
| "num_input_tokens_seen": 2305288, |
| "step": 5615 |
| }, |
| { |
| "epoch": 6.803874092009686, |
| "grad_norm": 3.8400421142578125, |
| "learning_rate": 1.4019835504411827e-05, |
| "loss": 0.0542, |
| "num_input_tokens_seen": 2307304, |
| "step": 5620 |
| }, |
| { |
| "epoch": 6.809927360774818, |
| "grad_norm": 0.3626413643360138, |
| "learning_rate": 1.3972403043683419e-05, |
| "loss": 0.0524, |
| "num_input_tokens_seen": 2309448, |
| "step": 5625 |
| }, |
| { |
| "epoch": 6.815980629539951, |
| "grad_norm": 1.7563663721084595, |
| "learning_rate": 1.3925019818116164e-05, |
| "loss": 0.1005, |
| "num_input_tokens_seen": 2311368, |
| "step": 5630 |
| }, |
| { |
| "epoch": 6.822033898305085, |
| "grad_norm": 7.347732067108154, |
| "learning_rate": 1.387768603926302e-05, |
| "loss": 0.2338, |
| "num_input_tokens_seen": 2313448, |
| "step": 5635 |
| }, |
| { |
| "epoch": 6.828087167070218, |
| "grad_norm": 2.2824957370758057, |
| "learning_rate": 1.383040191845619e-05, |
| "loss": 0.176, |
| "num_input_tokens_seen": 2315464, |
| "step": 5640 |
| }, |
| { |
| "epoch": 6.8341404358353515, |
| "grad_norm": 5.796999454498291, |
| "learning_rate": 1.378316766680615e-05, |
| "loss": 0.0912, |
| "num_input_tokens_seen": 2317480, |
| "step": 5645 |
| }, |
| { |
| "epoch": 6.840193704600484, |
| "grad_norm": 2.5402140617370605, |
| "learning_rate": 1.373598349520073e-05, |
| "loss": 0.1809, |
| "num_input_tokens_seen": 2319432, |
| "step": 5650 |
| }, |
| { |
| "epoch": 6.846246973365617, |
| "grad_norm": 4.791908264160156, |
| "learning_rate": 1.3688849614304164e-05, |
| "loss": 0.2282, |
| "num_input_tokens_seen": 2321512, |
| "step": 5655 |
| }, |
| { |
| "epoch": 6.852300242130751, |
| "grad_norm": 4.897888660430908, |
| "learning_rate": 1.3641766234556146e-05, |
| "loss": 0.1905, |
| "num_input_tokens_seen": 2323560, |
| "step": 5660 |
| }, |
| { |
| "epoch": 6.858353510895884, |
| "grad_norm": 3.5213470458984375, |
| "learning_rate": 1.3594733566170926e-05, |
| "loss": 0.0668, |
| "num_input_tokens_seen": 2325576, |
| "step": 5665 |
| }, |
| { |
| "epoch": 6.864406779661017, |
| "grad_norm": 3.2041327953338623, |
| "learning_rate": 1.3547751819136309e-05, |
| "loss": 0.0957, |
| "num_input_tokens_seen": 2327496, |
| "step": 5670 |
| }, |
| { |
| "epoch": 6.87046004842615, |
| "grad_norm": 2.667874813079834, |
| "learning_rate": 1.350082120321276e-05, |
| "loss": 0.0558, |
| "num_input_tokens_seen": 2329576, |
| "step": 5675 |
| }, |
| { |
| "epoch": 6.876513317191283, |
| "grad_norm": 5.709193706512451, |
| "learning_rate": 1.3453941927932456e-05, |
| "loss": 0.2192, |
| "num_input_tokens_seen": 2331656, |
| "step": 5680 |
| }, |
| { |
| "epoch": 6.8825665859564165, |
| "grad_norm": 5.8245768547058105, |
| "learning_rate": 1.3407114202598369e-05, |
| "loss": 0.0549, |
| "num_input_tokens_seen": 2333800, |
| "step": 5685 |
| }, |
| { |
| "epoch": 6.88861985472155, |
| "grad_norm": 5.625098705291748, |
| "learning_rate": 1.3360338236283295e-05, |
| "loss": 0.0654, |
| "num_input_tokens_seen": 2336008, |
| "step": 5690 |
| }, |
| { |
| "epoch": 6.894673123486683, |
| "grad_norm": 9.947223663330078, |
| "learning_rate": 1.3313614237828948e-05, |
| "loss": 0.1191, |
| "num_input_tokens_seen": 2337928, |
| "step": 5695 |
| }, |
| { |
| "epoch": 6.900726392251816, |
| "grad_norm": 3.8002381324768066, |
| "learning_rate": 1.3266942415845018e-05, |
| "loss": 0.189, |
| "num_input_tokens_seen": 2340008, |
| "step": 5700 |
| }, |
| { |
| "epoch": 6.906779661016949, |
| "grad_norm": 0.2843150198459625, |
| "learning_rate": 1.3220322978708242e-05, |
| "loss": 0.2774, |
| "num_input_tokens_seen": 2342024, |
| "step": 5705 |
| }, |
| { |
| "epoch": 6.912832929782082, |
| "grad_norm": 3.9901978969573975, |
| "learning_rate": 1.317375613456147e-05, |
| "loss": 0.0321, |
| "num_input_tokens_seen": 2343976, |
| "step": 5710 |
| }, |
| { |
| "epoch": 6.918886198547216, |
| "grad_norm": 5.7010416984558105, |
| "learning_rate": 1.3127242091312752e-05, |
| "loss": 0.0905, |
| "num_input_tokens_seen": 2345928, |
| "step": 5715 |
| }, |
| { |
| "epoch": 6.924939467312349, |
| "grad_norm": 9.902931213378906, |
| "learning_rate": 1.3080781056634373e-05, |
| "loss": 0.147, |
| "num_input_tokens_seen": 2347976, |
| "step": 5720 |
| }, |
| { |
| "epoch": 6.9309927360774815, |
| "grad_norm": 5.970206260681152, |
| "learning_rate": 1.3034373237961983e-05, |
| "loss": 0.1639, |
| "num_input_tokens_seen": 2349992, |
| "step": 5725 |
| }, |
| { |
| "epoch": 6.937046004842615, |
| "grad_norm": 9.21063232421875, |
| "learning_rate": 1.2988018842493604e-05, |
| "loss": 0.1798, |
| "num_input_tokens_seen": 2351976, |
| "step": 5730 |
| }, |
| { |
| "epoch": 6.943099273607748, |
| "grad_norm": 5.441684246063232, |
| "learning_rate": 1.2941718077188758e-05, |
| "loss": 0.0791, |
| "num_input_tokens_seen": 2353992, |
| "step": 5735 |
| }, |
| { |
| "epoch": 6.9491525423728815, |
| "grad_norm": 5.263315677642822, |
| "learning_rate": 1.2895471148767508e-05, |
| "loss": 0.2302, |
| "num_input_tokens_seen": 2355976, |
| "step": 5740 |
| }, |
| { |
| "epoch": 6.955205811138015, |
| "grad_norm": 0.33733436465263367, |
| "learning_rate": 1.2849278263709572e-05, |
| "loss": 0.1627, |
| "num_input_tokens_seen": 2358152, |
| "step": 5745 |
| }, |
| { |
| "epoch": 6.961259079903147, |
| "grad_norm": 2.2974305152893066, |
| "learning_rate": 1.2803139628253364e-05, |
| "loss": 0.117, |
| "num_input_tokens_seen": 2360040, |
| "step": 5750 |
| }, |
| { |
| "epoch": 6.967312348668281, |
| "grad_norm": 2.7991981506347656, |
| "learning_rate": 1.2757055448395092e-05, |
| "loss": 0.0867, |
| "num_input_tokens_seen": 2362056, |
| "step": 5755 |
| }, |
| { |
| "epoch": 6.973365617433414, |
| "grad_norm": 5.492253303527832, |
| "learning_rate": 1.271102592988782e-05, |
| "loss": 0.1119, |
| "num_input_tokens_seen": 2364008, |
| "step": 5760 |
| }, |
| { |
| "epoch": 6.979418886198547, |
| "grad_norm": 0.22008445858955383, |
| "learning_rate": 1.2665051278240602e-05, |
| "loss": 0.066, |
| "num_input_tokens_seen": 2366056, |
| "step": 5765 |
| }, |
| { |
| "epoch": 6.985472154963681, |
| "grad_norm": 0.251720666885376, |
| "learning_rate": 1.2619131698717504e-05, |
| "loss": 0.1107, |
| "num_input_tokens_seen": 2368072, |
| "step": 5770 |
| }, |
| { |
| "epoch": 6.991525423728813, |
| "grad_norm": 4.450534820556641, |
| "learning_rate": 1.2573267396336686e-05, |
| "loss": 0.1177, |
| "num_input_tokens_seen": 2370024, |
| "step": 5775 |
| }, |
| { |
| "epoch": 6.9975786924939465, |
| "grad_norm": 0.8103474378585815, |
| "learning_rate": 1.2527458575869539e-05, |
| "loss": 0.0205, |
| "num_input_tokens_seen": 2372008, |
| "step": 5780 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_loss": 0.15040120482444763, |
| "eval_runtime": 4.5759, |
| "eval_samples_per_second": 80.204, |
| "eval_steps_per_second": 20.106, |
| "num_input_tokens_seen": 2372464, |
| "step": 5782 |
| }, |
| { |
| "epoch": 7.00363196125908, |
| "grad_norm": 4.991612434387207, |
| "learning_rate": 1.2481705441839756e-05, |
| "loss": 0.4001, |
| "num_input_tokens_seen": 2373648, |
| "step": 5785 |
| }, |
| { |
| "epoch": 7.009685230024213, |
| "grad_norm": 0.7985994815826416, |
| "learning_rate": 1.2436008198522376e-05, |
| "loss": 0.0437, |
| "num_input_tokens_seen": 2375696, |
| "step": 5790 |
| }, |
| { |
| "epoch": 7.0157384987893465, |
| "grad_norm": 2.3747811317443848, |
| "learning_rate": 1.2390367049942916e-05, |
| "loss": 0.0563, |
| "num_input_tokens_seen": 2377872, |
| "step": 5795 |
| }, |
| { |
| "epoch": 7.021791767554479, |
| "grad_norm": 6.454826831817627, |
| "learning_rate": 1.2344782199876431e-05, |
| "loss": 0.0908, |
| "num_input_tokens_seen": 2379792, |
| "step": 5800 |
| }, |
| { |
| "epoch": 7.027845036319612, |
| "grad_norm": 0.03636226803064346, |
| "learning_rate": 1.2299253851846651e-05, |
| "loss": 0.0884, |
| "num_input_tokens_seen": 2381744, |
| "step": 5805 |
| }, |
| { |
| "epoch": 7.033898305084746, |
| "grad_norm": 0.8091753721237183, |
| "learning_rate": 1.2253782209125012e-05, |
| "loss": 0.1468, |
| "num_input_tokens_seen": 2383664, |
| "step": 5810 |
| }, |
| { |
| "epoch": 7.039951573849879, |
| "grad_norm": 1.8999519348144531, |
| "learning_rate": 1.220836747472978e-05, |
| "loss": 0.0527, |
| "num_input_tokens_seen": 2385744, |
| "step": 5815 |
| }, |
| { |
| "epoch": 7.046004842615012, |
| "grad_norm": 0.8117446899414062, |
| "learning_rate": 1.2163009851425137e-05, |
| "loss": 0.0384, |
| "num_input_tokens_seen": 2387920, |
| "step": 5820 |
| }, |
| { |
| "epoch": 7.052058111380146, |
| "grad_norm": 0.4487296938896179, |
| "learning_rate": 1.2117709541720306e-05, |
| "loss": 0.0764, |
| "num_input_tokens_seen": 2390000, |
| "step": 5825 |
| }, |
| { |
| "epoch": 7.058111380145278, |
| "grad_norm": 2.3434858322143555, |
| "learning_rate": 1.2072466747868597e-05, |
| "loss": 0.1071, |
| "num_input_tokens_seen": 2392016, |
| "step": 5830 |
| }, |
| { |
| "epoch": 7.0641646489104115, |
| "grad_norm": 7.249058723449707, |
| "learning_rate": 1.2027281671866531e-05, |
| "loss": 0.0572, |
| "num_input_tokens_seen": 2394032, |
| "step": 5835 |
| }, |
| { |
| "epoch": 7.070217917675545, |
| "grad_norm": 0.018748486414551735, |
| "learning_rate": 1.198215451545293e-05, |
| "loss": 0.1064, |
| "num_input_tokens_seen": 2395888, |
| "step": 5840 |
| }, |
| { |
| "epoch": 7.076271186440678, |
| "grad_norm": 4.1508564949035645, |
| "learning_rate": 1.193708548010804e-05, |
| "loss": 0.0788, |
| "num_input_tokens_seen": 2398032, |
| "step": 5845 |
| }, |
| { |
| "epoch": 7.0823244552058116, |
| "grad_norm": 0.01983875036239624, |
| "learning_rate": 1.1892074767052611e-05, |
| "loss": 0.0342, |
| "num_input_tokens_seen": 2400016, |
| "step": 5850 |
| }, |
| { |
| "epoch": 7.088377723970944, |
| "grad_norm": 5.080287456512451, |
| "learning_rate": 1.1847122577246964e-05, |
| "loss": 0.0491, |
| "num_input_tokens_seen": 2402032, |
| "step": 5855 |
| }, |
| { |
| "epoch": 7.094430992736077, |
| "grad_norm": 2.0395522117614746, |
| "learning_rate": 1.1802229111390157e-05, |
| "loss": 0.0128, |
| "num_input_tokens_seen": 2404048, |
| "step": 5860 |
| }, |
| { |
| "epoch": 7.100484261501211, |
| "grad_norm": 5.25778341293335, |
| "learning_rate": 1.175739456991908e-05, |
| "loss": 0.1062, |
| "num_input_tokens_seen": 2406128, |
| "step": 5865 |
| }, |
| { |
| "epoch": 7.106537530266344, |
| "grad_norm": 6.711263656616211, |
| "learning_rate": 1.1712619153007517e-05, |
| "loss": 0.1401, |
| "num_input_tokens_seen": 2408112, |
| "step": 5870 |
| }, |
| { |
| "epoch": 7.112590799031477, |
| "grad_norm": 5.80398416519165, |
| "learning_rate": 1.166790306056528e-05, |
| "loss": 0.1134, |
| "num_input_tokens_seen": 2410160, |
| "step": 5875 |
| }, |
| { |
| "epoch": 7.11864406779661, |
| "grad_norm": 5.206965446472168, |
| "learning_rate": 1.1623246492237305e-05, |
| "loss": 0.0945, |
| "num_input_tokens_seen": 2412112, |
| "step": 5880 |
| }, |
| { |
| "epoch": 7.124697336561743, |
| "grad_norm": 0.28761962056159973, |
| "learning_rate": 1.1578649647402806e-05, |
| "loss": 0.0389, |
| "num_input_tokens_seen": 2414224, |
| "step": 5885 |
| }, |
| { |
| "epoch": 7.1307506053268765, |
| "grad_norm": 2.857328176498413, |
| "learning_rate": 1.1534112725174306e-05, |
| "loss": 0.0971, |
| "num_input_tokens_seen": 2416272, |
| "step": 5890 |
| }, |
| { |
| "epoch": 7.13680387409201, |
| "grad_norm": 2.5085062980651855, |
| "learning_rate": 1.1489635924396817e-05, |
| "loss": 0.0905, |
| "num_input_tokens_seen": 2418224, |
| "step": 5895 |
| }, |
| { |
| "epoch": 7.142857142857143, |
| "grad_norm": 0.11224648356437683, |
| "learning_rate": 1.1445219443646896e-05, |
| "loss": 0.0208, |
| "num_input_tokens_seen": 2420336, |
| "step": 5900 |
| }, |
| { |
| "epoch": 7.148910411622276, |
| "grad_norm": 0.478684663772583, |
| "learning_rate": 1.1400863481231833e-05, |
| "loss": 0.0516, |
| "num_input_tokens_seen": 2422288, |
| "step": 5905 |
| }, |
| { |
| "epoch": 7.154963680387409, |
| "grad_norm": 3.883321523666382, |
| "learning_rate": 1.1356568235188682e-05, |
| "loss": 0.0703, |
| "num_input_tokens_seen": 2424400, |
| "step": 5910 |
| }, |
| { |
| "epoch": 7.161016949152542, |
| "grad_norm": 5.41986083984375, |
| "learning_rate": 1.1312333903283435e-05, |
| "loss": 0.1168, |
| "num_input_tokens_seen": 2426384, |
| "step": 5915 |
| }, |
| { |
| "epoch": 7.167070217917676, |
| "grad_norm": 0.2709377110004425, |
| "learning_rate": 1.1268160683010096e-05, |
| "loss": 0.0523, |
| "num_input_tokens_seen": 2428400, |
| "step": 5920 |
| }, |
| { |
| "epoch": 7.173123486682809, |
| "grad_norm": 5.297135829925537, |
| "learning_rate": 1.122404877158986e-05, |
| "loss": 0.1166, |
| "num_input_tokens_seen": 2430416, |
| "step": 5925 |
| }, |
| { |
| "epoch": 7.1791767554479415, |
| "grad_norm": 0.9408299326896667, |
| "learning_rate": 1.1179998365970174e-05, |
| "loss": 0.1321, |
| "num_input_tokens_seen": 2432464, |
| "step": 5930 |
| }, |
| { |
| "epoch": 7.185230024213075, |
| "grad_norm": 6.506756782531738, |
| "learning_rate": 1.113600966282386e-05, |
| "loss": 0.0385, |
| "num_input_tokens_seen": 2434480, |
| "step": 5935 |
| }, |
| { |
| "epoch": 7.191283292978208, |
| "grad_norm": 0.5841665267944336, |
| "learning_rate": 1.1092082858548275e-05, |
| "loss": 0.0832, |
| "num_input_tokens_seen": 2436496, |
| "step": 5940 |
| }, |
| { |
| "epoch": 7.197336561743342, |
| "grad_norm": 0.013317148201167583, |
| "learning_rate": 1.1048218149264434e-05, |
| "loss": 0.0993, |
| "num_input_tokens_seen": 2438544, |
| "step": 5945 |
| }, |
| { |
| "epoch": 7.203389830508475, |
| "grad_norm": 0.01834205724298954, |
| "learning_rate": 1.1004415730816083e-05, |
| "loss": 0.0511, |
| "num_input_tokens_seen": 2440528, |
| "step": 5950 |
| }, |
| { |
| "epoch": 7.209443099273607, |
| "grad_norm": 7.901388645172119, |
| "learning_rate": 1.0960675798768871e-05, |
| "loss": 0.2747, |
| "num_input_tokens_seen": 2442576, |
| "step": 5955 |
| }, |
| { |
| "epoch": 7.215496368038741, |
| "grad_norm": 6.9650492668151855, |
| "learning_rate": 1.0916998548409449e-05, |
| "loss": 0.1191, |
| "num_input_tokens_seen": 2444560, |
| "step": 5960 |
| }, |
| { |
| "epoch": 7.221549636803874, |
| "grad_norm": 0.1719561368227005, |
| "learning_rate": 1.0873384174744641e-05, |
| "loss": 0.0347, |
| "num_input_tokens_seen": 2446704, |
| "step": 5965 |
| }, |
| { |
| "epoch": 7.227602905569007, |
| "grad_norm": 6.2616095542907715, |
| "learning_rate": 1.0829832872500523e-05, |
| "loss": 0.1151, |
| "num_input_tokens_seen": 2448720, |
| "step": 5970 |
| }, |
| { |
| "epoch": 7.233656174334141, |
| "grad_norm": 5.786017417907715, |
| "learning_rate": 1.078634483612157e-05, |
| "loss": 0.1013, |
| "num_input_tokens_seen": 2450832, |
| "step": 5975 |
| }, |
| { |
| "epoch": 7.239709443099273, |
| "grad_norm": 2.1609995365142822, |
| "learning_rate": 1.0742920259769792e-05, |
| "loss": 0.0251, |
| "num_input_tokens_seen": 2452752, |
| "step": 5980 |
| }, |
| { |
| "epoch": 7.245762711864407, |
| "grad_norm": 3.690556764602661, |
| "learning_rate": 1.06995593373239e-05, |
| "loss": 0.1575, |
| "num_input_tokens_seen": 2454832, |
| "step": 5985 |
| }, |
| { |
| "epoch": 7.25181598062954, |
| "grad_norm": 6.517083644866943, |
| "learning_rate": 1.0656262262378367e-05, |
| "loss": 0.0948, |
| "num_input_tokens_seen": 2456848, |
| "step": 5990 |
| }, |
| { |
| "epoch": 7.257869249394673, |
| "grad_norm": 5.877458095550537, |
| "learning_rate": 1.0613029228242627e-05, |
| "loss": 0.1154, |
| "num_input_tokens_seen": 2459024, |
| "step": 5995 |
| }, |
| { |
| "epoch": 7.263922518159807, |
| "grad_norm": 0.49661943316459656, |
| "learning_rate": 1.0569860427940179e-05, |
| "loss": 0.0497, |
| "num_input_tokens_seen": 2461168, |
| "step": 6000 |
| }, |
| { |
| "epoch": 7.269975786924939, |
| "grad_norm": 4.893890857696533, |
| "learning_rate": 1.0526756054207737e-05, |
| "loss": 0.022, |
| "num_input_tokens_seen": 2463120, |
| "step": 6005 |
| }, |
| { |
| "epoch": 7.276029055690072, |
| "grad_norm": 9.290037155151367, |
| "learning_rate": 1.0483716299494392e-05, |
| "loss": 0.1265, |
| "num_input_tokens_seen": 2465168, |
| "step": 6010 |
| }, |
| { |
| "epoch": 7.282082324455206, |
| "grad_norm": 5.3339314460754395, |
| "learning_rate": 1.044074135596069e-05, |
| "loss": 0.165, |
| "num_input_tokens_seen": 2467248, |
| "step": 6015 |
| }, |
| { |
| "epoch": 7.288135593220339, |
| "grad_norm": 0.101209856569767, |
| "learning_rate": 1.0397831415477823e-05, |
| "loss": 0.1604, |
| "num_input_tokens_seen": 2469200, |
| "step": 6020 |
| }, |
| { |
| "epoch": 7.2941888619854724, |
| "grad_norm": 6.609338283538818, |
| "learning_rate": 1.0354986669626796e-05, |
| "loss": 0.0876, |
| "num_input_tokens_seen": 2471312, |
| "step": 6025 |
| }, |
| { |
| "epoch": 7.300242130750606, |
| "grad_norm": 8.601812362670898, |
| "learning_rate": 1.0312207309697502e-05, |
| "loss": 0.0983, |
| "num_input_tokens_seen": 2473424, |
| "step": 6030 |
| }, |
| { |
| "epoch": 7.306295399515738, |
| "grad_norm": 0.25469648838043213, |
| "learning_rate": 1.0269493526687915e-05, |
| "loss": 0.1301, |
| "num_input_tokens_seen": 2475504, |
| "step": 6035 |
| }, |
| { |
| "epoch": 7.312348668280872, |
| "grad_norm": 1.2198680639266968, |
| "learning_rate": 1.0226845511303219e-05, |
| "loss": 0.093, |
| "num_input_tokens_seen": 2477392, |
| "step": 6040 |
| }, |
| { |
| "epoch": 7.318401937046005, |
| "grad_norm": 6.0976057052612305, |
| "learning_rate": 1.0184263453954988e-05, |
| "loss": 0.1598, |
| "num_input_tokens_seen": 2479504, |
| "step": 6045 |
| }, |
| { |
| "epoch": 7.324455205811138, |
| "grad_norm": 0.11773672699928284, |
| "learning_rate": 1.0141747544760285e-05, |
| "loss": 0.1831, |
| "num_input_tokens_seen": 2481584, |
| "step": 6050 |
| }, |
| { |
| "epoch": 7.330508474576272, |
| "grad_norm": 0.2373896986246109, |
| "learning_rate": 1.0099297973540852e-05, |
| "loss": 0.1016, |
| "num_input_tokens_seen": 2483632, |
| "step": 6055 |
| }, |
| { |
| "epoch": 7.336561743341404, |
| "grad_norm": 0.4794990122318268, |
| "learning_rate": 1.0056914929822248e-05, |
| "loss": 0.1583, |
| "num_input_tokens_seen": 2485680, |
| "step": 6060 |
| }, |
| { |
| "epoch": 7.342615012106537, |
| "grad_norm": 3.694774866104126, |
| "learning_rate": 1.0014598602832995e-05, |
| "loss": 0.1414, |
| "num_input_tokens_seen": 2487824, |
| "step": 6065 |
| }, |
| { |
| "epoch": 7.348668280871671, |
| "grad_norm": 5.654700756072998, |
| "learning_rate": 9.972349181503773e-06, |
| "loss": 0.2079, |
| "num_input_tokens_seen": 2489872, |
| "step": 6070 |
| }, |
| { |
| "epoch": 7.354721549636804, |
| "grad_norm": 2.5101606845855713, |
| "learning_rate": 9.930166854466516e-06, |
| "loss": 0.1189, |
| "num_input_tokens_seen": 2491888, |
| "step": 6075 |
| }, |
| { |
| "epoch": 7.3607748184019375, |
| "grad_norm": 3.4558751583099365, |
| "learning_rate": 9.888051810053617e-06, |
| "loss": 0.063, |
| "num_input_tokens_seen": 2493968, |
| "step": 6080 |
| }, |
| { |
| "epoch": 7.36682808716707, |
| "grad_norm": 1.2189325094223022, |
| "learning_rate": 9.846004236297052e-06, |
| "loss": 0.0761, |
| "num_input_tokens_seen": 2495920, |
| "step": 6085 |
| }, |
| { |
| "epoch": 7.372881355932203, |
| "grad_norm": 2.1722373962402344, |
| "learning_rate": 9.804024320927604e-06, |
| "loss": 0.0449, |
| "num_input_tokens_seen": 2498000, |
| "step": 6090 |
| }, |
| { |
| "epoch": 7.378934624697337, |
| "grad_norm": 6.354626655578613, |
| "learning_rate": 9.76211225137392e-06, |
| "loss": 0.0556, |
| "num_input_tokens_seen": 2499952, |
| "step": 6095 |
| }, |
| { |
| "epoch": 7.38498789346247, |
| "grad_norm": 2.806201934814453, |
| "learning_rate": 9.720268214761763e-06, |
| "loss": 0.0527, |
| "num_input_tokens_seen": 2501968, |
| "step": 6100 |
| }, |
| { |
| "epoch": 7.391041162227603, |
| "grad_norm": 1.7928763628005981, |
| "learning_rate": 9.678492397913167e-06, |
| "loss": 0.0513, |
| "num_input_tokens_seen": 2503984, |
| "step": 6105 |
| }, |
| { |
| "epoch": 7.397094430992736, |
| "grad_norm": 1.5846754312515259, |
| "learning_rate": 9.636784987345554e-06, |
| "loss": 0.0094, |
| "num_input_tokens_seen": 2505968, |
| "step": 6110 |
| }, |
| { |
| "epoch": 7.403147699757869, |
| "grad_norm": 1.3514759540557861, |
| "learning_rate": 9.595146169270944e-06, |
| "loss": 0.0665, |
| "num_input_tokens_seen": 2508080, |
| "step": 6115 |
| }, |
| { |
| "epoch": 7.4092009685230025, |
| "grad_norm": 6.123665809631348, |
| "learning_rate": 9.553576129595101e-06, |
| "loss": 0.2015, |
| "num_input_tokens_seen": 2510160, |
| "step": 6120 |
| }, |
| { |
| "epoch": 7.415254237288136, |
| "grad_norm": 2.2483015060424805, |
| "learning_rate": 9.512075053916735e-06, |
| "loss": 0.1365, |
| "num_input_tokens_seen": 2512304, |
| "step": 6125 |
| }, |
| { |
| "epoch": 7.421307506053269, |
| "grad_norm": 2.598407745361328, |
| "learning_rate": 9.470643127526627e-06, |
| "loss": 0.0505, |
| "num_input_tokens_seen": 2514544, |
| "step": 6130 |
| }, |
| { |
| "epoch": 7.427360774818402, |
| "grad_norm": 0.049765050411224365, |
| "learning_rate": 9.429280535406834e-06, |
| "loss": 0.0258, |
| "num_input_tokens_seen": 2516592, |
| "step": 6135 |
| }, |
| { |
| "epoch": 7.433414043583535, |
| "grad_norm": 4.562868118286133, |
| "learning_rate": 9.387987462229859e-06, |
| "loss": 0.1327, |
| "num_input_tokens_seen": 2518512, |
| "step": 6140 |
| }, |
| { |
| "epoch": 7.439467312348668, |
| "grad_norm": 3.8121907711029053, |
| "learning_rate": 9.346764092357801e-06, |
| "loss": 0.0704, |
| "num_input_tokens_seen": 2520592, |
| "step": 6145 |
| }, |
| { |
| "epoch": 7.445520581113802, |
| "grad_norm": 0.061380598694086075, |
| "learning_rate": 9.305610609841598e-06, |
| "loss": 0.1017, |
| "num_input_tokens_seen": 2522640, |
| "step": 6150 |
| }, |
| { |
| "epoch": 7.451573849878935, |
| "grad_norm": 0.5764665007591248, |
| "learning_rate": 9.264527198420117e-06, |
| "loss": 0.0743, |
| "num_input_tokens_seen": 2524592, |
| "step": 6155 |
| }, |
| { |
| "epoch": 7.4576271186440675, |
| "grad_norm": 7.019524097442627, |
| "learning_rate": 9.2235140415194e-06, |
| "loss": 0.1273, |
| "num_input_tokens_seen": 2526576, |
| "step": 6160 |
| }, |
| { |
| "epoch": 7.463680387409201, |
| "grad_norm": 0.13237552344799042, |
| "learning_rate": 9.182571322251796e-06, |
| "loss": 0.0638, |
| "num_input_tokens_seen": 2528656, |
| "step": 6165 |
| }, |
| { |
| "epoch": 7.469733656174334, |
| "grad_norm": 5.415895462036133, |
| "learning_rate": 9.141699223415221e-06, |
| "loss": 0.1563, |
| "num_input_tokens_seen": 2530864, |
| "step": 6170 |
| }, |
| { |
| "epoch": 7.4757869249394675, |
| "grad_norm": 6.8290557861328125, |
| "learning_rate": 9.10089792749223e-06, |
| "loss": 0.0785, |
| "num_input_tokens_seen": 2532880, |
| "step": 6175 |
| }, |
| { |
| "epoch": 7.481840193704601, |
| "grad_norm": 8.107266426086426, |
| "learning_rate": 9.06016761664929e-06, |
| "loss": 0.1175, |
| "num_input_tokens_seen": 2534864, |
| "step": 6180 |
| }, |
| { |
| "epoch": 7.487893462469733, |
| "grad_norm": 5.507659435272217, |
| "learning_rate": 9.019508472735958e-06, |
| "loss": 0.1338, |
| "num_input_tokens_seen": 2536912, |
| "step": 6185 |
| }, |
| { |
| "epoch": 7.493946731234867, |
| "grad_norm": 4.443814754486084, |
| "learning_rate": 8.978920677284022e-06, |
| "loss": 0.0693, |
| "num_input_tokens_seen": 2538832, |
| "step": 6190 |
| }, |
| { |
| "epoch": 7.5, |
| "grad_norm": 5.766138553619385, |
| "learning_rate": 8.938404411506732e-06, |
| "loss": 0.2827, |
| "num_input_tokens_seen": 2540880, |
| "step": 6195 |
| }, |
| { |
| "epoch": 7.5, |
| "eval_loss": 0.1561979204416275, |
| "eval_runtime": 4.5842, |
| "eval_samples_per_second": 80.058, |
| "eval_steps_per_second": 20.069, |
| "num_input_tokens_seen": 2540880, |
| "step": 6195 |
| }, |
| { |
| "epoch": 7.506053268765133, |
| "grad_norm": 4.710324287414551, |
| "learning_rate": 8.897959856297971e-06, |
| "loss": 0.0657, |
| "num_input_tokens_seen": 2542832, |
| "step": 6200 |
| }, |
| { |
| "epoch": 7.512106537530267, |
| "grad_norm": 0.08274981379508972, |
| "learning_rate": 8.857587192231452e-06, |
| "loss": 0.0517, |
| "num_input_tokens_seen": 2544784, |
| "step": 6205 |
| }, |
| { |
| "epoch": 7.518159806295399, |
| "grad_norm": 0.5334417223930359, |
| "learning_rate": 8.817286599559932e-06, |
| "loss": 0.0684, |
| "num_input_tokens_seen": 2546832, |
| "step": 6210 |
| }, |
| { |
| "epoch": 7.5242130750605325, |
| "grad_norm": 1.4246139526367188, |
| "learning_rate": 8.777058258214377e-06, |
| "loss": 0.0981, |
| "num_input_tokens_seen": 2549008, |
| "step": 6215 |
| }, |
| { |
| "epoch": 7.530266343825666, |
| "grad_norm": 4.641688346862793, |
| "learning_rate": 8.736902347803163e-06, |
| "loss": 0.1203, |
| "num_input_tokens_seen": 2551120, |
| "step": 6220 |
| }, |
| { |
| "epoch": 7.536319612590799, |
| "grad_norm": 2.8254716396331787, |
| "learning_rate": 8.696819047611288e-06, |
| "loss": 0.0808, |
| "num_input_tokens_seen": 2553168, |
| "step": 6225 |
| }, |
| { |
| "epoch": 7.5423728813559325, |
| "grad_norm": 3.209864377975464, |
| "learning_rate": 8.65680853659958e-06, |
| "loss": 0.0453, |
| "num_input_tokens_seen": 2555184, |
| "step": 6230 |
| }, |
| { |
| "epoch": 7.548426150121065, |
| "grad_norm": 3.2419934272766113, |
| "learning_rate": 8.616870993403864e-06, |
| "loss": 0.0221, |
| "num_input_tokens_seen": 2557264, |
| "step": 6235 |
| }, |
| { |
| "epoch": 7.554479418886198, |
| "grad_norm": 0.510710597038269, |
| "learning_rate": 8.577006596334191e-06, |
| "loss": 0.1491, |
| "num_input_tokens_seen": 2559248, |
| "step": 6240 |
| }, |
| { |
| "epoch": 7.560532687651332, |
| "grad_norm": 2.6407363414764404, |
| "learning_rate": 8.537215523374038e-06, |
| "loss": 0.1646, |
| "num_input_tokens_seen": 2561264, |
| "step": 6245 |
| }, |
| { |
| "epoch": 7.566585956416465, |
| "grad_norm": 5.177677154541016, |
| "learning_rate": 8.4974979521795e-06, |
| "loss": 0.1805, |
| "num_input_tokens_seen": 2563120, |
| "step": 6250 |
| }, |
| { |
| "epoch": 7.572639225181598, |
| "grad_norm": 0.05995741859078407, |
| "learning_rate": 8.45785406007852e-06, |
| "loss": 0.2352, |
| "num_input_tokens_seen": 2565104, |
| "step": 6255 |
| }, |
| { |
| "epoch": 7.578692493946731, |
| "grad_norm": 4.417571544647217, |
| "learning_rate": 8.418284024070069e-06, |
| "loss": 0.0918, |
| "num_input_tokens_seen": 2567216, |
| "step": 6260 |
| }, |
| { |
| "epoch": 7.584745762711864, |
| "grad_norm": 3.200150728225708, |
| "learning_rate": 8.378788020823394e-06, |
| "loss": 0.0234, |
| "num_input_tokens_seen": 2569360, |
| "step": 6265 |
| }, |
| { |
| "epoch": 7.5907990314769975, |
| "grad_norm": 10.74376392364502, |
| "learning_rate": 8.33936622667719e-06, |
| "loss": 0.1187, |
| "num_input_tokens_seen": 2571536, |
| "step": 6270 |
| }, |
| { |
| "epoch": 7.596852300242131, |
| "grad_norm": 0.05067841336131096, |
| "learning_rate": 8.300018817638825e-06, |
| "loss": 0.2934, |
| "num_input_tokens_seen": 2573648, |
| "step": 6275 |
| }, |
| { |
| "epoch": 7.602905569007264, |
| "grad_norm": 0.693376362323761, |
| "learning_rate": 8.260745969383565e-06, |
| "loss": 0.0099, |
| "num_input_tokens_seen": 2575888, |
| "step": 6280 |
| }, |
| { |
| "epoch": 7.608958837772397, |
| "grad_norm": 3.702101230621338, |
| "learning_rate": 8.221547857253781e-06, |
| "loss": 0.0783, |
| "num_input_tokens_seen": 2578032, |
| "step": 6285 |
| }, |
| { |
| "epoch": 7.61501210653753, |
| "grad_norm": 3.041938543319702, |
| "learning_rate": 8.182424656258178e-06, |
| "loss": 0.1982, |
| "num_input_tokens_seen": 2580016, |
| "step": 6290 |
| }, |
| { |
| "epoch": 7.621065375302663, |
| "grad_norm": 0.7098401784896851, |
| "learning_rate": 8.143376541070993e-06, |
| "loss": 0.172, |
| "num_input_tokens_seen": 2582192, |
| "step": 6295 |
| }, |
| { |
| "epoch": 7.627118644067797, |
| "grad_norm": 3.364931106567383, |
| "learning_rate": 8.104403686031225e-06, |
| "loss": 0.1141, |
| "num_input_tokens_seen": 2584208, |
| "step": 6300 |
| }, |
| { |
| "epoch": 7.63317191283293, |
| "grad_norm": 0.41202157735824585, |
| "learning_rate": 8.06550626514185e-06, |
| "loss": 0.0881, |
| "num_input_tokens_seen": 2586160, |
| "step": 6305 |
| }, |
| { |
| "epoch": 7.6392251815980625, |
| "grad_norm": 4.636420726776123, |
| "learning_rate": 8.026684452069084e-06, |
| "loss": 0.032, |
| "num_input_tokens_seen": 2588240, |
| "step": 6310 |
| }, |
| { |
| "epoch": 7.645278450363196, |
| "grad_norm": 3.400038719177246, |
| "learning_rate": 7.987938420141536e-06, |
| "loss": 0.0891, |
| "num_input_tokens_seen": 2590480, |
| "step": 6315 |
| }, |
| { |
| "epoch": 7.651331719128329, |
| "grad_norm": 4.440576553344727, |
| "learning_rate": 7.949268342349495e-06, |
| "loss": 0.1652, |
| "num_input_tokens_seen": 2592400, |
| "step": 6320 |
| }, |
| { |
| "epoch": 7.657384987893463, |
| "grad_norm": 7.222400188446045, |
| "learning_rate": 7.910674391344129e-06, |
| "loss": 0.0654, |
| "num_input_tokens_seen": 2594352, |
| "step": 6325 |
| }, |
| { |
| "epoch": 7.663438256658596, |
| "grad_norm": 7.135024070739746, |
| "learning_rate": 7.872156739436722e-06, |
| "loss": 0.1163, |
| "num_input_tokens_seen": 2596464, |
| "step": 6330 |
| }, |
| { |
| "epoch": 7.669491525423728, |
| "grad_norm": 3.5936965942382812, |
| "learning_rate": 7.833715558597907e-06, |
| "loss": 0.1517, |
| "num_input_tokens_seen": 2598544, |
| "step": 6335 |
| }, |
| { |
| "epoch": 7.675544794188862, |
| "grad_norm": 2.601381540298462, |
| "learning_rate": 7.795351020456887e-06, |
| "loss": 0.0728, |
| "num_input_tokens_seen": 2600656, |
| "step": 6340 |
| }, |
| { |
| "epoch": 7.681598062953995, |
| "grad_norm": 1.4275619983673096, |
| "learning_rate": 7.757063296300681e-06, |
| "loss": 0.0455, |
| "num_input_tokens_seen": 2602832, |
| "step": 6345 |
| }, |
| { |
| "epoch": 7.687651331719128, |
| "grad_norm": 4.785684585571289, |
| "learning_rate": 7.718852557073366e-06, |
| "loss": 0.1142, |
| "num_input_tokens_seen": 2605008, |
| "step": 6350 |
| }, |
| { |
| "epoch": 7.693704600484262, |
| "grad_norm": 1.9919321537017822, |
| "learning_rate": 7.680718973375287e-06, |
| "loss": 0.0911, |
| "num_input_tokens_seen": 2607152, |
| "step": 6355 |
| }, |
| { |
| "epoch": 7.699757869249394, |
| "grad_norm": 4.593861103057861, |
| "learning_rate": 7.642662715462315e-06, |
| "loss": 0.0768, |
| "num_input_tokens_seen": 2609264, |
| "step": 6360 |
| }, |
| { |
| "epoch": 7.7058111380145276, |
| "grad_norm": 1.1676124334335327, |
| "learning_rate": 7.604683953245076e-06, |
| "loss": 0.0514, |
| "num_input_tokens_seen": 2611344, |
| "step": 6365 |
| }, |
| { |
| "epoch": 7.711864406779661, |
| "grad_norm": 9.047789573669434, |
| "learning_rate": 7.566782856288224e-06, |
| "loss": 0.1201, |
| "num_input_tokens_seen": 2613488, |
| "step": 6370 |
| }, |
| { |
| "epoch": 7.717917675544794, |
| "grad_norm": 5.686391830444336, |
| "learning_rate": 7.5289595938096344e-06, |
| "loss": 0.1994, |
| "num_input_tokens_seen": 2615408, |
| "step": 6375 |
| }, |
| { |
| "epoch": 7.723970944309928, |
| "grad_norm": 5.593163967132568, |
| "learning_rate": 7.4912143346796805e-06, |
| "loss": 0.1044, |
| "num_input_tokens_seen": 2617424, |
| "step": 6380 |
| }, |
| { |
| "epoch": 7.73002421307506, |
| "grad_norm": 0.4675053060054779, |
| "learning_rate": 7.4535472474204645e-06, |
| "loss": 0.1039, |
| "num_input_tokens_seen": 2619312, |
| "step": 6385 |
| }, |
| { |
| "epoch": 7.736077481840193, |
| "grad_norm": 4.127689361572266, |
| "learning_rate": 7.415958500205103e-06, |
| "loss": 0.1168, |
| "num_input_tokens_seen": 2621168, |
| "step": 6390 |
| }, |
| { |
| "epoch": 7.742130750605327, |
| "grad_norm": 5.092752933502197, |
| "learning_rate": 7.37844826085691e-06, |
| "loss": 0.0661, |
| "num_input_tokens_seen": 2623152, |
| "step": 6395 |
| }, |
| { |
| "epoch": 7.74818401937046, |
| "grad_norm": 0.2673223614692688, |
| "learning_rate": 7.341016696848699e-06, |
| "loss": 0.0332, |
| "num_input_tokens_seen": 2625328, |
| "step": 6400 |
| }, |
| { |
| "epoch": 7.754237288135593, |
| "grad_norm": 0.20804698765277863, |
| "learning_rate": 7.303663975302022e-06, |
| "loss": 0.026, |
| "num_input_tokens_seen": 2627536, |
| "step": 6405 |
| }, |
| { |
| "epoch": 7.760290556900727, |
| "grad_norm": 0.20616967976093292, |
| "learning_rate": 7.2663902629864165e-06, |
| "loss": 0.0101, |
| "num_input_tokens_seen": 2629616, |
| "step": 6410 |
| }, |
| { |
| "epoch": 7.766343825665859, |
| "grad_norm": 3.6831769943237305, |
| "learning_rate": 7.229195726318669e-06, |
| "loss": 0.0538, |
| "num_input_tokens_seen": 2631696, |
| "step": 6415 |
| }, |
| { |
| "epoch": 7.772397094430993, |
| "grad_norm": 0.7039980292320251, |
| "learning_rate": 7.192080531362067e-06, |
| "loss": 0.064, |
| "num_input_tokens_seen": 2633776, |
| "step": 6420 |
| }, |
| { |
| "epoch": 7.778450363196126, |
| "grad_norm": 3.7811477184295654, |
| "learning_rate": 7.155044843825651e-06, |
| "loss": 0.0414, |
| "num_input_tokens_seen": 2635920, |
| "step": 6425 |
| }, |
| { |
| "epoch": 7.784503631961259, |
| "grad_norm": 6.906268119812012, |
| "learning_rate": 7.118088829063504e-06, |
| "loss": 0.1027, |
| "num_input_tokens_seen": 2637936, |
| "step": 6430 |
| }, |
| { |
| "epoch": 7.790556900726393, |
| "grad_norm": 3.0784387588500977, |
| "learning_rate": 7.081212652073979e-06, |
| "loss": 0.0815, |
| "num_input_tokens_seen": 2639984, |
| "step": 6435 |
| }, |
| { |
| "epoch": 7.796610169491525, |
| "grad_norm": 1.9412931203842163, |
| "learning_rate": 7.044416477498972e-06, |
| "loss": 0.1324, |
| "num_input_tokens_seen": 2642000, |
| "step": 6440 |
| }, |
| { |
| "epoch": 7.802663438256658, |
| "grad_norm": 0.9284259080886841, |
| "learning_rate": 7.007700469623185e-06, |
| "loss": 0.0571, |
| "num_input_tokens_seen": 2644016, |
| "step": 6445 |
| }, |
| { |
| "epoch": 7.808716707021792, |
| "grad_norm": 2.565072774887085, |
| "learning_rate": 6.971064792373427e-06, |
| "loss": 0.1923, |
| "num_input_tokens_seen": 2646000, |
| "step": 6450 |
| }, |
| { |
| "epoch": 7.814769975786925, |
| "grad_norm": 2.1427745819091797, |
| "learning_rate": 6.934509609317821e-06, |
| "loss": 0.1555, |
| "num_input_tokens_seen": 2648048, |
| "step": 6455 |
| }, |
| { |
| "epoch": 7.8208232445520585, |
| "grad_norm": 5.358201026916504, |
| "learning_rate": 6.898035083665124e-06, |
| "loss": 0.0466, |
| "num_input_tokens_seen": 2650064, |
| "step": 6460 |
| }, |
| { |
| "epoch": 7.826876513317191, |
| "grad_norm": 3.4232592582702637, |
| "learning_rate": 6.861641378263964e-06, |
| "loss": 0.0734, |
| "num_input_tokens_seen": 2652016, |
| "step": 6465 |
| }, |
| { |
| "epoch": 7.832929782082324, |
| "grad_norm": 2.332578182220459, |
| "learning_rate": 6.825328655602153e-06, |
| "loss": 0.1261, |
| "num_input_tokens_seen": 2654192, |
| "step": 6470 |
| }, |
| { |
| "epoch": 7.838983050847458, |
| "grad_norm": 0.7169421911239624, |
| "learning_rate": 6.789097077805917e-06, |
| "loss": 0.1027, |
| "num_input_tokens_seen": 2656208, |
| "step": 6475 |
| }, |
| { |
| "epoch": 7.845036319612591, |
| "grad_norm": 5.153744220733643, |
| "learning_rate": 6.7529468066392015e-06, |
| "loss": 0.0898, |
| "num_input_tokens_seen": 2658384, |
| "step": 6480 |
| }, |
| { |
| "epoch": 7.851089588377724, |
| "grad_norm": 0.8772520422935486, |
| "learning_rate": 6.7168780035029385e-06, |
| "loss": 0.0203, |
| "num_input_tokens_seen": 2660528, |
| "step": 6485 |
| }, |
| { |
| "epoch": 7.857142857142857, |
| "grad_norm": 7.855628967285156, |
| "learning_rate": 6.680890829434325e-06, |
| "loss": 0.157, |
| "num_input_tokens_seen": 2662640, |
| "step": 6490 |
| }, |
| { |
| "epoch": 7.86319612590799, |
| "grad_norm": 3.3216187953948975, |
| "learning_rate": 6.644985445106114e-06, |
| "loss": 0.0637, |
| "num_input_tokens_seen": 2664624, |
| "step": 6495 |
| }, |
| { |
| "epoch": 7.8692493946731235, |
| "grad_norm": 0.16674460470676422, |
| "learning_rate": 6.609162010825881e-06, |
| "loss": 0.016, |
| "num_input_tokens_seen": 2666640, |
| "step": 6500 |
| }, |
| { |
| "epoch": 7.875302663438257, |
| "grad_norm": 4.573734283447266, |
| "learning_rate": 6.573420686535317e-06, |
| "loss": 0.0683, |
| "num_input_tokens_seen": 2668592, |
| "step": 6505 |
| }, |
| { |
| "epoch": 7.88135593220339, |
| "grad_norm": 4.325008869171143, |
| "learning_rate": 6.537761631809533e-06, |
| "loss": 0.1327, |
| "num_input_tokens_seen": 2670704, |
| "step": 6510 |
| }, |
| { |
| "epoch": 7.8874092009685235, |
| "grad_norm": 1.69081449508667, |
| "learning_rate": 6.502185005856312e-06, |
| "loss": 0.0717, |
| "num_input_tokens_seen": 2672752, |
| "step": 6515 |
| }, |
| { |
| "epoch": 7.893462469733656, |
| "grad_norm": 1.8181393146514893, |
| "learning_rate": 6.4666909675154155e-06, |
| "loss": 0.0724, |
| "num_input_tokens_seen": 2674864, |
| "step": 6520 |
| }, |
| { |
| "epoch": 7.899515738498789, |
| "grad_norm": 0.46458661556243896, |
| "learning_rate": 6.431279675257873e-06, |
| "loss": 0.2251, |
| "num_input_tokens_seen": 2676944, |
| "step": 6525 |
| }, |
| { |
| "epoch": 7.905569007263923, |
| "grad_norm": 3.5621135234832764, |
| "learning_rate": 6.395951287185295e-06, |
| "loss": 0.0576, |
| "num_input_tokens_seen": 2679024, |
| "step": 6530 |
| }, |
| { |
| "epoch": 7.911622276029056, |
| "grad_norm": 1.915932059288025, |
| "learning_rate": 6.360705961029126e-06, |
| "loss": 0.035, |
| "num_input_tokens_seen": 2680976, |
| "step": 6535 |
| }, |
| { |
| "epoch": 7.917675544794189, |
| "grad_norm": 6.927842140197754, |
| "learning_rate": 6.325543854149968e-06, |
| "loss": 0.108, |
| "num_input_tokens_seen": 2683088, |
| "step": 6540 |
| }, |
| { |
| "epoch": 7.923728813559322, |
| "grad_norm": 0.36779117584228516, |
| "learning_rate": 6.290465123536876e-06, |
| "loss": 0.0904, |
| "num_input_tokens_seen": 2685072, |
| "step": 6545 |
| }, |
| { |
| "epoch": 7.929782082324455, |
| "grad_norm": 0.3823559880256653, |
| "learning_rate": 6.255469925806643e-06, |
| "loss": 0.084, |
| "num_input_tokens_seen": 2687184, |
| "step": 6550 |
| }, |
| { |
| "epoch": 7.9358353510895885, |
| "grad_norm": 1.9843477010726929, |
| "learning_rate": 6.220558417203132e-06, |
| "loss": 0.0953, |
| "num_input_tokens_seen": 2689232, |
| "step": 6555 |
| }, |
| { |
| "epoch": 7.941888619854722, |
| "grad_norm": 0.8949267864227295, |
| "learning_rate": 6.185730753596539e-06, |
| "loss": 0.0793, |
| "num_input_tokens_seen": 2691280, |
| "step": 6560 |
| }, |
| { |
| "epoch": 7.947941888619855, |
| "grad_norm": 0.34748074412345886, |
| "learning_rate": 6.150987090482715e-06, |
| "loss": 0.0306, |
| "num_input_tokens_seen": 2693328, |
| "step": 6565 |
| }, |
| { |
| "epoch": 7.953995157384988, |
| "grad_norm": 2.629479169845581, |
| "learning_rate": 6.116327582982484e-06, |
| "loss": 0.1464, |
| "num_input_tokens_seen": 2695440, |
| "step": 6570 |
| }, |
| { |
| "epoch": 7.960048426150121, |
| "grad_norm": 0.09015600383281708, |
| "learning_rate": 6.0817523858409245e-06, |
| "loss": 0.0922, |
| "num_input_tokens_seen": 2697488, |
| "step": 6575 |
| }, |
| { |
| "epoch": 7.966101694915254, |
| "grad_norm": 4.677306175231934, |
| "learning_rate": 6.047261653426708e-06, |
| "loss": 0.1554, |
| "num_input_tokens_seen": 2699504, |
| "step": 6580 |
| }, |
| { |
| "epoch": 7.972154963680388, |
| "grad_norm": 6.132607460021973, |
| "learning_rate": 6.012855539731374e-06, |
| "loss": 0.0634, |
| "num_input_tokens_seen": 2701456, |
| "step": 6585 |
| }, |
| { |
| "epoch": 7.978208232445521, |
| "grad_norm": 4.510989189147949, |
| "learning_rate": 5.978534198368691e-06, |
| "loss": 0.0738, |
| "num_input_tokens_seen": 2703504, |
| "step": 6590 |
| }, |
| { |
| "epoch": 7.9842615012106535, |
| "grad_norm": 1.4074878692626953, |
| "learning_rate": 5.944297782573918e-06, |
| "loss": 0.1079, |
| "num_input_tokens_seen": 2705616, |
| "step": 6595 |
| }, |
| { |
| "epoch": 7.990314769975787, |
| "grad_norm": 4.238768577575684, |
| "learning_rate": 5.910146445203154e-06, |
| "loss": 0.0776, |
| "num_input_tokens_seen": 2707728, |
| "step": 6600 |
| }, |
| { |
| "epoch": 7.99636803874092, |
| "grad_norm": 0.08241457492113113, |
| "learning_rate": 5.876080338732643e-06, |
| "loss": 0.1001, |
| "num_input_tokens_seen": 2709776, |
| "step": 6605 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_loss": 0.15882021188735962, |
| "eval_runtime": 4.5817, |
| "eval_samples_per_second": 80.1, |
| "eval_steps_per_second": 20.08, |
| "num_input_tokens_seen": 2710624, |
| "step": 6608 |
| }, |
| { |
| "epoch": 8.002421307506053, |
| "grad_norm": 2.513517141342163, |
| "learning_rate": 5.842099615258109e-06, |
| "loss": 0.064, |
| "num_input_tokens_seen": 2711456, |
| "step": 6610 |
| }, |
| { |
| "epoch": 8.008474576271187, |
| "grad_norm": 0.1411186158657074, |
| "learning_rate": 5.808204426494054e-06, |
| "loss": 0.1748, |
| "num_input_tokens_seen": 2713536, |
| "step": 6615 |
| }, |
| { |
| "epoch": 8.01452784503632, |
| "grad_norm": 0.5461141467094421, |
| "learning_rate": 5.774394923773088e-06, |
| "loss": 0.1396, |
| "num_input_tokens_seen": 2715680, |
| "step": 6620 |
| }, |
| { |
| "epoch": 8.020581113801454, |
| "grad_norm": 2.81977915763855, |
| "learning_rate": 5.74067125804526e-06, |
| "loss": 0.0513, |
| "num_input_tokens_seen": 2717728, |
| "step": 6625 |
| }, |
| { |
| "epoch": 8.026634382566586, |
| "grad_norm": 9.47875690460205, |
| "learning_rate": 5.70703357987738e-06, |
| "loss": 0.0797, |
| "num_input_tokens_seen": 2719712, |
| "step": 6630 |
| }, |
| { |
| "epoch": 8.032687651331718, |
| "grad_norm": 2.103945016860962, |
| "learning_rate": 5.673482039452363e-06, |
| "loss": 0.0679, |
| "num_input_tokens_seen": 2721856, |
| "step": 6635 |
| }, |
| { |
| "epoch": 8.038740920096853, |
| "grad_norm": 10.135988235473633, |
| "learning_rate": 5.640016786568525e-06, |
| "loss": 0.1698, |
| "num_input_tokens_seen": 2724000, |
| "step": 6640 |
| }, |
| { |
| "epoch": 8.044794188861985, |
| "grad_norm": 0.5726349949836731, |
| "learning_rate": 5.606637970638917e-06, |
| "loss": 0.1044, |
| "num_input_tokens_seen": 2725792, |
| "step": 6645 |
| }, |
| { |
| "epoch": 8.05084745762712, |
| "grad_norm": 0.0631587952375412, |
| "learning_rate": 5.573345740690714e-06, |
| "loss": 0.1507, |
| "num_input_tokens_seen": 2727744, |
| "step": 6650 |
| }, |
| { |
| "epoch": 8.056900726392252, |
| "grad_norm": 3.7353861331939697, |
| "learning_rate": 5.540140245364478e-06, |
| "loss": 0.0763, |
| "num_input_tokens_seen": 2729856, |
| "step": 6655 |
| }, |
| { |
| "epoch": 8.062953995157384, |
| "grad_norm": 0.1272682547569275, |
| "learning_rate": 5.5070216329135365e-06, |
| "loss": 0.0488, |
| "num_input_tokens_seen": 2731872, |
| "step": 6660 |
| }, |
| { |
| "epoch": 8.069007263922519, |
| "grad_norm": 0.2341405749320984, |
| "learning_rate": 5.473990051203298e-06, |
| "loss": 0.0809, |
| "num_input_tokens_seen": 2734016, |
| "step": 6665 |
| }, |
| { |
| "epoch": 8.075060532687651, |
| "grad_norm": 1.8176710605621338, |
| "learning_rate": 5.441045647710627e-06, |
| "loss": 0.0458, |
| "num_input_tokens_seen": 2736032, |
| "step": 6670 |
| }, |
| { |
| "epoch": 8.081113801452785, |
| "grad_norm": 7.36388635635376, |
| "learning_rate": 5.408188569523137e-06, |
| "loss": 0.1572, |
| "num_input_tokens_seen": 2737952, |
| "step": 6675 |
| }, |
| { |
| "epoch": 8.087167070217918, |
| "grad_norm": 2.5287160873413086, |
| "learning_rate": 5.375418963338566e-06, |
| "loss": 0.0209, |
| "num_input_tokens_seen": 2739968, |
| "step": 6680 |
| }, |
| { |
| "epoch": 8.09322033898305, |
| "grad_norm": 3.441671133041382, |
| "learning_rate": 5.342736975464116e-06, |
| "loss": 0.1182, |
| "num_input_tokens_seen": 2742016, |
| "step": 6685 |
| }, |
| { |
| "epoch": 8.099273607748184, |
| "grad_norm": 2.918954610824585, |
| "learning_rate": 5.310142751815792e-06, |
| "loss": 0.0744, |
| "num_input_tokens_seen": 2744128, |
| "step": 6690 |
| }, |
| { |
| "epoch": 8.105326876513317, |
| "grad_norm": 0.13784159719944, |
| "learning_rate": 5.277636437917769e-06, |
| "loss": 0.0489, |
| "num_input_tokens_seen": 2746112, |
| "step": 6695 |
| }, |
| { |
| "epoch": 8.111380145278451, |
| "grad_norm": 0.6086945533752441, |
| "learning_rate": 5.245218178901717e-06, |
| "loss": 0.0761, |
| "num_input_tokens_seen": 2748128, |
| "step": 6700 |
| }, |
| { |
| "epoch": 8.117433414043584, |
| "grad_norm": 5.943281650543213, |
| "learning_rate": 5.212888119506168e-06, |
| "loss": 0.0651, |
| "num_input_tokens_seen": 2750176, |
| "step": 6705 |
| }, |
| { |
| "epoch": 8.123486682808716, |
| "grad_norm": 0.10667125880718231, |
| "learning_rate": 5.180646404075862e-06, |
| "loss": 0.1376, |
| "num_input_tokens_seen": 2752256, |
| "step": 6710 |
| }, |
| { |
| "epoch": 8.12953995157385, |
| "grad_norm": 0.2919732630252838, |
| "learning_rate": 5.1484931765611286e-06, |
| "loss": 0.037, |
| "num_input_tokens_seen": 2754208, |
| "step": 6715 |
| }, |
| { |
| "epoch": 8.135593220338983, |
| "grad_norm": 0.1272069811820984, |
| "learning_rate": 5.116428580517207e-06, |
| "loss": 0.0543, |
| "num_input_tokens_seen": 2756352, |
| "step": 6720 |
| }, |
| { |
| "epoch": 8.141646489104117, |
| "grad_norm": 5.189438819885254, |
| "learning_rate": 5.084452759103603e-06, |
| "loss": 0.1686, |
| "num_input_tokens_seen": 2758528, |
| "step": 6725 |
| }, |
| { |
| "epoch": 8.14769975786925, |
| "grad_norm": 1.4413750171661377, |
| "learning_rate": 5.052565855083511e-06, |
| "loss": 0.05, |
| "num_input_tokens_seen": 2760608, |
| "step": 6730 |
| }, |
| { |
| "epoch": 8.153753026634382, |
| "grad_norm": 0.21941789984703064, |
| "learning_rate": 5.020768010823102e-06, |
| "loss": 0.0895, |
| "num_input_tokens_seen": 2762656, |
| "step": 6735 |
| }, |
| { |
| "epoch": 8.159806295399516, |
| "grad_norm": 6.086516857147217, |
| "learning_rate": 4.98905936829093e-06, |
| "loss": 0.3365, |
| "num_input_tokens_seen": 2764672, |
| "step": 6740 |
| }, |
| { |
| "epoch": 8.165859564164649, |
| "grad_norm": 4.337617874145508, |
| "learning_rate": 4.957440069057281e-06, |
| "loss": 0.2026, |
| "num_input_tokens_seen": 2766752, |
| "step": 6745 |
| }, |
| { |
| "epoch": 8.171912832929783, |
| "grad_norm": 0.7985682487487793, |
| "learning_rate": 4.92591025429357e-06, |
| "loss": 0.1161, |
| "num_input_tokens_seen": 2768736, |
| "step": 6750 |
| }, |
| { |
| "epoch": 8.177966101694915, |
| "grad_norm": 0.06866363435983658, |
| "learning_rate": 4.8944700647716616e-06, |
| "loss": 0.0773, |
| "num_input_tokens_seen": 2770752, |
| "step": 6755 |
| }, |
| { |
| "epoch": 8.184019370460048, |
| "grad_norm": 1.1329652070999146, |
| "learning_rate": 4.863119640863284e-06, |
| "loss": 0.0797, |
| "num_input_tokens_seen": 2772928, |
| "step": 6760 |
| }, |
| { |
| "epoch": 8.190072639225182, |
| "grad_norm": 4.368817329406738, |
| "learning_rate": 4.831859122539381e-06, |
| "loss": 0.1068, |
| "num_input_tokens_seen": 2774976, |
| "step": 6765 |
| }, |
| { |
| "epoch": 8.196125907990314, |
| "grad_norm": 4.116227149963379, |
| "learning_rate": 4.800688649369489e-06, |
| "loss": 0.0271, |
| "num_input_tokens_seen": 2777152, |
| "step": 6770 |
| }, |
| { |
| "epoch": 8.202179176755449, |
| "grad_norm": 1.6234118938446045, |
| "learning_rate": 4.769608360521135e-06, |
| "loss": 0.0401, |
| "num_input_tokens_seen": 2779296, |
| "step": 6775 |
| }, |
| { |
| "epoch": 8.208232445520581, |
| "grad_norm": 0.17533978819847107, |
| "learning_rate": 4.7386183947591815e-06, |
| "loss": 0.0862, |
| "num_input_tokens_seen": 2781376, |
| "step": 6780 |
| }, |
| { |
| "epoch": 8.214285714285714, |
| "grad_norm": 6.969298362731934, |
| "learning_rate": 4.7077188904452255e-06, |
| "loss": 0.1029, |
| "num_input_tokens_seen": 2783424, |
| "step": 6785 |
| }, |
| { |
| "epoch": 8.220338983050848, |
| "grad_norm": 4.845013618469238, |
| "learning_rate": 4.676909985536981e-06, |
| "loss": 0.0861, |
| "num_input_tokens_seen": 2785376, |
| "step": 6790 |
| }, |
| { |
| "epoch": 8.22639225181598, |
| "grad_norm": 0.1180926263332367, |
| "learning_rate": 4.64619181758767e-06, |
| "loss": 0.0417, |
| "num_input_tokens_seen": 2787456, |
| "step": 6795 |
| }, |
| { |
| "epoch": 8.232445520581114, |
| "grad_norm": 0.3309163451194763, |
| "learning_rate": 4.615564523745391e-06, |
| "loss": 0.0407, |
| "num_input_tokens_seen": 2789568, |
| "step": 6800 |
| }, |
| { |
| "epoch": 8.238498789346247, |
| "grad_norm": 0.4439374506473541, |
| "learning_rate": 4.585028240752498e-06, |
| "loss": 0.0463, |
| "num_input_tokens_seen": 2791584, |
| "step": 6805 |
| }, |
| { |
| "epoch": 8.24455205811138, |
| "grad_norm": 0.6282607913017273, |
| "learning_rate": 4.554583104945037e-06, |
| "loss": 0.0457, |
| "num_input_tokens_seen": 2793632, |
| "step": 6810 |
| }, |
| { |
| "epoch": 8.250605326876514, |
| "grad_norm": 12.020580291748047, |
| "learning_rate": 4.524229252252091e-06, |
| "loss": 0.176, |
| "num_input_tokens_seen": 2795744, |
| "step": 6815 |
| }, |
| { |
| "epoch": 8.256658595641646, |
| "grad_norm": 0.6101036071777344, |
| "learning_rate": 4.493966818195191e-06, |
| "loss": 0.091, |
| "num_input_tokens_seen": 2797696, |
| "step": 6820 |
| }, |
| { |
| "epoch": 8.26271186440678, |
| "grad_norm": 6.851560592651367, |
| "learning_rate": 4.463795937887713e-06, |
| "loss": 0.1245, |
| "num_input_tokens_seen": 2799744, |
| "step": 6825 |
| }, |
| { |
| "epoch": 8.268765133171913, |
| "grad_norm": 0.21290670335292816, |
| "learning_rate": 4.433716746034252e-06, |
| "loss": 0.0675, |
| "num_input_tokens_seen": 2801824, |
| "step": 6830 |
| }, |
| { |
| "epoch": 8.274818401937045, |
| "grad_norm": 0.04258127510547638, |
| "learning_rate": 4.40372937693008e-06, |
| "loss": 0.1002, |
| "num_input_tokens_seen": 2803872, |
| "step": 6835 |
| }, |
| { |
| "epoch": 8.28087167070218, |
| "grad_norm": 0.23941421508789062, |
| "learning_rate": 4.3738339644604635e-06, |
| "loss": 0.1303, |
| "num_input_tokens_seen": 2805824, |
| "step": 6840 |
| }, |
| { |
| "epoch": 8.286924939467312, |
| "grad_norm": 0.6830506920814514, |
| "learning_rate": 4.344030642100133e-06, |
| "loss": 0.0172, |
| "num_input_tokens_seen": 2807712, |
| "step": 6845 |
| }, |
| { |
| "epoch": 8.292978208232446, |
| "grad_norm": 0.09925970435142517, |
| "learning_rate": 4.314319542912643e-06, |
| "loss": 0.0334, |
| "num_input_tokens_seen": 2809760, |
| "step": 6850 |
| }, |
| { |
| "epoch": 8.299031476997579, |
| "grad_norm": 3.751558542251587, |
| "learning_rate": 4.284700799549829e-06, |
| "loss": 0.1723, |
| "num_input_tokens_seen": 2811872, |
| "step": 6855 |
| }, |
| { |
| "epoch": 8.305084745762711, |
| "grad_norm": 4.737812042236328, |
| "learning_rate": 4.255174544251147e-06, |
| "loss": 0.1962, |
| "num_input_tokens_seen": 2813888, |
| "step": 6860 |
| }, |
| { |
| "epoch": 8.311138014527845, |
| "grad_norm": 3.3046317100524902, |
| "learning_rate": 4.225740908843146e-06, |
| "loss": 0.0687, |
| "num_input_tokens_seen": 2815808, |
| "step": 6865 |
| }, |
| { |
| "epoch": 8.317191283292978, |
| "grad_norm": 0.9242627024650574, |
| "learning_rate": 4.196400024738831e-06, |
| "loss": 0.0231, |
| "num_input_tokens_seen": 2817760, |
| "step": 6870 |
| }, |
| { |
| "epoch": 8.323244552058112, |
| "grad_norm": 4.347622394561768, |
| "learning_rate": 4.167152022937124e-06, |
| "loss": 0.0313, |
| "num_input_tokens_seen": 2819776, |
| "step": 6875 |
| }, |
| { |
| "epoch": 8.329297820823244, |
| "grad_norm": 9.906876564025879, |
| "learning_rate": 4.137997034022237e-06, |
| "loss": 0.0923, |
| "num_input_tokens_seen": 2821824, |
| "step": 6880 |
| }, |
| { |
| "epoch": 8.335351089588377, |
| "grad_norm": 2.6566002368927, |
| "learning_rate": 4.108935188163096e-06, |
| "loss": 0.042, |
| "num_input_tokens_seen": 2823968, |
| "step": 6885 |
| }, |
| { |
| "epoch": 8.341404358353511, |
| "grad_norm": 0.5351431369781494, |
| "learning_rate": 4.079966615112782e-06, |
| "loss": 0.0691, |
| "num_input_tokens_seen": 2825920, |
| "step": 6890 |
| }, |
| { |
| "epoch": 8.347457627118644, |
| "grad_norm": 0.3128598630428314, |
| "learning_rate": 4.05109144420795e-06, |
| "loss": 0.0254, |
| "num_input_tokens_seen": 2828224, |
| "step": 6895 |
| }, |
| { |
| "epoch": 8.353510895883778, |
| "grad_norm": 0.5572378635406494, |
| "learning_rate": 4.022309804368215e-06, |
| "loss": 0.0951, |
| "num_input_tokens_seen": 2830208, |
| "step": 6900 |
| }, |
| { |
| "epoch": 8.35956416464891, |
| "grad_norm": 0.455200731754303, |
| "learning_rate": 3.993621824095622e-06, |
| "loss": 0.0888, |
| "num_input_tokens_seen": 2832160, |
| "step": 6905 |
| }, |
| { |
| "epoch": 8.365617433414043, |
| "grad_norm": 2.736868381500244, |
| "learning_rate": 3.965027631474036e-06, |
| "loss": 0.0434, |
| "num_input_tokens_seen": 2834208, |
| "step": 6910 |
| }, |
| { |
| "epoch": 8.371670702179177, |
| "grad_norm": 5.61325216293335, |
| "learning_rate": 3.936527354168606e-06, |
| "loss": 0.0488, |
| "num_input_tokens_seen": 2836320, |
| "step": 6915 |
| }, |
| { |
| "epoch": 8.37772397094431, |
| "grad_norm": 0.13815198838710785, |
| "learning_rate": 3.90812111942516e-06, |
| "loss": 0.0717, |
| "num_input_tokens_seen": 2838464, |
| "step": 6920 |
| }, |
| { |
| "epoch": 8.383777239709444, |
| "grad_norm": 0.10977087169885635, |
| "learning_rate": 3.8798090540696495e-06, |
| "loss": 0.1805, |
| "num_input_tokens_seen": 2840512, |
| "step": 6925 |
| }, |
| { |
| "epoch": 8.389830508474576, |
| "grad_norm": 1.4197776317596436, |
| "learning_rate": 3.851591284507591e-06, |
| "loss": 0.0433, |
| "num_input_tokens_seen": 2842592, |
| "step": 6930 |
| }, |
| { |
| "epoch": 8.39588377723971, |
| "grad_norm": 4.4109883308410645, |
| "learning_rate": 3.82346793672351e-06, |
| "loss": 0.1743, |
| "num_input_tokens_seen": 2844576, |
| "step": 6935 |
| }, |
| { |
| "epoch": 8.401937046004843, |
| "grad_norm": 0.10218428820371628, |
| "learning_rate": 3.795439136280346e-06, |
| "loss": 0.0671, |
| "num_input_tokens_seen": 2846720, |
| "step": 6940 |
| }, |
| { |
| "epoch": 8.407990314769975, |
| "grad_norm": 2.4533486366271973, |
| "learning_rate": 3.767505008318914e-06, |
| "loss": 0.1105, |
| "num_input_tokens_seen": 2848832, |
| "step": 6945 |
| }, |
| { |
| "epoch": 8.41404358353511, |
| "grad_norm": 0.9111641049385071, |
| "learning_rate": 3.739665677557341e-06, |
| "loss": 0.0978, |
| "num_input_tokens_seen": 2850880, |
| "step": 6950 |
| }, |
| { |
| "epoch": 8.420096852300242, |
| "grad_norm": 0.06459851562976837, |
| "learning_rate": 3.711921268290533e-06, |
| "loss": 0.0228, |
| "num_input_tokens_seen": 2852896, |
| "step": 6955 |
| }, |
| { |
| "epoch": 8.426150121065376, |
| "grad_norm": 0.08616799116134644, |
| "learning_rate": 3.6842719043895748e-06, |
| "loss": 0.1082, |
| "num_input_tokens_seen": 2855008, |
| "step": 6960 |
| }, |
| { |
| "epoch": 8.432203389830509, |
| "grad_norm": 0.536651611328125, |
| "learning_rate": 3.656717709301194e-06, |
| "loss": 0.0382, |
| "num_input_tokens_seen": 2856960, |
| "step": 6965 |
| }, |
| { |
| "epoch": 8.438256658595641, |
| "grad_norm": 5.659543514251709, |
| "learning_rate": 3.629258806047231e-06, |
| "loss": 0.1379, |
| "num_input_tokens_seen": 2859200, |
| "step": 6970 |
| }, |
| { |
| "epoch": 8.444309927360775, |
| "grad_norm": 1.424406886100769, |
| "learning_rate": 3.60189531722408e-06, |
| "loss": 0.0356, |
| "num_input_tokens_seen": 2861280, |
| "step": 6975 |
| }, |
| { |
| "epoch": 8.450363196125908, |
| "grad_norm": 1.0679043531417847, |
| "learning_rate": 3.5746273650021228e-06, |
| "loss": 0.013, |
| "num_input_tokens_seen": 2863392, |
| "step": 6980 |
| }, |
| { |
| "epoch": 8.456416464891042, |
| "grad_norm": 4.228886604309082, |
| "learning_rate": 3.5474550711252026e-06, |
| "loss": 0.0767, |
| "num_input_tokens_seen": 2865344, |
| "step": 6985 |
| }, |
| { |
| "epoch": 8.462469733656174, |
| "grad_norm": 3.4282588958740234, |
| "learning_rate": 3.5203785569100674e-06, |
| "loss": 0.1068, |
| "num_input_tokens_seen": 2867424, |
| "step": 6990 |
| }, |
| { |
| "epoch": 8.468523002421307, |
| "grad_norm": 0.013153821229934692, |
| "learning_rate": 3.493397943245852e-06, |
| "loss": 0.0051, |
| "num_input_tokens_seen": 2869472, |
| "step": 6995 |
| }, |
| { |
| "epoch": 8.474576271186441, |
| "grad_norm": 1.3492847681045532, |
| "learning_rate": 3.466513350593506e-06, |
| "loss": 0.083, |
| "num_input_tokens_seen": 2871680, |
| "step": 7000 |
| }, |
| { |
| "epoch": 8.480629539951574, |
| "grad_norm": 0.17737948894500732, |
| "learning_rate": 3.439724898985278e-06, |
| "loss": 0.0866, |
| "num_input_tokens_seen": 2873760, |
| "step": 7005 |
| }, |
| { |
| "epoch": 8.486682808716708, |
| "grad_norm": 0.177162766456604, |
| "learning_rate": 3.4130327080241636e-06, |
| "loss": 0.1555, |
| "num_input_tokens_seen": 2875712, |
| "step": 7010 |
| }, |
| { |
| "epoch": 8.49273607748184, |
| "grad_norm": 1.8084608316421509, |
| "learning_rate": 3.3864368968834074e-06, |
| "loss": 0.0909, |
| "num_input_tokens_seen": 2877696, |
| "step": 7015 |
| }, |
| { |
| "epoch": 8.498789346246973, |
| "grad_norm": 4.3322858810424805, |
| "learning_rate": 3.3599375843059193e-06, |
| "loss": 0.0458, |
| "num_input_tokens_seen": 2879680, |
| "step": 7020 |
| }, |
| { |
| "epoch": 8.5, |
| "eval_loss": 0.1609281599521637, |
| "eval_runtime": 4.5734, |
| "eval_samples_per_second": 80.246, |
| "eval_steps_per_second": 20.116, |
| "num_input_tokens_seen": 2880128, |
| "step": 7021 |
| }, |
| { |
| "epoch": 8.504842615012107, |
| "grad_norm": 2.0026533603668213, |
| "learning_rate": 3.3335348886037815e-06, |
| "loss": 0.0488, |
| "num_input_tokens_seen": 2881728, |
| "step": 7025 |
| }, |
| { |
| "epoch": 8.51089588377724, |
| "grad_norm": 0.5009611248970032, |
| "learning_rate": 3.3072289276576964e-06, |
| "loss": 0.1506, |
| "num_input_tokens_seen": 2883744, |
| "step": 7030 |
| }, |
| { |
| "epoch": 8.516949152542374, |
| "grad_norm": 0.33006390929222107, |
| "learning_rate": 3.281019818916492e-06, |
| "loss": 0.0674, |
| "num_input_tokens_seen": 2885792, |
| "step": 7035 |
| }, |
| { |
| "epoch": 8.523002421307506, |
| "grad_norm": 4.603799819946289, |
| "learning_rate": 3.254907679396574e-06, |
| "loss": 0.0554, |
| "num_input_tokens_seen": 2888000, |
| "step": 7040 |
| }, |
| { |
| "epoch": 8.529055690072639, |
| "grad_norm": 7.967130661010742, |
| "learning_rate": 3.2288926256813846e-06, |
| "loss": 0.0574, |
| "num_input_tokens_seen": 2890016, |
| "step": 7045 |
| }, |
| { |
| "epoch": 8.535108958837773, |
| "grad_norm": 6.041900157928467, |
| "learning_rate": 3.2029747739209247e-06, |
| "loss": 0.0822, |
| "num_input_tokens_seen": 2891968, |
| "step": 7050 |
| }, |
| { |
| "epoch": 8.541162227602905, |
| "grad_norm": 2.6833653450012207, |
| "learning_rate": 3.177154239831223e-06, |
| "loss": 0.0605, |
| "num_input_tokens_seen": 2893952, |
| "step": 7055 |
| }, |
| { |
| "epoch": 8.54721549636804, |
| "grad_norm": 6.842079162597656, |
| "learning_rate": 3.1514311386937917e-06, |
| "loss": 0.167, |
| "num_input_tokens_seen": 2895904, |
| "step": 7060 |
| }, |
| { |
| "epoch": 8.553268765133172, |
| "grad_norm": 0.07613459974527359, |
| "learning_rate": 3.1258055853551487e-06, |
| "loss": 0.0747, |
| "num_input_tokens_seen": 2897952, |
| "step": 7065 |
| }, |
| { |
| "epoch": 8.559322033898304, |
| "grad_norm": 0.6995208263397217, |
| "learning_rate": 3.1002776942262696e-06, |
| "loss": 0.0433, |
| "num_input_tokens_seen": 2900064, |
| "step": 7070 |
| }, |
| { |
| "epoch": 8.565375302663439, |
| "grad_norm": 4.104430675506592, |
| "learning_rate": 3.0748475792821197e-06, |
| "loss": 0.1335, |
| "num_input_tokens_seen": 2902432, |
| "step": 7075 |
| }, |
| { |
| "epoch": 8.571428571428571, |
| "grad_norm": 5.85823917388916, |
| "learning_rate": 3.0495153540611e-06, |
| "loss": 0.0937, |
| "num_input_tokens_seen": 2904512, |
| "step": 7080 |
| }, |
| { |
| "epoch": 8.577481840193705, |
| "grad_norm": 1.4460917711257935, |
| "learning_rate": 3.024281131664569e-06, |
| "loss": 0.0436, |
| "num_input_tokens_seen": 2906496, |
| "step": 7085 |
| }, |
| { |
| "epoch": 8.583535108958838, |
| "grad_norm": 0.2464975118637085, |
| "learning_rate": 2.999145024756325e-06, |
| "loss": 0.1751, |
| "num_input_tokens_seen": 2908544, |
| "step": 7090 |
| }, |
| { |
| "epoch": 8.58958837772397, |
| "grad_norm": 6.364808082580566, |
| "learning_rate": 2.9741071455621245e-06, |
| "loss": 0.0699, |
| "num_input_tokens_seen": 2910688, |
| "step": 7095 |
| }, |
| { |
| "epoch": 8.595641646489105, |
| "grad_norm": 0.0688992291688919, |
| "learning_rate": 2.9491676058691437e-06, |
| "loss": 0.1593, |
| "num_input_tokens_seen": 2912832, |
| "step": 7100 |
| }, |
| { |
| "epoch": 8.601694915254237, |
| "grad_norm": 0.6298401355743408, |
| "learning_rate": 2.924326517025508e-06, |
| "loss": 0.1751, |
| "num_input_tokens_seen": 2914816, |
| "step": 7105 |
| }, |
| { |
| "epoch": 8.607748184019371, |
| "grad_norm": 2.046719551086426, |
| "learning_rate": 2.8995839899397915e-06, |
| "loss": 0.0117, |
| "num_input_tokens_seen": 2916928, |
| "step": 7110 |
| }, |
| { |
| "epoch": 8.613801452784504, |
| "grad_norm": 6.791380405426025, |
| "learning_rate": 2.8749401350805115e-06, |
| "loss": 0.0582, |
| "num_input_tokens_seen": 2918912, |
| "step": 7115 |
| }, |
| { |
| "epoch": 8.619854721549636, |
| "grad_norm": 7.068711280822754, |
| "learning_rate": 2.8503950624756415e-06, |
| "loss": 0.1209, |
| "num_input_tokens_seen": 2920896, |
| "step": 7120 |
| }, |
| { |
| "epoch": 8.62590799031477, |
| "grad_norm": 0.11452826112508774, |
| "learning_rate": 2.825948881712123e-06, |
| "loss": 0.0824, |
| "num_input_tokens_seen": 2922976, |
| "step": 7125 |
| }, |
| { |
| "epoch": 8.631961259079903, |
| "grad_norm": 4.309703350067139, |
| "learning_rate": 2.801601701935369e-06, |
| "loss": 0.0265, |
| "num_input_tokens_seen": 2925120, |
| "step": 7130 |
| }, |
| { |
| "epoch": 8.638014527845037, |
| "grad_norm": 5.783072471618652, |
| "learning_rate": 2.777353631848789e-06, |
| "loss": 0.2264, |
| "num_input_tokens_seen": 2927072, |
| "step": 7135 |
| }, |
| { |
| "epoch": 8.64406779661017, |
| "grad_norm": 6.108299255371094, |
| "learning_rate": 2.7532047797132867e-06, |
| "loss": 0.1097, |
| "num_input_tokens_seen": 2929152, |
| "step": 7140 |
| }, |
| { |
| "epoch": 8.650121065375302, |
| "grad_norm": 1.342014193534851, |
| "learning_rate": 2.7291552533467853e-06, |
| "loss": 0.0541, |
| "num_input_tokens_seen": 2931136, |
| "step": 7145 |
| }, |
| { |
| "epoch": 8.656174334140436, |
| "grad_norm": 0.19719941914081573, |
| "learning_rate": 2.7052051601237473e-06, |
| "loss": 0.0733, |
| "num_input_tokens_seen": 2933312, |
| "step": 7150 |
| }, |
| { |
| "epoch": 8.662227602905569, |
| "grad_norm": 5.709043979644775, |
| "learning_rate": 2.681354606974698e-06, |
| "loss": 0.1117, |
| "num_input_tokens_seen": 2935328, |
| "step": 7155 |
| }, |
| { |
| "epoch": 8.668280871670703, |
| "grad_norm": 7.4091901779174805, |
| "learning_rate": 2.6576037003857414e-06, |
| "loss": 0.1103, |
| "num_input_tokens_seen": 2937216, |
| "step": 7160 |
| }, |
| { |
| "epoch": 8.674334140435835, |
| "grad_norm": 4.7495527267456055, |
| "learning_rate": 2.633952546398083e-06, |
| "loss": 0.0773, |
| "num_input_tokens_seen": 2939168, |
| "step": 7165 |
| }, |
| { |
| "epoch": 8.680387409200968, |
| "grad_norm": 6.540948867797852, |
| "learning_rate": 2.6104012506075692e-06, |
| "loss": 0.0429, |
| "num_input_tokens_seen": 2941504, |
| "step": 7170 |
| }, |
| { |
| "epoch": 8.686440677966102, |
| "grad_norm": 5.340511322021484, |
| "learning_rate": 2.5869499181641916e-06, |
| "loss": 0.1727, |
| "num_input_tokens_seen": 2943520, |
| "step": 7175 |
| }, |
| { |
| "epoch": 8.692493946731235, |
| "grad_norm": 9.046024322509766, |
| "learning_rate": 2.5635986537716538e-06, |
| "loss": 0.1482, |
| "num_input_tokens_seen": 2945568, |
| "step": 7180 |
| }, |
| { |
| "epoch": 8.698547215496369, |
| "grad_norm": 6.008487701416016, |
| "learning_rate": 2.540347561686873e-06, |
| "loss": 0.0563, |
| "num_input_tokens_seen": 2947488, |
| "step": 7185 |
| }, |
| { |
| "epoch": 8.704600484261501, |
| "grad_norm": 1.535462498664856, |
| "learning_rate": 2.5171967457195216e-06, |
| "loss": 0.2149, |
| "num_input_tokens_seen": 2949504, |
| "step": 7190 |
| }, |
| { |
| "epoch": 8.710653753026634, |
| "grad_norm": 1.0134094953536987, |
| "learning_rate": 2.494146309231571e-06, |
| "loss": 0.1471, |
| "num_input_tokens_seen": 2951552, |
| "step": 7195 |
| }, |
| { |
| "epoch": 8.716707021791768, |
| "grad_norm": 8.139573097229004, |
| "learning_rate": 2.471196355136826e-06, |
| "loss": 0.1541, |
| "num_input_tokens_seen": 2953632, |
| "step": 7200 |
| }, |
| { |
| "epoch": 8.7227602905569, |
| "grad_norm": 0.31339648365974426, |
| "learning_rate": 2.4483469859004625e-06, |
| "loss": 0.1033, |
| "num_input_tokens_seen": 2955936, |
| "step": 7205 |
| }, |
| { |
| "epoch": 8.728813559322035, |
| "grad_norm": 2.6392133235931396, |
| "learning_rate": 2.425598303538576e-06, |
| "loss": 0.0152, |
| "num_input_tokens_seen": 2958048, |
| "step": 7210 |
| }, |
| { |
| "epoch": 8.734866828087167, |
| "grad_norm": 0.007008890621364117, |
| "learning_rate": 2.402950409617727e-06, |
| "loss": 0.0336, |
| "num_input_tokens_seen": 2960160, |
| "step": 7215 |
| }, |
| { |
| "epoch": 8.7409200968523, |
| "grad_norm": 0.641621470451355, |
| "learning_rate": 2.380403405254475e-06, |
| "loss": 0.1413, |
| "num_input_tokens_seen": 2962208, |
| "step": 7220 |
| }, |
| { |
| "epoch": 8.746973365617434, |
| "grad_norm": 0.4098236858844757, |
| "learning_rate": 2.35795739111494e-06, |
| "loss": 0.0205, |
| "num_input_tokens_seen": 2964320, |
| "step": 7225 |
| }, |
| { |
| "epoch": 8.753026634382566, |
| "grad_norm": 1.6772291660308838, |
| "learning_rate": 2.335612467414344e-06, |
| "loss": 0.1145, |
| "num_input_tokens_seen": 2966272, |
| "step": 7230 |
| }, |
| { |
| "epoch": 8.7590799031477, |
| "grad_norm": 1.6794875860214233, |
| "learning_rate": 2.313368733916585e-06, |
| "loss": 0.0659, |
| "num_input_tokens_seen": 2968288, |
| "step": 7235 |
| }, |
| { |
| "epoch": 8.765133171912833, |
| "grad_norm": 6.174964427947998, |
| "learning_rate": 2.291226289933751e-06, |
| "loss": 0.1205, |
| "num_input_tokens_seen": 2970208, |
| "step": 7240 |
| }, |
| { |
| "epoch": 8.771186440677965, |
| "grad_norm": 0.636359691619873, |
| "learning_rate": 2.2691852343257157e-06, |
| "loss": 0.0074, |
| "num_input_tokens_seen": 2972352, |
| "step": 7245 |
| }, |
| { |
| "epoch": 8.7772397094431, |
| "grad_norm": 1.1045042276382446, |
| "learning_rate": 2.2472456654996755e-06, |
| "loss": 0.1758, |
| "num_input_tokens_seen": 2974368, |
| "step": 7250 |
| }, |
| { |
| "epoch": 8.783292978208232, |
| "grad_norm": 6.679035186767578, |
| "learning_rate": 2.2254076814097163e-06, |
| "loss": 0.1391, |
| "num_input_tokens_seen": 2976288, |
| "step": 7255 |
| }, |
| { |
| "epoch": 8.789346246973366, |
| "grad_norm": 6.327536582946777, |
| "learning_rate": 2.203671379556388e-06, |
| "loss": 0.2639, |
| "num_input_tokens_seen": 2978240, |
| "step": 7260 |
| }, |
| { |
| "epoch": 8.795399515738499, |
| "grad_norm": 6.892092704772949, |
| "learning_rate": 2.1820368569862444e-06, |
| "loss": 0.1743, |
| "num_input_tokens_seen": 2980256, |
| "step": 7265 |
| }, |
| { |
| "epoch": 8.801452784503631, |
| "grad_norm": 4.450016975402832, |
| "learning_rate": 2.1605042102914227e-06, |
| "loss": 0.1708, |
| "num_input_tokens_seen": 2982400, |
| "step": 7270 |
| }, |
| { |
| "epoch": 8.807506053268765, |
| "grad_norm": 7.299108028411865, |
| "learning_rate": 2.1390735356092206e-06, |
| "loss": 0.168, |
| "num_input_tokens_seen": 2984416, |
| "step": 7275 |
| }, |
| { |
| "epoch": 8.813559322033898, |
| "grad_norm": 0.5720050930976868, |
| "learning_rate": 2.1177449286216565e-06, |
| "loss": 0.1734, |
| "num_input_tokens_seen": 2986496, |
| "step": 7280 |
| }, |
| { |
| "epoch": 8.819612590799032, |
| "grad_norm": 2.3085198402404785, |
| "learning_rate": 2.0965184845550407e-06, |
| "loss": 0.0285, |
| "num_input_tokens_seen": 2988512, |
| "step": 7285 |
| }, |
| { |
| "epoch": 8.825665859564165, |
| "grad_norm": 2.5211293697357178, |
| "learning_rate": 2.075394298179553e-06, |
| "loss": 0.0939, |
| "num_input_tokens_seen": 2990560, |
| "step": 7290 |
| }, |
| { |
| "epoch": 8.831719128329297, |
| "grad_norm": 11.825849533081055, |
| "learning_rate": 2.0543724638088347e-06, |
| "loss": 0.1561, |
| "num_input_tokens_seen": 2992768, |
| "step": 7295 |
| }, |
| { |
| "epoch": 8.837772397094431, |
| "grad_norm": 4.789031982421875, |
| "learning_rate": 2.0334530752995433e-06, |
| "loss": 0.0939, |
| "num_input_tokens_seen": 2994784, |
| "step": 7300 |
| }, |
| { |
| "epoch": 8.843825665859564, |
| "grad_norm": 0.1911478191614151, |
| "learning_rate": 2.01263622605094e-06, |
| "loss": 0.1379, |
| "num_input_tokens_seen": 2996896, |
| "step": 7305 |
| }, |
| { |
| "epoch": 8.849878934624698, |
| "grad_norm": 1.790691614151001, |
| "learning_rate": 1.991922009004485e-06, |
| "loss": 0.1036, |
| "num_input_tokens_seen": 2998976, |
| "step": 7310 |
| }, |
| { |
| "epoch": 8.85593220338983, |
| "grad_norm": 0.69582200050354, |
| "learning_rate": 1.9713105166434042e-06, |
| "loss": 0.1181, |
| "num_input_tokens_seen": 3001184, |
| "step": 7315 |
| }, |
| { |
| "epoch": 8.861985472154963, |
| "grad_norm": 5.200904846191406, |
| "learning_rate": 1.950801840992303e-06, |
| "loss": 0.1421, |
| "num_input_tokens_seen": 3003168, |
| "step": 7320 |
| }, |
| { |
| "epoch": 8.868038740920097, |
| "grad_norm": 0.38341599702835083, |
| "learning_rate": 1.930396073616725e-06, |
| "loss": 0.1463, |
| "num_input_tokens_seen": 3005152, |
| "step": 7325 |
| }, |
| { |
| "epoch": 8.87409200968523, |
| "grad_norm": 0.5471208691596985, |
| "learning_rate": 1.9100933056227593e-06, |
| "loss": 0.0775, |
| "num_input_tokens_seen": 3007200, |
| "step": 7330 |
| }, |
| { |
| "epoch": 8.880145278450364, |
| "grad_norm": 0.09188104420900345, |
| "learning_rate": 1.8898936276566303e-06, |
| "loss": 0.0454, |
| "num_input_tokens_seen": 3009280, |
| "step": 7335 |
| }, |
| { |
| "epoch": 8.886198547215496, |
| "grad_norm": 5.813639163970947, |
| "learning_rate": 1.8697971299043048e-06, |
| "loss": 0.1039, |
| "num_input_tokens_seen": 3011360, |
| "step": 7340 |
| }, |
| { |
| "epoch": 8.892251815980629, |
| "grad_norm": 1.5798746347427368, |
| "learning_rate": 1.8498039020910628e-06, |
| "loss": 0.0886, |
| "num_input_tokens_seen": 3013568, |
| "step": 7345 |
| }, |
| { |
| "epoch": 8.898305084745763, |
| "grad_norm": 3.015583038330078, |
| "learning_rate": 1.8299140334811226e-06, |
| "loss": 0.0553, |
| "num_input_tokens_seen": 3015552, |
| "step": 7350 |
| }, |
| { |
| "epoch": 8.904358353510895, |
| "grad_norm": 8.158613204956055, |
| "learning_rate": 1.8101276128772272e-06, |
| "loss": 0.1808, |
| "num_input_tokens_seen": 3017536, |
| "step": 7355 |
| }, |
| { |
| "epoch": 8.91041162227603, |
| "grad_norm": 1.8312183618545532, |
| "learning_rate": 1.7904447286202607e-06, |
| "loss": 0.1005, |
| "num_input_tokens_seen": 3019584, |
| "step": 7360 |
| }, |
| { |
| "epoch": 8.916464891041162, |
| "grad_norm": 5.6660919189453125, |
| "learning_rate": 1.7708654685888337e-06, |
| "loss": 0.0898, |
| "num_input_tokens_seen": 3021728, |
| "step": 7365 |
| }, |
| { |
| "epoch": 8.922518159806295, |
| "grad_norm": 0.28093379735946655, |
| "learning_rate": 1.7513899201989148e-06, |
| "loss": 0.0113, |
| "num_input_tokens_seen": 3023584, |
| "step": 7370 |
| }, |
| { |
| "epoch": 8.928571428571429, |
| "grad_norm": 8.074005126953125, |
| "learning_rate": 1.7320181704034237e-06, |
| "loss": 0.1523, |
| "num_input_tokens_seen": 3025600, |
| "step": 7375 |
| }, |
| { |
| "epoch": 8.934624697336561, |
| "grad_norm": 2.8498823642730713, |
| "learning_rate": 1.7127503056918542e-06, |
| "loss": 0.0602, |
| "num_input_tokens_seen": 3027680, |
| "step": 7380 |
| }, |
| { |
| "epoch": 8.940677966101696, |
| "grad_norm": 0.15879835188388824, |
| "learning_rate": 1.6935864120898704e-06, |
| "loss": 0.0356, |
| "num_input_tokens_seen": 3029856, |
| "step": 7385 |
| }, |
| { |
| "epoch": 8.946731234866828, |
| "grad_norm": 7.197122097015381, |
| "learning_rate": 1.674526575158944e-06, |
| "loss": 0.1736, |
| "num_input_tokens_seen": 3032096, |
| "step": 7390 |
| }, |
| { |
| "epoch": 8.95278450363196, |
| "grad_norm": 0.51031494140625, |
| "learning_rate": 1.6555708799959547e-06, |
| "loss": 0.0252, |
| "num_input_tokens_seen": 3034112, |
| "step": 7395 |
| }, |
| { |
| "epoch": 8.958837772397095, |
| "grad_norm": 0.7516043186187744, |
| "learning_rate": 1.6367194112328288e-06, |
| "loss": 0.0302, |
| "num_input_tokens_seen": 3036096, |
| "step": 7400 |
| }, |
| { |
| "epoch": 8.964891041162227, |
| "grad_norm": 0.05814617499709129, |
| "learning_rate": 1.617972253036143e-06, |
| "loss": 0.099, |
| "num_input_tokens_seen": 3038080, |
| "step": 7405 |
| }, |
| { |
| "epoch": 8.970944309927361, |
| "grad_norm": 0.5936756730079651, |
| "learning_rate": 1.5993294891067573e-06, |
| "loss": 0.0268, |
| "num_input_tokens_seen": 3040064, |
| "step": 7410 |
| }, |
| { |
| "epoch": 8.976997578692494, |
| "grad_norm": 1.6873228549957275, |
| "learning_rate": 1.580791202679438e-06, |
| "loss": 0.1383, |
| "num_input_tokens_seen": 3042048, |
| "step": 7415 |
| }, |
| { |
| "epoch": 8.983050847457626, |
| "grad_norm": 7.362498760223389, |
| "learning_rate": 1.562357476522497e-06, |
| "loss": 0.0392, |
| "num_input_tokens_seen": 3044192, |
| "step": 7420 |
| }, |
| { |
| "epoch": 8.98910411622276, |
| "grad_norm": 1.2069581747055054, |
| "learning_rate": 1.5440283929374023e-06, |
| "loss": 0.0879, |
| "num_input_tokens_seen": 3046112, |
| "step": 7425 |
| }, |
| { |
| "epoch": 8.995157384987893, |
| "grad_norm": 1.0542585849761963, |
| "learning_rate": 1.5258040337584322e-06, |
| "loss": 0.1856, |
| "num_input_tokens_seen": 3048000, |
| "step": 7430 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_loss": 0.16094733774662018, |
| "eval_runtime": 4.5518, |
| "eval_samples_per_second": 80.628, |
| "eval_steps_per_second": 20.212, |
| "num_input_tokens_seen": 3049392, |
| "step": 7434 |
| }, |
| { |
| "epoch": 9.001210653753027, |
| "grad_norm": 1.983082890510559, |
| "learning_rate": 1.5076844803522922e-06, |
| "loss": 0.0777, |
| "num_input_tokens_seen": 3049808, |
| "step": 7435 |
| }, |
| { |
| "epoch": 9.00726392251816, |
| "grad_norm": 5.638378620147705, |
| "learning_rate": 1.4896698136177612e-06, |
| "loss": 0.1153, |
| "num_input_tokens_seen": 3051792, |
| "step": 7440 |
| }, |
| { |
| "epoch": 9.013317191283292, |
| "grad_norm": 9.8755521774292, |
| "learning_rate": 1.4717601139853266e-06, |
| "loss": 0.0989, |
| "num_input_tokens_seen": 3053776, |
| "step": 7445 |
| }, |
| { |
| "epoch": 9.019370460048426, |
| "grad_norm": 0.596442461013794, |
| "learning_rate": 1.4539554614168339e-06, |
| "loss": 0.0655, |
| "num_input_tokens_seen": 3055856, |
| "step": 7450 |
| }, |
| { |
| "epoch": 9.025423728813559, |
| "grad_norm": 2.234306573867798, |
| "learning_rate": 1.4362559354051092e-06, |
| "loss": 0.0259, |
| "num_input_tokens_seen": 3057840, |
| "step": 7455 |
| }, |
| { |
| "epoch": 9.031476997578693, |
| "grad_norm": 2.3881747722625732, |
| "learning_rate": 1.4186616149736349e-06, |
| "loss": 0.2286, |
| "num_input_tokens_seen": 3059920, |
| "step": 7460 |
| }, |
| { |
| "epoch": 9.037530266343826, |
| "grad_norm": 1.5024694204330444, |
| "learning_rate": 1.401172578676166e-06, |
| "loss": 0.1341, |
| "num_input_tokens_seen": 3061872, |
| "step": 7465 |
| }, |
| { |
| "epoch": 9.043583535108958, |
| "grad_norm": 0.1409914493560791, |
| "learning_rate": 1.383788904596403e-06, |
| "loss": 0.0601, |
| "num_input_tokens_seen": 3063888, |
| "step": 7470 |
| }, |
| { |
| "epoch": 9.049636803874092, |
| "grad_norm": 5.075223922729492, |
| "learning_rate": 1.3665106703476178e-06, |
| "loss": 0.1218, |
| "num_input_tokens_seen": 3065872, |
| "step": 7475 |
| }, |
| { |
| "epoch": 9.055690072639225, |
| "grad_norm": 4.891570568084717, |
| "learning_rate": 1.349337953072341e-06, |
| "loss": 0.1693, |
| "num_input_tokens_seen": 3067888, |
| "step": 7480 |
| }, |
| { |
| "epoch": 9.061743341404359, |
| "grad_norm": 1.4571635723114014, |
| "learning_rate": 1.3322708294419923e-06, |
| "loss": 0.0342, |
| "num_input_tokens_seen": 3069968, |
| "step": 7485 |
| }, |
| { |
| "epoch": 9.067796610169491, |
| "grad_norm": 0.18257658183574677, |
| "learning_rate": 1.3153093756565426e-06, |
| "loss": 0.0094, |
| "num_input_tokens_seen": 3072176, |
| "step": 7490 |
| }, |
| { |
| "epoch": 9.073849878934624, |
| "grad_norm": 0.030617251992225647, |
| "learning_rate": 1.298453667444169e-06, |
| "loss": 0.0444, |
| "num_input_tokens_seen": 3074288, |
| "step": 7495 |
| }, |
| { |
| "epoch": 9.079903147699758, |
| "grad_norm": 4.042976379394531, |
| "learning_rate": 1.281703780060947e-06, |
| "loss": 0.0983, |
| "num_input_tokens_seen": 3076304, |
| "step": 7500 |
| }, |
| { |
| "epoch": 9.08595641646489, |
| "grad_norm": 0.46019235253334045, |
| "learning_rate": 1.265059788290468e-06, |
| "loss": 0.0984, |
| "num_input_tokens_seen": 3078320, |
| "step": 7505 |
| }, |
| { |
| "epoch": 9.092009685230025, |
| "grad_norm": 0.3823973536491394, |
| "learning_rate": 1.2485217664435418e-06, |
| "loss": 0.0429, |
| "num_input_tokens_seen": 3080464, |
| "step": 7510 |
| }, |
| { |
| "epoch": 9.098062953995157, |
| "grad_norm": 1.2773817777633667, |
| "learning_rate": 1.232089788357843e-06, |
| "loss": 0.0618, |
| "num_input_tokens_seen": 3082672, |
| "step": 7515 |
| }, |
| { |
| "epoch": 9.104116222760291, |
| "grad_norm": 6.81667423248291, |
| "learning_rate": 1.2157639273975979e-06, |
| "loss": 0.2343, |
| "num_input_tokens_seen": 3084720, |
| "step": 7520 |
| }, |
| { |
| "epoch": 9.110169491525424, |
| "grad_norm": 3.501394748687744, |
| "learning_rate": 1.19954425645325e-06, |
| "loss": 0.1071, |
| "num_input_tokens_seen": 3086864, |
| "step": 7525 |
| }, |
| { |
| "epoch": 9.116222760290556, |
| "grad_norm": 4.856332778930664, |
| "learning_rate": 1.183430847941125e-06, |
| "loss": 0.1255, |
| "num_input_tokens_seen": 3088880, |
| "step": 7530 |
| }, |
| { |
| "epoch": 9.12227602905569, |
| "grad_norm": 6.885472774505615, |
| "learning_rate": 1.1674237738031223e-06, |
| "loss": 0.1039, |
| "num_input_tokens_seen": 3090960, |
| "step": 7535 |
| }, |
| { |
| "epoch": 9.128329297820823, |
| "grad_norm": 0.33454495668411255, |
| "learning_rate": 1.1515231055063914e-06, |
| "loss": 0.1404, |
| "num_input_tokens_seen": 3093040, |
| "step": 7540 |
| }, |
| { |
| "epoch": 9.134382566585957, |
| "grad_norm": 4.594442367553711, |
| "learning_rate": 1.135728914043005e-06, |
| "loss": 0.0211, |
| "num_input_tokens_seen": 3095024, |
| "step": 7545 |
| }, |
| { |
| "epoch": 9.14043583535109, |
| "grad_norm": 3.8089771270751953, |
| "learning_rate": 1.120041269929642e-06, |
| "loss": 0.0929, |
| "num_input_tokens_seen": 3097008, |
| "step": 7550 |
| }, |
| { |
| "epoch": 9.146489104116222, |
| "grad_norm": 5.433687210083008, |
| "learning_rate": 1.1044602432072836e-06, |
| "loss": 0.1376, |
| "num_input_tokens_seen": 3099184, |
| "step": 7555 |
| }, |
| { |
| "epoch": 9.152542372881356, |
| "grad_norm": 3.2371695041656494, |
| "learning_rate": 1.0889859034408922e-06, |
| "loss": 0.0278, |
| "num_input_tokens_seen": 3101328, |
| "step": 7560 |
| }, |
| { |
| "epoch": 9.158595641646489, |
| "grad_norm": 7.783466815948486, |
| "learning_rate": 1.0736183197191024e-06, |
| "loss": 0.0766, |
| "num_input_tokens_seen": 3103408, |
| "step": 7565 |
| }, |
| { |
| "epoch": 9.164648910411623, |
| "grad_norm": 1.0674914121627808, |
| "learning_rate": 1.0583575606539108e-06, |
| "loss": 0.1019, |
| "num_input_tokens_seen": 3105616, |
| "step": 7570 |
| }, |
| { |
| "epoch": 9.170702179176756, |
| "grad_norm": 0.39573797583580017, |
| "learning_rate": 1.0432036943803708e-06, |
| "loss": 0.0384, |
| "num_input_tokens_seen": 3107536, |
| "step": 7575 |
| }, |
| { |
| "epoch": 9.176755447941888, |
| "grad_norm": 0.9420876502990723, |
| "learning_rate": 1.0281567885562947e-06, |
| "loss": 0.1868, |
| "num_input_tokens_seen": 3109648, |
| "step": 7580 |
| }, |
| { |
| "epoch": 9.182808716707022, |
| "grad_norm": 0.4029005169868469, |
| "learning_rate": 1.0132169103619444e-06, |
| "loss": 0.0853, |
| "num_input_tokens_seen": 3111504, |
| "step": 7585 |
| }, |
| { |
| "epoch": 9.188861985472155, |
| "grad_norm": 5.7842698097229, |
| "learning_rate": 9.98384126499735e-07, |
| "loss": 0.0881, |
| "num_input_tokens_seen": 3113424, |
| "step": 7590 |
| }, |
| { |
| "epoch": 9.194915254237289, |
| "grad_norm": 6.040023326873779, |
| "learning_rate": 9.836585031939154e-07, |
| "loss": 0.107, |
| "num_input_tokens_seen": 3115504, |
| "step": 7595 |
| }, |
| { |
| "epoch": 9.200968523002421, |
| "grad_norm": 0.3490646481513977, |
| "learning_rate": 9.690401061903249e-07, |
| "loss": 0.0503, |
| "num_input_tokens_seen": 3117488, |
| "step": 7600 |
| }, |
| { |
| "epoch": 9.207021791767554, |
| "grad_norm": 4.309531211853027, |
| "learning_rate": 9.545290007560437e-07, |
| "loss": 0.0953, |
| "num_input_tokens_seen": 3119376, |
| "step": 7605 |
| }, |
| { |
| "epoch": 9.213075060532688, |
| "grad_norm": 0.2243291288614273, |
| "learning_rate": 9.401252516791304e-07, |
| "loss": 0.1075, |
| "num_input_tokens_seen": 3121424, |
| "step": 7610 |
| }, |
| { |
| "epoch": 9.21912832929782, |
| "grad_norm": 6.078351020812988, |
| "learning_rate": 9.258289232683321e-07, |
| "loss": 0.15, |
| "num_input_tokens_seen": 3123504, |
| "step": 7615 |
| }, |
| { |
| "epoch": 9.225181598062955, |
| "grad_norm": 0.08517712354660034, |
| "learning_rate": 9.11640079352788e-07, |
| "loss": 0.1062, |
| "num_input_tokens_seen": 3125712, |
| "step": 7620 |
| }, |
| { |
| "epoch": 9.231234866828087, |
| "grad_norm": 3.3524436950683594, |
| "learning_rate": 8.975587832817545e-07, |
| "loss": 0.136, |
| "num_input_tokens_seen": 3127824, |
| "step": 7625 |
| }, |
| { |
| "epoch": 9.23728813559322, |
| "grad_norm": 1.0113067626953125, |
| "learning_rate": 8.835850979243055e-07, |
| "loss": 0.081, |
| "num_input_tokens_seen": 3129936, |
| "step": 7630 |
| }, |
| { |
| "epoch": 9.243341404358354, |
| "grad_norm": 6.101165294647217, |
| "learning_rate": 8.697190856690685e-07, |
| "loss": 0.0731, |
| "num_input_tokens_seen": 3131984, |
| "step": 7635 |
| }, |
| { |
| "epoch": 9.249394673123486, |
| "grad_norm": 7.550969123840332, |
| "learning_rate": 8.559608084239474e-07, |
| "loss": 0.0445, |
| "num_input_tokens_seen": 3134064, |
| "step": 7640 |
| }, |
| { |
| "epoch": 9.25544794188862, |
| "grad_norm": 0.6591706275939941, |
| "learning_rate": 8.423103276158306e-07, |
| "loss": 0.054, |
| "num_input_tokens_seen": 3136176, |
| "step": 7645 |
| }, |
| { |
| "epoch": 9.261501210653753, |
| "grad_norm": 2.5267579555511475, |
| "learning_rate": 8.287677041903308e-07, |
| "loss": 0.0777, |
| "num_input_tokens_seen": 3138288, |
| "step": 7650 |
| }, |
| { |
| "epoch": 9.267554479418886, |
| "grad_norm": 6.8405585289001465, |
| "learning_rate": 8.15332998611501e-07, |
| "loss": 0.0748, |
| "num_input_tokens_seen": 3140272, |
| "step": 7655 |
| }, |
| { |
| "epoch": 9.27360774818402, |
| "grad_norm": 4.520885944366455, |
| "learning_rate": 8.020062708615745e-07, |
| "loss": 0.1528, |
| "num_input_tokens_seen": 3142448, |
| "step": 7660 |
| }, |
| { |
| "epoch": 9.279661016949152, |
| "grad_norm": 1.5813335180282593, |
| "learning_rate": 7.887875804406946e-07, |
| "loss": 0.1642, |
| "num_input_tokens_seen": 3144528, |
| "step": 7665 |
| }, |
| { |
| "epoch": 9.285714285714286, |
| "grad_norm": 7.437231063842773, |
| "learning_rate": 7.756769863666524e-07, |
| "loss": 0.0751, |
| "num_input_tokens_seen": 3146512, |
| "step": 7670 |
| }, |
| { |
| "epoch": 9.291767554479419, |
| "grad_norm": 0.8976998329162598, |
| "learning_rate": 7.626745471746022e-07, |
| "loss": 0.0366, |
| "num_input_tokens_seen": 3148560, |
| "step": 7675 |
| }, |
| { |
| "epoch": 9.297820823244551, |
| "grad_norm": 5.735642910003662, |
| "learning_rate": 7.497803209168347e-07, |
| "loss": 0.1955, |
| "num_input_tokens_seen": 3150640, |
| "step": 7680 |
| }, |
| { |
| "epoch": 9.303874092009686, |
| "grad_norm": 6.1282639503479, |
| "learning_rate": 7.369943651624938e-07, |
| "loss": 0.0938, |
| "num_input_tokens_seen": 3152688, |
| "step": 7685 |
| }, |
| { |
| "epoch": 9.309927360774818, |
| "grad_norm": 8.234983444213867, |
| "learning_rate": 7.243167369973242e-07, |
| "loss": 0.1524, |
| "num_input_tokens_seen": 3154672, |
| "step": 7690 |
| }, |
| { |
| "epoch": 9.315980629539952, |
| "grad_norm": 11.793670654296875, |
| "learning_rate": 7.117474930234124e-07, |
| "loss": 0.1478, |
| "num_input_tokens_seen": 3156656, |
| "step": 7695 |
| }, |
| { |
| "epoch": 9.322033898305085, |
| "grad_norm": 0.2102554440498352, |
| "learning_rate": 6.992866893589578e-07, |
| "loss": 0.074, |
| "num_input_tokens_seen": 3158640, |
| "step": 7700 |
| }, |
| { |
| "epoch": 9.328087167070217, |
| "grad_norm": 1.4114265441894531, |
| "learning_rate": 6.869343816379825e-07, |
| "loss": 0.0223, |
| "num_input_tokens_seen": 3160624, |
| "step": 7705 |
| }, |
| { |
| "epoch": 9.334140435835351, |
| "grad_norm": 1.1425305604934692, |
| "learning_rate": 6.74690625010116e-07, |
| "loss": 0.0126, |
| "num_input_tokens_seen": 3162608, |
| "step": 7710 |
| }, |
| { |
| "epoch": 9.340193704600484, |
| "grad_norm": 0.6410977840423584, |
| "learning_rate": 6.625554741403333e-07, |
| "loss": 0.1421, |
| "num_input_tokens_seen": 3164560, |
| "step": 7715 |
| }, |
| { |
| "epoch": 9.346246973365618, |
| "grad_norm": 6.864235877990723, |
| "learning_rate": 6.505289832087231e-07, |
| "loss": 0.1654, |
| "num_input_tokens_seen": 3166768, |
| "step": 7720 |
| }, |
| { |
| "epoch": 9.35230024213075, |
| "grad_norm": 0.35761308670043945, |
| "learning_rate": 6.386112059102251e-07, |
| "loss": 0.1199, |
| "num_input_tokens_seen": 3168912, |
| "step": 7725 |
| }, |
| { |
| "epoch": 9.358353510895883, |
| "grad_norm": 0.04573501646518707, |
| "learning_rate": 6.268021954544096e-07, |
| "loss": 0.0494, |
| "num_input_tokens_seen": 3170800, |
| "step": 7730 |
| }, |
| { |
| "epoch": 9.364406779661017, |
| "grad_norm": 0.10186677426099777, |
| "learning_rate": 6.15102004565235e-07, |
| "loss": 0.041, |
| "num_input_tokens_seen": 3172784, |
| "step": 7735 |
| }, |
| { |
| "epoch": 9.37046004842615, |
| "grad_norm": 0.06820578128099442, |
| "learning_rate": 6.035106854808014e-07, |
| "loss": 0.0475, |
| "num_input_tokens_seen": 3174928, |
| "step": 7740 |
| }, |
| { |
| "epoch": 9.376513317191284, |
| "grad_norm": 0.32402148842811584, |
| "learning_rate": 5.920282899531421e-07, |
| "loss": 0.1466, |
| "num_input_tokens_seen": 3176976, |
| "step": 7745 |
| }, |
| { |
| "epoch": 9.382566585956416, |
| "grad_norm": 4.519848823547363, |
| "learning_rate": 5.806548692479624e-07, |
| "loss": 0.0724, |
| "num_input_tokens_seen": 3178896, |
| "step": 7750 |
| }, |
| { |
| "epoch": 9.388619854721549, |
| "grad_norm": 1.1942616701126099, |
| "learning_rate": 5.693904741444267e-07, |
| "loss": 0.0868, |
| "num_input_tokens_seen": 3180848, |
| "step": 7755 |
| }, |
| { |
| "epoch": 9.394673123486683, |
| "grad_norm": 0.24089713394641876, |
| "learning_rate": 5.58235154934944e-07, |
| "loss": 0.0606, |
| "num_input_tokens_seen": 3182704, |
| "step": 7760 |
| }, |
| { |
| "epoch": 9.400726392251816, |
| "grad_norm": 0.04828169196844101, |
| "learning_rate": 5.471889614249104e-07, |
| "loss": 0.0213, |
| "num_input_tokens_seen": 3184848, |
| "step": 7765 |
| }, |
| { |
| "epoch": 9.40677966101695, |
| "grad_norm": 4.41227388381958, |
| "learning_rate": 5.362519429325225e-07, |
| "loss": 0.0704, |
| "num_input_tokens_seen": 3186832, |
| "step": 7770 |
| }, |
| { |
| "epoch": 9.412832929782082, |
| "grad_norm": 8.546942710876465, |
| "learning_rate": 5.254241482885253e-07, |
| "loss": 0.093, |
| "num_input_tokens_seen": 3188912, |
| "step": 7775 |
| }, |
| { |
| "epoch": 9.418886198547215, |
| "grad_norm": 5.857113361358643, |
| "learning_rate": 5.147056258360289e-07, |
| "loss": 0.2003, |
| "num_input_tokens_seen": 3191152, |
| "step": 7780 |
| }, |
| { |
| "epoch": 9.424939467312349, |
| "grad_norm": 0.9563597440719604, |
| "learning_rate": 5.040964234302559e-07, |
| "loss": 0.0421, |
| "num_input_tokens_seen": 3193232, |
| "step": 7785 |
| }, |
| { |
| "epoch": 9.430992736077481, |
| "grad_norm": 3.2596330642700195, |
| "learning_rate": 4.935965884383525e-07, |
| "loss": 0.0406, |
| "num_input_tokens_seen": 3195312, |
| "step": 7790 |
| }, |
| { |
| "epoch": 9.437046004842616, |
| "grad_norm": 0.06693828850984573, |
| "learning_rate": 4.832061677391697e-07, |
| "loss": 0.0459, |
| "num_input_tokens_seen": 3197328, |
| "step": 7795 |
| }, |
| { |
| "epoch": 9.443099273607748, |
| "grad_norm": 1.464663028717041, |
| "learning_rate": 4.729252077230517e-07, |
| "loss": 0.0572, |
| "num_input_tokens_seen": 3199280, |
| "step": 7800 |
| }, |
| { |
| "epoch": 9.44915254237288, |
| "grad_norm": 0.9203391671180725, |
| "learning_rate": 4.6275375429163656e-07, |
| "loss": 0.0406, |
| "num_input_tokens_seen": 3201328, |
| "step": 7805 |
| }, |
| { |
| "epoch": 9.455205811138015, |
| "grad_norm": 0.721315860748291, |
| "learning_rate": 4.526918528576396e-07, |
| "loss": 0.0139, |
| "num_input_tokens_seen": 3203344, |
| "step": 7810 |
| }, |
| { |
| "epoch": 9.461259079903147, |
| "grad_norm": 1.4303781986236572, |
| "learning_rate": 4.427395483446617e-07, |
| "loss": 0.1111, |
| "num_input_tokens_seen": 3205488, |
| "step": 7815 |
| }, |
| { |
| "epoch": 9.467312348668282, |
| "grad_norm": 3.8508174419403076, |
| "learning_rate": 4.328968851869758e-07, |
| "loss": 0.2106, |
| "num_input_tokens_seen": 3207504, |
| "step": 7820 |
| }, |
| { |
| "epoch": 9.473365617433414, |
| "grad_norm": 2.1763241291046143, |
| "learning_rate": 4.231639073293492e-07, |
| "loss": 0.0216, |
| "num_input_tokens_seen": 3209712, |
| "step": 7825 |
| }, |
| { |
| "epoch": 9.479418886198546, |
| "grad_norm": 7.907344818115234, |
| "learning_rate": 4.13540658226827e-07, |
| "loss": 0.1066, |
| "num_input_tokens_seen": 3211728, |
| "step": 7830 |
| }, |
| { |
| "epoch": 9.48547215496368, |
| "grad_norm": 7.968501091003418, |
| "learning_rate": 4.040271808445406e-07, |
| "loss": 0.2031, |
| "num_input_tokens_seen": 3213616, |
| "step": 7835 |
| }, |
| { |
| "epoch": 9.491525423728813, |
| "grad_norm": 1.147912859916687, |
| "learning_rate": 3.94623517657533e-07, |
| "loss": 0.0102, |
| "num_input_tokens_seen": 3215536, |
| "step": 7840 |
| }, |
| { |
| "epoch": 9.497578692493947, |
| "grad_norm": 2.5614442825317383, |
| "learning_rate": 3.8532971065055045e-07, |
| "loss": 0.0522, |
| "num_input_tokens_seen": 3217552, |
| "step": 7845 |
| }, |
| { |
| "epoch": 9.5, |
| "eval_loss": 0.16040408611297607, |
| "eval_runtime": 4.5854, |
| "eval_samples_per_second": 80.037, |
| "eval_steps_per_second": 20.064, |
| "num_input_tokens_seen": 3218352, |
| "step": 7847 |
| }, |
| { |
| "epoch": 9.50363196125908, |
| "grad_norm": 6.244605541229248, |
| "learning_rate": 3.761458013178648e-07, |
| "loss": 0.0483, |
| "num_input_tokens_seen": 3219664, |
| "step": 7850 |
| }, |
| { |
| "epoch": 9.509685230024212, |
| "grad_norm": 0.11520939320325851, |
| "learning_rate": 3.670718306630766e-07, |
| "loss": 0.1404, |
| "num_input_tokens_seen": 3221648, |
| "step": 7855 |
| }, |
| { |
| "epoch": 9.515738498789347, |
| "grad_norm": 0.5533179640769958, |
| "learning_rate": 3.5810783919895673e-07, |
| "loss": 0.0363, |
| "num_input_tokens_seen": 3223632, |
| "step": 7860 |
| }, |
| { |
| "epoch": 9.521791767554479, |
| "grad_norm": 5.129673004150391, |
| "learning_rate": 3.4925386694723284e-07, |
| "loss": 0.0456, |
| "num_input_tokens_seen": 3225616, |
| "step": 7865 |
| }, |
| { |
| "epoch": 9.527845036319613, |
| "grad_norm": 6.019620418548584, |
| "learning_rate": 3.405099534384393e-07, |
| "loss": 0.1101, |
| "num_input_tokens_seen": 3227728, |
| "step": 7870 |
| }, |
| { |
| "epoch": 9.533898305084746, |
| "grad_norm": 0.03893245384097099, |
| "learning_rate": 3.31876137711723e-07, |
| "loss": 0.0851, |
| "num_input_tokens_seen": 3229744, |
| "step": 7875 |
| }, |
| { |
| "epoch": 9.539951573849878, |
| "grad_norm": 9.873018264770508, |
| "learning_rate": 3.233524583146741e-07, |
| "loss": 0.1517, |
| "num_input_tokens_seen": 3231664, |
| "step": 7880 |
| }, |
| { |
| "epoch": 9.546004842615012, |
| "grad_norm": 1.3719098567962646, |
| "learning_rate": 3.149389533031566e-07, |
| "loss": 0.1342, |
| "num_input_tokens_seen": 3233712, |
| "step": 7885 |
| }, |
| { |
| "epoch": 9.552058111380145, |
| "grad_norm": 6.197670936584473, |
| "learning_rate": 3.066356602411419e-07, |
| "loss": 0.2945, |
| "num_input_tokens_seen": 3235728, |
| "step": 7890 |
| }, |
| { |
| "epoch": 9.558111380145279, |
| "grad_norm": 1.7446709871292114, |
| "learning_rate": 2.984426162005227e-07, |
| "loss": 0.0866, |
| "num_input_tokens_seen": 3237712, |
| "step": 7895 |
| }, |
| { |
| "epoch": 9.564164648910412, |
| "grad_norm": 0.39076244831085205, |
| "learning_rate": 2.903598577609717e-07, |
| "loss": 0.1491, |
| "num_input_tokens_seen": 3239664, |
| "step": 7900 |
| }, |
| { |
| "epoch": 9.570217917675544, |
| "grad_norm": 1.8794441223144531, |
| "learning_rate": 2.823874210097638e-07, |
| "loss": 0.0952, |
| "num_input_tokens_seen": 3241776, |
| "step": 7905 |
| }, |
| { |
| "epoch": 9.576271186440678, |
| "grad_norm": 0.4310949444770813, |
| "learning_rate": 2.745253415416177e-07, |
| "loss": 0.023, |
| "num_input_tokens_seen": 3243824, |
| "step": 7910 |
| }, |
| { |
| "epoch": 9.58232445520581, |
| "grad_norm": 0.6770046949386597, |
| "learning_rate": 2.6677365445852976e-07, |
| "loss": 0.1038, |
| "num_input_tokens_seen": 3246000, |
| "step": 7915 |
| }, |
| { |
| "epoch": 9.588377723970945, |
| "grad_norm": 3.035773515701294, |
| "learning_rate": 2.5913239436964054e-07, |
| "loss": 0.0265, |
| "num_input_tokens_seen": 3248112, |
| "step": 7920 |
| }, |
| { |
| "epoch": 9.594430992736077, |
| "grad_norm": 0.0690949484705925, |
| "learning_rate": 2.5160159539105443e-07, |
| "loss": 0.0036, |
| "num_input_tokens_seen": 3250256, |
| "step": 7925 |
| }, |
| { |
| "epoch": 9.600484261501212, |
| "grad_norm": 2.347848892211914, |
| "learning_rate": 2.441812911456981e-07, |
| "loss": 0.0254, |
| "num_input_tokens_seen": 3252368, |
| "step": 7930 |
| }, |
| { |
| "epoch": 9.606537530266344, |
| "grad_norm": 0.4707547426223755, |
| "learning_rate": 2.3687151476317337e-07, |
| "loss": 0.0311, |
| "num_input_tokens_seen": 3254416, |
| "step": 7935 |
| }, |
| { |
| "epoch": 9.612590799031477, |
| "grad_norm": 1.3051100969314575, |
| "learning_rate": 2.2967229887960186e-07, |
| "loss": 0.0423, |
| "num_input_tokens_seen": 3256496, |
| "step": 7940 |
| }, |
| { |
| "epoch": 9.61864406779661, |
| "grad_norm": 4.094726085662842, |
| "learning_rate": 2.2258367563748884e-07, |
| "loss": 0.0552, |
| "num_input_tokens_seen": 3258576, |
| "step": 7945 |
| }, |
| { |
| "epoch": 9.624697336561743, |
| "grad_norm": 0.5801100134849548, |
| "learning_rate": 2.1560567668556797e-07, |
| "loss": 0.1695, |
| "num_input_tokens_seen": 3260496, |
| "step": 7950 |
| }, |
| { |
| "epoch": 9.630750605326877, |
| "grad_norm": 0.6484699249267578, |
| "learning_rate": 2.0873833317866798e-07, |
| "loss": 0.077, |
| "num_input_tokens_seen": 3262608, |
| "step": 7955 |
| }, |
| { |
| "epoch": 9.63680387409201, |
| "grad_norm": 3.7120988368988037, |
| "learning_rate": 2.019816757775711e-07, |
| "loss": 0.0599, |
| "num_input_tokens_seen": 3264592, |
| "step": 7960 |
| }, |
| { |
| "epoch": 9.642857142857142, |
| "grad_norm": 2.2407562732696533, |
| "learning_rate": 1.9533573464888543e-07, |
| "loss": 0.0174, |
| "num_input_tokens_seen": 3266704, |
| "step": 7965 |
| }, |
| { |
| "epoch": 9.648910411622277, |
| "grad_norm": 10.029207229614258, |
| "learning_rate": 1.8880053946488675e-07, |
| "loss": 0.1942, |
| "num_input_tokens_seen": 3268816, |
| "step": 7970 |
| }, |
| { |
| "epoch": 9.654963680387409, |
| "grad_norm": 0.6442005634307861, |
| "learning_rate": 1.8237611940341291e-07, |
| "loss": 0.1252, |
| "num_input_tokens_seen": 3270864, |
| "step": 7975 |
| }, |
| { |
| "epoch": 9.661016949152543, |
| "grad_norm": 10.1329984664917, |
| "learning_rate": 1.760625031477142e-07, |
| "loss": 0.2343, |
| "num_input_tokens_seen": 3272944, |
| "step": 7980 |
| }, |
| { |
| "epoch": 9.667070217917676, |
| "grad_norm": 0.7737054824829102, |
| "learning_rate": 1.6985971888633935e-07, |
| "loss": 0.0099, |
| "num_input_tokens_seen": 3274992, |
| "step": 7985 |
| }, |
| { |
| "epoch": 9.673123486682808, |
| "grad_norm": 0.4194134473800659, |
| "learning_rate": 1.637677943129967e-07, |
| "loss": 0.1094, |
| "num_input_tokens_seen": 3277008, |
| "step": 7990 |
| }, |
| { |
| "epoch": 9.679176755447942, |
| "grad_norm": 1.6003715991973877, |
| "learning_rate": 1.5778675662643793e-07, |
| "loss": 0.1485, |
| "num_input_tokens_seen": 3278928, |
| "step": 7995 |
| }, |
| { |
| "epoch": 9.685230024213075, |
| "grad_norm": 0.3803640604019165, |
| "learning_rate": 1.5191663253034116e-07, |
| "loss": 0.0433, |
| "num_input_tokens_seen": 3280944, |
| "step": 8000 |
| }, |
| { |
| "epoch": 9.69128329297821, |
| "grad_norm": 6.657588005065918, |
| "learning_rate": 1.461574482331779e-07, |
| "loss": 0.1022, |
| "num_input_tokens_seen": 3282960, |
| "step": 8005 |
| }, |
| { |
| "epoch": 9.697336561743342, |
| "grad_norm": 3.707159996032715, |
| "learning_rate": 1.4050922944811305e-07, |
| "loss": 0.0805, |
| "num_input_tokens_seen": 3285008, |
| "step": 8010 |
| }, |
| { |
| "epoch": 9.703389830508474, |
| "grad_norm": 9.373906135559082, |
| "learning_rate": 1.349720013928718e-07, |
| "loss": 0.1608, |
| "num_input_tokens_seen": 3287088, |
| "step": 8015 |
| }, |
| { |
| "epoch": 9.709443099273608, |
| "grad_norm": 6.443699359893799, |
| "learning_rate": 1.2954578878964507e-07, |
| "loss": 0.2076, |
| "num_input_tokens_seen": 3289168, |
| "step": 8020 |
| }, |
| { |
| "epoch": 9.71549636803874, |
| "grad_norm": 6.1982421875, |
| "learning_rate": 1.2423061586496477e-07, |
| "loss": 0.1625, |
| "num_input_tokens_seen": 3291376, |
| "step": 8025 |
| }, |
| { |
| "epoch": 9.721549636803875, |
| "grad_norm": 0.5799146890640259, |
| "learning_rate": 1.1902650634960378e-07, |
| "loss": 0.0786, |
| "num_input_tokens_seen": 3293360, |
| "step": 8030 |
| }, |
| { |
| "epoch": 9.727602905569007, |
| "grad_norm": 0.31346967816352844, |
| "learning_rate": 1.1393348347846777e-07, |
| "loss": 0.0491, |
| "num_input_tokens_seen": 3295344, |
| "step": 8035 |
| }, |
| { |
| "epoch": 9.73365617433414, |
| "grad_norm": 2.450915813446045, |
| "learning_rate": 1.0895156999048972e-07, |
| "loss": 0.0661, |
| "num_input_tokens_seen": 3297392, |
| "step": 8040 |
| }, |
| { |
| "epoch": 9.739709443099274, |
| "grad_norm": 2.6705565452575684, |
| "learning_rate": 1.0408078812853273e-07, |
| "loss": 0.1291, |
| "num_input_tokens_seen": 3299376, |
| "step": 8045 |
| }, |
| { |
| "epoch": 9.745762711864407, |
| "grad_norm": 0.06930442154407501, |
| "learning_rate": 9.932115963928734e-08, |
| "loss": 0.0463, |
| "num_input_tokens_seen": 3301360, |
| "step": 8050 |
| }, |
| { |
| "epoch": 9.75181598062954, |
| "grad_norm": 6.6655402183532715, |
| "learning_rate": 9.467270577317167e-08, |
| "loss": 0.0745, |
| "num_input_tokens_seen": 3303440, |
| "step": 8055 |
| }, |
| { |
| "epoch": 9.757869249394673, |
| "grad_norm": 5.793399810791016, |
| "learning_rate": 9.013544728424528e-08, |
| "loss": 0.1174, |
| "num_input_tokens_seen": 3305552, |
| "step": 8060 |
| }, |
| { |
| "epoch": 9.763922518159806, |
| "grad_norm": 0.10008306801319122, |
| "learning_rate": 8.570940443010655e-08, |
| "loss": 0.0508, |
| "num_input_tokens_seen": 3307728, |
| "step": 8065 |
| }, |
| { |
| "epoch": 9.76997578692494, |
| "grad_norm": 0.7323419451713562, |
| "learning_rate": 8.139459697181218e-08, |
| "loss": 0.1837, |
| "num_input_tokens_seen": 3309776, |
| "step": 8070 |
| }, |
| { |
| "epoch": 9.776029055690072, |
| "grad_norm": 7.605753421783447, |
| "learning_rate": 7.719104417377443e-08, |
| "loss": 0.0955, |
| "num_input_tokens_seen": 3311760, |
| "step": 8075 |
| }, |
| { |
| "epoch": 9.782082324455207, |
| "grad_norm": 5.1498870849609375, |
| "learning_rate": 7.30987648036946e-08, |
| "loss": 0.0404, |
| "num_input_tokens_seen": 3313808, |
| "step": 8080 |
| }, |
| { |
| "epoch": 9.788135593220339, |
| "grad_norm": 4.2535810470581055, |
| "learning_rate": 6.911777713246581e-08, |
| "loss": 0.0995, |
| "num_input_tokens_seen": 3315888, |
| "step": 8085 |
| }, |
| { |
| "epoch": 9.794188861985472, |
| "grad_norm": 3.450693130493164, |
| "learning_rate": 6.524809893409256e-08, |
| "loss": 0.0462, |
| "num_input_tokens_seen": 3318000, |
| "step": 8090 |
| }, |
| { |
| "epoch": 9.800242130750606, |
| "grad_norm": 2.4119420051574707, |
| "learning_rate": 6.148974748561299e-08, |
| "loss": 0.0788, |
| "num_input_tokens_seen": 3320016, |
| "step": 8095 |
| }, |
| { |
| "epoch": 9.806295399515738, |
| "grad_norm": 0.20463275909423828, |
| "learning_rate": 5.784273956702391e-08, |
| "loss": 0.136, |
| "num_input_tokens_seen": 3322096, |
| "step": 8100 |
| }, |
| { |
| "epoch": 9.812348668280872, |
| "grad_norm": 3.652512788772583, |
| "learning_rate": 5.4307091461205936e-08, |
| "loss": 0.0674, |
| "num_input_tokens_seen": 3324176, |
| "step": 8105 |
| }, |
| { |
| "epoch": 9.818401937046005, |
| "grad_norm": 0.506850004196167, |
| "learning_rate": 5.08828189538485e-08, |
| "loss": 0.0522, |
| "num_input_tokens_seen": 3326320, |
| "step": 8110 |
| }, |
| { |
| "epoch": 9.824455205811137, |
| "grad_norm": 7.119671821594238, |
| "learning_rate": 4.7569937333372115e-08, |
| "loss": 0.0571, |
| "num_input_tokens_seen": 3328464, |
| "step": 8115 |
| }, |
| { |
| "epoch": 9.830508474576272, |
| "grad_norm": 0.008174745365977287, |
| "learning_rate": 4.436846139087847e-08, |
| "loss": 0.0237, |
| "num_input_tokens_seen": 3330480, |
| "step": 8120 |
| }, |
| { |
| "epoch": 9.836561743341404, |
| "grad_norm": 1.4426367282867432, |
| "learning_rate": 4.127840542006711e-08, |
| "loss": 0.0669, |
| "num_input_tokens_seen": 3332624, |
| "step": 8125 |
| }, |
| { |
| "epoch": 9.842615012106538, |
| "grad_norm": 2.028547763824463, |
| "learning_rate": 3.829978321718553e-08, |
| "loss": 0.0795, |
| "num_input_tokens_seen": 3334768, |
| "step": 8130 |
| }, |
| { |
| "epoch": 9.84866828087167, |
| "grad_norm": 2.7887542247772217, |
| "learning_rate": 3.543260808095139e-08, |
| "loss": 0.0316, |
| "num_input_tokens_seen": 3336784, |
| "step": 8135 |
| }, |
| { |
| "epoch": 9.854721549636803, |
| "grad_norm": 3.320316791534424, |
| "learning_rate": 3.267689281250541e-08, |
| "loss": 0.0624, |
| "num_input_tokens_seen": 3338832, |
| "step": 8140 |
| }, |
| { |
| "epoch": 9.860774818401937, |
| "grad_norm": 9.407702445983887, |
| "learning_rate": 3.003264971535857e-08, |
| "loss": 0.1638, |
| "num_input_tokens_seen": 3340848, |
| "step": 8145 |
| }, |
| { |
| "epoch": 9.86682808716707, |
| "grad_norm": 0.1599888801574707, |
| "learning_rate": 2.7499890595314438e-08, |
| "loss": 0.1581, |
| "num_input_tokens_seen": 3342960, |
| "step": 8150 |
| }, |
| { |
| "epoch": 9.872881355932204, |
| "grad_norm": 2.643625259399414, |
| "learning_rate": 2.507862676044137e-08, |
| "loss": 0.1443, |
| "num_input_tokens_seen": 3345104, |
| "step": 8155 |
| }, |
| { |
| "epoch": 9.878934624697337, |
| "grad_norm": 2.9549529552459717, |
| "learning_rate": 2.2768869021014274e-08, |
| "loss": 0.1202, |
| "num_input_tokens_seen": 3347024, |
| "step": 8160 |
| }, |
| { |
| "epoch": 9.884987893462469, |
| "grad_norm": 6.08317756652832, |
| "learning_rate": 2.0570627689459054e-08, |
| "loss": 0.0827, |
| "num_input_tokens_seen": 3349200, |
| "step": 8165 |
| }, |
| { |
| "epoch": 9.891041162227603, |
| "grad_norm": 0.14019866287708282, |
| "learning_rate": 1.848391258031379e-08, |
| "loss": 0.0283, |
| "num_input_tokens_seen": 3351248, |
| "step": 8170 |
| }, |
| { |
| "epoch": 9.897094430992736, |
| "grad_norm": 4.22549295425415, |
| "learning_rate": 1.6508733010184297e-08, |
| "loss": 0.0468, |
| "num_input_tokens_seen": 3353488, |
| "step": 8175 |
| }, |
| { |
| "epoch": 9.90314769975787, |
| "grad_norm": 0.9411844611167908, |
| "learning_rate": 1.4645097797694186e-08, |
| "loss": 0.015, |
| "num_input_tokens_seen": 3355440, |
| "step": 8180 |
| }, |
| { |
| "epoch": 9.909200968523002, |
| "grad_norm": 5.702022552490234, |
| "learning_rate": 1.2893015263459874e-08, |
| "loss": 0.2151, |
| "num_input_tokens_seen": 3357296, |
| "step": 8185 |
| }, |
| { |
| "epoch": 9.915254237288135, |
| "grad_norm": 1.883554220199585, |
| "learning_rate": 1.125249323004618e-08, |
| "loss": 0.1424, |
| "num_input_tokens_seen": 3359280, |
| "step": 8190 |
| }, |
| { |
| "epoch": 9.92130750605327, |
| "grad_norm": 5.344539165496826, |
| "learning_rate": 9.723539021927463e-09, |
| "loss": 0.243, |
| "num_input_tokens_seen": 3361328, |
| "step": 8195 |
| }, |
| { |
| "epoch": 9.927360774818402, |
| "grad_norm": 0.5315026640892029, |
| "learning_rate": 8.306159465459872e-09, |
| "loss": 0.0859, |
| "num_input_tokens_seen": 3363344, |
| "step": 8200 |
| }, |
| { |
| "epoch": 9.933414043583536, |
| "grad_norm": 4.213244915008545, |
| "learning_rate": 7.00036088885081e-09, |
| "loss": 0.149, |
| "num_input_tokens_seen": 3365296, |
| "step": 8205 |
| }, |
| { |
| "epoch": 9.939467312348668, |
| "grad_norm": 0.8035793900489807, |
| "learning_rate": 5.806149122128401e-09, |
| "loss": 0.0801, |
| "num_input_tokens_seen": 3367504, |
| "step": 8210 |
| }, |
| { |
| "epoch": 9.9455205811138, |
| "grad_norm": 5.933956146240234, |
| "learning_rate": 4.723529497113743e-09, |
| "loss": 0.0346, |
| "num_input_tokens_seen": 3369616, |
| "step": 8215 |
| }, |
| { |
| "epoch": 9.951573849878935, |
| "grad_norm": 6.575443744659424, |
| "learning_rate": 3.752506847407023e-09, |
| "loss": 0.0627, |
| "num_input_tokens_seen": 3371728, |
| "step": 8220 |
| }, |
| { |
| "epoch": 9.957627118644067, |
| "grad_norm": 3.750946283340454, |
| "learning_rate": 2.8930855083542096e-09, |
| "loss": 0.1372, |
| "num_input_tokens_seen": 3373648, |
| "step": 8225 |
| }, |
| { |
| "epoch": 9.963680387409202, |
| "grad_norm": 0.5259419083595276, |
| "learning_rate": 2.145269317033183e-09, |
| "loss": 0.1955, |
| "num_input_tokens_seen": 3375664, |
| "step": 8230 |
| }, |
| { |
| "epoch": 9.969733656174334, |
| "grad_norm": 6.630932331085205, |
| "learning_rate": 1.509061612234297e-09, |
| "loss": 0.1024, |
| "num_input_tokens_seen": 3377808, |
| "step": 8235 |
| }, |
| { |
| "epoch": 9.975786924939467, |
| "grad_norm": 4.802211761474609, |
| "learning_rate": 9.844652344492832e-10, |
| "loss": 0.069, |
| "num_input_tokens_seen": 3379888, |
| "step": 8240 |
| }, |
| { |
| "epoch": 9.9818401937046, |
| "grad_norm": 5.706575870513916, |
| "learning_rate": 5.714825258545942e-10, |
| "loss": 0.155, |
| "num_input_tokens_seen": 3382064, |
| "step": 8245 |
| }, |
| { |
| "epoch": 9.987893462469733, |
| "grad_norm": 1.3004391193389893, |
| "learning_rate": 2.7011533030585347e-10, |
| "loss": 0.0399, |
| "num_input_tokens_seen": 3384144, |
| "step": 8250 |
| }, |
| { |
| "epoch": 9.993946731234868, |
| "grad_norm": 2.925779342651367, |
| "learning_rate": 8.036499332397807e-11, |
| "loss": 0.0171, |
| "num_input_tokens_seen": 3386160, |
| "step": 8255 |
| }, |
| { |
| "epoch": 10.0, |
| "grad_norm": 1.5842012166976929, |
| "learning_rate": 2.2323620896269604e-12, |
| "loss": 0.0796, |
| "num_input_tokens_seen": 3388032, |
| "step": 8260 |
| }, |
| { |
| "epoch": 10.0, |
| "eval_loss": 0.16043449938297272, |
| "eval_runtime": 4.5828, |
| "eval_samples_per_second": 80.082, |
| "eval_steps_per_second": 20.075, |
| "num_input_tokens_seen": 3388032, |
| "step": 8260 |
| }, |
| { |
| "epoch": 10.0, |
| "num_input_tokens_seen": 3388032, |
| "step": 8260, |
| "total_flos": 1.525669618557911e+17, |
| "train_loss": 0.11986262800496694, |
| "train_runtime": 1426.229, |
| "train_samples_per_second": 23.145, |
| "train_steps_per_second": 5.791 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 8260, |
| "num_input_tokens_seen": 3388032, |
| "num_train_epochs": 10, |
| "save_steps": 413, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.525669618557911e+17, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
