| { |
| "best_global_step": 300, |
| "best_metric": 0.16209302842617035, |
| "best_model_checkpoint": "saves_multiple/prefix-tuning/llama-3-8b-instruct/train_cb_456_1760637753/checkpoint-300", |
| "epoch": 20.0, |
| "eval_steps": 100, |
| "global_step": 1000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.1, |
| "grad_norm": 216.57647705078125, |
| "learning_rate": 4.0000000000000003e-07, |
| "loss": 9.2623, |
| "num_input_tokens_seen": 2944, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.2, |
| "grad_norm": 150.08148193359375, |
| "learning_rate": 9.000000000000001e-07, |
| "loss": 8.7722, |
| "num_input_tokens_seen": 6208, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.3, |
| "grad_norm": 134.6036376953125, |
| "learning_rate": 1.4000000000000001e-06, |
| "loss": 8.0747, |
| "num_input_tokens_seen": 9440, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.4, |
| "grad_norm": 120.53459930419922, |
| "learning_rate": 1.9000000000000002e-06, |
| "loss": 7.2417, |
| "num_input_tokens_seen": 12320, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.5, |
| "grad_norm": 107.87600708007812, |
| "learning_rate": 2.4000000000000003e-06, |
| "loss": 5.8971, |
| "num_input_tokens_seen": 16096, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.6, |
| "grad_norm": 91.98301696777344, |
| "learning_rate": 2.9e-06, |
| "loss": 4.5398, |
| "num_input_tokens_seen": 18880, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.7, |
| "grad_norm": 104.20735168457031, |
| "learning_rate": 3.4000000000000005e-06, |
| "loss": 3.4192, |
| "num_input_tokens_seen": 22240, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.8, |
| "grad_norm": 57.80829620361328, |
| "learning_rate": 3.900000000000001e-06, |
| "loss": 1.8096, |
| "num_input_tokens_seen": 25376, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.9, |
| "grad_norm": 49.72511672973633, |
| "learning_rate": 4.4e-06, |
| "loss": 1.07, |
| "num_input_tokens_seen": 28576, |
| "step": 45 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 45.287750244140625, |
| "learning_rate": 4.9000000000000005e-06, |
| "loss": 0.6796, |
| "num_input_tokens_seen": 32448, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.1, |
| "grad_norm": 67.8308334350586, |
| "learning_rate": 5.400000000000001e-06, |
| "loss": 0.5664, |
| "num_input_tokens_seen": 35776, |
| "step": 55 |
| }, |
| { |
| "epoch": 1.2, |
| "grad_norm": 48.61396408081055, |
| "learning_rate": 5.9e-06, |
| "loss": 0.2188, |
| "num_input_tokens_seen": 38912, |
| "step": 60 |
| }, |
| { |
| "epoch": 1.3, |
| "grad_norm": 52.29746627807617, |
| "learning_rate": 6.4000000000000006e-06, |
| "loss": 0.3773, |
| "num_input_tokens_seen": 42368, |
| "step": 65 |
| }, |
| { |
| "epoch": 1.4, |
| "grad_norm": 33.272586822509766, |
| "learning_rate": 6.9e-06, |
| "loss": 0.2119, |
| "num_input_tokens_seen": 45920, |
| "step": 70 |
| }, |
| { |
| "epoch": 1.5, |
| "grad_norm": 15.55538272857666, |
| "learning_rate": 7.4e-06, |
| "loss": 0.4496, |
| "num_input_tokens_seen": 49024, |
| "step": 75 |
| }, |
| { |
| "epoch": 1.6, |
| "grad_norm": 28.139711380004883, |
| "learning_rate": 7.9e-06, |
| "loss": 0.2051, |
| "num_input_tokens_seen": 52448, |
| "step": 80 |
| }, |
| { |
| "epoch": 1.7, |
| "grad_norm": 62.42750549316406, |
| "learning_rate": 8.400000000000001e-06, |
| "loss": 0.3832, |
| "num_input_tokens_seen": 55680, |
| "step": 85 |
| }, |
| { |
| "epoch": 1.8, |
| "grad_norm": 16.478151321411133, |
| "learning_rate": 8.900000000000001e-06, |
| "loss": 0.2837, |
| "num_input_tokens_seen": 59072, |
| "step": 90 |
| }, |
| { |
| "epoch": 1.9, |
| "grad_norm": 43.594581604003906, |
| "learning_rate": 9.4e-06, |
| "loss": 0.2905, |
| "num_input_tokens_seen": 62368, |
| "step": 95 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 9.988426208496094, |
| "learning_rate": 9.9e-06, |
| "loss": 0.1956, |
| "num_input_tokens_seen": 65088, |
| "step": 100 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 0.20375482738018036, |
| "eval_runtime": 1.0065, |
| "eval_samples_per_second": 49.678, |
| "eval_steps_per_second": 12.916, |
| "num_input_tokens_seen": 65088, |
| "step": 100 |
| }, |
| { |
| "epoch": 2.1, |
| "grad_norm": 45.27996063232422, |
| "learning_rate": 9.999512620046523e-06, |
| "loss": 0.2352, |
| "num_input_tokens_seen": 67968, |
| "step": 105 |
| }, |
| { |
| "epoch": 2.2, |
| "grad_norm": 24.10486602783203, |
| "learning_rate": 9.997532801828659e-06, |
| "loss": 0.3626, |
| "num_input_tokens_seen": 70592, |
| "step": 110 |
| }, |
| { |
| "epoch": 2.3, |
| "grad_norm": 55.39781188964844, |
| "learning_rate": 9.994030686707171e-06, |
| "loss": 0.4318, |
| "num_input_tokens_seen": 73632, |
| "step": 115 |
| }, |
| { |
| "epoch": 2.4, |
| "grad_norm": 35.644168853759766, |
| "learning_rate": 9.989007341460251e-06, |
| "loss": 0.2275, |
| "num_input_tokens_seen": 77120, |
| "step": 120 |
| }, |
| { |
| "epoch": 2.5, |
| "grad_norm": 69.64350128173828, |
| "learning_rate": 9.982464296247523e-06, |
| "loss": 0.1836, |
| "num_input_tokens_seen": 80448, |
| "step": 125 |
| }, |
| { |
| "epoch": 2.6, |
| "grad_norm": 25.893815994262695, |
| "learning_rate": 9.974403544143942e-06, |
| "loss": 0.2254, |
| "num_input_tokens_seen": 83488, |
| "step": 130 |
| }, |
| { |
| "epoch": 2.7, |
| "grad_norm": 48.531349182128906, |
| "learning_rate": 9.964827540532685e-06, |
| "loss": 0.3111, |
| "num_input_tokens_seen": 86720, |
| "step": 135 |
| }, |
| { |
| "epoch": 2.8, |
| "grad_norm": 14.120803833007812, |
| "learning_rate": 9.953739202357219e-06, |
| "loss": 0.3352, |
| "num_input_tokens_seen": 90176, |
| "step": 140 |
| }, |
| { |
| "epoch": 2.9, |
| "grad_norm": 10.534299850463867, |
| "learning_rate": 9.941141907232766e-06, |
| "loss": 0.2023, |
| "num_input_tokens_seen": 94176, |
| "step": 145 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 15.623373031616211, |
| "learning_rate": 9.927039492417452e-06, |
| "loss": 0.179, |
| "num_input_tokens_seen": 97536, |
| "step": 150 |
| }, |
| { |
| "epoch": 3.1, |
| "grad_norm": 24.761083602905273, |
| "learning_rate": 9.911436253643445e-06, |
| "loss": 0.3012, |
| "num_input_tokens_seen": 100672, |
| "step": 155 |
| }, |
| { |
| "epoch": 3.2, |
| "grad_norm": 18.8632869720459, |
| "learning_rate": 9.894336943808426e-06, |
| "loss": 0.1366, |
| "num_input_tokens_seen": 103808, |
| "step": 160 |
| }, |
| { |
| "epoch": 3.3, |
| "grad_norm": 9.393210411071777, |
| "learning_rate": 9.875746771527817e-06, |
| "loss": 0.186, |
| "num_input_tokens_seen": 106464, |
| "step": 165 |
| }, |
| { |
| "epoch": 3.4, |
| "grad_norm": 16.760845184326172, |
| "learning_rate": 9.85567139954818e-06, |
| "loss": 0.2138, |
| "num_input_tokens_seen": 109056, |
| "step": 170 |
| }, |
| { |
| "epoch": 3.5, |
| "grad_norm": 34.08476638793945, |
| "learning_rate": 9.834116943022299e-06, |
| "loss": 0.2066, |
| "num_input_tokens_seen": 111520, |
| "step": 175 |
| }, |
| { |
| "epoch": 3.6, |
| "grad_norm": 23.190500259399414, |
| "learning_rate": 9.811089967646427e-06, |
| "loss": 0.275, |
| "num_input_tokens_seen": 114816, |
| "step": 180 |
| }, |
| { |
| "epoch": 3.7, |
| "grad_norm": 12.0489501953125, |
| "learning_rate": 9.786597487660336e-06, |
| "loss": 0.2247, |
| "num_input_tokens_seen": 118528, |
| "step": 185 |
| }, |
| { |
| "epoch": 3.8, |
| "grad_norm": 11.4762601852417, |
| "learning_rate": 9.760646963710694e-06, |
| "loss": 0.2004, |
| "num_input_tokens_seen": 121568, |
| "step": 190 |
| }, |
| { |
| "epoch": 3.9, |
| "grad_norm": 18.891124725341797, |
| "learning_rate": 9.733246300578482e-06, |
| "loss": 0.218, |
| "num_input_tokens_seen": 125344, |
| "step": 195 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 44.311527252197266, |
| "learning_rate": 9.704403844771128e-06, |
| "loss": 0.1539, |
| "num_input_tokens_seen": 128896, |
| "step": 200 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_loss": 0.18065515160560608, |
| "eval_runtime": 0.9979, |
| "eval_samples_per_second": 50.106, |
| "eval_steps_per_second": 13.027, |
| "num_input_tokens_seen": 128896, |
| "step": 200 |
| }, |
| { |
| "epoch": 4.1, |
| "grad_norm": 15.962028503417969, |
| "learning_rate": 9.674128381980073e-06, |
| "loss": 0.2518, |
| "num_input_tokens_seen": 132000, |
| "step": 205 |
| }, |
| { |
| "epoch": 4.2, |
| "grad_norm": 19.0295352935791, |
| "learning_rate": 9.642429134404568e-06, |
| "loss": 0.1297, |
| "num_input_tokens_seen": 136032, |
| "step": 210 |
| }, |
| { |
| "epoch": 4.3, |
| "grad_norm": 22.2943115234375, |
| "learning_rate": 9.609315757942504e-06, |
| "loss": 0.1967, |
| "num_input_tokens_seen": 139392, |
| "step": 215 |
| }, |
| { |
| "epoch": 4.4, |
| "grad_norm": 35.93865203857422, |
| "learning_rate": 9.574798339249124e-06, |
| "loss": 0.1113, |
| "num_input_tokens_seen": 142624, |
| "step": 220 |
| }, |
| { |
| "epoch": 4.5, |
| "grad_norm": 30.04070281982422, |
| "learning_rate": 9.538887392664544e-06, |
| "loss": 0.2285, |
| "num_input_tokens_seen": 146144, |
| "step": 225 |
| }, |
| { |
| "epoch": 4.6, |
| "grad_norm": 35.45005416870117, |
| "learning_rate": 9.501593857010968e-06, |
| "loss": 0.1175, |
| "num_input_tokens_seen": 149248, |
| "step": 230 |
| }, |
| { |
| "epoch": 4.7, |
| "grad_norm": 75.65644073486328, |
| "learning_rate": 9.46292909226063e-06, |
| "loss": 0.2548, |
| "num_input_tokens_seen": 152384, |
| "step": 235 |
| }, |
| { |
| "epoch": 4.8, |
| "grad_norm": 37.20109939575195, |
| "learning_rate": 9.42290487607542e-06, |
| "loss": 0.3188, |
| "num_input_tokens_seen": 155232, |
| "step": 240 |
| }, |
| { |
| "epoch": 4.9, |
| "grad_norm": 19.07550621032715, |
| "learning_rate": 9.381533400219319e-06, |
| "loss": 0.1796, |
| "num_input_tokens_seen": 159104, |
| "step": 245 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 34.64167404174805, |
| "learning_rate": 9.338827266844643e-06, |
| "loss": 0.2762, |
| "num_input_tokens_seen": 162144, |
| "step": 250 |
| }, |
| { |
| "epoch": 5.1, |
| "grad_norm": 12.19721508026123, |
| "learning_rate": 9.294799484653323e-06, |
| "loss": 0.1075, |
| "num_input_tokens_seen": 165312, |
| "step": 255 |
| }, |
| { |
| "epoch": 5.2, |
| "grad_norm": 10.703926086425781, |
| "learning_rate": 9.24946346493432e-06, |
| "loss": 0.1454, |
| "num_input_tokens_seen": 169696, |
| "step": 260 |
| }, |
| { |
| "epoch": 5.3, |
| "grad_norm": 4.545947551727295, |
| "learning_rate": 9.202833017478421e-06, |
| "loss": 0.1456, |
| "num_input_tokens_seen": 173504, |
| "step": 265 |
| }, |
| { |
| "epoch": 5.4, |
| "grad_norm": 55.721229553222656, |
| "learning_rate": 9.154922346371641e-06, |
| "loss": 0.2572, |
| "num_input_tokens_seen": 176256, |
| "step": 270 |
| }, |
| { |
| "epoch": 5.5, |
| "grad_norm": 27.98261070251465, |
| "learning_rate": 9.10574604566852e-06, |
| "loss": 0.1196, |
| "num_input_tokens_seen": 179104, |
| "step": 275 |
| }, |
| { |
| "epoch": 5.6, |
| "grad_norm": 28.25328254699707, |
| "learning_rate": 9.055319094946633e-06, |
| "loss": 0.2833, |
| "num_input_tokens_seen": 182112, |
| "step": 280 |
| }, |
| { |
| "epoch": 5.7, |
| "grad_norm": 65.87811279296875, |
| "learning_rate": 9.003656854743667e-06, |
| "loss": 0.2797, |
| "num_input_tokens_seen": 185024, |
| "step": 285 |
| }, |
| { |
| "epoch": 5.8, |
| "grad_norm": 41.558692932128906, |
| "learning_rate": 8.950775061878453e-06, |
| "loss": 0.2964, |
| "num_input_tokens_seen": 188032, |
| "step": 290 |
| }, |
| { |
| "epoch": 5.9, |
| "grad_norm": 41.10008239746094, |
| "learning_rate": 8.896689824657371e-06, |
| "loss": 0.2251, |
| "num_input_tokens_seen": 190816, |
| "step": 295 |
| }, |
| { |
| "epoch": 6.0, |
| "grad_norm": 19.21298599243164, |
| "learning_rate": 8.841417617967618e-06, |
| "loss": 0.1384, |
| "num_input_tokens_seen": 193888, |
| "step": 300 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_loss": 0.16209302842617035, |
| "eval_runtime": 1.0001, |
| "eval_samples_per_second": 49.994, |
| "eval_steps_per_second": 12.998, |
| "num_input_tokens_seen": 193888, |
| "step": 300 |
| }, |
| { |
| "epoch": 6.1, |
| "grad_norm": 13.841469764709473, |
| "learning_rate": 8.784975278258783e-06, |
| "loss": 0.2431, |
| "num_input_tokens_seen": 197152, |
| "step": 305 |
| }, |
| { |
| "epoch": 6.2, |
| "grad_norm": 4.108739376068115, |
| "learning_rate": 8.727379998414311e-06, |
| "loss": 0.0386, |
| "num_input_tokens_seen": 200032, |
| "step": 310 |
| }, |
| { |
| "epoch": 6.3, |
| "grad_norm": 1.0758922100067139, |
| "learning_rate": 8.668649322514382e-06, |
| "loss": 0.0371, |
| "num_input_tokens_seen": 203744, |
| "step": 315 |
| }, |
| { |
| "epoch": 6.4, |
| "grad_norm": 23.765316009521484, |
| "learning_rate": 8.608801140491811e-06, |
| "loss": 0.0174, |
| "num_input_tokens_seen": 206880, |
| "step": 320 |
| }, |
| { |
| "epoch": 6.5, |
| "grad_norm": 81.70988464355469, |
| "learning_rate": 8.547853682682605e-06, |
| "loss": 0.3998, |
| "num_input_tokens_seen": 209952, |
| "step": 325 |
| }, |
| { |
| "epoch": 6.6, |
| "grad_norm": 148.9218292236328, |
| "learning_rate": 8.485825514272824e-06, |
| "loss": 0.1394, |
| "num_input_tokens_seen": 213280, |
| "step": 330 |
| }, |
| { |
| "epoch": 6.7, |
| "grad_norm": 90.68417358398438, |
| "learning_rate": 8.422735529643445e-06, |
| "loss": 0.2914, |
| "num_input_tokens_seen": 216448, |
| "step": 335 |
| }, |
| { |
| "epoch": 6.8, |
| "grad_norm": 84.91841125488281, |
| "learning_rate": 8.358602946614952e-06, |
| "loss": 0.4754, |
| "num_input_tokens_seen": 219776, |
| "step": 340 |
| }, |
| { |
| "epoch": 6.9, |
| "grad_norm": 6.3870463371276855, |
| "learning_rate": 8.293447300593402e-06, |
| "loss": 0.1109, |
| "num_input_tokens_seen": 223136, |
| "step": 345 |
| }, |
| { |
| "epoch": 7.0, |
| "grad_norm": 46.83969497680664, |
| "learning_rate": 8.227288438619754e-06, |
| "loss": 0.1319, |
| "num_input_tokens_seen": 226880, |
| "step": 350 |
| }, |
| { |
| "epoch": 7.1, |
| "grad_norm": 19.829757690429688, |
| "learning_rate": 8.160146513324256e-06, |
| "loss": 0.0609, |
| "num_input_tokens_seen": 229856, |
| "step": 355 |
| }, |
| { |
| "epoch": 7.2, |
| "grad_norm": 8.89151382446289, |
| "learning_rate": 8.092041976787772e-06, |
| "loss": 0.214, |
| "num_input_tokens_seen": 233216, |
| "step": 360 |
| }, |
| { |
| "epoch": 7.3, |
| "grad_norm": 22.78290367126465, |
| "learning_rate": 8.022995574311876e-06, |
| "loss": 0.1058, |
| "num_input_tokens_seen": 236416, |
| "step": 365 |
| }, |
| { |
| "epoch": 7.4, |
| "grad_norm": 18.72032356262207, |
| "learning_rate": 7.953028338099628e-06, |
| "loss": 0.0806, |
| "num_input_tokens_seen": 239456, |
| "step": 370 |
| }, |
| { |
| "epoch": 7.5, |
| "grad_norm": 34.90778350830078, |
| "learning_rate": 7.882161580848966e-06, |
| "loss": 0.1732, |
| "num_input_tokens_seen": 242272, |
| "step": 375 |
| }, |
| { |
| "epoch": 7.6, |
| "grad_norm": 81.65283203125, |
| "learning_rate": 7.810416889260653e-06, |
| "loss": 0.2579, |
| "num_input_tokens_seen": 245376, |
| "step": 380 |
| }, |
| { |
| "epoch": 7.7, |
| "grad_norm": 54.231712341308594, |
| "learning_rate": 7.737816117462752e-06, |
| "loss": 0.1688, |
| "num_input_tokens_seen": 248864, |
| "step": 385 |
| }, |
| { |
| "epoch": 7.8, |
| "grad_norm": 6.326272487640381, |
| "learning_rate": 7.66438138035365e-06, |
| "loss": 0.069, |
| "num_input_tokens_seen": 251776, |
| "step": 390 |
| }, |
| { |
| "epoch": 7.9, |
| "grad_norm": 24.330530166625977, |
| "learning_rate": 7.590135046865652e-06, |
| "loss": 0.0395, |
| "num_input_tokens_seen": 255360, |
| "step": 395 |
| }, |
| { |
| "epoch": 8.0, |
| "grad_norm": 37.1357421875, |
| "learning_rate": 7.515099733151177e-06, |
| "loss": 0.2604, |
| "num_input_tokens_seen": 258816, |
| "step": 400 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_loss": 0.18744546175003052, |
| "eval_runtime": 0.9989, |
| "eval_samples_per_second": 50.055, |
| "eval_steps_per_second": 13.014, |
| "num_input_tokens_seen": 258816, |
| "step": 400 |
| }, |
| { |
| "epoch": 8.1, |
| "grad_norm": 2.0634098052978516, |
| "learning_rate": 7.4392982956936644e-06, |
| "loss": 0.0269, |
| "num_input_tokens_seen": 262144, |
| "step": 405 |
| }, |
| { |
| "epoch": 8.2, |
| "grad_norm": 9.939993858337402, |
| "learning_rate": 7.362753824345271e-06, |
| "loss": 0.1619, |
| "num_input_tokens_seen": 265440, |
| "step": 410 |
| }, |
| { |
| "epoch": 8.3, |
| "grad_norm": 40.41669464111328, |
| "learning_rate": 7.285489635293472e-06, |
| "loss": 0.1923, |
| "num_input_tokens_seen": 269248, |
| "step": 415 |
| }, |
| { |
| "epoch": 8.4, |
| "grad_norm": 9.423033714294434, |
| "learning_rate": 7.207529263958727e-06, |
| "loss": 0.0225, |
| "num_input_tokens_seen": 272096, |
| "step": 420 |
| }, |
| { |
| "epoch": 8.5, |
| "grad_norm": 81.35832214355469, |
| "learning_rate": 7.128896457825364e-06, |
| "loss": 0.1014, |
| "num_input_tokens_seen": 274912, |
| "step": 425 |
| }, |
| { |
| "epoch": 8.6, |
| "grad_norm": 92.09923553466797, |
| "learning_rate": 7.049615169207864e-06, |
| "loss": 0.1776, |
| "num_input_tokens_seen": 277856, |
| "step": 430 |
| }, |
| { |
| "epoch": 8.7, |
| "grad_norm": 41.74745559692383, |
| "learning_rate": 6.9697095479547564e-06, |
| "loss": 0.0569, |
| "num_input_tokens_seen": 281408, |
| "step": 435 |
| }, |
| { |
| "epoch": 8.8, |
| "grad_norm": 1.260631799697876, |
| "learning_rate": 6.889203934092337e-06, |
| "loss": 0.0729, |
| "num_input_tokens_seen": 284960, |
| "step": 440 |
| }, |
| { |
| "epoch": 8.9, |
| "grad_norm": 11.80173397064209, |
| "learning_rate": 6.808122850410461e-06, |
| "loss": 0.0428, |
| "num_input_tokens_seen": 288000, |
| "step": 445 |
| }, |
| { |
| "epoch": 9.0, |
| "grad_norm": 1.4177440404891968, |
| "learning_rate": 6.7264909949926735e-06, |
| "loss": 0.0264, |
| "num_input_tokens_seen": 291584, |
| "step": 450 |
| }, |
| { |
| "epoch": 9.1, |
| "grad_norm": 14.504668235778809, |
| "learning_rate": 6.644333233692917e-06, |
| "loss": 0.029, |
| "num_input_tokens_seen": 295264, |
| "step": 455 |
| }, |
| { |
| "epoch": 9.2, |
| "grad_norm": 35.566810607910156, |
| "learning_rate": 6.561674592561164e-06, |
| "loss": 0.0487, |
| "num_input_tokens_seen": 298368, |
| "step": 460 |
| }, |
| { |
| "epoch": 9.3, |
| "grad_norm": 0.43563374876976013, |
| "learning_rate": 6.4785402502202345e-06, |
| "loss": 0.0025, |
| "num_input_tokens_seen": 301760, |
| "step": 465 |
| }, |
| { |
| "epoch": 9.4, |
| "grad_norm": 65.56232452392578, |
| "learning_rate": 6.3949555301961474e-06, |
| "loss": 0.0865, |
| "num_input_tokens_seen": 304736, |
| "step": 470 |
| }, |
| { |
| "epoch": 9.5, |
| "grad_norm": 93.48302459716797, |
| "learning_rate": 6.310945893204324e-06, |
| "loss": 0.0722, |
| "num_input_tokens_seen": 307872, |
| "step": 475 |
| }, |
| { |
| "epoch": 9.6, |
| "grad_norm": 0.22434131801128387, |
| "learning_rate": 6.2265369293940135e-06, |
| "loss": 0.008, |
| "num_input_tokens_seen": 310624, |
| "step": 480 |
| }, |
| { |
| "epoch": 9.7, |
| "grad_norm": 0.6443999409675598, |
| "learning_rate": 6.141754350553279e-06, |
| "loss": 0.0332, |
| "num_input_tokens_seen": 314016, |
| "step": 485 |
| }, |
| { |
| "epoch": 9.8, |
| "grad_norm": 0.9288974404335022, |
| "learning_rate": 6.056623982276945e-06, |
| "loss": 0.0317, |
| "num_input_tokens_seen": 317376, |
| "step": 490 |
| }, |
| { |
| "epoch": 9.9, |
| "grad_norm": 1.3583974838256836, |
| "learning_rate": 5.97117175609986e-06, |
| "loss": 0.0318, |
| "num_input_tokens_seen": 320256, |
| "step": 495 |
| }, |
| { |
| "epoch": 10.0, |
| "grad_norm": 0.43309640884399414, |
| "learning_rate": 5.885423701597918e-06, |
| "loss": 0.0017, |
| "num_input_tokens_seen": 323328, |
| "step": 500 |
| }, |
| { |
| "epoch": 10.0, |
| "eval_loss": 0.2034723162651062, |
| "eval_runtime": 0.9994, |
| "eval_samples_per_second": 50.028, |
| "eval_steps_per_second": 13.007, |
| "num_input_tokens_seen": 323328, |
| "step": 500 |
| }, |
| { |
| "epoch": 10.1, |
| "grad_norm": 0.028279408812522888, |
| "learning_rate": 5.799405938459175e-06, |
| "loss": 0.0007, |
| "num_input_tokens_seen": 326624, |
| "step": 505 |
| }, |
| { |
| "epoch": 10.2, |
| "grad_norm": 0.04337608441710472, |
| "learning_rate": 5.7131446685275595e-06, |
| "loss": 0.0046, |
| "num_input_tokens_seen": 329824, |
| "step": 510 |
| }, |
| { |
| "epoch": 10.3, |
| "grad_norm": 0.10003524273633957, |
| "learning_rate": 5.626666167821522e-06, |
| "loss": 0.0049, |
| "num_input_tokens_seen": 333664, |
| "step": 515 |
| }, |
| { |
| "epoch": 10.4, |
| "grad_norm": 2.51832914352417, |
| "learning_rate": 5.539996778530114e-06, |
| "loss": 0.0717, |
| "num_input_tokens_seen": 337248, |
| "step": 520 |
| }, |
| { |
| "epoch": 10.5, |
| "grad_norm": 1.407471776008606, |
| "learning_rate": 5.453162900988902e-06, |
| "loss": 0.0623, |
| "num_input_tokens_seen": 340192, |
| "step": 525 |
| }, |
| { |
| "epoch": 10.6, |
| "grad_norm": 0.4082932770252228, |
| "learning_rate": 5.366190985638159e-06, |
| "loss": 0.0057, |
| "num_input_tokens_seen": 343232, |
| "step": 530 |
| }, |
| { |
| "epoch": 10.7, |
| "grad_norm": 0.08292396366596222, |
| "learning_rate": 5.27910752496582e-06, |
| "loss": 0.0331, |
| "num_input_tokens_seen": 346400, |
| "step": 535 |
| }, |
| { |
| "epoch": 10.8, |
| "grad_norm": 0.014418110251426697, |
| "learning_rate": 5.1919390454376e-06, |
| "loss": 0.0028, |
| "num_input_tokens_seen": 349760, |
| "step": 540 |
| }, |
| { |
| "epoch": 10.9, |
| "grad_norm": 10.531606674194336, |
| "learning_rate": 5.1047120994167855e-06, |
| "loss": 0.0056, |
| "num_input_tokens_seen": 352352, |
| "step": 545 |
| }, |
| { |
| "epoch": 11.0, |
| "grad_norm": 0.25946757197380066, |
| "learning_rate": 5.0174532570761194e-06, |
| "loss": 0.002, |
| "num_input_tokens_seen": 355584, |
| "step": 550 |
| }, |
| { |
| "epoch": 11.1, |
| "grad_norm": 0.05245262011885643, |
| "learning_rate": 4.9301890983042744e-06, |
| "loss": 0.0003, |
| "num_input_tokens_seen": 359200, |
| "step": 555 |
| }, |
| { |
| "epoch": 11.2, |
| "grad_norm": 0.3186964988708496, |
| "learning_rate": 4.842946204609359e-06, |
| "loss": 0.0213, |
| "num_input_tokens_seen": 363200, |
| "step": 560 |
| }, |
| { |
| "epoch": 11.3, |
| "grad_norm": 0.11435585469007492, |
| "learning_rate": 4.755751151021934e-06, |
| "loss": 0.0007, |
| "num_input_tokens_seen": 366624, |
| "step": 565 |
| }, |
| { |
| "epoch": 11.4, |
| "grad_norm": 0.02673327922821045, |
| "learning_rate": 4.668630498000001e-06, |
| "loss": 0.0005, |
| "num_input_tokens_seen": 369824, |
| "step": 570 |
| }, |
| { |
| "epoch": 11.5, |
| "grad_norm": 22.57182502746582, |
| "learning_rate": 4.581610783338424e-06, |
| "loss": 0.0024, |
| "num_input_tokens_seen": 373120, |
| "step": 575 |
| }, |
| { |
| "epoch": 11.6, |
| "grad_norm": 13.380699157714844, |
| "learning_rate": 4.494718514085269e-06, |
| "loss": 0.002, |
| "num_input_tokens_seen": 375776, |
| "step": 580 |
| }, |
| { |
| "epoch": 11.7, |
| "grad_norm": 0.11530610173940659, |
| "learning_rate": 4.4079801584674955e-06, |
| "loss": 0.0029, |
| "num_input_tokens_seen": 378624, |
| "step": 585 |
| }, |
| { |
| "epoch": 11.8, |
| "grad_norm": 0.466453492641449, |
| "learning_rate": 4.321422137828479e-06, |
| "loss": 0.0003, |
| "num_input_tokens_seen": 381728, |
| "step": 590 |
| }, |
| { |
| "epoch": 11.9, |
| "grad_norm": 0.0489952377974987, |
| "learning_rate": 4.23507081857981e-06, |
| "loss": 0.0051, |
| "num_input_tokens_seen": 385312, |
| "step": 595 |
| }, |
| { |
| "epoch": 12.0, |
| "grad_norm": 0.6647362112998962, |
| "learning_rate": 4.148952504169839e-06, |
| "loss": 0.0008, |
| "num_input_tokens_seen": 388448, |
| "step": 600 |
| }, |
| { |
| "epoch": 12.0, |
| "eval_loss": 0.2536269426345825, |
| "eval_runtime": 1.0014, |
| "eval_samples_per_second": 49.928, |
| "eval_steps_per_second": 12.981, |
| "num_input_tokens_seen": 388448, |
| "step": 600 |
| }, |
| { |
| "epoch": 12.1, |
| "grad_norm": 0.053329646587371826, |
| "learning_rate": 4.063093427071376e-06, |
| "loss": 0.0003, |
| "num_input_tokens_seen": 391296, |
| "step": 605 |
| }, |
| { |
| "epoch": 12.2, |
| "grad_norm": 0.05639015883207321, |
| "learning_rate": 3.977519740791049e-06, |
| "loss": 0.0022, |
| "num_input_tokens_seen": 394688, |
| "step": 610 |
| }, |
| { |
| "epoch": 12.3, |
| "grad_norm": 0.0420084111392498, |
| "learning_rate": 3.892257511902664e-06, |
| "loss": 0.0003, |
| "num_input_tokens_seen": 397792, |
| "step": 615 |
| }, |
| { |
| "epoch": 12.4, |
| "grad_norm": 0.9871878623962402, |
| "learning_rate": 3.8073327121070968e-06, |
| "loss": 0.0004, |
| "num_input_tokens_seen": 400576, |
| "step": 620 |
| }, |
| { |
| "epoch": 12.5, |
| "grad_norm": 0.32017242908477783, |
| "learning_rate": 3.7227712103210485e-06, |
| "loss": 0.0003, |
| "num_input_tokens_seen": 404000, |
| "step": 625 |
| }, |
| { |
| "epoch": 12.6, |
| "grad_norm": 0.1881232112646103, |
| "learning_rate": 3.6385987647971287e-06, |
| "loss": 0.0002, |
| "num_input_tokens_seen": 407712, |
| "step": 630 |
| }, |
| { |
| "epoch": 12.7, |
| "grad_norm": 0.10421431809663773, |
| "learning_rate": 3.5548410152776414e-06, |
| "loss": 0.0004, |
| "num_input_tokens_seen": 411104, |
| "step": 635 |
| }, |
| { |
| "epoch": 12.8, |
| "grad_norm": 0.011882122606039047, |
| "learning_rate": 3.471523475184472e-06, |
| "loss": 0.0006, |
| "num_input_tokens_seen": 414624, |
| "step": 640 |
| }, |
| { |
| "epoch": 12.9, |
| "grad_norm": 0.011652891524136066, |
| "learning_rate": 3.3886715238474454e-06, |
| "loss": 0.0002, |
| "num_input_tokens_seen": 417824, |
| "step": 645 |
| }, |
| { |
| "epoch": 13.0, |
| "grad_norm": 0.020541567355394363, |
| "learning_rate": 3.3063103987735433e-06, |
| "loss": 0.0003, |
| "num_input_tokens_seen": 421248, |
| "step": 650 |
| }, |
| { |
| "epoch": 13.1, |
| "grad_norm": 0.02439752034842968, |
| "learning_rate": 3.224465187959316e-06, |
| "loss": 0.0002, |
| "num_input_tokens_seen": 424800, |
| "step": 655 |
| }, |
| { |
| "epoch": 13.2, |
| "grad_norm": 0.01759609952569008, |
| "learning_rate": 3.1431608222488276e-06, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 427872, |
| "step": 660 |
| }, |
| { |
| "epoch": 13.3, |
| "grad_norm": 0.015870150178670883, |
| "learning_rate": 3.0624220677394854e-06, |
| "loss": 0.0002, |
| "num_input_tokens_seen": 431392, |
| "step": 665 |
| }, |
| { |
| "epoch": 13.4, |
| "grad_norm": 0.027557481080293655, |
| "learning_rate": 2.98227351823805e-06, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 434176, |
| "step": 670 |
| }, |
| { |
| "epoch": 13.5, |
| "grad_norm": 0.16971592605113983, |
| "learning_rate": 2.9027395877691143e-06, |
| "loss": 0.0002, |
| "num_input_tokens_seen": 437696, |
| "step": 675 |
| }, |
| { |
| "epoch": 13.6, |
| "grad_norm": 0.17097657918930054, |
| "learning_rate": 2.8238445031383634e-06, |
| "loss": 0.0002, |
| "num_input_tokens_seen": 440064, |
| "step": 680 |
| }, |
| { |
| "epoch": 13.7, |
| "grad_norm": 0.024238118901848793, |
| "learning_rate": 2.7456122965528475e-06, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 443328, |
| "step": 685 |
| }, |
| { |
| "epoch": 13.8, |
| "grad_norm": 0.007093928754329681, |
| "learning_rate": 2.6680667983005446e-06, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 447072, |
| "step": 690 |
| }, |
| { |
| "epoch": 13.9, |
| "grad_norm": 0.01546875573694706, |
| "learning_rate": 2.5912316294914232e-06, |
| "loss": 0.0002, |
| "num_input_tokens_seen": 450688, |
| "step": 695 |
| }, |
| { |
| "epoch": 14.0, |
| "grad_norm": 0.042617473751306534, |
| "learning_rate": 2.5151301948622235e-06, |
| "loss": 0.0002, |
| "num_input_tokens_seen": 453984, |
| "step": 700 |
| }, |
| { |
| "epoch": 14.0, |
| "eval_loss": 0.28826868534088135, |
| "eval_runtime": 1.001, |
| "eval_samples_per_second": 49.95, |
| "eval_steps_per_second": 12.987, |
| "num_input_tokens_seen": 453984, |
| "step": 700 |
| }, |
| { |
| "epoch": 14.1, |
| "grad_norm": 0.04438012093305588, |
| "learning_rate": 2.4397856756471435e-06, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 457504, |
| "step": 705 |
| }, |
| { |
| "epoch": 14.2, |
| "grad_norm": 0.009802593849599361, |
| "learning_rate": 2.3652210225166122e-06, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 460896, |
| "step": 710 |
| }, |
| { |
| "epoch": 14.3, |
| "grad_norm": 0.009903536178171635, |
| "learning_rate": 2.2914589485863015e-06, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 463840, |
| "step": 715 |
| }, |
| { |
| "epoch": 14.4, |
| "grad_norm": 0.007097623776644468, |
| "learning_rate": 2.218521922498476e-06, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 467648, |
| "step": 720 |
| }, |
| { |
| "epoch": 14.5, |
| "grad_norm": 0.018301447853446007, |
| "learning_rate": 2.146432161577842e-06, |
| "loss": 0.0002, |
| "num_input_tokens_seen": 470688, |
| "step": 725 |
| }, |
| { |
| "epoch": 14.6, |
| "grad_norm": 0.03601658716797829, |
| "learning_rate": 2.075211625063923e-06, |
| "loss": 0.0002, |
| "num_input_tokens_seen": 473952, |
| "step": 730 |
| }, |
| { |
| "epoch": 14.7, |
| "grad_norm": 0.038516778498888016, |
| "learning_rate": 2.0048820074220716e-06, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 477120, |
| "step": 735 |
| }, |
| { |
| "epoch": 14.8, |
| "grad_norm": 0.07624400407075882, |
| "learning_rate": 1.9354647317351187e-06, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 480704, |
| "step": 740 |
| }, |
| { |
| "epoch": 14.9, |
| "grad_norm": 0.013465417549014091, |
| "learning_rate": 1.8669809431776991e-06, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 483744, |
| "step": 745 |
| }, |
| { |
| "epoch": 15.0, |
| "grad_norm": 0.007154775317758322, |
| "learning_rate": 1.799451502575222e-06, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 487232, |
| "step": 750 |
| }, |
| { |
| "epoch": 15.1, |
| "grad_norm": 0.008196992799639702, |
| "learning_rate": 1.7328969800494727e-06, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 491104, |
| "step": 755 |
| }, |
| { |
| "epoch": 15.2, |
| "grad_norm": 0.005913514643907547, |
| "learning_rate": 1.6673376487527382e-06, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 493568, |
| "step": 760 |
| }, |
| { |
| "epoch": 15.3, |
| "grad_norm": 0.008342737331986427, |
| "learning_rate": 1.6027934786924187e-06, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 496928, |
| "step": 765 |
| }, |
| { |
| "epoch": 15.4, |
| "grad_norm": 0.036556925624608994, |
| "learning_rate": 1.5392841306479667e-06, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 499936, |
| "step": 770 |
| }, |
| { |
| "epoch": 15.5, |
| "grad_norm": 0.04268655180931091, |
| "learning_rate": 1.4768289501820265e-06, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 503232, |
| "step": 775 |
| }, |
| { |
| "epoch": 15.6, |
| "grad_norm": 0.02554980479180813, |
| "learning_rate": 1.4154469617475864e-06, |
| "loss": 0.0002, |
| "num_input_tokens_seen": 506848, |
| "step": 780 |
| }, |
| { |
| "epoch": 15.7, |
| "grad_norm": 0.010822230018675327, |
| "learning_rate": 1.3551568628929434e-06, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 510304, |
| "step": 785 |
| }, |
| { |
| "epoch": 15.8, |
| "grad_norm": 0.007679897826164961, |
| "learning_rate": 1.2959770185662502e-06, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 512992, |
| "step": 790 |
| }, |
| { |
| "epoch": 15.9, |
| "grad_norm": 0.05034717917442322, |
| "learning_rate": 1.2379254555213788e-06, |
| "loss": 0.0002, |
| "num_input_tokens_seen": 516032, |
| "step": 795 |
| }, |
| { |
| "epoch": 16.0, |
| "grad_norm": 0.01680305227637291, |
| "learning_rate": 1.1810198568267906e-06, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 519200, |
| "step": 800 |
| }, |
| { |
| "epoch": 16.0, |
| "eval_loss": 0.2697804570198059, |
| "eval_runtime": 0.9988, |
| "eval_samples_per_second": 50.059, |
| "eval_steps_per_second": 13.015, |
| "num_input_tokens_seen": 519200, |
| "step": 800 |
| }, |
| { |
| "epoch": 16.1, |
| "grad_norm": 0.018977373838424683, |
| "learning_rate": 1.1252775564791023e-06, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 522272, |
| "step": 805 |
| }, |
| { |
| "epoch": 16.2, |
| "grad_norm": 0.0821557492017746, |
| "learning_rate": 1.0707155341229902e-06, |
| "loss": 0.0002, |
| "num_input_tokens_seen": 525440, |
| "step": 810 |
| }, |
| { |
| "epoch": 16.3, |
| "grad_norm": 0.029497282579541206, |
| "learning_rate": 1.0173504098790188e-06, |
| "loss": 0.0002, |
| "num_input_tokens_seen": 529056, |
| "step": 815 |
| }, |
| { |
| "epoch": 16.4, |
| "grad_norm": 0.013569852337241173, |
| "learning_rate": 9.651984392809916e-07, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 532192, |
| "step": 820 |
| }, |
| { |
| "epoch": 16.5, |
| "grad_norm": 0.013164045289158821, |
| "learning_rate": 9.142755083243577e-07, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 535712, |
| "step": 825 |
| }, |
| { |
| "epoch": 16.6, |
| "grad_norm": 0.025486232712864876, |
| "learning_rate": 8.645971286271903e-07, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 538752, |
| "step": 830 |
| }, |
| { |
| "epoch": 16.7, |
| "grad_norm": 0.014193262904882431, |
| "learning_rate": 8.161784327051919e-07, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 542368, |
| "step": 835 |
| }, |
| { |
| "epoch": 16.8, |
| "grad_norm": 0.011246598325669765, |
| "learning_rate": 7.690341693621805e-07, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 545088, |
| "step": 840 |
| }, |
| { |
| "epoch": 16.9, |
| "grad_norm": 0.04158206656575203, |
| "learning_rate": 7.23178699197467e-07, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 548800, |
| "step": 845 |
| }, |
| { |
| "epoch": 17.0, |
| "grad_norm": 0.004439216572791338, |
| "learning_rate": 6.786259902314768e-07, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 551552, |
| "step": 850 |
| }, |
| { |
| "epoch": 17.1, |
| "grad_norm": 0.027351979166269302, |
| "learning_rate": 6.353896136509524e-07, |
| "loss": 0.0002, |
| "num_input_tokens_seen": 554528, |
| "step": 855 |
| }, |
| { |
| "epoch": 17.2, |
| "grad_norm": 0.00909334421157837, |
| "learning_rate": 5.934827396750392e-07, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 557952, |
| "step": 860 |
| }, |
| { |
| "epoch": 17.3, |
| "grad_norm": 0.012324375100433826, |
| "learning_rate": 5.529181335435124e-07, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 560960, |
| "step": 865 |
| }, |
| { |
| "epoch": 17.4, |
| "grad_norm": 0.018054546788334846, |
| "learning_rate": 5.137081516283582e-07, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 564288, |
| "step": 870 |
| }, |
| { |
| "epoch": 17.5, |
| "grad_norm": 0.011498761363327503, |
| "learning_rate": 4.758647376699033e-07, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 566880, |
| "step": 875 |
| }, |
| { |
| "epoch": 17.6, |
| "grad_norm": 0.019566155970096588, |
| "learning_rate": 4.3939941913863525e-07, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 570208, |
| "step": 880 |
| }, |
| { |
| "epoch": 17.7, |
| "grad_norm": 0.0616542249917984, |
| "learning_rate": 4.043233037238281e-07, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 573568, |
| "step": 885 |
| }, |
| { |
| "epoch": 17.8, |
| "grad_norm": 0.02959338016808033, |
| "learning_rate": 3.7064707595002636e-07, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 576896, |
| "step": 890 |
| }, |
| { |
| "epoch": 17.9, |
| "grad_norm": 0.03563592955470085, |
| "learning_rate": 3.3838099392243915e-07, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 580672, |
| "step": 895 |
| }, |
| { |
| "epoch": 18.0, |
| "grad_norm": 0.004577992018312216, |
| "learning_rate": 3.0753488620222037e-07, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 583712, |
| "step": 900 |
| }, |
| { |
| "epoch": 18.0, |
| "eval_loss": 0.2686527371406555, |
| "eval_runtime": 1.0019, |
| "eval_samples_per_second": 49.907, |
| "eval_steps_per_second": 12.976, |
| "num_input_tokens_seen": 583712, |
| "step": 900 |
| }, |
| { |
| "epoch": 18.1, |
| "grad_norm": 0.009997401386499405, |
| "learning_rate": 2.7811814881259503e-07, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 587040, |
| "step": 905 |
| }, |
| { |
| "epoch": 18.2, |
| "grad_norm": 0.007089632097631693, |
| "learning_rate": 2.5013974237673824e-07, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 590496, |
| "step": 910 |
| }, |
| { |
| "epoch": 18.3, |
| "grad_norm": 0.005006881896406412, |
| "learning_rate": 2.2360818938828189e-07, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 593792, |
| "step": 915 |
| }, |
| { |
| "epoch": 18.4, |
| "grad_norm": 0.01716301590204239, |
| "learning_rate": 1.9853157161528468e-07, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 597408, |
| "step": 920 |
| }, |
| { |
| "epoch": 18.5, |
| "grad_norm": 0.013674321584403515, |
| "learning_rate": 1.7491752763844294e-07, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 600864, |
| "step": 925 |
| }, |
| { |
| "epoch": 18.6, |
| "grad_norm": 0.038443662226200104, |
| "learning_rate": 1.5277325052430569e-07, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 604096, |
| "step": 930 |
| }, |
| { |
| "epoch": 18.7, |
| "grad_norm": 0.02057618647813797, |
| "learning_rate": 1.3210548563419857e-07, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 607200, |
| "step": 935 |
| }, |
| { |
| "epoch": 18.8, |
| "grad_norm": 0.014067213051021099, |
| "learning_rate": 1.1292052856952063e-07, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 610432, |
| "step": 940 |
| }, |
| { |
| "epoch": 18.9, |
| "grad_norm": 0.020766226574778557, |
| "learning_rate": 9.522422325404234e-08, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 613184, |
| "step": 945 |
| }, |
| { |
| "epoch": 19.0, |
| "grad_norm": 0.00667183892801404, |
| "learning_rate": 7.90219601537906e-08, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 616096, |
| "step": 950 |
| }, |
| { |
| "epoch": 19.1, |
| "grad_norm": 0.0170288048684597, |
| "learning_rate": 6.431867463506047e-08, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 619456, |
| "step": 955 |
| }, |
| { |
| "epoch": 19.2, |
| "grad_norm": 0.010430488735437393, |
| "learning_rate": 5.111884546105506e-08, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 622752, |
| "step": 960 |
| }, |
| { |
| "epoch": 19.3, |
| "grad_norm": 0.060864806175231934, |
| "learning_rate": 3.9426493427611177e-08, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 625504, |
| "step": 965 |
| }, |
| { |
| "epoch": 19.4, |
| "grad_norm": 0.013428901322185993, |
| "learning_rate": 2.9245180138423033e-08, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 628960, |
| "step": 970 |
| }, |
| { |
| "epoch": 19.5, |
| "grad_norm": 0.021914439275860786, |
| "learning_rate": 2.057800692014833e-08, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 632128, |
| "step": 975 |
| }, |
| { |
| "epoch": 19.6, |
| "grad_norm": 0.010772191919386387, |
| "learning_rate": 1.3427613877709523e-08, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 635232, |
| "step": 980 |
| }, |
| { |
| "epoch": 19.7, |
| "grad_norm": 0.015666857361793518, |
| "learning_rate": 7.796179090094891e-09, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 638400, |
| "step": 985 |
| }, |
| { |
| "epoch": 19.8, |
| "grad_norm": 0.017693420872092247, |
| "learning_rate": 3.685417946894254e-09, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 641568, |
| "step": 990 |
| }, |
| { |
| "epoch": 19.9, |
| "grad_norm": 0.0059068226255476475, |
| "learning_rate": 1.096582625772502e-09, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 644704, |
| "step": 995 |
| }, |
| { |
| "epoch": 20.0, |
| "grad_norm": 0.03871485963463783, |
| "learning_rate": 3.0461711048035415e-11, |
| "loss": 0.0001, |
| "num_input_tokens_seen": 648352, |
| "step": 1000 |
| }, |
| { |
| "epoch": 20.0, |
| "eval_loss": 0.27483537793159485, |
| "eval_runtime": 1.0018, |
| "eval_samples_per_second": 49.911, |
| "eval_steps_per_second": 12.977, |
| "num_input_tokens_seen": 648352, |
| "step": 1000 |
| }, |
| { |
| "epoch": 20.0, |
| "num_input_tokens_seen": 648352, |
| "step": 1000, |
| "total_flos": 2.9194997525643264e+16, |
| "train_loss": 0.3380334594594024, |
| "train_runtime": 177.1764, |
| "train_samples_per_second": 22.576, |
| "train_steps_per_second": 5.644 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 1000, |
| "num_input_tokens_seen": 648352, |
| "num_train_epochs": 20, |
| "save_steps": 100, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 2.9194997525643264e+16, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
