| {"loss": 0.62886596, "token_acc": 0.79235101, "grad_norm": 5.16465052, "learning_rate": 7e-08, "memory(GiB)": 20.13, "train_speed(iter/s)": 0.05631, "epoch": 0.00111919, "global_step/max_steps": "1/2679", "percentage": "0.04%", "elapsed_time": "14s", "remaining_time": "10h 42m 23s"} |
| {"loss": 0.68389672, "token_acc": 0.79593064, "grad_norm": 5.07414096, "learning_rate": 3.7e-07, "memory(GiB)": 20.13, "train_speed(iter/s)": 0.186614, "epoch": 0.00559597, "global_step/max_steps": "5/2679", "percentage": "0.19%", "elapsed_time": "23s", "remaining_time": "3h 28m 49s"} |
| {"loss": 0.63307619, "token_acc": 0.82044081, "grad_norm": 4.64163619, "learning_rate": 7.5e-07, "memory(GiB)": 36.34, "train_speed(iter/s)": 0.263435, "epoch": 0.01119194, "global_step/max_steps": "10/2679", "percentage": "0.37%", "elapsed_time": "34s", "remaining_time": "2h 33m 53s"} |
| {"loss": 0.63045325, "token_acc": 0.82181353, "grad_norm": 4.46340677, "learning_rate": 1.12e-06, "memory(GiB)": 47.65, "train_speed(iter/s)": 0.305451, "epoch": 0.01678791, "global_step/max_steps": "15/2679", "percentage": "0.56%", "elapsed_time": "45s", "remaining_time": "2h 15m 23s"} |
| {"loss": 0.60309005, "token_acc": 0.82321715, "grad_norm": 3.26727218, "learning_rate": 1.49e-06, "memory(GiB)": 47.65, "train_speed(iter/s)": 0.332742, "epoch": 0.02238388, "global_step/max_steps": "20/2679", "percentage": "0.75%", "elapsed_time": "56s", "remaining_time": "2h 5m 44s"} |
| {"loss": 0.55287218, "token_acc": 0.81580642, "grad_norm": 2.55577089, "learning_rate": 1.87e-06, "memory(GiB)": 47.65, "train_speed(iter/s)": 0.34915, "epoch": 0.02797985, "global_step/max_steps": "25/2679", "percentage": "0.93%", "elapsed_time": "1m 8s", "remaining_time": "2h 0m 44s"} |
| {"loss": 0.47245288, "token_acc": 0.8561354, "grad_norm": 2.35164077, "learning_rate": 2.24e-06, "memory(GiB)": 60.63, "train_speed(iter/s)": 0.362678, "epoch": 0.03357583, "global_step/max_steps": "30/2679", "percentage": "1.12%", "elapsed_time": "1m 19s", "remaining_time": "1h 56m 46s"} |
| {"loss": 0.4703599, "token_acc": 0.83799732, "grad_norm": 2.17185397, "learning_rate": 2.61e-06, "memory(GiB)": 60.63, "train_speed(iter/s)": 0.374036, "epoch": 0.0391718, "global_step/max_steps": "35/2679", "percentage": "1.31%", "elapsed_time": "1m 30s", "remaining_time": "1h 53m 34s"} |
| {"loss": 0.43998089, "token_acc": 0.86375, "grad_norm": 1.84728609, "learning_rate": 2.99e-06, "memory(GiB)": 60.63, "train_speed(iter/s)": 0.382317, "epoch": 0.04476777, "global_step/max_steps": "40/2679", "percentage": "1.49%", "elapsed_time": "1m 41s", "remaining_time": "1h 51m 20s"} |
| {"loss": 0.41998448, "token_acc": 0.87018675, "grad_norm": 1.63319522, "learning_rate": 3.36e-06, "memory(GiB)": 60.63, "train_speed(iter/s)": 0.389981, "epoch": 0.05036374, "global_step/max_steps": "45/2679", "percentage": "1.68%", "elapsed_time": "1m 52s", "remaining_time": "1h 49m 17s"} |
| {"loss": 0.41311321, "token_acc": 0.86478621, "grad_norm": 1.60019556, "learning_rate": 3.73e-06, "memory(GiB)": 60.63, "train_speed(iter/s)": 0.39553, "epoch": 0.05595971, "global_step/max_steps": "50/2679", "percentage": "1.87%", "elapsed_time": "2m 3s", "remaining_time": "1h 47m 49s"} |
| {"loss": 0.38757427, "token_acc": 0.88649975, "grad_norm": 1.43953203, "learning_rate": 4.1e-06, "memory(GiB)": 60.63, "train_speed(iter/s)": 0.399908, "epoch": 0.06155568, "global_step/max_steps": "55/2679", "percentage": "2.05%", "elapsed_time": "2m 14s", "remaining_time": "1h 46m 41s"} |
| {"loss": 0.36163509, "token_acc": 0.86419949, "grad_norm": 1.60083362, "learning_rate": 4.48e-06, "memory(GiB)": 60.63, "train_speed(iter/s)": 0.404673, "epoch": 0.06715165, "global_step/max_steps": "60/2679", "percentage": "2.24%", "elapsed_time": "2m 24s", "remaining_time": "1h 45m 25s"} |
| {"loss": 0.36112957, "token_acc": 0.86986474, "grad_norm": 1.47995877, "learning_rate": 4.85e-06, "memory(GiB)": 60.63, "train_speed(iter/s)": 0.407667, "epoch": 0.07274762, "global_step/max_steps": "65/2679", "percentage": "2.43%", "elapsed_time": "2m 36s", "remaining_time": "1h 44m 36s"} |
| {"loss": 0.36722732, "token_acc": 0.88338164, "grad_norm": 1.57149238, "learning_rate": 5.22e-06, "memory(GiB)": 60.63, "train_speed(iter/s)": 0.410585, "epoch": 0.07834359, "global_step/max_steps": "70/2679", "percentage": "2.61%", "elapsed_time": "2m 47s", "remaining_time": "1h 43m 49s"} |
| {"loss": 0.37027693, "token_acc": 0.8807967, "grad_norm": 1.54381566, "learning_rate": 5.6e-06, "memory(GiB)": 60.63, "train_speed(iter/s)": 0.41383, "epoch": 0.08393956, "global_step/max_steps": "75/2679", "percentage": "2.80%", "elapsed_time": "2m 57s", "remaining_time": "1h 42m 55s"} |
| {"loss": 0.36136508, "token_acc": 0.87003936, "grad_norm": 1.24845717, "learning_rate": 5.97e-06, "memory(GiB)": 60.63, "train_speed(iter/s)": 0.415453, "epoch": 0.08953553, "global_step/max_steps": "80/2679", "percentage": "2.99%", "elapsed_time": "3m 9s", "remaining_time": "1h 42m 26s"} |
| {"loss": 0.39811656, "token_acc": 0.86926414, "grad_norm": 1.48181913, "learning_rate": 6.34e-06, "memory(GiB)": 60.63, "train_speed(iter/s)": 0.417038, "epoch": 0.09513151, "global_step/max_steps": "85/2679", "percentage": "3.17%", "elapsed_time": "3m 20s", "remaining_time": "1h 41m 57s"} |
| {"loss": 0.38755939, "token_acc": 0.86518253, "grad_norm": 1.66889889, "learning_rate": 6.72e-06, "memory(GiB)": 60.63, "train_speed(iter/s)": 0.419293, "epoch": 0.10072748, "global_step/max_steps": "90/2679", "percentage": "3.36%", "elapsed_time": "3m 31s", "remaining_time": "1h 41m 17s"} |
| {"loss": 0.38646846, "token_acc": 0.86672635, "grad_norm": 1.4128881, "learning_rate": 7.09e-06, "memory(GiB)": 60.63, "train_speed(iter/s)": 0.421241, "epoch": 0.10632345, "global_step/max_steps": "95/2679", "percentage": "3.55%", "elapsed_time": "3m 42s", "remaining_time": "1h 40m 42s"} |
| {"loss": 0.34529109, "token_acc": 0.87736941, "grad_norm": 1.48944825, "learning_rate": 7.46e-06, "memory(GiB)": 60.63, "train_speed(iter/s)": 0.421626, "epoch": 0.11191942, "global_step/max_steps": "100/2679", "percentage": "3.73%", "elapsed_time": "3m 53s", "remaining_time": "1h 40m 30s"} |
| {"loss": 0.32161517, "token_acc": 0.89538161, "grad_norm": 1.62732811, "learning_rate": 7.84e-06, "memory(GiB)": 60.63, "train_speed(iter/s)": 0.423347, "epoch": 0.11751539, "global_step/max_steps": "105/2679", "percentage": "3.92%", "elapsed_time": "4m 4s", "remaining_time": "1h 39m 57s"} |
| {"loss": 0.37918944, "token_acc": 0.8600062, "grad_norm": 1.38241964, "learning_rate": 8.21e-06, "memory(GiB)": 60.63, "train_speed(iter/s)": 0.424564, "epoch": 0.12311136, "global_step/max_steps": "110/2679", "percentage": "4.11%", "elapsed_time": "4m 15s", "remaining_time": "1h 39m 32s"} |
| {"loss": 0.34900508, "token_acc": 0.88590866, "grad_norm": 1.68094947, "learning_rate": 8.58e-06, "memory(GiB)": 60.63, "train_speed(iter/s)": 0.425465, "epoch": 0.12870733, "global_step/max_steps": "115/2679", "percentage": "4.29%", "elapsed_time": "4m 26s", "remaining_time": "1h 39m 11s"} |
| {"loss": 0.3525516, "token_acc": 0.87892305, "grad_norm": 1.39291361, "learning_rate": 8.96e-06, "memory(GiB)": 60.63, "train_speed(iter/s)": 0.426128, "epoch": 0.1343033, "global_step/max_steps": "120/2679", "percentage": "4.48%", "elapsed_time": "4m 38s", "remaining_time": "1h 38m 53s"} |
| {"loss": 0.34694281, "token_acc": 0.87220934, "grad_norm": 1.45629747, "learning_rate": 9.33e-06, "memory(GiB)": 60.63, "train_speed(iter/s)": 0.42724, "epoch": 0.13989927, "global_step/max_steps": "125/2679", "percentage": "4.67%", "elapsed_time": "4m 49s", "remaining_time": "1h 38m 29s"} |
| {"loss": 0.34943225, "token_acc": 0.88396523, "grad_norm": 1.56942174, "learning_rate": 9.7e-06, "memory(GiB)": 60.63, "train_speed(iter/s)": 0.428067, "epoch": 0.14549524, "global_step/max_steps": "130/2679", "percentage": "4.85%", "elapsed_time": "5m 0s", "remaining_time": "1h 38m 8s"} |
| {"loss": 0.34488034, "token_acc": 0.86004993, "grad_norm": 1.74313134, "learning_rate": 1e-05, "memory(GiB)": 60.63, "train_speed(iter/s)": 0.428777, "epoch": 0.15109121, "global_step/max_steps": "135/2679", "percentage": "5.04%", "elapsed_time": "5m 11s", "remaining_time": "1h 37m 49s"} |
| {"loss": 0.37110326, "token_acc": 0.86884456, "grad_norm": 1.64947262, "learning_rate": 1e-05, "memory(GiB)": 60.63, "train_speed(iter/s)": 0.429568, "epoch": 0.15668719, "global_step/max_steps": "140/2679", "percentage": "5.23%", "elapsed_time": "5m 22s", "remaining_time": "1h 37m 29s"} |
| {"loss": 0.36332459, "token_acc": 0.86019995, "grad_norm": 1.63552502, "learning_rate": 1e-05, "memory(GiB)": 60.63, "train_speed(iter/s)": 0.430153, "epoch": 0.16228316, "global_step/max_steps": "145/2679", "percentage": "5.41%", "elapsed_time": "5m 33s", "remaining_time": "1h 37m 12s"} |
| {"loss": 0.32439365, "token_acc": 0.88797737, "grad_norm": 1.64623301, "learning_rate": 1e-05, "memory(GiB)": 60.63, "train_speed(iter/s)": 0.430915, "epoch": 0.16787913, "global_step/max_steps": "150/2679", "percentage": "5.60%", "elapsed_time": "5m 44s", "remaining_time": "1h 36m 52s"} |
| {"loss": 0.34078293, "token_acc": 0.88475444, "grad_norm": 1.3250587, "learning_rate": 1e-05, "memory(GiB)": 60.63, "train_speed(iter/s)": 0.431242, "epoch": 0.1734751, "global_step/max_steps": "155/2679", "percentage": "5.79%", "elapsed_time": "5m 56s", "remaining_time": "1h 36m 38s"} |
| {"loss": 0.33334119, "token_acc": 0.87869033, "grad_norm": 1.37679753, "learning_rate": 1e-05, "memory(GiB)": 60.63, "train_speed(iter/s)": 0.431984, "epoch": 0.17907107, "global_step/max_steps": "160/2679", "percentage": "5.97%", "elapsed_time": "6m 7s", "remaining_time": "1h 36m 18s"} |
| {"loss": 0.34389503, "token_acc": 0.90451895, "grad_norm": 1.6068527, "learning_rate": 1e-05, "memory(GiB)": 60.63, "train_speed(iter/s)": 0.432638, "epoch": 0.18466704, "global_step/max_steps": "165/2679", "percentage": "6.16%", "elapsed_time": "6m 18s", "remaining_time": "1h 35m 59s"} |
| {"loss": 0.33083992, "token_acc": 0.87313821, "grad_norm": 1.44614462, "learning_rate": 1e-05, "memory(GiB)": 60.63, "train_speed(iter/s)": 0.433378, "epoch": 0.19026301, "global_step/max_steps": "170/2679", "percentage": "6.35%", "elapsed_time": "6m 28s", "remaining_time": "1h 35m 39s"} |
| {"loss": 0.36241767, "token_acc": 0.85922769, "grad_norm": 1.76565128, "learning_rate": 9.99e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.433466, "epoch": 0.19585898, "global_step/max_steps": "175/2679", "percentage": "6.53%", "elapsed_time": "6m 40s", "remaining_time": "1h 35m 28s"} |
| {"loss": 0.32959971, "token_acc": 0.87231057, "grad_norm": 1.63477579, "learning_rate": 9.99e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.434039, "epoch": 0.20145495, "global_step/max_steps": "180/2679", "percentage": "6.72%", "elapsed_time": "6m 51s", "remaining_time": "1h 35m 10s"} |
| {"loss": 0.31329002, "token_acc": 0.86384765, "grad_norm": 1.3351222, "learning_rate": 9.99e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.434381, "epoch": 0.20705092, "global_step/max_steps": "185/2679", "percentage": "6.91%", "elapsed_time": "7m 2s", "remaining_time": "1h 34m 56s"} |
| {"loss": 0.33907201, "token_acc": 0.88280909, "grad_norm": 1.54128736, "learning_rate": 9.99e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.434814, "epoch": 0.21264689, "global_step/max_steps": "190/2679", "percentage": "7.09%", "elapsed_time": "7m 13s", "remaining_time": "1h 34m 40s"} |
| {"loss": 0.34030852, "token_acc": 0.87775963, "grad_norm": 1.37701538, "learning_rate": 9.99e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.435029, "epoch": 0.21824287, "global_step/max_steps": "195/2679", "percentage": "7.28%", "elapsed_time": "7m 24s", "remaining_time": "1h 34m 27s"} |
| {"loss": 0.32567344, "token_acc": 0.86200395, "grad_norm": 1.44120532, "learning_rate": 9.98e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.435215, "epoch": 0.22383884, "global_step/max_steps": "200/2679", "percentage": "7.47%", "elapsed_time": "7m 36s", "remaining_time": "1h 34m 14s"} |
| {"eval_loss": 0.33167222, "eval_token_acc": 0.87663535, "eval_runtime": 7.2132, "eval_samples_per_second": 14.973, "eval_steps_per_second": 2.495, "epoch": 0.22383884, "global_step/max_steps": "200/2679", "percentage": "7.47%", "elapsed_time": "7m 43s", "remaining_time": "1h 35m 44s"} |
| {"loss": 0.33215861, "token_acc": 0.87508065, "grad_norm": 1.48400836, "learning_rate": 9.98e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.428914, "epoch": 0.22943481, "global_step/max_steps": "205/2679", "percentage": "7.65%", "elapsed_time": "7m 54s", "remaining_time": "1h 35m 27s"} |
| {"loss": 0.33353844, "token_acc": 0.89216343, "grad_norm": 1.47360715, "learning_rate": 9.98e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.429533, "epoch": 0.23503078, "global_step/max_steps": "210/2679", "percentage": "7.84%", "elapsed_time": "8m 5s", "remaining_time": "1h 35m 8s"} |
| {"loss": 0.32031379, "token_acc": 0.86683292, "grad_norm": 1.28723684, "learning_rate": 9.98e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.430139, "epoch": 0.24062675, "global_step/max_steps": "215/2679", "percentage": "8.03%", "elapsed_time": "8m 16s", "remaining_time": "1h 34m 49s"} |
| {"loss": 0.34436259, "token_acc": 0.88265265, "grad_norm": 1.53951633, "learning_rate": 9.97e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.430589, "epoch": 0.24622272, "global_step/max_steps": "220/2679", "percentage": "8.21%", "elapsed_time": "8m 27s", "remaining_time": "1h 34m 33s"} |
| {"loss": 0.32616651, "token_acc": 0.89956985, "grad_norm": 1.44984597, "learning_rate": 9.97e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.431069, "epoch": 0.25181869, "global_step/max_steps": "225/2679", "percentage": "8.40%", "elapsed_time": "8m 38s", "remaining_time": "1h 34m 16s"} |
| {"loss": 0.35327907, "token_acc": 0.86194633, "grad_norm": 1.49689032, "learning_rate": 9.96e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.431666, "epoch": 0.25741466, "global_step/max_steps": "230/2679", "percentage": "8.59%", "elapsed_time": "8m 49s", "remaining_time": "1h 33m 57s"} |
| {"loss": 0.32247834, "token_acc": 0.88440881, "grad_norm": 1.45162495, "learning_rate": 9.96e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.432177, "epoch": 0.26301063, "global_step/max_steps": "235/2679", "percentage": "8.77%", "elapsed_time": "9m 0s", "remaining_time": "1h 33m 40s"} |
| {"loss": 0.34239693, "token_acc": 0.88389889, "grad_norm": 1.44035168, "learning_rate": 9.96e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.432663, "epoch": 0.2686066, "global_step/max_steps": "240/2679", "percentage": "8.96%", "elapsed_time": "9m 11s", "remaining_time": "1h 33m 22s"} |
| {"loss": 0.3179687, "token_acc": 0.89510387, "grad_norm": 1.32892153, "learning_rate": 9.95e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.43251, "epoch": 0.27420257, "global_step/max_steps": "245/2679", "percentage": "9.15%", "elapsed_time": "9m 23s", "remaining_time": "1h 33m 14s"} |
| {"loss": 0.34756718, "token_acc": 0.8748805, "grad_norm": 1.40424874, "learning_rate": 9.95e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.432616, "epoch": 0.27979855, "global_step/max_steps": "250/2679", "percentage": "9.33%", "elapsed_time": "9m 34s", "remaining_time": "1h 33m 1s"} |
| {"loss": 0.31067924, "token_acc": 0.86827586, "grad_norm": 1.2344579, "learning_rate": 9.94e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.432875, "epoch": 0.28539452, "global_step/max_steps": "255/2679", "percentage": "9.52%", "elapsed_time": "9m 45s", "remaining_time": "1h 32m 47s"} |
| {"loss": 0.34387898, "token_acc": 0.87375398, "grad_norm": 1.43785547, "learning_rate": 9.94e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.432668, "epoch": 0.29099049, "global_step/max_steps": "260/2679", "percentage": "9.71%", "elapsed_time": "9m 57s", "remaining_time": "1h 32m 39s"} |
| {"loss": 0.32631023, "token_acc": 0.89580407, "grad_norm": 1.48587272, "learning_rate": 9.93e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.432971, "epoch": 0.29658646, "global_step/max_steps": "265/2679", "percentage": "9.89%", "elapsed_time": "10m 8s", "remaining_time": "1h 32m 24s"} |
| {"loss": 0.3259692, "token_acc": 0.8650042, "grad_norm": 1.46490463, "learning_rate": 9.93e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.433333, "epoch": 0.30218243, "global_step/max_steps": "270/2679", "percentage": "10.08%", "elapsed_time": "10m 19s", "remaining_time": "1h 32m 9s"} |
| {"loss": 0.32187819, "token_acc": 0.88645472, "grad_norm": 1.37036088, "learning_rate": 9.92e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.433685, "epoch": 0.3077784, "global_step/max_steps": "275/2679", "percentage": "10.27%", "elapsed_time": "10m 30s", "remaining_time": "1h 31m 53s"} |
| {"loss": 0.35928206, "token_acc": 0.84705011, "grad_norm": 1.46317702, "learning_rate": 9.92e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.433804, "epoch": 0.31337437, "global_step/max_steps": "280/2679", "percentage": "10.45%", "elapsed_time": "10m 42s", "remaining_time": "1h 31m 41s"} |
| {"loss": 0.34660048, "token_acc": 0.89063959, "grad_norm": 1.41305192, "learning_rate": 9.91e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.434237, "epoch": 0.31897034, "global_step/max_steps": "285/2679", "percentage": "10.64%", "elapsed_time": "10m 52s", "remaining_time": "1h 31m 24s"} |
| {"loss": 0.34029214, "token_acc": 0.86188613, "grad_norm": 1.33913194, "learning_rate": 9.91e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.434574, "epoch": 0.32456631, "global_step/max_steps": "290/2679", "percentage": "10.82%", "elapsed_time": "11m 3s", "remaining_time": "1h 31m 9s"} |
| {"loss": 0.32945647, "token_acc": 0.8687799, "grad_norm": 1.55055176, "learning_rate": 9.9e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.434805, "epoch": 0.33016228, "global_step/max_steps": "295/2679", "percentage": "11.01%", "elapsed_time": "11m 15s", "remaining_time": "1h 30m 55s"} |
| {"loss": 0.31978264, "token_acc": 0.87482711, "grad_norm": 1.49523193, "learning_rate": 9.9e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.4352, "epoch": 0.33575825, "global_step/max_steps": "300/2679", "percentage": "11.20%", "elapsed_time": "11m 25s", "remaining_time": "1h 30m 39s"} |
| {"loss": 0.291679, "token_acc": 0.87641113, "grad_norm": 1.38317342, "learning_rate": 9.89e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.435369, "epoch": 0.34135422, "global_step/max_steps": "305/2679", "percentage": "11.38%", "elapsed_time": "11m 37s", "remaining_time": "1h 30m 26s"} |
| {"loss": 0.30531526, "token_acc": 0.87635763, "grad_norm": 1.46465296, "learning_rate": 9.88e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.435737, "epoch": 0.3469502, "global_step/max_steps": "310/2679", "percentage": "11.57%", "elapsed_time": "11m 48s", "remaining_time": "1h 30m 11s"} |
| {"loss": 0.31190386, "token_acc": 0.88265273, "grad_norm": 1.50371689, "learning_rate": 9.88e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.436009, "epoch": 0.35254617, "global_step/max_steps": "315/2679", "percentage": "11.76%", "elapsed_time": "11m 59s", "remaining_time": "1h 29m 56s"} |
| {"loss": 0.33403194, "token_acc": 0.87762188, "grad_norm": 1.3897305, "learning_rate": 9.87e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.436297, "epoch": 0.35814214, "global_step/max_steps": "320/2679", "percentage": "11.94%", "elapsed_time": "12m 10s", "remaining_time": "1h 29m 42s"} |
| {"loss": 0.33297195, "token_acc": 0.83956719, "grad_norm": 1.30575353, "learning_rate": 9.86e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.436454, "epoch": 0.36373811, "global_step/max_steps": "325/2679", "percentage": "12.13%", "elapsed_time": "12m 21s", "remaining_time": "1h 29m 29s"} |
| {"loss": 0.29703014, "token_acc": 0.87245517, "grad_norm": 1.24726013, "learning_rate": 9.85e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.436574, "epoch": 0.36933408, "global_step/max_steps": "330/2679", "percentage": "12.32%", "elapsed_time": "12m 32s", "remaining_time": "1h 29m 16s"} |
| {"loss": 0.28598487, "token_acc": 0.89175258, "grad_norm": 1.36122212, "learning_rate": 9.85e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.436805, "epoch": 0.37493005, "global_step/max_steps": "335/2679", "percentage": "12.50%", "elapsed_time": "12m 43s", "remaining_time": "1h 29m 2s"} |
| {"loss": 0.31956565, "token_acc": 0.88919822, "grad_norm": 1.37372058, "learning_rate": 9.84e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.436964, "epoch": 0.38052602, "global_step/max_steps": "340/2679", "percentage": "12.69%", "elapsed_time": "12m 54s", "remaining_time": "1h 28m 49s"} |
| {"loss": 0.32744243, "token_acc": 0.88707758, "grad_norm": 1.5066374, "learning_rate": 9.83e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.43725, "epoch": 0.38612199, "global_step/max_steps": "345/2679", "percentage": "12.88%", "elapsed_time": "13m 5s", "remaining_time": "1h 28m 35s"} |
| {"loss": 0.30742359, "token_acc": 0.87246785, "grad_norm": 1.52850648, "learning_rate": 9.82e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.437467, "epoch": 0.39171796, "global_step/max_steps": "350/2679", "percentage": "13.06%", "elapsed_time": "13m 16s", "remaining_time": "1h 28m 21s"} |
| {"loss": 0.32868967, "token_acc": 0.87244293, "grad_norm": 1.36336764, "learning_rate": 9.82e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.437632, "epoch": 0.39731393, "global_step/max_steps": "355/2679", "percentage": "13.25%", "elapsed_time": "13m 27s", "remaining_time": "1h 28m 8s"} |
| {"loss": 0.32504239, "token_acc": 0.87940721, "grad_norm": 1.33350389, "learning_rate": 9.81e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.437831, "epoch": 0.4029099, "global_step/max_steps": "360/2679", "percentage": "13.44%", "elapsed_time": "13m 38s", "remaining_time": "1h 27m 54s"} |
| {"loss": 0.34006174, "token_acc": 0.87485223, "grad_norm": 1.23295092, "learning_rate": 9.8e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.437909, "epoch": 0.40850588, "global_step/max_steps": "365/2679", "percentage": "13.62%", "elapsed_time": "13m 50s", "remaining_time": "1h 27m 42s"} |
| {"loss": 0.29794698, "token_acc": 0.89186304, "grad_norm": 1.58503906, "learning_rate": 9.79e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.437933, "epoch": 0.41410185, "global_step/max_steps": "370/2679", "percentage": "13.81%", "elapsed_time": "14m 1s", "remaining_time": "1h 27m 31s"} |
| {"loss": 0.30135636, "token_acc": 0.88843963, "grad_norm": 1.2214506, "learning_rate": 9.78e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.438112, "epoch": 0.41969782, "global_step/max_steps": "375/2679", "percentage": "14.00%", "elapsed_time": "14m 12s", "remaining_time": "1h 27m 18s"} |
| {"loss": 0.30278621, "token_acc": 0.89834166, "grad_norm": 1.21265882, "learning_rate": 9.77e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.438308, "epoch": 0.42529379, "global_step/max_steps": "380/2679", "percentage": "14.18%", "elapsed_time": "14m 23s", "remaining_time": "1h 27m 4s"} |
| {"loss": 0.31080146, "token_acc": 0.88116711, "grad_norm": 1.2480113, "learning_rate": 9.76e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.438551, "epoch": 0.43088976, "global_step/max_steps": "385/2679", "percentage": "14.37%", "elapsed_time": "14m 34s", "remaining_time": "1h 26m 50s"} |
| {"loss": 0.30190392, "token_acc": 0.87552477, "grad_norm": 1.47459693, "learning_rate": 9.75e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.438709, "epoch": 0.43648573, "global_step/max_steps": "390/2679", "percentage": "14.56%", "elapsed_time": "14m 45s", "remaining_time": "1h 26m 37s"} |
| {"loss": 0.29653289, "token_acc": 0.88712112, "grad_norm": 1.34541298, "learning_rate": 9.74e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.4389, "epoch": 0.4420817, "global_step/max_steps": "395/2679", "percentage": "14.74%", "elapsed_time": "14m 56s", "remaining_time": "1h 26m 24s"} |
| {"loss": 0.28368549, "token_acc": 0.9217437, "grad_norm": 1.32290957, "learning_rate": 9.73e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.438943, "epoch": 0.44767767, "global_step/max_steps": "400/2679", "percentage": "14.93%", "elapsed_time": "15m 7s", "remaining_time": "1h 26m 12s"} |
| {"eval_loss": 0.3092663, "eval_token_acc": 0.88256127, "eval_runtime": 6.9665, "eval_samples_per_second": 15.503, "eval_steps_per_second": 2.584, "epoch": 0.44767767, "global_step/max_steps": "400/2679", "percentage": "14.93%", "elapsed_time": "15m 14s", "remaining_time": "1h 26m 52s"} |
| {"loss": 0.30450578, "token_acc": 0.90111925, "grad_norm": 1.52873466, "learning_rate": 9.72e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.435736, "epoch": 0.45327364, "global_step/max_steps": "405/2679", "percentage": "15.12%", "elapsed_time": "15m 26s", "remaining_time": "1h 26m 39s"} |
| {"loss": 0.29214427, "token_acc": 0.90525137, "grad_norm": 1.22486761, "learning_rate": 9.71e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.435701, "epoch": 0.45886961, "global_step/max_steps": "410/2679", "percentage": "15.30%", "elapsed_time": "15m 37s", "remaining_time": "1h 26m 29s"} |
| {"loss": 0.29977682, "token_acc": 0.88928981, "grad_norm": 1.44197054, "learning_rate": 9.7e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.43594, "epoch": 0.46446558, "global_step/max_steps": "415/2679", "percentage": "15.49%", "elapsed_time": "15m 48s", "remaining_time": "1h 26m 15s"} |
| {"loss": 0.32122171, "token_acc": 0.89991878, "grad_norm": 1.43660358, "learning_rate": 9.69e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.436145, "epoch": 0.47006156, "global_step/max_steps": "420/2679", "percentage": "15.68%", "elapsed_time": "15m 59s", "remaining_time": "1h 26m 1s"} |
| {"loss": 0.33009186, "token_acc": 0.88419548, "grad_norm": 1.3801418, "learning_rate": 9.68e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.4362, "epoch": 0.47565753, "global_step/max_steps": "425/2679", "percentage": "15.86%", "elapsed_time": "16m 10s", "remaining_time": "1h 25m 49s"} |
| {"loss": 0.3034874, "token_acc": 0.88969581, "grad_norm": 1.40496707, "learning_rate": 9.67e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.43639, "epoch": 0.4812535, "global_step/max_steps": "430/2679", "percentage": "16.05%", "elapsed_time": "16m 21s", "remaining_time": "1h 25m 36s"} |
| {"loss": 0.31147742, "token_acc": 0.8878697, "grad_norm": 1.39424075, "learning_rate": 9.66e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.436681, "epoch": 0.48684947, "global_step/max_steps": "435/2679", "percentage": "16.24%", "elapsed_time": "16m 32s", "remaining_time": "1h 25m 21s"} |
| {"loss": 0.29181449, "token_acc": 0.8804818, "grad_norm": 1.32370937, "learning_rate": 9.65e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.436873, "epoch": 0.49244544, "global_step/max_steps": "440/2679", "percentage": "16.42%", "elapsed_time": "16m 43s", "remaining_time": "1h 25m 7s"} |
| {"loss": 0.31753454, "token_acc": 0.88809621, "grad_norm": 1.34828306, "learning_rate": 9.64e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.437019, "epoch": 0.49804141, "global_step/max_steps": "445/2679", "percentage": "16.61%", "elapsed_time": "16m 54s", "remaining_time": "1h 24m 55s"} |
| {"loss": 0.3303339, "token_acc": 0.89101706, "grad_norm": 1.1722563, "learning_rate": 9.62e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.437217, "epoch": 0.50363738, "global_step/max_steps": "450/2679", "percentage": "16.80%", "elapsed_time": "17m 5s", "remaining_time": "1h 24m 41s"} |
| {"loss": 0.30872655, "token_acc": 0.9122999, "grad_norm": 1.15950837, "learning_rate": 9.61e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.437445, "epoch": 0.50923335, "global_step/max_steps": "455/2679", "percentage": "16.98%", "elapsed_time": "17m 16s", "remaining_time": "1h 24m 27s"} |
| {"loss": 0.31238852, "token_acc": 0.88802121, "grad_norm": 1.2400253, "learning_rate": 9.6e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.437333, "epoch": 0.51482932, "global_step/max_steps": "460/2679", "percentage": "17.17%", "elapsed_time": "17m 28s", "remaining_time": "1h 24m 17s"} |
| {"loss": 0.32456112, "token_acc": 0.8953193, "grad_norm": 1.35946051, "learning_rate": 9.59e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.437433, "epoch": 0.52042529, "global_step/max_steps": "465/2679", "percentage": "17.36%", "elapsed_time": "17m 39s", "remaining_time": "1h 24m 5s"} |
| {"loss": 0.27809227, "token_acc": 0.89547881, "grad_norm": 1.362138, "learning_rate": 9.58e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.437616, "epoch": 0.52602126, "global_step/max_steps": "470/2679", "percentage": "17.54%", "elapsed_time": "17m 50s", "remaining_time": "1h 23m 51s"} |
| {"loss": 0.29432025, "token_acc": 0.90258308, "grad_norm": 1.41497787, "learning_rate": 9.56e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.437602, "epoch": 0.53161724, "global_step/max_steps": "475/2679", "percentage": "17.73%", "elapsed_time": "18m 2s", "remaining_time": "1h 23m 40s"} |
| {"loss": 0.30683239, "token_acc": 0.8856636, "grad_norm": 1.3939804, "learning_rate": 9.55e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.437622, "epoch": 0.53721321, "global_step/max_steps": "480/2679", "percentage": "17.92%", "elapsed_time": "18m 13s", "remaining_time": "1h 23m 29s"} |
| {"loss": 0.28441198, "token_acc": 0.89466826, "grad_norm": 1.34709619, "learning_rate": 9.54e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.43775, "epoch": 0.54280918, "global_step/max_steps": "485/2679", "percentage": "18.10%", "elapsed_time": "18m 24s", "remaining_time": "1h 23m 16s"} |
| {"loss": 0.31086383, "token_acc": 0.88097759, "grad_norm": 1.29984087, "learning_rate": 9.52e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.437894, "epoch": 0.54840515, "global_step/max_steps": "490/2679", "percentage": "18.29%", "elapsed_time": "18m 35s", "remaining_time": "1h 23m 3s"} |
| {"loss": 0.30520866, "token_acc": 0.91568092, "grad_norm": 1.26829788, "learning_rate": 9.51e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.438015, "epoch": 0.55400112, "global_step/max_steps": "495/2679", "percentage": "18.48%", "elapsed_time": "18m 46s", "remaining_time": "1h 22m 51s"} |
| {"loss": 0.30751405, "token_acc": 0.90948574, "grad_norm": 1.31318428, "learning_rate": 9.5e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.438086, "epoch": 0.55959709, "global_step/max_steps": "500/2679", "percentage": "18.66%", "elapsed_time": "18m 57s", "remaining_time": "1h 22m 39s"} |
| {"loss": 0.28363032, "token_acc": 0.90893471, "grad_norm": 1.30912425, "learning_rate": 9.48e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.438191, "epoch": 0.56519306, "global_step/max_steps": "505/2679", "percentage": "18.85%", "elapsed_time": "19m 9s", "remaining_time": "1h 22m 26s"} |
| {"loss": 0.32272062, "token_acc": 0.85674787, "grad_norm": 1.34388358, "learning_rate": 9.47e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.438392, "epoch": 0.57078903, "global_step/max_steps": "510/2679", "percentage": "19.04%", "elapsed_time": "19m 19s", "remaining_time": "1h 22m 13s"} |
| {"loss": 0.29890728, "token_acc": 0.89900461, "grad_norm": 1.29582709, "learning_rate": 9.46e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.438591, "epoch": 0.576385, "global_step/max_steps": "515/2679", "percentage": "19.22%", "elapsed_time": "19m 30s", "remaining_time": "1h 21m 59s"} |
| {"loss": 0.27740734, "token_acc": 0.90481208, "grad_norm": 1.26735063, "learning_rate": 9.44e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.438791, "epoch": 0.58198097, "global_step/max_steps": "520/2679", "percentage": "19.41%", "elapsed_time": "19m 41s", "remaining_time": "1h 21m 46s"} |
| {"loss": 0.32281246, "token_acc": 0.87207002, "grad_norm": 1.21767459, "learning_rate": 9.43e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.438878, "epoch": 0.58757694, "global_step/max_steps": "525/2679", "percentage": "19.60%", "elapsed_time": "19m 52s", "remaining_time": "1h 21m 34s"} |
| {"loss": 0.29692304, "token_acc": 0.89624653, "grad_norm": 1.45620383, "learning_rate": 9.41e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.439094, "epoch": 0.59317292, "global_step/max_steps": "530/2679", "percentage": "19.78%", "elapsed_time": "20m 3s", "remaining_time": "1h 21m 20s"} |
| {"loss": 0.30197906, "token_acc": 0.91314463, "grad_norm": 1.24825747, "learning_rate": 9.4e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.439146, "epoch": 0.59876889, "global_step/max_steps": "535/2679", "percentage": "19.97%", "elapsed_time": "20m 14s", "remaining_time": "1h 21m 8s"} |
| {"loss": 0.27764373, "token_acc": 0.88463562, "grad_norm": 1.52427606, "learning_rate": 9.39e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.439252, "epoch": 0.60436486, "global_step/max_steps": "540/2679", "percentage": "20.16%", "elapsed_time": "20m 26s", "remaining_time": "1h 20m 56s"} |
| {"loss": 0.32024946, "token_acc": 0.89944266, "grad_norm": 1.3011129, "learning_rate": 9.37e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.4393, "epoch": 0.60996083, "global_step/max_steps": "545/2679", "percentage": "20.34%", "elapsed_time": "20m 37s", "remaining_time": "1h 20m 44s"} |
| {"loss": 0.27188871, "token_acc": 0.86054588, "grad_norm": 1.13123013, "learning_rate": 9.36e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.439451, "epoch": 0.6155568, "global_step/max_steps": "550/2679", "percentage": "20.53%", "elapsed_time": "20m 48s", "remaining_time": "1h 20m 31s"} |
| {"loss": 0.26129484, "token_acc": 0.91111705, "grad_norm": 1.23254024, "learning_rate": 9.34e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.439623, "epoch": 0.62115277, "global_step/max_steps": "555/2679", "percentage": "20.72%", "elapsed_time": "20m 59s", "remaining_time": "1h 20m 18s"} |
| {"loss": 0.32519431, "token_acc": 0.87382618, "grad_norm": 1.18139599, "learning_rate": 9.32e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.439747, "epoch": 0.62674874, "global_step/max_steps": "560/2679", "percentage": "20.90%", "elapsed_time": "21m 10s", "remaining_time": "1h 20m 5s"} |
| {"loss": 0.29087398, "token_acc": 0.90972784, "grad_norm": 1.22452101, "learning_rate": 9.31e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.439918, "epoch": 0.63234471, "global_step/max_steps": "565/2679", "percentage": "21.09%", "elapsed_time": "21m 20s", "remaining_time": "1h 19m 52s"} |
| {"loss": 0.29872594, "token_acc": 0.90028366, "grad_norm": 1.36908316, "learning_rate": 9.29e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.439995, "epoch": 0.63794068, "global_step/max_steps": "570/2679", "percentage": "21.28%", "elapsed_time": "21m 32s", "remaining_time": "1h 19m 40s"} |
| {"loss": 0.26016717, "token_acc": 0.90747674, "grad_norm": 1.33068032, "learning_rate": 9.28e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.440027, "epoch": 0.64353665, "global_step/max_steps": "575/2679", "percentage": "21.46%", "elapsed_time": "21m 43s", "remaining_time": "1h 19m 29s"} |
| {"loss": 0.31593778, "token_acc": 0.88314723, "grad_norm": 1.28619663, "learning_rate": 9.26e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.440197, "epoch": 0.64913262, "global_step/max_steps": "580/2679", "percentage": "21.65%", "elapsed_time": "21m 54s", "remaining_time": "1h 19m 16s"} |
| {"loss": 0.29399905, "token_acc": 0.89094695, "grad_norm": 1.13990576, "learning_rate": 9.24e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.440402, "epoch": 0.6547286, "global_step/max_steps": "585/2679", "percentage": "21.84%", "elapsed_time": "22m 4s", "remaining_time": "1h 19m 2s"} |
| {"loss": 0.3221622, "token_acc": 0.86678053, "grad_norm": 1.44356309, "learning_rate": 9.23e-06, "memory(GiB)": 74.34, "train_speed(iter/s)": 0.440311, "epoch": 0.66032457, "global_step/max_steps": "590/2679", "percentage": "22.02%", "elapsed_time": "22m 16s", "remaining_time": "1h 18m 52s"} |
| {"loss": 0.28130388, "token_acc": 0.87385515, "grad_norm": 1.20022484, "learning_rate": 9.21e-06, "memory(GiB)": 74.34, "train_speed(iter/s)": 0.440357, "epoch": 0.66592054, "global_step/max_steps": "595/2679", "percentage": "22.21%", "elapsed_time": "22m 27s", "remaining_time": "1h 18m 40s"} |
| {"loss": 0.27870941, "token_acc": 0.88203313, "grad_norm": 1.47522091, "learning_rate": 9.2e-06, "memory(GiB)": 74.34, "train_speed(iter/s)": 0.440536, "epoch": 0.67151651, "global_step/max_steps": "600/2679", "percentage": "22.40%", "elapsed_time": "22m 38s", "remaining_time": "1h 18m 27s"} |
| {"eval_loss": 0.29483041, "eval_token_acc": 0.8872909, "eval_runtime": 7.0603, "eval_samples_per_second": 15.297, "eval_steps_per_second": 2.549, "epoch": 0.67151651, "global_step/max_steps": "600/2679", "percentage": "22.40%", "elapsed_time": "22m 45s", "remaining_time": "1h 18m 52s"} |
| {"loss": 0.28652351, "token_acc": 0.91776799, "grad_norm": 1.30458322, "learning_rate": 9.18e-06, "memory(GiB)": 74.34, "train_speed(iter/s)": 0.438257, "epoch": 0.67711248, "global_step/max_steps": "605/2679", "percentage": "22.58%", "elapsed_time": "22m 57s", "remaining_time": "1h 18m 40s"} |
| {"loss": 0.2902668, "token_acc": 0.90143072, "grad_norm": 1.26924063, "learning_rate": 9.16e-06, "memory(GiB)": 74.34, "train_speed(iter/s)": 0.438378, "epoch": 0.68270845, "global_step/max_steps": "610/2679", "percentage": "22.77%", "elapsed_time": "23m 8s", "remaining_time": "1h 18m 28s"} |
| {"loss": 0.2846664, "token_acc": 0.89561444, "grad_norm": 1.37819003, "learning_rate": 9.14e-06, "memory(GiB)": 74.34, "train_speed(iter/s)": 0.438524, "epoch": 0.68830442, "global_step/max_steps": "615/2679", "percentage": "22.96%", "elapsed_time": "23m 19s", "remaining_time": "1h 18m 15s"} |
| {"loss": 0.28765049, "token_acc": 0.89397842, "grad_norm": 1.35443863, "learning_rate": 9.13e-06, "memory(GiB)": 74.34, "train_speed(iter/s)": 0.438652, "epoch": 0.69390039, "global_step/max_steps": "620/2679", "percentage": "23.14%", "elapsed_time": "23m 30s", "remaining_time": "1h 18m 2s"} |
| {"loss": 0.29815445, "token_acc": 0.8984062, "grad_norm": 1.13898951, "learning_rate": 9.11e-06, "memory(GiB)": 74.34, "train_speed(iter/s)": 0.438809, "epoch": 0.69949636, "global_step/max_steps": "625/2679", "percentage": "23.33%", "elapsed_time": "23m 40s", "remaining_time": "1h 17m 49s"} |
| {"loss": 0.28049934, "token_acc": 0.88901642, "grad_norm": 1.19527546, "learning_rate": 9.09e-06, "memory(GiB)": 74.34, "train_speed(iter/s)": 0.438978, "epoch": 0.70509233, "global_step/max_steps": "630/2679", "percentage": "23.52%", "elapsed_time": "23m 51s", "remaining_time": "1h 17m 36s"} |
| {"loss": 0.26827381, "token_acc": 0.90768561, "grad_norm": 1.17596457, "learning_rate": 9.07e-06, "memory(GiB)": 74.34, "train_speed(iter/s)": 0.439114, "epoch": 0.7106883, "global_step/max_steps": "635/2679", "percentage": "23.70%", "elapsed_time": "24m 2s", "remaining_time": "1h 17m 24s"} |
| {"loss": 0.28814275, "token_acc": 0.9060787, "grad_norm": 1.24250099, "learning_rate": 9.06e-06, "memory(GiB)": 74.34, "train_speed(iter/s)": 0.439243, "epoch": 0.71628428, "global_step/max_steps": "640/2679", "percentage": "23.89%", "elapsed_time": "24m 13s", "remaining_time": "1h 17m 11s"} |
| {"loss": 0.26821465, "token_acc": 0.89467393, "grad_norm": 1.3719294, "learning_rate": 9.04e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.439225, "epoch": 0.72188025, "global_step/max_steps": "645/2679", "percentage": "24.08%", "elapsed_time": "24m 25s", "remaining_time": "1h 17m 0s"} |
| {"loss": 0.28612697, "token_acc": 0.90880753, "grad_norm": 1.30475188, "learning_rate": 9.02e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.439405, "epoch": 0.72747622, "global_step/max_steps": "650/2679", "percentage": "24.26%", "elapsed_time": "24m 35s", "remaining_time": "1h 16m 47s"} |
| {"loss": 0.27723224, "token_acc": 0.87575653, "grad_norm": 1.32925137, "learning_rate": 9e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.439539, "epoch": 0.73307219, "global_step/max_steps": "655/2679", "percentage": "24.45%", "elapsed_time": "24m 46s", "remaining_time": "1h 16m 34s"} |
| {"loss": 0.29653203, "token_acc": 0.88958369, "grad_norm": 1.44090201, "learning_rate": 8.98e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.439621, "epoch": 0.73866816, "global_step/max_steps": "660/2679", "percentage": "24.64%", "elapsed_time": "24m 57s", "remaining_time": "1h 16m 22s"} |
| {"loss": 0.32388077, "token_acc": 0.87773298, "grad_norm": 1.34111348, "learning_rate": 8.96e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.439702, "epoch": 0.74426413, "global_step/max_steps": "665/2679", "percentage": "24.82%", "elapsed_time": "25m 9s", "remaining_time": "1h 16m 10s"} |
| {"loss": 0.26616921, "token_acc": 0.90208531, "grad_norm": 1.14812081, "learning_rate": 8.94e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.439783, "epoch": 0.7498601, "global_step/max_steps": "670/2679", "percentage": "25.01%", "elapsed_time": "25m 20s", "remaining_time": "1h 15m 58s"} |
| {"loss": 0.28416414, "token_acc": 0.89023429, "grad_norm": 1.28022023, "learning_rate": 8.93e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.439907, "epoch": 0.75545607, "global_step/max_steps": "675/2679", "percentage": "25.20%", "elapsed_time": "25m 31s", "remaining_time": "1h 15m 45s"} |
| {"loss": 0.28161783, "token_acc": 0.90596728, "grad_norm": 1.2417853, "learning_rate": 8.91e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.439804, "epoch": 0.76105204, "global_step/max_steps": "680/2679", "percentage": "25.38%", "elapsed_time": "25m 42s", "remaining_time": "1h 15m 35s"} |
| {"loss": 0.27280674, "token_acc": 0.92257552, "grad_norm": 1.26144211, "learning_rate": 8.89e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.43982, "epoch": 0.76664801, "global_step/max_steps": "685/2679", "percentage": "25.57%", "elapsed_time": "25m 54s", "remaining_time": "1h 15m 23s"} |
| {"loss": 0.30169415, "token_acc": 0.87711062, "grad_norm": 1.27043408, "learning_rate": 8.87e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.439933, "epoch": 0.77224398, "global_step/max_steps": "690/2679", "percentage": "25.76%", "elapsed_time": "26m 5s", "remaining_time": "1h 15m 11s"} |
| {"loss": 0.28254821, "token_acc": 0.88769531, "grad_norm": 1.07630544, "learning_rate": 8.85e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.439949, "epoch": 0.77783996, "global_step/max_steps": "695/2679", "percentage": "25.94%", "elapsed_time": "26m 16s", "remaining_time": "1h 15m 0s"} |
| {"loss": 0.26552324, "token_acc": 0.91541554, "grad_norm": 1.25027616, "learning_rate": 8.83e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.439982, "epoch": 0.78343593, "global_step/max_steps": "700/2679", "percentage": "26.13%", "elapsed_time": "26m 27s", "remaining_time": "1h 14m 48s"} |
| {"loss": 0.29363403, "token_acc": 0.89760613, "grad_norm": 1.36674697, "learning_rate": 8.81e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.440074, "epoch": 0.7890319, "global_step/max_steps": "705/2679", "percentage": "26.32%", "elapsed_time": "26m 38s", "remaining_time": "1h 14m 36s"} |
| {"loss": 0.29573874, "token_acc": 0.88981153, "grad_norm": 1.22025888, "learning_rate": 8.79e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.440121, "epoch": 0.79462787, "global_step/max_steps": "710/2679", "percentage": "26.50%", "elapsed_time": "26m 49s", "remaining_time": "1h 14m 24s"} |
| {"loss": 0.30378628, "token_acc": 0.88946903, "grad_norm": 1.21804775, "learning_rate": 8.77e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.440276, "epoch": 0.80022384, "global_step/max_steps": "715/2679", "percentage": "26.69%", "elapsed_time": "27m 0s", "remaining_time": "1h 14m 11s"} |
| {"loss": 0.28245592, "token_acc": 0.898187, "grad_norm": 1.26510996, "learning_rate": 8.75e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.440328, "epoch": 0.80581981, "global_step/max_steps": "720/2679", "percentage": "26.88%", "elapsed_time": "27m 11s", "remaining_time": "1h 13m 59s"} |
| {"loss": 0.30694237, "token_acc": 0.88731656, "grad_norm": 1.31422924, "learning_rate": 8.73e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.440438, "epoch": 0.81141578, "global_step/max_steps": "725/2679", "percentage": "27.06%", "elapsed_time": "27m 22s", "remaining_time": "1h 13m 47s"} |
| {"loss": 0.27415836, "token_acc": 0.90948529, "grad_norm": 1.18734831, "learning_rate": 8.71e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.440501, "epoch": 0.81701175, "global_step/max_steps": "730/2679", "percentage": "27.25%", "elapsed_time": "27m 33s", "remaining_time": "1h 13m 35s"} |
| {"loss": 0.271012, "token_acc": 0.87934801, "grad_norm": 1.35994493, "learning_rate": 8.69e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.440597, "epoch": 0.82260772, "global_step/max_steps": "735/2679", "percentage": "27.44%", "elapsed_time": "27m 44s", "remaining_time": "1h 13m 23s"} |
| {"loss": 0.27054176, "token_acc": 0.90249957, "grad_norm": 1.51077591, "learning_rate": 8.67e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.4407, "epoch": 0.82820369, "global_step/max_steps": "740/2679", "percentage": "27.62%", "elapsed_time": "27m 55s", "remaining_time": "1h 13m 11s"} |
| {"loss": 0.28331041, "token_acc": 0.90238074, "grad_norm": 1.40061778, "learning_rate": 8.64e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.440837, "epoch": 0.83379966, "global_step/max_steps": "745/2679", "percentage": "27.81%", "elapsed_time": "28m 6s", "remaining_time": "1h 12m 58s"} |
| {"loss": 0.26736317, "token_acc": 0.90185318, "grad_norm": 1.36823051, "learning_rate": 8.62e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.440947, "epoch": 0.83939564, "global_step/max_steps": "750/2679", "percentage": "28.00%", "elapsed_time": "28m 17s", "remaining_time": "1h 12m 46s"} |
| {"loss": 0.30713892, "token_acc": 0.88231206, "grad_norm": 1.39378273, "learning_rate": 8.6e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.441058, "epoch": 0.84499161, "global_step/max_steps": "755/2679", "percentage": "28.18%", "elapsed_time": "28m 28s", "remaining_time": "1h 12m 33s"} |
| {"loss": 0.26855524, "token_acc": 0.9061901, "grad_norm": 1.25133257, "learning_rate": 8.58e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.441146, "epoch": 0.85058758, "global_step/max_steps": "760/2679", "percentage": "28.37%", "elapsed_time": "28m 39s", "remaining_time": "1h 12m 21s"} |
| {"loss": 0.28615451, "token_acc": 0.89243487, "grad_norm": 1.14920554, "learning_rate": 8.56e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.441261, "epoch": 0.85618355, "global_step/max_steps": "765/2679", "percentage": "28.56%", "elapsed_time": "28m 50s", "remaining_time": "1h 12m 9s"} |
| {"loss": 0.24949636, "token_acc": 0.91769901, "grad_norm": 1.3533982, "learning_rate": 8.54e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.441405, "epoch": 0.86177952, "global_step/max_steps": "770/2679", "percentage": "28.74%", "elapsed_time": "29m 1s", "remaining_time": "1h 11m 56s"} |
| {"loss": 0.2959528, "token_acc": 0.91898773, "grad_norm": 1.32879403, "learning_rate": 8.51e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.441471, "epoch": 0.86737549, "global_step/max_steps": "775/2679", "percentage": "28.93%", "elapsed_time": "29m 12s", "remaining_time": "1h 11m 44s"} |
| {"loss": 0.28633945, "token_acc": 0.92591746, "grad_norm": 1.1816061, "learning_rate": 8.49e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.441539, "epoch": 0.87297146, "global_step/max_steps": "780/2679", "percentage": "29.12%", "elapsed_time": "29m 23s", "remaining_time": "1h 11m 32s"} |
| {"loss": 0.29375567, "token_acc": 0.89268481, "grad_norm": 1.41510475, "learning_rate": 8.47e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.441678, "epoch": 0.87856743, "global_step/max_steps": "785/2679", "percentage": "29.30%", "elapsed_time": "29m 33s", "remaining_time": "1h 11m 20s"} |
| {"loss": 0.281478, "token_acc": 0.89271417, "grad_norm": 1.33242833, "learning_rate": 8.45e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.441774, "epoch": 0.8841634, "global_step/max_steps": "790/2679", "percentage": "29.49%", "elapsed_time": "29m 44s", "remaining_time": "1h 11m 7s"} |
| {"loss": 0.29062953, "token_acc": 0.91259452, "grad_norm": 1.29473581, "learning_rate": 8.43e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.441807, "epoch": 0.88975937, "global_step/max_steps": "795/2679", "percentage": "29.68%", "elapsed_time": "29m 56s", "remaining_time": "1h 10m 56s"} |
| {"loss": 0.24327602, "token_acc": 0.92466572, "grad_norm": 1.35066528, "learning_rate": 8.4e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.441924, "epoch": 0.89535534, "global_step/max_steps": "800/2679", "percentage": "29.86%", "elapsed_time": "30m 6s", "remaining_time": "1h 10m 43s"} |
| {"eval_loss": 0.28589845, "eval_token_acc": 0.8901816, "eval_runtime": 6.807, "eval_samples_per_second": 15.866, "eval_steps_per_second": 2.644, "epoch": 0.89535534, "global_step/max_steps": "800/2679", "percentage": "29.86%", "elapsed_time": "30m 13s", "remaining_time": "1h 11m 0s"} |
| {"loss": 0.28470268, "token_acc": 0.88216014, "grad_norm": 1.26744377, "learning_rate": 8.38e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.440333, "epoch": 0.90095132, "global_step/max_steps": "805/2679", "percentage": "30.05%", "elapsed_time": "30m 24s", "remaining_time": "1h 10m 48s"} |
| {"loss": 0.2918314, "token_acc": 0.88401336, "grad_norm": 1.12282297, "learning_rate": 8.36e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.44046, "epoch": 0.90654729, "global_step/max_steps": "810/2679", "percentage": "30.24%", "elapsed_time": "30m 35s", "remaining_time": "1h 10m 35s"} |
| {"loss": 0.30235221, "token_acc": 0.91602317, "grad_norm": 1.14871565, "learning_rate": 8.33e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.440534, "epoch": 0.91214326, "global_step/max_steps": "815/2679", "percentage": "30.42%", "elapsed_time": "30m 46s", "remaining_time": "1h 10m 23s"} |
| {"loss": 0.28354111, "token_acc": 0.90274776, "grad_norm": 1.17442661, "learning_rate": 8.31e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.440593, "epoch": 0.91773923, "global_step/max_steps": "820/2679", "percentage": "30.61%", "elapsed_time": "30m 57s", "remaining_time": "1h 10m 11s"} |
| {"loss": 0.27711418, "token_acc": 0.89093726, "grad_norm": 1.22540547, "learning_rate": 8.29e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.4407, "epoch": 0.9233352, "global_step/max_steps": "825/2679", "percentage": "30.80%", "elapsed_time": "31m 8s", "remaining_time": "1h 9m 59s"} |
| {"loss": 0.29121375, "token_acc": 0.87393541, "grad_norm": 1.34644256, "learning_rate": 8.27e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.440733, "epoch": 0.92893117, "global_step/max_steps": "830/2679", "percentage": "30.98%", "elapsed_time": "31m 19s", "remaining_time": "1h 9m 47s"} |
| {"loss": 0.28851516, "token_acc": 0.9124697, "grad_norm": 1.23830216, "learning_rate": 8.24e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.440867, "epoch": 0.93452714, "global_step/max_steps": "835/2679", "percentage": "31.17%", "elapsed_time": "31m 30s", "remaining_time": "1h 9m 35s"} |
| {"loss": 0.26634119, "token_acc": 0.90715487, "grad_norm": 1.16149353, "learning_rate": 8.22e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.440832, "epoch": 0.94012311, "global_step/max_steps": "840/2679", "percentage": "31.35%", "elapsed_time": "31m 42s", "remaining_time": "1h 9m 24s"} |
| {"loss": 0.29005437, "token_acc": 0.88375796, "grad_norm": 1.24001597, "learning_rate": 8.19e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.440898, "epoch": 0.94571908, "global_step/max_steps": "845/2679", "percentage": "31.54%", "elapsed_time": "31m 53s", "remaining_time": "1h 9m 12s"} |
| {"loss": 0.28755078, "token_acc": 0.92450624, "grad_norm": 1.16450051, "learning_rate": 8.17e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.440884, "epoch": 0.95131505, "global_step/max_steps": "850/2679", "percentage": "31.73%", "elapsed_time": "32m 4s", "remaining_time": "1h 9m 1s"} |
| {"loss": 0.26259241, "token_acc": 0.90955919, "grad_norm": 1.2592467, "learning_rate": 8.15e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.44096, "epoch": 0.95691102, "global_step/max_steps": "855/2679", "percentage": "31.91%", "elapsed_time": "32m 15s", "remaining_time": "1h 8m 49s"} |
| {"loss": 0.27598083, "token_acc": 0.90500656, "grad_norm": 1.34158107, "learning_rate": 8.12e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.441042, "epoch": 0.96250699, "global_step/max_steps": "860/2679", "percentage": "32.10%", "elapsed_time": "32m 26s", "remaining_time": "1h 8m 37s"} |
| {"loss": 0.28642559, "token_acc": 0.88759921, "grad_norm": 1.38476828, "learning_rate": 8.1e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.441132, "epoch": 0.96810297, "global_step/max_steps": "865/2679", "percentage": "32.29%", "elapsed_time": "32m 37s", "remaining_time": "1h 8m 25s"} |
| {"loss": 0.2778089, "token_acc": 0.91464289, "grad_norm": 1.10081703, "learning_rate": 8.07e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.441057, "epoch": 0.97369894, "global_step/max_steps": "870/2679", "percentage": "32.47%", "elapsed_time": "32m 49s", "remaining_time": "1h 8m 14s"} |
| {"loss": 0.29184866, "token_acc": 0.90704745, "grad_norm": 1.2864756, "learning_rate": 8.05e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.440924, "epoch": 0.97929491, "global_step/max_steps": "875/2679", "percentage": "32.66%", "elapsed_time": "33m 1s", "remaining_time": "1h 8m 4s"} |
| {"loss": 0.26892548, "token_acc": 0.90591665, "grad_norm": 1.2247325, "learning_rate": 8.03e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.441031, "epoch": 0.98489088, "global_step/max_steps": "880/2679", "percentage": "32.85%", "elapsed_time": "33m 11s", "remaining_time": "1h 7m 52s"} |
| {"loss": 0.27104039, "token_acc": 0.92317572, "grad_norm": 1.19982959, "learning_rate": 8e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.441122, "epoch": 0.99048685, "global_step/max_steps": "885/2679", "percentage": "33.03%", "elapsed_time": "33m 22s", "remaining_time": "1h 7m 40s"} |
| {"loss": 0.28195949, "token_acc": 0.87470167, "grad_norm": 1.33209756, "learning_rate": 7.98e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.441189, "epoch": 0.99608282, "global_step/max_steps": "890/2679", "percentage": "33.22%", "elapsed_time": "33m 33s", "remaining_time": "1h 7m 28s"} |
| {"loss": 0.29261341, "token_acc": 0.89584408, "grad_norm": 1.93433754, "learning_rate": 7.95e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.441502, "epoch": 1.00111919, "global_step/max_steps": "895/2679", "percentage": "33.41%", "elapsed_time": "33m 43s", "remaining_time": "1h 7m 14s"} |
| {"loss": 0.24628019, "token_acc": 0.92366067, "grad_norm": 1.18711028, "learning_rate": 7.93e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.441578, "epoch": 1.00671517, "global_step/max_steps": "900/2679", "percentage": "33.59%", "elapsed_time": "33m 54s", "remaining_time": "1h 7m 2s"} |
| {"loss": 0.2344028, "token_acc": 0.9254386, "grad_norm": 1.21301553, "learning_rate": 7.9e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.441623, "epoch": 1.01231114, "global_step/max_steps": "905/2679", "percentage": "33.78%", "elapsed_time": "34m 5s", "remaining_time": "1h 6m 50s"} |
| {"loss": 0.26413169, "token_acc": 0.91323577, "grad_norm": 1.14134424, "learning_rate": 7.88e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.441683, "epoch": 1.01790711, "global_step/max_steps": "910/2679", "percentage": "33.97%", "elapsed_time": "34m 16s", "remaining_time": "1h 6m 38s"} |
| {"loss": 0.20402198, "token_acc": 0.92649479, "grad_norm": 1.13350383, "learning_rate": 7.85e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.441687, "epoch": 1.02350308, "global_step/max_steps": "915/2679", "percentage": "34.15%", "elapsed_time": "34m 28s", "remaining_time": "1h 6m 27s"} |
| {"loss": 0.2431134, "token_acc": 0.91024194, "grad_norm": 1.37803126, "learning_rate": 7.83e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.441708, "epoch": 1.02909905, "global_step/max_steps": "920/2679", "percentage": "34.34%", "elapsed_time": "34m 39s", "remaining_time": "1h 6m 15s"} |
| {"loss": 0.23109763, "token_acc": 0.91808212, "grad_norm": 1.15598365, "learning_rate": 7.8e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.441735, "epoch": 1.03469502, "global_step/max_steps": "925/2679", "percentage": "34.53%", "elapsed_time": "34m 50s", "remaining_time": "1h 6m 4s"} |
| {"loss": 0.25525484, "token_acc": 0.90902517, "grad_norm": 1.17972803, "learning_rate": 7.77e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.441814, "epoch": 1.04029099, "global_step/max_steps": "930/2679", "percentage": "34.71%", "elapsed_time": "35m 1s", "remaining_time": "1h 5m 52s"} |
| {"loss": 0.2434761, "token_acc": 0.89989953, "grad_norm": 1.26006964, "learning_rate": 7.75e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.441913, "epoch": 1.04588696, "global_step/max_steps": "935/2679", "percentage": "34.90%", "elapsed_time": "35m 12s", "remaining_time": "1h 5m 40s"} |
| {"loss": 0.19405093, "token_acc": 0.92260536, "grad_norm": 1.22477775, "learning_rate": 7.72e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.44197, "epoch": 1.05148293, "global_step/max_steps": "940/2679", "percentage": "35.09%", "elapsed_time": "35m 23s", "remaining_time": "1h 5m 28s"} |
| {"loss": 0.20441272, "token_acc": 0.91406318, "grad_norm": 1.23505576, "learning_rate": 7.7e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.44192, "epoch": 1.0570789, "global_step/max_steps": "945/2679", "percentage": "35.27%", "elapsed_time": "35m 35s", "remaining_time": "1h 5m 17s"} |
| {"loss": 0.23828611, "token_acc": 0.92785151, "grad_norm": 1.1426157, "learning_rate": 7.67e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.441992, "epoch": 1.06267487, "global_step/max_steps": "950/2679", "percentage": "35.46%", "elapsed_time": "35m 45s", "remaining_time": "1h 5m 5s"} |
| {"loss": 0.22539873, "token_acc": 0.91593521, "grad_norm": 1.37853515, "learning_rate": 7.64e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442055, "epoch": 1.06827084, "global_step/max_steps": "955/2679", "percentage": "35.65%", "elapsed_time": "35m 56s", "remaining_time": "1h 4m 53s"} |
| {"loss": 0.2061914, "token_acc": 0.91508188, "grad_norm": 1.17942812, "learning_rate": 7.62e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442084, "epoch": 1.07386682, "global_step/max_steps": "960/2679", "percentage": "35.83%", "elapsed_time": "36m 8s", "remaining_time": "1h 4m 42s"} |
| {"loss": 0.21941919, "token_acc": 0.91771362, "grad_norm": 1.23069145, "learning_rate": 7.59e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442162, "epoch": 1.07946279, "global_step/max_steps": "965/2679", "percentage": "36.02%", "elapsed_time": "36m 19s", "remaining_time": "1h 4m 30s"} |
| {"loss": 0.2205348, "token_acc": 0.94575874, "grad_norm": 1.1943055, "learning_rate": 7.57e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442247, "epoch": 1.08505876, "global_step/max_steps": "970/2679", "percentage": "36.21%", "elapsed_time": "36m 29s", "remaining_time": "1h 4m 18s"} |
| {"loss": 0.21462595, "token_acc": 0.9223216, "grad_norm": 1.20079442, "learning_rate": 7.54e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442312, "epoch": 1.09065473, "global_step/max_steps": "975/2679", "percentage": "36.39%", "elapsed_time": "36m 40s", "remaining_time": "1h 4m 6s"} |
| {"loss": 0.218554, "token_acc": 0.91556599, "grad_norm": 1.17034402, "learning_rate": 7.51e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.44232, "epoch": 1.0962507, "global_step/max_steps": "980/2679", "percentage": "36.58%", "elapsed_time": "36m 52s", "remaining_time": "1h 3m 55s"} |
| {"loss": 0.22841272, "token_acc": 0.89678955, "grad_norm": 1.34714082, "learning_rate": 7.49e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442341, "epoch": 1.10184667, "global_step/max_steps": "985/2679", "percentage": "36.77%", "elapsed_time": "37m 3s", "remaining_time": "1h 3m 43s"} |
| {"loss": 0.22382619, "token_acc": 0.91098673, "grad_norm": 1.28848681, "learning_rate": 7.46e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.44243, "epoch": 1.10744264, "global_step/max_steps": "990/2679", "percentage": "36.95%", "elapsed_time": "37m 14s", "remaining_time": "1h 3m 31s"} |
| {"loss": 0.23409326, "token_acc": 0.92573024, "grad_norm": 1.29237124, "learning_rate": 7.43e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442512, "epoch": 1.11303861, "global_step/max_steps": "995/2679", "percentage": "37.14%", "elapsed_time": "37m 25s", "remaining_time": "1h 3m 19s"} |
| {"loss": 0.22590425, "token_acc": 0.90129532, "grad_norm": 1.27511366, "learning_rate": 7.4e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442589, "epoch": 1.11863458, "global_step/max_steps": "1000/2679", "percentage": "37.33%", "elapsed_time": "37m 36s", "remaining_time": "1h 3m 7s"} |
| {"eval_loss": 0.27820867, "eval_token_acc": 0.89306939, "eval_runtime": 6.9579, "eval_samples_per_second": 15.522, "eval_steps_per_second": 2.587, "epoch": 1.11863458, "global_step/max_steps": "1000/2679", "percentage": "37.33%", "elapsed_time": "37m 43s", "remaining_time": "1h 3m 19s"} |
| {"loss": 0.22948971, "token_acc": 0.92415321, "grad_norm": 1.16591315, "learning_rate": 7.38e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.441179, "epoch": 1.12423055, "global_step/max_steps": "1005/2679", "percentage": "37.51%", "elapsed_time": "37m 54s", "remaining_time": "1h 3m 8s"} |
| {"loss": 0.22051914, "token_acc": 0.90393596, "grad_norm": 1.39028826, "learning_rate": 7.35e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.441266, "epoch": 1.12982652, "global_step/max_steps": "1010/2679", "percentage": "37.70%", "elapsed_time": "38m 5s", "remaining_time": "1h 2m 56s"} |
| {"loss": 0.23391256, "token_acc": 0.90567813, "grad_norm": 1.26631796, "learning_rate": 7.32e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.441356, "epoch": 1.1354225, "global_step/max_steps": "1015/2679", "percentage": "37.89%", "elapsed_time": "38m 16s", "remaining_time": "1h 2m 44s"} |
| {"loss": 0.22755015, "token_acc": 0.90226527, "grad_norm": 1.34431102, "learning_rate": 7.3e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.441351, "epoch": 1.14101847, "global_step/max_steps": "1020/2679", "percentage": "38.07%", "elapsed_time": "38m 27s", "remaining_time": "1h 2m 33s"} |
| {"loss": 0.22950523, "token_acc": 0.90841153, "grad_norm": 1.34705861, "learning_rate": 7.27e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.441385, "epoch": 1.14661444, "global_step/max_steps": "1025/2679", "percentage": "38.26%", "elapsed_time": "38m 38s", "remaining_time": "1h 2m 21s"} |
| {"loss": 0.22843094, "token_acc": 0.93016712, "grad_norm": 1.1974418, "learning_rate": 7.24e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.441424, "epoch": 1.15221041, "global_step/max_steps": "1030/2679", "percentage": "38.45%", "elapsed_time": "38m 49s", "remaining_time": "1h 2m 10s"} |
| {"loss": 0.2418364, "token_acc": 0.89947963, "grad_norm": 1.20945667, "learning_rate": 7.21e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.441417, "epoch": 1.15780638, "global_step/max_steps": "1035/2679", "percentage": "38.63%", "elapsed_time": "39m 1s", "remaining_time": "1h 1m 59s"} |
| {"loss": 0.21626463, "token_acc": 0.91790307, "grad_norm": 1.02349998, "learning_rate": 7.19e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.441454, "epoch": 1.16340235, "global_step/max_steps": "1040/2679", "percentage": "38.82%", "elapsed_time": "39m 12s", "remaining_time": "1h 1m 47s"} |
| {"loss": 0.23219399, "token_acc": 0.88172439, "grad_norm": 1.22957178, "learning_rate": 7.16e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.441534, "epoch": 1.16899832, "global_step/max_steps": "1045/2679", "percentage": "39.01%", "elapsed_time": "39m 23s", "remaining_time": "1h 1m 35s"} |
| {"loss": 0.22575865, "token_acc": 0.93204766, "grad_norm": 1.38182109, "learning_rate": 7.13e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.441598, "epoch": 1.17459429, "global_step/max_steps": "1050/2679", "percentage": "39.19%", "elapsed_time": "39m 34s", "remaining_time": "1h 1m 23s"} |
| {"loss": 0.2314517, "token_acc": 0.93448795, "grad_norm": 1.29626941, "learning_rate": 7.1e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.441672, "epoch": 1.18019026, "global_step/max_steps": "1055/2679", "percentage": "39.38%", "elapsed_time": "39m 45s", "remaining_time": "1h 1m 11s"} |
| {"loss": 0.21464844, "token_acc": 0.90601564, "grad_norm": 1.34880935, "learning_rate": 7.07e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.441753, "epoch": 1.18578623, "global_step/max_steps": "1060/2679", "percentage": "39.57%", "elapsed_time": "39m 56s", "remaining_time": "1h 0m 59s"} |
| {"loss": 0.22807834, "token_acc": 0.91108672, "grad_norm": 1.32822181, "learning_rate": 7.05e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.441851, "epoch": 1.1913822, "global_step/max_steps": "1065/2679", "percentage": "39.75%", "elapsed_time": "40m 6s", "remaining_time": "1h 0m 47s"} |
| {"loss": 0.23301771, "token_acc": 0.91748425, "grad_norm": 1.36042099, "learning_rate": 7.02e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.441884, "epoch": 1.19697818, "global_step/max_steps": "1070/2679", "percentage": "39.94%", "elapsed_time": "40m 18s", "remaining_time": "1h 0m 36s"} |
| {"loss": 0.21682215, "token_acc": 0.89501332, "grad_norm": 1.25464423, "learning_rate": 6.99e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.44185, "epoch": 1.20257415, "global_step/max_steps": "1075/2679", "percentage": "40.13%", "elapsed_time": "40m 29s", "remaining_time": "1h 0m 25s"} |
| {"loss": 0.20190167, "token_acc": 0.93737647, "grad_norm": 1.3824811, "learning_rate": 6.96e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.441931, "epoch": 1.20817012, "global_step/max_steps": "1080/2679", "percentage": "40.31%", "elapsed_time": "40m 40s", "remaining_time": "1h 0m 13s"} |
| {"loss": 0.23871922, "token_acc": 0.91237866, "grad_norm": 1.47386302, "learning_rate": 6.93e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442046, "epoch": 1.21376609, "global_step/max_steps": "1085/2679", "percentage": "40.50%", "elapsed_time": "40m 51s", "remaining_time": "1h 0m 1s"} |
| {"loss": 0.22519474, "token_acc": 0.90900721, "grad_norm": 1.13080836, "learning_rate": 6.9e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442134, "epoch": 1.21936206, "global_step/max_steps": "1090/2679", "percentage": "40.69%", "elapsed_time": "41m 1s", "remaining_time": "59m 49s"} |
| {"loss": 0.2180618, "token_acc": 0.91306276, "grad_norm": 1.21852623, "learning_rate": 6.88e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442209, "epoch": 1.22495803, "global_step/max_steps": "1095/2679", "percentage": "40.87%", "elapsed_time": "41m 12s", "remaining_time": "59m 37s"} |
| {"loss": 0.24117613, "token_acc": 0.92088316, "grad_norm": 1.09044361, "learning_rate": 6.85e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442112, "epoch": 1.230554, "global_step/max_steps": "1100/2679", "percentage": "41.06%", "elapsed_time": "41m 24s", "remaining_time": "59m 26s"} |
| {"loss": 0.25599411, "token_acc": 0.91317614, "grad_norm": 1.398802, "learning_rate": 6.82e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442091, "epoch": 1.23614997, "global_step/max_steps": "1105/2679", "percentage": "41.25%", "elapsed_time": "41m 36s", "remaining_time": "59m 15s"} |
| {"loss": 0.24390604, "token_acc": 0.89462337, "grad_norm": 1.10052288, "learning_rate": 6.79e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442118, "epoch": 1.24174594, "global_step/max_steps": "1110/2679", "percentage": "41.43%", "elapsed_time": "41m 47s", "remaining_time": "59m 4s"} |
| {"loss": 0.21798553, "token_acc": 0.93506616, "grad_norm": 1.53961583, "learning_rate": 6.76e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442222, "epoch": 1.24734191, "global_step/max_steps": "1115/2679", "percentage": "41.62%", "elapsed_time": "41m 57s", "remaining_time": "58m 51s"} |
| {"loss": 0.2340394, "token_acc": 0.90186638, "grad_norm": 1.34096345, "learning_rate": 6.73e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442281, "epoch": 1.25293788, "global_step/max_steps": "1120/2679", "percentage": "41.81%", "elapsed_time": "42m 8s", "remaining_time": "58m 40s"} |
| {"loss": 0.21949756, "token_acc": 0.90676204, "grad_norm": 1.29134159, "learning_rate": 6.7e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442351, "epoch": 1.25853386, "global_step/max_steps": "1125/2679", "percentage": "41.99%", "elapsed_time": "42m 19s", "remaining_time": "58m 28s"} |
| {"loss": 0.23506007, "token_acc": 0.90128908, "grad_norm": 1.31124083, "learning_rate": 6.67e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442396, "epoch": 1.26412983, "global_step/max_steps": "1130/2679", "percentage": "42.18%", "elapsed_time": "42m 30s", "remaining_time": "58m 16s"} |
| {"loss": 0.23589206, "token_acc": 0.92025146, "grad_norm": 1.0574242, "learning_rate": 6.64e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442451, "epoch": 1.2697258, "global_step/max_steps": "1135/2679", "percentage": "42.37%", "elapsed_time": "42m 41s", "remaining_time": "58m 5s"} |
| {"loss": 0.23713765, "token_acc": 0.91393854, "grad_norm": 1.24280779, "learning_rate": 6.62e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442509, "epoch": 1.27532177, "global_step/max_steps": "1140/2679", "percentage": "42.55%", "elapsed_time": "42m 52s", "remaining_time": "57m 53s"} |
| {"loss": 0.21896126, "token_acc": 0.90748013, "grad_norm": 1.33810189, "learning_rate": 6.59e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442574, "epoch": 1.28091774, "global_step/max_steps": "1145/2679", "percentage": "42.74%", "elapsed_time": "43m 3s", "remaining_time": "57m 41s"} |
| {"loss": 0.22135844, "token_acc": 0.91021114, "grad_norm": 1.20345198, "learning_rate": 6.56e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442638, "epoch": 1.28651371, "global_step/max_steps": "1150/2679", "percentage": "42.93%", "elapsed_time": "43m 14s", "remaining_time": "57m 29s"} |
| {"loss": 0.23257537, "token_acc": 0.90422323, "grad_norm": 1.26367028, "learning_rate": 6.53e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442662, "epoch": 1.29210968, "global_step/max_steps": "1155/2679", "percentage": "43.11%", "elapsed_time": "43m 25s", "remaining_time": "57m 18s"} |
| {"loss": 0.22711627, "token_acc": 0.92044514, "grad_norm": 1.20727639, "learning_rate": 6.5e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442681, "epoch": 1.29770565, "global_step/max_steps": "1160/2679", "percentage": "43.30%", "elapsed_time": "43m 37s", "remaining_time": "57m 6s"} |
| {"loss": 0.2248944, "token_acc": 0.91739606, "grad_norm": 1.18080952, "learning_rate": 6.47e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442681, "epoch": 1.30330162, "global_step/max_steps": "1165/2679", "percentage": "43.49%", "elapsed_time": "43m 48s", "remaining_time": "56m 55s"} |
| {"loss": 0.23195705, "token_acc": 0.8935371, "grad_norm": 1.14840064, "learning_rate": 6.44e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442724, "epoch": 1.30889759, "global_step/max_steps": "1170/2679", "percentage": "43.67%", "elapsed_time": "43m 59s", "remaining_time": "56m 44s"} |
| {"loss": 0.20594814, "token_acc": 0.91383905, "grad_norm": 1.20693967, "learning_rate": 6.41e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442783, "epoch": 1.31449356, "global_step/max_steps": "1175/2679", "percentage": "43.86%", "elapsed_time": "44m 10s", "remaining_time": "56m 32s"} |
| {"loss": 0.21650777, "token_acc": 0.89388256, "grad_norm": 1.25934673, "learning_rate": 6.38e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442813, "epoch": 1.32008954, "global_step/max_steps": "1180/2679", "percentage": "44.05%", "elapsed_time": "44m 21s", "remaining_time": "56m 20s"} |
| {"loss": 0.19177072, "token_acc": 0.9389083, "grad_norm": 1.02836555, "learning_rate": 6.35e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442901, "epoch": 1.32568551, "global_step/max_steps": "1185/2679", "percentage": "44.23%", "elapsed_time": "44m 32s", "remaining_time": "56m 8s"} |
| {"loss": 0.19847515, "token_acc": 0.93771822, "grad_norm": 1.24272604, "learning_rate": 6.32e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442961, "epoch": 1.33128148, "global_step/max_steps": "1190/2679", "percentage": "44.42%", "elapsed_time": "44m 43s", "remaining_time": "55m 57s"} |
| {"loss": 0.22710476, "token_acc": 0.91893991, "grad_norm": 1.19833244, "learning_rate": 6.29e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.443014, "epoch": 1.33687745, "global_step/max_steps": "1195/2679", "percentage": "44.61%", "elapsed_time": "44m 54s", "remaining_time": "55m 45s"} |
| {"loss": 0.20722079, "token_acc": 0.8979671, "grad_norm": 1.23113466, "learning_rate": 6.26e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.443079, "epoch": 1.34247342, "global_step/max_steps": "1200/2679", "percentage": "44.79%", "elapsed_time": "45m 4s", "remaining_time": "55m 33s"} |
| {"eval_loss": 0.27264249, "eval_token_acc": 0.89519948, "eval_runtime": 6.9525, "eval_samples_per_second": 15.534, "eval_steps_per_second": 2.589, "epoch": 1.34247342, "global_step/max_steps": "1200/2679", "percentage": "44.79%", "elapsed_time": "45m 11s", "remaining_time": "55m 42s"} |
| {"loss": 0.20924101, "token_acc": 0.92160628, "grad_norm": 1.12727768, "learning_rate": 6.23e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.441933, "epoch": 1.34806939, "global_step/max_steps": "1205/2679", "percentage": "44.98%", "elapsed_time": "45m 23s", "remaining_time": "55m 31s"} |
| {"loss": 0.23527143, "token_acc": 0.90644643, "grad_norm": 1.06740956, "learning_rate": 6.2e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442008, "epoch": 1.35366536, "global_step/max_steps": "1210/2679", "percentage": "45.17%", "elapsed_time": "45m 34s", "remaining_time": "55m 19s"} |
| {"loss": 0.23747463, "token_acc": 0.92208277, "grad_norm": 1.03340454, "learning_rate": 6.17e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442044, "epoch": 1.35926133, "global_step/max_steps": "1215/2679", "percentage": "45.35%", "elapsed_time": "45m 45s", "remaining_time": "55m 7s"} |
| {"loss": 0.25555353, "token_acc": 0.92846687, "grad_norm": 1.13095836, "learning_rate": 6.14e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442064, "epoch": 1.3648573, "global_step/max_steps": "1220/2679", "percentage": "45.54%", "elapsed_time": "45m 56s", "remaining_time": "54m 56s"} |
| {"loss": 0.25298817, "token_acc": 0.91425597, "grad_norm": 1.33154895, "learning_rate": 6.11e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442081, "epoch": 1.37045327, "global_step/max_steps": "1225/2679", "percentage": "45.73%", "elapsed_time": "46m 7s", "remaining_time": "54m 44s"} |
| {"loss": 0.23409848, "token_acc": 0.90471276, "grad_norm": 1.33244581, "learning_rate": 6.08e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442093, "epoch": 1.37604924, "global_step/max_steps": "1230/2679", "percentage": "45.91%", "elapsed_time": "46m 18s", "remaining_time": "54m 33s"} |
| {"loss": 0.21449604, "token_acc": 0.89226407, "grad_norm": 1.21489975, "learning_rate": 6.05e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442158, "epoch": 1.38164522, "global_step/max_steps": "1235/2679", "percentage": "46.10%", "elapsed_time": "46m 29s", "remaining_time": "54m 21s"} |
| {"loss": 0.23834963, "token_acc": 0.91451583, "grad_norm": 1.25628467, "learning_rate": 6.02e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442193, "epoch": 1.38724119, "global_step/max_steps": "1240/2679", "percentage": "46.29%", "elapsed_time": "46m 40s", "remaining_time": "54m 10s"} |
| {"loss": 0.23556228, "token_acc": 0.90387738, "grad_norm": 1.2999055, "learning_rate": 5.99e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442245, "epoch": 1.39283716, "global_step/max_steps": "1245/2679", "percentage": "46.47%", "elapsed_time": "46m 51s", "remaining_time": "53m 58s"} |
| {"loss": 0.22490892, "token_acc": 0.91501508, "grad_norm": 1.29428547, "learning_rate": 5.96e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442271, "epoch": 1.39843313, "global_step/max_steps": "1250/2679", "percentage": "46.66%", "elapsed_time": "47m 2s", "remaining_time": "53m 47s"} |
| {"loss": 0.24717479, "token_acc": 0.89729849, "grad_norm": 0.9496233, "learning_rate": 5.93e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442325, "epoch": 1.4040291, "global_step/max_steps": "1255/2679", "percentage": "46.85%", "elapsed_time": "47m 13s", "remaining_time": "53m 35s"} |
| {"loss": 0.23408446, "token_acc": 0.90311987, "grad_norm": 1.17914356, "learning_rate": 5.9e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442353, "epoch": 1.40962507, "global_step/max_steps": "1260/2679", "percentage": "47.03%", "elapsed_time": "47m 25s", "remaining_time": "53m 24s"} |
| {"loss": 0.23514757, "token_acc": 0.93075431, "grad_norm": 1.23861734, "learning_rate": 5.87e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.44237, "epoch": 1.41522104, "global_step/max_steps": "1265/2679", "percentage": "47.22%", "elapsed_time": "47m 36s", "remaining_time": "53m 12s"} |
| {"loss": 0.198953, "token_acc": 0.92164441, "grad_norm": 1.31718773, "learning_rate": 5.84e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442434, "epoch": 1.42081701, "global_step/max_steps": "1270/2679", "percentage": "47.41%", "elapsed_time": "47m 47s", "remaining_time": "53m 0s"} |
| {"loss": 0.21227779, "token_acc": 0.92042315, "grad_norm": 1.16050025, "learning_rate": 5.81e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442486, "epoch": 1.42641298, "global_step/max_steps": "1275/2679", "percentage": "47.59%", "elapsed_time": "47m 58s", "remaining_time": "52m 49s"} |
| {"loss": 0.2088788, "token_acc": 0.94465257, "grad_norm": 1.39901255, "learning_rate": 5.78e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442527, "epoch": 1.43200895, "global_step/max_steps": "1280/2679", "percentage": "47.78%", "elapsed_time": "48m 9s", "remaining_time": "52m 37s"} |
| {"loss": 0.20969834, "token_acc": 0.90144449, "grad_norm": 1.31972128, "learning_rate": 5.75e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442545, "epoch": 1.43760492, "global_step/max_steps": "1285/2679", "percentage": "47.97%", "elapsed_time": "48m 20s", "remaining_time": "52m 26s"} |
| {"loss": 0.20608165, "token_acc": 0.93818093, "grad_norm": 1.31744769, "learning_rate": 5.72e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442591, "epoch": 1.4432009, "global_step/max_steps": "1290/2679", "percentage": "48.15%", "elapsed_time": "48m 31s", "remaining_time": "52m 14s"} |
| {"loss": 0.19446863, "token_acc": 0.91684688, "grad_norm": 1.296268, "learning_rate": 5.69e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442634, "epoch": 1.44879687, "global_step/max_steps": "1295/2679", "percentage": "48.34%", "elapsed_time": "48m 42s", "remaining_time": "52m 3s"} |
| {"loss": 0.22998292, "token_acc": 0.9138939, "grad_norm": 1.36941208, "learning_rate": 5.66e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.44269, "epoch": 1.45439284, "global_step/max_steps": "1300/2679", "percentage": "48.53%", "elapsed_time": "48m 53s", "remaining_time": "51m 51s"} |
| {"loss": 0.23601608, "token_acc": 0.92506717, "grad_norm": 1.17610569, "learning_rate": 5.62e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442695, "epoch": 1.45998881, "global_step/max_steps": "1305/2679", "percentage": "48.71%", "elapsed_time": "49m 4s", "remaining_time": "51m 40s"} |
| {"loss": 0.2151722, "token_acc": 0.93262852, "grad_norm": 1.40123957, "learning_rate": 5.59e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442695, "epoch": 1.46558478, "global_step/max_steps": "1310/2679", "percentage": "48.90%", "elapsed_time": "49m 15s", "remaining_time": "51m 28s"} |
| {"loss": 0.22861848, "token_acc": 0.89962762, "grad_norm": 1.21803576, "learning_rate": 5.56e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442705, "epoch": 1.47118075, "global_step/max_steps": "1315/2679", "percentage": "49.09%", "elapsed_time": "49m 27s", "remaining_time": "51m 17s"} |
| {"loss": 0.21792028, "token_acc": 0.93169262, "grad_norm": 1.19193508, "learning_rate": 5.53e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442752, "epoch": 1.47677672, "global_step/max_steps": "1320/2679", "percentage": "49.27%", "elapsed_time": "49m 37s", "remaining_time": "51m 5s"} |
| {"loss": 0.21971464, "token_acc": 0.91358272, "grad_norm": 1.28136933, "learning_rate": 5.5e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442809, "epoch": 1.48237269, "global_step/max_steps": "1325/2679", "percentage": "49.46%", "elapsed_time": "49m 48s", "remaining_time": "50m 54s"} |
| {"loss": 0.22595077, "token_acc": 0.90604423, "grad_norm": 1.18471243, "learning_rate": 5.47e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442858, "epoch": 1.48796866, "global_step/max_steps": "1330/2679", "percentage": "49.65%", "elapsed_time": "49m 59s", "remaining_time": "50m 42s"} |
| {"loss": 0.23206425, "token_acc": 0.89178726, "grad_norm": 1.27778419, "learning_rate": 5.44e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442871, "epoch": 1.49356463, "global_step/max_steps": "1335/2679", "percentage": "49.83%", "elapsed_time": "50m 11s", "remaining_time": "50m 31s"} |
| {"loss": 0.21858892, "token_acc": 0.9205845, "grad_norm": 1.33935379, "learning_rate": 5.41e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442911, "epoch": 1.4991606, "global_step/max_steps": "1340/2679", "percentage": "50.02%", "elapsed_time": "50m 22s", "remaining_time": "50m 19s"} |
| {"loss": 0.22110031, "token_acc": 0.93085592, "grad_norm": 1.35509491, "learning_rate": 5.38e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442919, "epoch": 1.50475658, "global_step/max_steps": "1345/2679", "percentage": "50.21%", "elapsed_time": "50m 33s", "remaining_time": "50m 8s"} |
| {"loss": 0.22542815, "token_acc": 0.90778192, "grad_norm": 1.25647417, "learning_rate": 5.35e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442918, "epoch": 1.51035255, "global_step/max_steps": "1350/2679", "percentage": "50.39%", "elapsed_time": "50m 44s", "remaining_time": "49m 57s"} |
| {"loss": 0.24791021, "token_acc": 0.89924736, "grad_norm": 1.28886989, "learning_rate": 5.32e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442943, "epoch": 1.51594852, "global_step/max_steps": "1355/2679", "percentage": "50.58%", "elapsed_time": "50m 55s", "remaining_time": "49m 45s"} |
| {"loss": 0.19647455, "token_acc": 0.95440974, "grad_norm": 1.2436165, "learning_rate": 5.29e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442984, "epoch": 1.52154449, "global_step/max_steps": "1360/2679", "percentage": "50.77%", "elapsed_time": "51m 6s", "remaining_time": "49m 34s"} |
| {"loss": 0.21572742, "token_acc": 0.91285702, "grad_norm": 1.49349651, "learning_rate": 5.26e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.443011, "epoch": 1.52714046, "global_step/max_steps": "1365/2679", "percentage": "50.95%", "elapsed_time": "51m 17s", "remaining_time": "49m 22s"} |
| {"loss": 0.22728324, "token_acc": 0.92806444, "grad_norm": 1.2010854, "learning_rate": 5.23e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.443063, "epoch": 1.53273643, "global_step/max_steps": "1370/2679", "percentage": "51.14%", "elapsed_time": "51m 28s", "remaining_time": "49m 11s"} |
| {"loss": 0.22756319, "token_acc": 0.93050613, "grad_norm": 1.25502296, "learning_rate": 5.19e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.443119, "epoch": 1.5383324, "global_step/max_steps": "1375/2679", "percentage": "51.33%", "elapsed_time": "51m 39s", "remaining_time": "48m 59s"} |
| {"loss": 0.22217469, "token_acc": 0.9125027, "grad_norm": 1.25451546, "learning_rate": 5.16e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.443159, "epoch": 1.54392837, "global_step/max_steps": "1380/2679", "percentage": "51.51%", "elapsed_time": "51m 50s", "remaining_time": "48m 48s"} |
| {"loss": 0.22108982, "token_acc": 0.91567576, "grad_norm": 1.35700642, "learning_rate": 5.13e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.443218, "epoch": 1.54952434, "global_step/max_steps": "1385/2679", "percentage": "51.70%", "elapsed_time": "52m 1s", "remaining_time": "48m 36s"} |
| {"loss": 0.23357217, "token_acc": 0.90169646, "grad_norm": 1.05158969, "learning_rate": 5.1e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.443202, "epoch": 1.55512031, "global_step/max_steps": "1390/2679", "percentage": "51.89%", "elapsed_time": "52m 12s", "remaining_time": "48m 25s"} |
| {"loss": 0.23662758, "token_acc": 0.91214417, "grad_norm": 1.2239121, "learning_rate": 5.07e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.443184, "epoch": 1.56071628, "global_step/max_steps": "1395/2679", "percentage": "52.07%", "elapsed_time": "52m 24s", "remaining_time": "48m 14s"} |
| {"loss": 0.23198478, "token_acc": 0.91110562, "grad_norm": 0.98804296, "learning_rate": 5.04e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.443156, "epoch": 1.56631226, "global_step/max_steps": "1400/2679", "percentage": "52.26%", "elapsed_time": "52m 35s", "remaining_time": "48m 3s"} |
| {"eval_loss": 0.26712084, "eval_token_acc": 0.89587076, "eval_runtime": 7.0213, "eval_samples_per_second": 15.382, "eval_steps_per_second": 2.564, "epoch": 1.56631226, "global_step/max_steps": "1400/2679", "percentage": "52.26%", "elapsed_time": "52m 42s", "remaining_time": "48m 9s"} |
| {"loss": 0.2124896, "token_acc": 0.91967375, "grad_norm": 0.97628682, "learning_rate": 5.01e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442121, "epoch": 1.57190823, "global_step/max_steps": "1405/2679", "percentage": "52.44%", "elapsed_time": "52m 54s", "remaining_time": "47m 58s"} |
| {"loss": 0.2040406, "token_acc": 0.90668222, "grad_norm": 1.12375284, "learning_rate": 4.98e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442164, "epoch": 1.5775042, "global_step/max_steps": "1410/2679", "percentage": "52.63%", "elapsed_time": "53m 5s", "remaining_time": "47m 46s"} |
| {"loss": 0.23937025, "token_acc": 0.90990091, "grad_norm": 1.25159857, "learning_rate": 4.95e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.44216, "epoch": 1.58310017, "global_step/max_steps": "1415/2679", "percentage": "52.82%", "elapsed_time": "53m 16s", "remaining_time": "47m 35s"} |
| {"loss": 0.20788743, "token_acc": 0.93009362, "grad_norm": 1.30595584, "learning_rate": 4.92e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.4422, "epoch": 1.58869614, "global_step/max_steps": "1420/2679", "percentage": "53.00%", "elapsed_time": "53m 27s", "remaining_time": "47m 24s"} |
| {"loss": 0.22498879, "token_acc": 0.90345132, "grad_norm": 1.11618685, "learning_rate": 4.89e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442238, "epoch": 1.59429211, "global_step/max_steps": "1425/2679", "percentage": "53.19%", "elapsed_time": "53m 38s", "remaining_time": "47m 12s"} |
| {"loss": 0.22998741, "token_acc": 0.90130183, "grad_norm": 1.31812047, "learning_rate": 4.85e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442274, "epoch": 1.59988808, "global_step/max_steps": "1430/2679", "percentage": "53.38%", "elapsed_time": "53m 49s", "remaining_time": "47m 1s"} |
| {"loss": 0.22384355, "token_acc": 0.93503896, "grad_norm": 1.24018117, "learning_rate": 4.82e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442293, "epoch": 1.60548405, "global_step/max_steps": "1435/2679", "percentage": "53.56%", "elapsed_time": "54m 1s", "remaining_time": "46m 49s"} |
| {"loss": 0.24482589, "token_acc": 0.901127, "grad_norm": 1.22777028, "learning_rate": 4.79e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442326, "epoch": 1.61108002, "global_step/max_steps": "1440/2679", "percentage": "53.75%", "elapsed_time": "54m 12s", "remaining_time": "46m 38s"} |
| {"loss": 0.19722661, "token_acc": 0.92704826, "grad_norm": 1.59125742, "learning_rate": 4.76e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442362, "epoch": 1.61667599, "global_step/max_steps": "1445/2679", "percentage": "53.94%", "elapsed_time": "54m 23s", "remaining_time": "46m 26s"} |
| {"loss": 0.2254833, "token_acc": 0.90284988, "grad_norm": 1.18971169, "learning_rate": 4.73e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442326, "epoch": 1.62227196, "global_step/max_steps": "1450/2679", "percentage": "54.12%", "elapsed_time": "54m 34s", "remaining_time": "46m 15s"} |
| {"loss": 0.22553804, "token_acc": 0.91438058, "grad_norm": 1.32013606, "learning_rate": 4.7e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442284, "epoch": 1.62786794, "global_step/max_steps": "1455/2679", "percentage": "54.31%", "elapsed_time": "54m 46s", "remaining_time": "46m 4s"} |
| {"loss": 0.21840162, "token_acc": 0.9385757, "grad_norm": 1.18500027, "learning_rate": 4.67e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442239, "epoch": 1.63346391, "global_step/max_steps": "1460/2679", "percentage": "54.50%", "elapsed_time": "54m 58s", "remaining_time": "45m 53s"} |
| {"loss": 0.19763825, "token_acc": 0.91462666, "grad_norm": 1.33078427, "learning_rate": 4.64e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442247, "epoch": 1.63905988, "global_step/max_steps": "1465/2679", "percentage": "54.68%", "elapsed_time": "55m 9s", "remaining_time": "45m 42s"} |
| {"loss": 0.23901806, "token_acc": 0.91819333, "grad_norm": 1.28433977, "learning_rate": 4.61e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442233, "epoch": 1.64465585, "global_step/max_steps": "1470/2679", "percentage": "54.87%", "elapsed_time": "55m 20s", "remaining_time": "45m 31s"} |
| {"loss": 0.22745914, "token_acc": 0.90435815, "grad_norm": 1.31367984, "learning_rate": 4.58e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442278, "epoch": 1.65025182, "global_step/max_steps": "1475/2679", "percentage": "55.06%", "elapsed_time": "55m 31s", "remaining_time": "45m 19s"} |
| {"loss": 0.21658368, "token_acc": 0.90276464, "grad_norm": 1.20827132, "learning_rate": 4.55e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442293, "epoch": 1.65584779, "global_step/max_steps": "1480/2679", "percentage": "55.24%", "elapsed_time": "55m 42s", "remaining_time": "45m 8s"} |
| {"loss": 0.23440585, "token_acc": 0.93296785, "grad_norm": 1.1610868, "learning_rate": 4.52e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442289, "epoch": 1.66144376, "global_step/max_steps": "1485/2679", "percentage": "55.43%", "elapsed_time": "55m 54s", "remaining_time": "44m 56s"} |
| {"loss": 0.22933557, "token_acc": 0.91644453, "grad_norm": 1.32817007, "learning_rate": 4.49e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442317, "epoch": 1.66703973, "global_step/max_steps": "1490/2679", "percentage": "55.62%", "elapsed_time": "56m 5s", "remaining_time": "44m 45s"} |
| {"loss": 0.23326986, "token_acc": 0.90472097, "grad_norm": 1.11291202, "learning_rate": 4.45e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442334, "epoch": 1.6726357, "global_step/max_steps": "1495/2679", "percentage": "55.80%", "elapsed_time": "56m 16s", "remaining_time": "44m 34s"} |
| {"loss": 0.2315913, "token_acc": 0.89254584, "grad_norm": 1.25333976, "learning_rate": 4.42e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.44238, "epoch": 1.67823167, "global_step/max_steps": "1500/2679", "percentage": "55.99%", "elapsed_time": "56m 27s", "remaining_time": "44m 22s"} |
| {"loss": 0.21184132, "token_acc": 0.90674603, "grad_norm": 1.24471426, "learning_rate": 4.39e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.44241, "epoch": 1.68382764, "global_step/max_steps": "1505/2679", "percentage": "56.18%", "elapsed_time": "56m 38s", "remaining_time": "44m 11s"} |
| {"loss": 0.22453079, "token_acc": 0.90766145, "grad_norm": 1.21496785, "learning_rate": 4.36e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442443, "epoch": 1.68942361, "global_step/max_steps": "1510/2679", "percentage": "56.36%", "elapsed_time": "56m 49s", "remaining_time": "43m 59s"} |
| {"loss": 0.23663247, "token_acc": 0.92247156, "grad_norm": 1.24400673, "learning_rate": 4.33e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442483, "epoch": 1.69501959, "global_step/max_steps": "1515/2679", "percentage": "56.55%", "elapsed_time": "57m 0s", "remaining_time": "43m 48s"} |
| {"loss": 0.22366881, "token_acc": 0.90075521, "grad_norm": 1.1909245, "learning_rate": 4.3e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442514, "epoch": 1.70061556, "global_step/max_steps": "1520/2679", "percentage": "56.74%", "elapsed_time": "57m 11s", "remaining_time": "43m 36s"} |
| {"loss": 0.19798751, "token_acc": 0.93585896, "grad_norm": 1.17525078, "learning_rate": 4.27e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442562, "epoch": 1.70621153, "global_step/max_steps": "1525/2679", "percentage": "56.92%", "elapsed_time": "57m 22s", "remaining_time": "43m 25s"} |
| {"loss": 0.21264272, "token_acc": 0.92335675, "grad_norm": 1.13211372, "learning_rate": 4.24e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442575, "epoch": 1.7118075, "global_step/max_steps": "1530/2679", "percentage": "57.11%", "elapsed_time": "57m 33s", "remaining_time": "43m 13s"} |
| {"loss": 0.22446442, "token_acc": 0.92874945, "grad_norm": 1.26523956, "learning_rate": 4.21e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442595, "epoch": 1.71740347, "global_step/max_steps": "1535/2679", "percentage": "57.30%", "elapsed_time": "57m 44s", "remaining_time": "43m 2s"} |
| {"loss": 0.21930482, "token_acc": 0.91416255, "grad_norm": 1.03024055, "learning_rate": 4.18e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442641, "epoch": 1.72299944, "global_step/max_steps": "1540/2679", "percentage": "57.48%", "elapsed_time": "57m 55s", "remaining_time": "42m 50s"} |
| {"loss": 0.23731518, "token_acc": 0.88723571, "grad_norm": 1.06776068, "learning_rate": 4.15e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442636, "epoch": 1.72859541, "global_step/max_steps": "1545/2679", "percentage": "57.67%", "elapsed_time": "58m 7s", "remaining_time": "42m 39s"} |
| {"loss": 0.21198184, "token_acc": 0.91845158, "grad_norm": 1.36346925, "learning_rate": 4.12e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442683, "epoch": 1.73419138, "global_step/max_steps": "1550/2679", "percentage": "57.86%", "elapsed_time": "58m 18s", "remaining_time": "42m 27s"} |
| {"loss": 0.2182554, "token_acc": 0.90528205, "grad_norm": 1.02335999, "learning_rate": 4.09e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.44271, "epoch": 1.73978735, "global_step/max_steps": "1555/2679", "percentage": "58.04%", "elapsed_time": "58m 29s", "remaining_time": "42m 16s"} |
| {"loss": 0.20367045, "token_acc": 0.90069448, "grad_norm": 1.14661556, "learning_rate": 4.06e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442728, "epoch": 1.74538332, "global_step/max_steps": "1560/2679", "percentage": "58.23%", "elapsed_time": "58m 40s", "remaining_time": "42m 5s"} |
| {"loss": 0.22918682, "token_acc": 0.89509434, "grad_norm": 1.13181325, "learning_rate": 4.03e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442772, "epoch": 1.75097929, "global_step/max_steps": "1565/2679", "percentage": "58.42%", "elapsed_time": "58m 51s", "remaining_time": "41m 53s"} |
| {"loss": 0.21526036, "token_acc": 0.90926276, "grad_norm": 1.2967207, "learning_rate": 4e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442777, "epoch": 1.75657527, "global_step/max_steps": "1570/2679", "percentage": "58.60%", "elapsed_time": "59m 2s", "remaining_time": "41m 42s"} |
| {"loss": 0.25894449, "token_acc": 0.9005579, "grad_norm": 1.40989743, "learning_rate": 3.97e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442768, "epoch": 1.76217124, "global_step/max_steps": "1575/2679", "percentage": "58.79%", "elapsed_time": "59m 13s", "remaining_time": "41m 31s"} |
| {"loss": 0.23918419, "token_acc": 0.89687536, "grad_norm": 1.01679499, "learning_rate": 3.94e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442739, "epoch": 1.76776721, "global_step/max_steps": "1580/2679", "percentage": "58.98%", "elapsed_time": "59m 25s", "remaining_time": "41m 19s"} |
| {"loss": 0.20447717, "token_acc": 0.88570576, "grad_norm": 1.14812525, "learning_rate": 3.91e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442745, "epoch": 1.77336318, "global_step/max_steps": "1585/2679", "percentage": "59.16%", "elapsed_time": "59m 36s", "remaining_time": "41m 8s"} |
| {"loss": 0.21482856, "token_acc": 0.92870818, "grad_norm": 1.14415504, "learning_rate": 3.88e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442808, "epoch": 1.77895915, "global_step/max_steps": "1590/2679", "percentage": "59.35%", "elapsed_time": "59m 47s", "remaining_time": "40m 57s"} |
| {"loss": 0.19644725, "token_acc": 0.93721271, "grad_norm": 1.21828675, "learning_rate": 3.85e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442822, "epoch": 1.78455512, "global_step/max_steps": "1595/2679", "percentage": "59.54%", "elapsed_time": "59m 58s", "remaining_time": "40m 45s"} |
| {"loss": 0.22937012, "token_acc": 0.89763673, "grad_norm": 0.97669862, "learning_rate": 3.82e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442818, "epoch": 1.79015109, "global_step/max_steps": "1600/2679", "percentage": "59.72%", "elapsed_time": "1h 0m 9s", "remaining_time": "40m 34s"} |
| {"eval_loss": 0.26657817, "eval_token_acc": 0.89660203, "eval_runtime": 6.8665, "eval_samples_per_second": 15.729, "eval_steps_per_second": 2.621, "epoch": 1.79015109, "global_step/max_steps": "1600/2679", "percentage": "59.72%", "elapsed_time": "1h 0m 16s", "remaining_time": "40m 39s"} |
| {"loss": 0.22518985, "token_acc": 0.912478, "grad_norm": 1.30866492, "learning_rate": 3.79e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.441936, "epoch": 1.79574706, "global_step/max_steps": "1605/2679", "percentage": "59.91%", "elapsed_time": "1h 0m 28s", "remaining_time": "40m 27s"} |
| {"loss": 0.20282168, "token_acc": 0.93883939, "grad_norm": 1.11690095, "learning_rate": 3.76e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.441961, "epoch": 1.80134303, "global_step/max_steps": "1610/2679", "percentage": "60.10%", "elapsed_time": "1h 0m 39s", "remaining_time": "40m 16s"} |
| {"loss": 0.19543896, "token_acc": 0.93909939, "grad_norm": 1.04022106, "learning_rate": 3.73e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.441996, "epoch": 1.806939, "global_step/max_steps": "1615/2679", "percentage": "60.28%", "elapsed_time": "1h 0m 50s", "remaining_time": "40m 5s"} |
| {"loss": 0.22716265, "token_acc": 0.9261505, "grad_norm": 1.27556717, "learning_rate": 3.7e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442058, "epoch": 1.81253497, "global_step/max_steps": "1620/2679", "percentage": "60.47%", "elapsed_time": "1h 1m 1s", "remaining_time": "39m 53s"} |
| {"loss": 0.18808451, "token_acc": 0.93915973, "grad_norm": 1.25022238, "learning_rate": 3.67e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442091, "epoch": 1.81813095, "global_step/max_steps": "1625/2679", "percentage": "60.66%", "elapsed_time": "1h 1m 12s", "remaining_time": "39m 41s"} |
| {"loss": 0.1879014, "token_acc": 0.91830537, "grad_norm": 1.22126462, "learning_rate": 3.64e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442136, "epoch": 1.82372692, "global_step/max_steps": "1630/2679", "percentage": "60.84%", "elapsed_time": "1h 1m 23s", "remaining_time": "39m 30s"} |
| {"loss": 0.21865699, "token_acc": 0.91948991, "grad_norm": 1.33096226, "learning_rate": 3.61e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442152, "epoch": 1.82932289, "global_step/max_steps": "1635/2679", "percentage": "61.03%", "elapsed_time": "1h 1m 34s", "remaining_time": "39m 19s"} |
| {"loss": 0.22961621, "token_acc": 0.91414619, "grad_norm": 1.21071447, "learning_rate": 3.58e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442168, "epoch": 1.83491886, "global_step/max_steps": "1640/2679", "percentage": "61.22%", "elapsed_time": "1h 1m 45s", "remaining_time": "39m 7s"} |
| {"loss": 0.22652824, "token_acc": 0.90931247, "grad_norm": 1.24189736, "learning_rate": 3.55e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442211, "epoch": 1.84051483, "global_step/max_steps": "1645/2679", "percentage": "61.40%", "elapsed_time": "1h 1m 56s", "remaining_time": "38m 56s"} |
| {"loss": 0.22636714, "token_acc": 0.90108078, "grad_norm": 1.20374227, "learning_rate": 3.52e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442246, "epoch": 1.8461108, "global_step/max_steps": "1650/2679", "percentage": "61.59%", "elapsed_time": "1h 2m 7s", "remaining_time": "38m 44s"} |
| {"loss": 0.22370563, "token_acc": 0.91364381, "grad_norm": 1.16821306, "learning_rate": 3.49e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442243, "epoch": 1.85170677, "global_step/max_steps": "1655/2679", "percentage": "61.78%", "elapsed_time": "1h 2m 18s", "remaining_time": "38m 33s"} |
| {"loss": 0.22471604, "token_acc": 0.90909965, "grad_norm": 1.01138684, "learning_rate": 3.46e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442263, "epoch": 1.85730274, "global_step/max_steps": "1660/2679", "percentage": "61.96%", "elapsed_time": "1h 2m 30s", "remaining_time": "38m 21s"} |
| {"loss": 0.20516133, "token_acc": 0.92688172, "grad_norm": 1.31898141, "learning_rate": 3.43e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442289, "epoch": 1.86289871, "global_step/max_steps": "1665/2679", "percentage": "62.15%", "elapsed_time": "1h 2m 41s", "remaining_time": "38m 10s"} |
| {"loss": 0.20016804, "token_acc": 0.93409334, "grad_norm": 1.12251161, "learning_rate": 3.4e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.44233, "epoch": 1.86849468, "global_step/max_steps": "1670/2679", "percentage": "62.34%", "elapsed_time": "1h 2m 52s", "remaining_time": "37m 59s"} |
| {"loss": 0.22241144, "token_acc": 0.93134651, "grad_norm": 1.25830115, "learning_rate": 3.37e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442364, "epoch": 1.87409065, "global_step/max_steps": "1675/2679", "percentage": "62.52%", "elapsed_time": "1h 3m 3s", "remaining_time": "37m 47s"} |
| {"loss": 0.20072911, "token_acc": 0.93575996, "grad_norm": 1.25473413, "learning_rate": 3.34e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.44241, "epoch": 1.87968663, "global_step/max_steps": "1680/2679", "percentage": "62.71%", "elapsed_time": "1h 3m 14s", "remaining_time": "37m 36s"} |
| {"loss": 0.20684497, "token_acc": 0.91460508, "grad_norm": 1.27198403, "learning_rate": 3.31e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442462, "epoch": 1.8852826, "global_step/max_steps": "1685/2679", "percentage": "62.90%", "elapsed_time": "1h 3m 24s", "remaining_time": "37m 24s"} |
| {"loss": 0.21820526, "token_acc": 0.90309106, "grad_norm": 1.08748277, "learning_rate": 3.29e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442493, "epoch": 1.89087857, "global_step/max_steps": "1690/2679", "percentage": "63.08%", "elapsed_time": "1h 3m 35s", "remaining_time": "37m 13s"} |
| {"loss": 0.2251756, "token_acc": 0.91250408, "grad_norm": 1.22570576, "learning_rate": 3.26e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442504, "epoch": 1.89647454, "global_step/max_steps": "1695/2679", "percentage": "63.27%", "elapsed_time": "1h 3m 47s", "remaining_time": "37m 1s"} |
| {"loss": 0.21893444, "token_acc": 0.9172448, "grad_norm": 0.96380504, "learning_rate": 3.23e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442555, "epoch": 1.90207051, "global_step/max_steps": "1700/2679", "percentage": "63.46%", "elapsed_time": "1h 3m 57s", "remaining_time": "36m 50s"} |
| {"loss": 0.20849004, "token_acc": 0.90632867, "grad_norm": 1.3805653, "learning_rate": 3.2e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442605, "epoch": 1.90766648, "global_step/max_steps": "1705/2679", "percentage": "63.64%", "elapsed_time": "1h 4m 8s", "remaining_time": "36m 38s"} |
| {"loss": 0.17915596, "token_acc": 0.92665685, "grad_norm": 1.28642558, "learning_rate": 3.17e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442658, "epoch": 1.91326245, "global_step/max_steps": "1710/2679", "percentage": "63.83%", "elapsed_time": "1h 4m 19s", "remaining_time": "36m 27s"} |
| {"loss": 0.22770329, "token_acc": 0.93601639, "grad_norm": 1.32885347, "learning_rate": 3.14e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442699, "epoch": 1.91885842, "global_step/max_steps": "1715/2679", "percentage": "64.02%", "elapsed_time": "1h 4m 30s", "remaining_time": "36m 15s"} |
| {"loss": 0.21141837, "token_acc": 0.93500212, "grad_norm": 1.27772743, "learning_rate": 3.11e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442736, "epoch": 1.92445439, "global_step/max_steps": "1720/2679", "percentage": "64.20%", "elapsed_time": "1h 4m 41s", "remaining_time": "36m 4s"} |
| {"loss": 0.19971803, "token_acc": 0.92485269, "grad_norm": 1.02450415, "learning_rate": 3.08e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.44273, "epoch": 1.93005036, "global_step/max_steps": "1725/2679", "percentage": "64.39%", "elapsed_time": "1h 4m 52s", "remaining_time": "35m 52s"} |
| {"loss": 0.23256092, "token_acc": 0.92299649, "grad_norm": 1.3251255, "learning_rate": 3.06e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442744, "epoch": 1.93564633, "global_step/max_steps": "1730/2679", "percentage": "64.58%", "elapsed_time": "1h 5m 4s", "remaining_time": "35m 41s"} |
| {"loss": 0.1975563, "token_acc": 0.90993507, "grad_norm": 1.1972149, "learning_rate": 3.03e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442793, "epoch": 1.94124231, "global_step/max_steps": "1735/2679", "percentage": "64.76%", "elapsed_time": "1h 5m 14s", "remaining_time": "35m 30s"} |
| {"loss": 0.23695369, "token_acc": 0.90102047, "grad_norm": 1.01512819, "learning_rate": 3e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442813, "epoch": 1.94683828, "global_step/max_steps": "1740/2679", "percentage": "64.95%", "elapsed_time": "1h 5m 26s", "remaining_time": "35m 18s"} |
| {"loss": 0.2143158, "token_acc": 0.8924484, "grad_norm": 1.192781, "learning_rate": 2.97e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442833, "epoch": 1.95243425, "global_step/max_steps": "1745/2679", "percentage": "65.14%", "elapsed_time": "1h 5m 37s", "remaining_time": "35m 7s"} |
| {"loss": 0.20518661, "token_acc": 0.94086807, "grad_norm": 1.2028476, "learning_rate": 2.94e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.44287, "epoch": 1.95803022, "global_step/max_steps": "1750/2679", "percentage": "65.32%", "elapsed_time": "1h 5m 48s", "remaining_time": "34m 55s"} |
| {"loss": 0.24009857, "token_acc": 0.91564081, "grad_norm": 1.23237444, "learning_rate": 2.91e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442864, "epoch": 1.96362619, "global_step/max_steps": "1755/2679", "percentage": "65.51%", "elapsed_time": "1h 5m 59s", "remaining_time": "34m 44s"} |
| {"loss": 0.19086207, "token_acc": 0.9319941, "grad_norm": 1.36947265, "learning_rate": 2.89e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442932, "epoch": 1.96922216, "global_step/max_steps": "1760/2679", "percentage": "65.70%", "elapsed_time": "1h 6m 10s", "remaining_time": "34m 33s"} |
| {"loss": 0.21189327, "token_acc": 0.91750203, "grad_norm": 1.12431011, "learning_rate": 2.86e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442946, "epoch": 1.97481813, "global_step/max_steps": "1765/2679", "percentage": "65.88%", "elapsed_time": "1h 6m 21s", "remaining_time": "34m 21s"} |
| {"loss": 0.18747849, "token_acc": 0.93068815, "grad_norm": 1.31440471, "learning_rate": 2.83e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442979, "epoch": 1.9804141, "global_step/max_steps": "1770/2679", "percentage": "66.07%", "elapsed_time": "1h 6m 32s", "remaining_time": "34m 10s"} |
| {"loss": 0.19675529, "token_acc": 0.94044985, "grad_norm": 1.22598033, "learning_rate": 2.8e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.443, "epoch": 1.98601007, "global_step/max_steps": "1775/2679", "percentage": "66.26%", "elapsed_time": "1h 6m 43s", "remaining_time": "33m 58s"} |
| {"loss": 0.24343226, "token_acc": 0.91879189, "grad_norm": 1.44640009, "learning_rate": 2.78e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.443018, "epoch": 1.99160604, "global_step/max_steps": "1780/2679", "percentage": "66.44%", "elapsed_time": "1h 6m 54s", "remaining_time": "33m 47s"} |
| {"loss": 0.19745703, "token_acc": 0.9319207, "grad_norm": 1.30114214, "learning_rate": 2.75e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.44305, "epoch": 1.99720201, "global_step/max_steps": "1785/2679", "percentage": "66.63%", "elapsed_time": "1h 7m 5s", "remaining_time": "33m 36s"} |
| {"loss": 0.18561924, "token_acc": 0.93829114, "grad_norm": 1.08502195, "learning_rate": 2.72e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.443192, "epoch": 2.00223839, "global_step/max_steps": "1790/2679", "percentage": "66.82%", "elapsed_time": "1h 7m 15s", "remaining_time": "33m 24s"} |
| {"loss": 0.17711581, "token_acc": 0.91219049, "grad_norm": 1.22787786, "learning_rate": 2.69e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.443214, "epoch": 2.00783436, "global_step/max_steps": "1795/2679", "percentage": "67.00%", "elapsed_time": "1h 7m 26s", "remaining_time": "33m 12s"} |
| {"loss": 0.19735143, "token_acc": 0.90935592, "grad_norm": 1.1346109, "learning_rate": 2.67e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.443215, "epoch": 2.01343033, "global_step/max_steps": "1800/2679", "percentage": "67.19%", "elapsed_time": "1h 7m 37s", "remaining_time": "33m 1s"} |
| {"eval_loss": 0.26367784, "eval_token_acc": 0.90014825, "eval_runtime": 6.9393, "eval_samples_per_second": 15.563, "eval_steps_per_second": 2.594, "epoch": 2.01343033, "global_step/max_steps": "1800/2679", "percentage": "67.19%", "elapsed_time": "1h 7m 44s", "remaining_time": "33m 4s"} |
| {"loss": 0.15310454, "token_acc": 0.95254301, "grad_norm": 1.24000564, "learning_rate": 2.64e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442444, "epoch": 2.0190263, "global_step/max_steps": "1805/2679", "percentage": "67.38%", "elapsed_time": "1h 7m 56s", "remaining_time": "32m 53s"} |
| {"loss": 0.16407121, "token_acc": 0.93482969, "grad_norm": 1.34221597, "learning_rate": 2.61e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442487, "epoch": 2.02462227, "global_step/max_steps": "1810/2679", "percentage": "67.56%", "elapsed_time": "1h 8m 7s", "remaining_time": "32m 42s"} |
| {"loss": 0.14936104, "token_acc": 0.94248884, "grad_norm": 1.30212405, "learning_rate": 2.58e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442503, "epoch": 2.03021824, "global_step/max_steps": "1815/2679", "percentage": "67.75%", "elapsed_time": "1h 8m 18s", "remaining_time": "32m 30s"} |
| {"loss": 0.20290287, "token_acc": 0.92293028, "grad_norm": 1.17343036, "learning_rate": 2.56e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442545, "epoch": 2.03581421, "global_step/max_steps": "1820/2679", "percentage": "67.94%", "elapsed_time": "1h 8m 29s", "remaining_time": "32m 19s"} |
| {"loss": 0.17040191, "token_acc": 0.92607587, "grad_norm": 1.17551448, "learning_rate": 2.53e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442569, "epoch": 2.04141018, "global_step/max_steps": "1825/2679", "percentage": "68.12%", "elapsed_time": "1h 8m 40s", "remaining_time": "32m 8s"} |
| {"loss": 0.16195244, "token_acc": 0.94241017, "grad_norm": 1.21817475, "learning_rate": 2.5e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442592, "epoch": 2.04700616, "global_step/max_steps": "1830/2679", "percentage": "68.31%", "elapsed_time": "1h 8m 51s", "remaining_time": "31m 56s"} |
| {"loss": 0.17841706, "token_acc": 0.93158909, "grad_norm": 1.277731, "learning_rate": 2.48e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442569, "epoch": 2.05260213, "global_step/max_steps": "1835/2679", "percentage": "68.50%", "elapsed_time": "1h 9m 2s", "remaining_time": "31m 45s"} |
| {"loss": 0.14802837, "token_acc": 0.9383999, "grad_norm": 1.2219998, "learning_rate": 2.45e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442615, "epoch": 2.0581981, "global_step/max_steps": "1840/2679", "percentage": "68.68%", "elapsed_time": "1h 9m 13s", "remaining_time": "31m 34s"} |
| {"loss": 0.16374334, "token_acc": 0.92602415, "grad_norm": 1.22276742, "learning_rate": 2.42e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442664, "epoch": 2.06379407, "global_step/max_steps": "1845/2679", "percentage": "68.87%", "elapsed_time": "1h 9m 24s", "remaining_time": "31m 22s"} |
| {"loss": 0.15906649, "token_acc": 0.94215145, "grad_norm": 1.17979448, "learning_rate": 2.4e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442708, "epoch": 2.06939004, "global_step/max_steps": "1850/2679", "percentage": "69.06%", "elapsed_time": "1h 9m 35s", "remaining_time": "31m 11s"} |
| {"loss": 0.17520735, "token_acc": 0.91987788, "grad_norm": 1.41283061, "learning_rate": 2.37e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442717, "epoch": 2.07498601, "global_step/max_steps": "1855/2679", "percentage": "69.24%", "elapsed_time": "1h 9m 46s", "remaining_time": "30m 59s"} |
| {"loss": 0.17997454, "token_acc": 0.93681063, "grad_norm": 1.12162432, "learning_rate": 2.34e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442756, "epoch": 2.08058198, "global_step/max_steps": "1860/2679", "percentage": "69.43%", "elapsed_time": "1h 9m 57s", "remaining_time": "30m 48s"} |
| {"loss": 0.17124714, "token_acc": 0.92767037, "grad_norm": 1.17857449, "learning_rate": 2.32e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442801, "epoch": 2.08617795, "global_step/max_steps": "1865/2679", "percentage": "69.62%", "elapsed_time": "1h 10m 8s", "remaining_time": "30m 36s"} |
| {"loss": 0.15400133, "token_acc": 0.93618733, "grad_norm": 1.27088897, "learning_rate": 2.29e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442847, "epoch": 2.09177392, "global_step/max_steps": "1870/2679", "percentage": "69.80%", "elapsed_time": "1h 10m 19s", "remaining_time": "30m 25s"} |
| {"loss": 0.16207342, "token_acc": 0.94001194, "grad_norm": 1.19306525, "learning_rate": 2.27e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442876, "epoch": 2.09736989, "global_step/max_steps": "1875/2679", "percentage": "69.99%", "elapsed_time": "1h 10m 30s", "remaining_time": "30m 13s"} |
| {"loss": 0.19941524, "token_acc": 0.90580217, "grad_norm": 1.14754356, "learning_rate": 2.24e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442873, "epoch": 2.10296586, "global_step/max_steps": "1880/2679", "percentage": "70.18%", "elapsed_time": "1h 10m 41s", "remaining_time": "30m 2s"} |
| {"loss": 0.17269876, "token_acc": 0.90997416, "grad_norm": 1.24796031, "learning_rate": 2.22e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442924, "epoch": 2.10856184, "global_step/max_steps": "1885/2679", "percentage": "70.36%", "elapsed_time": "1h 10m 52s", "remaining_time": "29m 51s"} |
| {"loss": 0.16721348, "token_acc": 0.9216136, "grad_norm": 1.28486589, "learning_rate": 2.19e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442938, "epoch": 2.11415781, "global_step/max_steps": "1890/2679", "percentage": "70.55%", "elapsed_time": "1h 11m 3s", "remaining_time": "29m 39s"} |
| {"loss": 0.176807, "token_acc": 0.93033846, "grad_norm": 1.19847795, "learning_rate": 2.16e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.44294, "epoch": 2.11975378, "global_step/max_steps": "1895/2679", "percentage": "70.74%", "elapsed_time": "1h 11m 14s", "remaining_time": "29m 28s"} |
| {"loss": 0.17396181, "token_acc": 0.92027443, "grad_norm": 1.19360058, "learning_rate": 2.14e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.44297, "epoch": 2.12534975, "global_step/max_steps": "1900/2679", "percentage": "70.92%", "elapsed_time": "1h 11m 25s", "remaining_time": "29m 17s"} |
| {"loss": 0.1667385, "token_acc": 0.94254124, "grad_norm": 1.342235, "learning_rate": 2.11e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442992, "epoch": 2.13094572, "global_step/max_steps": "1905/2679", "percentage": "71.11%", "elapsed_time": "1h 11m 36s", "remaining_time": "29m 5s"} |
| {"loss": 0.17441654, "token_acc": 0.94232851, "grad_norm": 1.25842088, "learning_rate": 2.09e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442995, "epoch": 2.13654169, "global_step/max_steps": "1910/2679", "percentage": "71.30%", "elapsed_time": "1h 11m 48s", "remaining_time": "28m 54s"} |
| {"loss": 0.16964505, "token_acc": 0.92642869, "grad_norm": 1.17801496, "learning_rate": 2.06e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.443028, "epoch": 2.14213766, "global_step/max_steps": "1915/2679", "percentage": "71.48%", "elapsed_time": "1h 11m 59s", "remaining_time": "28m 43s"} |
| {"loss": 0.17796407, "token_acc": 0.93994193, "grad_norm": 1.26392492, "learning_rate": 2.04e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.443046, "epoch": 2.14773363, "global_step/max_steps": "1920/2679", "percentage": "71.67%", "elapsed_time": "1h 12m 10s", "remaining_time": "28m 31s"} |
| {"loss": 0.15516247, "token_acc": 0.94128499, "grad_norm": 1.1220154, "learning_rate": 2.01e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.443057, "epoch": 2.1533296, "global_step/max_steps": "1925/2679", "percentage": "71.86%", "elapsed_time": "1h 12m 21s", "remaining_time": "28m 20s"} |
| {"loss": 0.17658886, "token_acc": 0.93370637, "grad_norm": 1.26377013, "learning_rate": 1.99e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.443079, "epoch": 2.15892557, "global_step/max_steps": "1930/2679", "percentage": "72.04%", "elapsed_time": "1h 12m 32s", "remaining_time": "28m 9s"} |
| {"loss": 0.13491592, "token_acc": 0.93735663, "grad_norm": 1.35305847, "learning_rate": 1.96e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.443143, "epoch": 2.16452154, "global_step/max_steps": "1935/2679", "percentage": "72.23%", "elapsed_time": "1h 12m 43s", "remaining_time": "27m 57s"} |
| {"loss": 0.15286179, "token_acc": 0.92891424, "grad_norm": 1.24725748, "learning_rate": 1.94e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.443177, "epoch": 2.17011752, "global_step/max_steps": "1940/2679", "percentage": "72.42%", "elapsed_time": "1h 12m 54s", "remaining_time": "27m 46s"} |
| {"loss": 0.18882177, "token_acc": 0.94967508, "grad_norm": 1.39696518, "learning_rate": 1.92e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.443164, "epoch": 2.17571349, "global_step/max_steps": "1945/2679", "percentage": "72.60%", "elapsed_time": "1h 13m 5s", "remaining_time": "27m 35s"} |
| {"loss": 0.17173498, "token_acc": 0.93747956, "grad_norm": 1.25632064, "learning_rate": 1.89e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.443167, "epoch": 2.18130946, "global_step/max_steps": "1950/2679", "percentage": "72.79%", "elapsed_time": "1h 13m 16s", "remaining_time": "27m 23s"} |
| {"loss": 0.14612654, "token_acc": 0.94690692, "grad_norm": 1.27466564, "learning_rate": 1.87e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.443202, "epoch": 2.18690543, "global_step/max_steps": "1955/2679", "percentage": "72.97%", "elapsed_time": "1h 13m 27s", "remaining_time": "27m 12s"} |
| {"loss": 0.15883901, "token_acc": 0.91070881, "grad_norm": 1.25631716, "learning_rate": 1.84e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.443238, "epoch": 2.1925014, "global_step/max_steps": "1960/2679", "percentage": "73.16%", "elapsed_time": "1h 13m 38s", "remaining_time": "27m 0s"} |
| {"loss": 0.15066602, "token_acc": 0.93479167, "grad_norm": 1.34449262, "learning_rate": 1.82e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.443271, "epoch": 2.19809737, "global_step/max_steps": "1965/2679", "percentage": "73.35%", "elapsed_time": "1h 13m 49s", "remaining_time": "26m 49s"} |
| {"loss": 0.15175378, "token_acc": 0.94028813, "grad_norm": 1.15864436, "learning_rate": 1.8e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.443297, "epoch": 2.20369334, "global_step/max_steps": "1970/2679", "percentage": "73.53%", "elapsed_time": "1h 14m 0s", "remaining_time": "26m 38s"} |
| {"loss": 0.18235549, "token_acc": 0.92014452, "grad_norm": 1.22727088, "learning_rate": 1.77e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.443305, "epoch": 2.20928931, "global_step/max_steps": "1975/2679", "percentage": "73.72%", "elapsed_time": "1h 14m 11s", "remaining_time": "26m 26s"} |
| {"loss": 0.15870845, "token_acc": 0.94132126, "grad_norm": 1.29373583, "learning_rate": 1.75e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.443331, "epoch": 2.21488528, "global_step/max_steps": "1980/2679", "percentage": "73.91%", "elapsed_time": "1h 14m 22s", "remaining_time": "26m 15s"} |
| {"loss": 0.17956327, "token_acc": 0.95061495, "grad_norm": 1.31316956, "learning_rate": 1.73e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.443374, "epoch": 2.22048125, "global_step/max_steps": "1985/2679", "percentage": "74.09%", "elapsed_time": "1h 14m 33s", "remaining_time": "26m 4s"} |
| {"loss": 0.16729335, "token_acc": 0.91635511, "grad_norm": 1.2183641, "learning_rate": 1.7e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.443402, "epoch": 2.22607722, "global_step/max_steps": "1990/2679", "percentage": "74.28%", "elapsed_time": "1h 14m 44s", "remaining_time": "25m 52s"} |
| {"loss": 0.17868465, "token_acc": 0.91940952, "grad_norm": 1.26604919, "learning_rate": 1.68e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.443423, "epoch": 2.2316732, "global_step/max_steps": "1995/2679", "percentage": "74.47%", "elapsed_time": "1h 14m 55s", "remaining_time": "25m 41s"} |
| {"loss": 0.16553314, "token_acc": 0.95011317, "grad_norm": 1.31819642, "learning_rate": 1.66e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.44344, "epoch": 2.23726917, "global_step/max_steps": "2000/2679", "percentage": "74.65%", "elapsed_time": "1h 15m 6s", "remaining_time": "25m 30s"} |
| {"eval_loss": 0.26636332, "eval_token_acc": 0.90047274, "eval_runtime": 6.8092, "eval_samples_per_second": 15.861, "eval_steps_per_second": 2.643, "epoch": 2.23726917, "global_step/max_steps": "2000/2679", "percentage": "74.65%", "elapsed_time": "1h 15m 13s", "remaining_time": "25m 32s"} |
| {"loss": 0.17230086, "token_acc": 0.91564067, "grad_norm": 1.26661983, "learning_rate": 1.63e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.441958, "epoch": 2.24286514, "global_step/max_steps": "2005/2679", "percentage": "74.84%", "elapsed_time": "1h 15m 33s", "remaining_time": "25m 23s"} |
| {"loss": 0.15712084, "token_acc": 0.94832682, "grad_norm": 1.47132503, "learning_rate": 1.61e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.441992, "epoch": 2.24846111, "global_step/max_steps": "2010/2679", "percentage": "75.03%", "elapsed_time": "1h 15m 44s", "remaining_time": "25m 12s"} |
| {"loss": 0.1742009, "token_acc": 0.93026076, "grad_norm": 1.06935067, "learning_rate": 1.59e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.441994, "epoch": 2.25405708, "global_step/max_steps": "2015/2679", "percentage": "75.21%", "elapsed_time": "1h 15m 55s", "remaining_time": "25m 1s"} |
| {"loss": 0.17503355, "token_acc": 0.93836791, "grad_norm": 1.35498677, "learning_rate": 1.57e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442019, "epoch": 2.25965305, "global_step/max_steps": "2020/2679", "percentage": "75.40%", "elapsed_time": "1h 16m 6s", "remaining_time": "24m 49s"} |
| {"loss": 0.15896976, "token_acc": 0.95733646, "grad_norm": 1.32467916, "learning_rate": 1.54e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442057, "epoch": 2.26524902, "global_step/max_steps": "2025/2679", "percentage": "75.59%", "elapsed_time": "1h 16m 17s", "remaining_time": "24m 38s"} |
| {"loss": 0.19799697, "token_acc": 0.90316446, "grad_norm": 1.17606498, "learning_rate": 1.52e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442042, "epoch": 2.27084499, "global_step/max_steps": "2030/2679", "percentage": "75.77%", "elapsed_time": "1h 16m 28s", "remaining_time": "24m 27s"} |
| {"loss": 0.16167512, "token_acc": 0.95345511, "grad_norm": 1.25875348, "learning_rate": 1.5e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.44208, "epoch": 2.27644096, "global_step/max_steps": "2035/2679", "percentage": "75.96%", "elapsed_time": "1h 16m 39s", "remaining_time": "24m 15s"} |
| {"loss": 0.16465919, "token_acc": 0.94616866, "grad_norm": 1.2271035, "learning_rate": 1.48e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442113, "epoch": 2.28203693, "global_step/max_steps": "2040/2679", "percentage": "76.15%", "elapsed_time": "1h 16m 50s", "remaining_time": "24m 4s"} |
| {"loss": 0.16746314, "token_acc": 0.93082637, "grad_norm": 1.24384235, "learning_rate": 1.45e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.44213, "epoch": 2.2876329, "global_step/max_steps": "2045/2679", "percentage": "76.33%", "elapsed_time": "1h 17m 1s", "remaining_time": "23m 52s"} |
| {"loss": 0.19054003, "token_acc": 0.92889463, "grad_norm": 1.1396957, "learning_rate": 1.43e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442155, "epoch": 2.29322888, "global_step/max_steps": "2050/2679", "percentage": "76.52%", "elapsed_time": "1h 17m 13s", "remaining_time": "23m 41s"} |
| {"loss": 0.16747789, "token_acc": 0.91842432, "grad_norm": 1.20586483, "learning_rate": 1.41e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442162, "epoch": 2.29882485, "global_step/max_steps": "2055/2679", "percentage": "76.71%", "elapsed_time": "1h 17m 24s", "remaining_time": "23m 30s"} |
| {"loss": 0.18378395, "token_acc": 0.93355108, "grad_norm": 1.25102428, "learning_rate": 1.39e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442144, "epoch": 2.30442082, "global_step/max_steps": "2060/2679", "percentage": "76.89%", "elapsed_time": "1h 17m 35s", "remaining_time": "23m 18s"} |
| {"loss": 0.16771526, "token_acc": 0.93080545, "grad_norm": 1.233565, "learning_rate": 1.37e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442179, "epoch": 2.31001679, "global_step/max_steps": "2065/2679", "percentage": "77.08%", "elapsed_time": "1h 17m 46s", "remaining_time": "23m 7s"} |
| {"loss": 0.16559837, "token_acc": 0.95538004, "grad_norm": 1.34177628, "learning_rate": 1.35e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442233, "epoch": 2.31561276, "global_step/max_steps": "2070/2679", "percentage": "77.27%", "elapsed_time": "1h 17m 57s", "remaining_time": "22m 56s"} |
| {"loss": 0.16012132, "token_acc": 0.94489594, "grad_norm": 1.11783667, "learning_rate": 1.33e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442251, "epoch": 2.32120873, "global_step/max_steps": "2075/2679", "percentage": "77.45%", "elapsed_time": "1h 18m 8s", "remaining_time": "22m 44s"} |
| {"loss": 0.17748787, "token_acc": 0.91268052, "grad_norm": 1.19025327, "learning_rate": 1.31e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442274, "epoch": 2.3268047, "global_step/max_steps": "2080/2679", "percentage": "77.64%", "elapsed_time": "1h 18m 19s", "remaining_time": "22m 33s"} |
| {"loss": 0.17413596, "token_acc": 0.94623656, "grad_norm": 1.21461772, "learning_rate": 1.28e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442306, "epoch": 2.33240067, "global_step/max_steps": "2085/2679", "percentage": "77.83%", "elapsed_time": "1h 18m 30s", "remaining_time": "22m 22s"} |
| {"loss": 0.16290172, "token_acc": 0.94963504, "grad_norm": 1.23216094, "learning_rate": 1.26e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442326, "epoch": 2.33799664, "global_step/max_steps": "2090/2679", "percentage": "78.01%", "elapsed_time": "1h 18m 41s", "remaining_time": "22m 10s"} |
| {"loss": 0.15581195, "token_acc": 0.93867373, "grad_norm": 1.25003445, "learning_rate": 1.24e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442336, "epoch": 2.34359261, "global_step/max_steps": "2095/2679", "percentage": "78.20%", "elapsed_time": "1h 18m 52s", "remaining_time": "21m 59s"} |
| {"loss": 0.18165855, "token_acc": 0.92623169, "grad_norm": 1.37810741, "learning_rate": 1.22e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.44234, "epoch": 2.34918858, "global_step/max_steps": "2100/2679", "percentage": "78.39%", "elapsed_time": "1h 19m 4s", "remaining_time": "21m 48s"} |
| {"loss": 0.18712418, "token_acc": 0.90303346, "grad_norm": 1.34233999, "learning_rate": 1.2e-06, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442305, "epoch": 2.35478456, "global_step/max_steps": "2105/2679", "percentage": "78.57%", "elapsed_time": "1h 19m 15s", "remaining_time": "21m 36s"} |
| {"loss": 0.14789709, "token_acc": 0.9666302, "grad_norm": 1.28175673, "learning_rate": 1.18e-06, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442322, "epoch": 2.36038053, "global_step/max_steps": "2110/2679", "percentage": "78.76%", "elapsed_time": "1h 19m 26s", "remaining_time": "21m 25s"} |
| {"loss": 0.17597637, "token_acc": 0.92466495, "grad_norm": 1.22684307, "learning_rate": 1.16e-06, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.44232, "epoch": 2.3659765, "global_step/max_steps": "2115/2679", "percentage": "78.95%", "elapsed_time": "1h 19m 38s", "remaining_time": "21m 14s"} |
| {"loss": 0.16379331, "token_acc": 0.9441531, "grad_norm": 1.3986087, "learning_rate": 1.14e-06, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442367, "epoch": 2.37157247, "global_step/max_steps": "2120/2679", "percentage": "79.13%", "elapsed_time": "1h 19m 49s", "remaining_time": "21m 2s"} |
| {"loss": 0.17396849, "token_acc": 0.94960921, "grad_norm": 1.37624987, "learning_rate": 1.12e-06, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442403, "epoch": 2.37716844, "global_step/max_steps": "2125/2679", "percentage": "79.32%", "elapsed_time": "1h 19m 59s", "remaining_time": "20m 51s"} |
| {"loss": 0.17383747, "token_acc": 0.9283328, "grad_norm": 1.25489922, "learning_rate": 1.1e-06, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442436, "epoch": 2.38276441, "global_step/max_steps": "2130/2679", "percentage": "79.51%", "elapsed_time": "1h 20m 10s", "remaining_time": "20m 39s"} |
| {"loss": 0.13334684, "token_acc": 0.95537152, "grad_norm": 1.38690187, "learning_rate": 1.09e-06, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442473, "epoch": 2.38836038, "global_step/max_steps": "2135/2679", "percentage": "79.69%", "elapsed_time": "1h 20m 21s", "remaining_time": "20m 28s"} |
| {"loss": 0.18759502, "token_acc": 0.9157839, "grad_norm": 1.38983551, "learning_rate": 1.07e-06, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.44251, "epoch": 2.39395635, "global_step/max_steps": "2140/2679", "percentage": "79.88%", "elapsed_time": "1h 20m 32s", "remaining_time": "20m 17s"} |
| {"loss": 0.1732502, "token_acc": 0.93912817, "grad_norm": 1.41016812, "learning_rate": 1.05e-06, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442532, "epoch": 2.39955232, "global_step/max_steps": "2145/2679", "percentage": "80.07%", "elapsed_time": "1h 20m 43s", "remaining_time": "20m 5s"} |
| {"loss": 0.18823726, "token_acc": 0.91737379, "grad_norm": 1.19166719, "learning_rate": 1.03e-06, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442533, "epoch": 2.40514829, "global_step/max_steps": "2150/2679", "percentage": "80.25%", "elapsed_time": "1h 20m 55s", "remaining_time": "19m 54s"} |
| {"loss": 0.13603872, "token_acc": 0.95960632, "grad_norm": 1.38939403, "learning_rate": 1.01e-06, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442574, "epoch": 2.41074426, "global_step/max_steps": "2155/2679", "percentage": "80.44%", "elapsed_time": "1h 21m 5s", "remaining_time": "19m 43s"} |
| {"loss": 0.14615517, "token_acc": 0.93392935, "grad_norm": 1.18391082, "learning_rate": 9.9e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442616, "epoch": 2.41634024, "global_step/max_steps": "2160/2679", "percentage": "80.63%", "elapsed_time": "1h 21m 16s", "remaining_time": "19m 31s"} |
| {"loss": 0.13922967, "token_acc": 0.93811704, "grad_norm": 1.18520191, "learning_rate": 9.7e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442654, "epoch": 2.42193621, "global_step/max_steps": "2165/2679", "percentage": "80.81%", "elapsed_time": "1h 21m 27s", "remaining_time": "19m 20s"} |
| {"loss": 0.18400617, "token_acc": 0.92253754, "grad_norm": 1.26455418, "learning_rate": 9.5e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442648, "epoch": 2.42753218, "global_step/max_steps": "2170/2679", "percentage": "81.00%", "elapsed_time": "1h 21m 38s", "remaining_time": "19m 9s"} |
| {"loss": 0.16243043, "token_acc": 0.91709234, "grad_norm": 1.35187552, "learning_rate": 9.4e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442638, "epoch": 2.43312815, "global_step/max_steps": "2175/2679", "percentage": "81.19%", "elapsed_time": "1h 21m 50s", "remaining_time": "18m 57s"} |
| {"loss": 0.16741896, "token_acc": 0.92929056, "grad_norm": 1.29401323, "learning_rate": 9.2e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442667, "epoch": 2.43872412, "global_step/max_steps": "2180/2679", "percentage": "81.37%", "elapsed_time": "1h 22m 1s", "remaining_time": "18m 46s"} |
| {"loss": 0.15757846, "token_acc": 0.94454491, "grad_norm": 1.18062285, "learning_rate": 9e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442706, "epoch": 2.44432009, "global_step/max_steps": "2185/2679", "percentage": "81.56%", "elapsed_time": "1h 22m 12s", "remaining_time": "18m 35s"} |
| {"loss": 0.15624526, "token_acc": 0.95351597, "grad_norm": 1.30119195, "learning_rate": 8.8e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442722, "epoch": 2.44991606, "global_step/max_steps": "2190/2679", "percentage": "81.75%", "elapsed_time": "1h 22m 23s", "remaining_time": "18m 23s"} |
| {"loss": 0.1632205, "token_acc": 0.93194671, "grad_norm": 1.23507955, "learning_rate": 8.7e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442767, "epoch": 2.45551203, "global_step/max_steps": "2195/2679", "percentage": "81.93%", "elapsed_time": "1h 22m 34s", "remaining_time": "18m 12s"} |
| {"loss": 0.1706944, "token_acc": 0.93428079, "grad_norm": 1.28774926, "learning_rate": 8.5e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442803, "epoch": 2.461108, "global_step/max_steps": "2200/2679", "percentage": "82.12%", "elapsed_time": "1h 22m 44s", "remaining_time": "18m 1s"} |
| {"eval_loss": 0.2705254, "eval_token_acc": 0.90000368, "eval_runtime": 6.8908, "eval_samples_per_second": 15.673, "eval_steps_per_second": 2.612, "epoch": 2.461108, "global_step/max_steps": "2200/2679", "percentage": "82.12%", "elapsed_time": "1h 22m 51s", "remaining_time": "18m 2s"} |
| {"loss": 0.14224892, "token_acc": 0.95685432, "grad_norm": 1.30469361, "learning_rate": 8.3e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442185, "epoch": 2.46670397, "global_step/max_steps": "2205/2679", "percentage": "82.31%", "elapsed_time": "1h 23m 3s", "remaining_time": "17m 51s"} |
| {"loss": 0.16315112, "token_acc": 0.93142633, "grad_norm": 1.11870203, "learning_rate": 8.1e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442192, "epoch": 2.47229994, "global_step/max_steps": "2210/2679", "percentage": "82.49%", "elapsed_time": "1h 23m 14s", "remaining_time": "17m 39s"} |
| {"loss": 0.13917865, "token_acc": 0.94708995, "grad_norm": 1.21209033, "learning_rate": 8e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.44221, "epoch": 2.47789591, "global_step/max_steps": "2215/2679", "percentage": "82.68%", "elapsed_time": "1h 23m 25s", "remaining_time": "17m 28s"} |
| {"loss": 0.18095112, "token_acc": 0.90733057, "grad_norm": 1.15564606, "learning_rate": 7.8e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442208, "epoch": 2.48349189, "global_step/max_steps": "2220/2679", "percentage": "82.87%", "elapsed_time": "1h 23m 36s", "remaining_time": "17m 17s"} |
| {"loss": 0.16513919, "token_acc": 0.94395902, "grad_norm": 1.33543872, "learning_rate": 7.6e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442235, "epoch": 2.48908786, "global_step/max_steps": "2225/2679", "percentage": "83.05%", "elapsed_time": "1h 23m 47s", "remaining_time": "17m 5s"} |
| {"loss": 0.15539069, "token_acc": 0.93520823, "grad_norm": 1.33262197, "learning_rate": 7.5e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442258, "epoch": 2.49468383, "global_step/max_steps": "2230/2679", "percentage": "83.24%", "elapsed_time": "1h 23m 58s", "remaining_time": "16m 54s"} |
| {"loss": 0.18741903, "token_acc": 0.92608958, "grad_norm": 1.32122289, "learning_rate": 7.3e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442295, "epoch": 2.5002798, "global_step/max_steps": "2235/2679", "percentage": "83.43%", "elapsed_time": "1h 24m 9s", "remaining_time": "16m 43s"} |
| {"loss": 0.16742052, "token_acc": 0.94711885, "grad_norm": 1.26743634, "learning_rate": 7.2e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.44228, "epoch": 2.50587577, "global_step/max_steps": "2240/2679", "percentage": "83.61%", "elapsed_time": "1h 24m 21s", "remaining_time": "16m 31s"} |
| {"loss": 0.16471757, "token_acc": 0.92486515, "grad_norm": 1.3375356, "learning_rate": 7e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442281, "epoch": 2.51147174, "global_step/max_steps": "2245/2679", "percentage": "83.80%", "elapsed_time": "1h 24m 32s", "remaining_time": "16m 20s"} |
| {"loss": 0.16255602, "token_acc": 0.92624087, "grad_norm": 1.31484158, "learning_rate": 6.8e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442312, "epoch": 2.51706771, "global_step/max_steps": "2250/2679", "percentage": "83.99%", "elapsed_time": "1h 24m 43s", "remaining_time": "16m 9s"} |
| {"loss": 0.18687601, "token_acc": 0.92658433, "grad_norm": 1.62474613, "learning_rate": 6.7e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442334, "epoch": 2.52266368, "global_step/max_steps": "2255/2679", "percentage": "84.17%", "elapsed_time": "1h 24m 54s", "remaining_time": "15m 57s"} |
| {"loss": 0.1689505, "token_acc": 0.91879557, "grad_norm": 1.2477032, "learning_rate": 6.5e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442341, "epoch": 2.52825965, "global_step/max_steps": "2260/2679", "percentage": "84.36%", "elapsed_time": "1h 25m 5s", "remaining_time": "15m 46s"} |
| {"loss": 0.17422327, "token_acc": 0.93166964, "grad_norm": 1.28850119, "learning_rate": 6.4e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442364, "epoch": 2.53385562, "global_step/max_steps": "2265/2679", "percentage": "84.55%", "elapsed_time": "1h 25m 16s", "remaining_time": "15m 35s"} |
| {"loss": 0.1696995, "token_acc": 0.92391669, "grad_norm": 1.42741307, "learning_rate": 6.2e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442389, "epoch": 2.53945159, "global_step/max_steps": "2270/2679", "percentage": "84.73%", "elapsed_time": "1h 25m 27s", "remaining_time": "15m 23s"} |
| {"loss": 0.15271944, "token_acc": 0.93732375, "grad_norm": 1.17324902, "learning_rate": 6.1e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442419, "epoch": 2.54504757, "global_step/max_steps": "2275/2679", "percentage": "84.92%", "elapsed_time": "1h 25m 38s", "remaining_time": "15m 12s"} |
| {"loss": 0.16869301, "token_acc": 0.95930029, "grad_norm": 1.21026744, "learning_rate": 5.9e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442439, "epoch": 2.55064354, "global_step/max_steps": "2280/2679", "percentage": "85.11%", "elapsed_time": "1h 25m 49s", "remaining_time": "15m 1s"} |
| {"loss": 0.16076574, "token_acc": 0.94681425, "grad_norm": 1.16056214, "learning_rate": 5.8e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442454, "epoch": 2.55623951, "global_step/max_steps": "2285/2679", "percentage": "85.29%", "elapsed_time": "1h 26m 1s", "remaining_time": "14m 49s"} |
| {"loss": 0.16253484, "token_acc": 0.95927374, "grad_norm": 1.24398731, "learning_rate": 5.7e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442484, "epoch": 2.56183548, "global_step/max_steps": "2290/2679", "percentage": "85.48%", "elapsed_time": "1h 26m 11s", "remaining_time": "14m 38s"} |
| {"loss": 0.16479987, "token_acc": 0.93481085, "grad_norm": 1.28258731, "learning_rate": 5.5e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442483, "epoch": 2.56743145, "global_step/max_steps": "2295/2679", "percentage": "85.67%", "elapsed_time": "1h 26m 23s", "remaining_time": "14m 27s"} |
| {"loss": 0.17062801, "token_acc": 0.93004675, "grad_norm": 1.27586633, "learning_rate": 5.4e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442503, "epoch": 2.57302742, "global_step/max_steps": "2300/2679", "percentage": "85.85%", "elapsed_time": "1h 26m 34s", "remaining_time": "14m 15s"} |
| {"loss": 0.17241375, "token_acc": 0.93175174, "grad_norm": 1.17604463, "learning_rate": 5.2e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442517, "epoch": 2.57862339, "global_step/max_steps": "2305/2679", "percentage": "86.04%", "elapsed_time": "1h 26m 45s", "remaining_time": "14m 4s"} |
| {"loss": 0.16632583, "token_acc": 0.93336979, "grad_norm": 1.05710145, "learning_rate": 5.1e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.44252, "epoch": 2.58421936, "global_step/max_steps": "2310/2679", "percentage": "86.23%", "elapsed_time": "1h 26m 56s", "remaining_time": "13m 53s"} |
| {"loss": 0.18920276, "token_acc": 0.9448139, "grad_norm": 1.3145687, "learning_rate": 5e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442544, "epoch": 2.58981533, "global_step/max_steps": "2315/2679", "percentage": "86.41%", "elapsed_time": "1h 27m 7s", "remaining_time": "13m 41s"} |
| {"loss": 0.17246813, "token_acc": 0.93403069, "grad_norm": 1.40429796, "learning_rate": 4.8e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442567, "epoch": 2.5954113, "global_step/max_steps": "2320/2679", "percentage": "86.60%", "elapsed_time": "1h 27m 18s", "remaining_time": "13m 30s"} |
| {"loss": 0.17692927, "token_acc": 0.93441317, "grad_norm": 1.22133738, "learning_rate": 4.7e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442561, "epoch": 2.60100727, "global_step/max_steps": "2325/2679", "percentage": "86.79%", "elapsed_time": "1h 27m 30s", "remaining_time": "13m 19s"} |
| {"loss": 0.1712024, "token_acc": 0.93429252, "grad_norm": 1.08626166, "learning_rate": 4.6e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442578, "epoch": 2.60660325, "global_step/max_steps": "2330/2679", "percentage": "86.97%", "elapsed_time": "1h 27m 41s", "remaining_time": "13m 8s"} |
| {"loss": 0.1632653, "token_acc": 0.92798521, "grad_norm": 1.17306679, "learning_rate": 4.4e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442595, "epoch": 2.61219922, "global_step/max_steps": "2335/2679", "percentage": "87.16%", "elapsed_time": "1h 27m 52s", "remaining_time": "12m 56s"} |
| {"loss": 0.17463017, "token_acc": 0.93032787, "grad_norm": 1.30993286, "learning_rate": 4.3e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442605, "epoch": 2.61779519, "global_step/max_steps": "2340/2679", "percentage": "87.35%", "elapsed_time": "1h 28m 3s", "remaining_time": "12m 45s"} |
| {"loss": 0.15369285, "token_acc": 0.95301418, "grad_norm": 1.29550582, "learning_rate": 4.2e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442635, "epoch": 2.62339116, "global_step/max_steps": "2345/2679", "percentage": "87.53%", "elapsed_time": "1h 28m 14s", "remaining_time": "12m 34s"} |
| {"loss": 0.15233397, "token_acc": 0.93955284, "grad_norm": 1.35036918, "learning_rate": 4.1e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442672, "epoch": 2.62898713, "global_step/max_steps": "2350/2679", "percentage": "87.72%", "elapsed_time": "1h 28m 25s", "remaining_time": "12m 22s"} |
| {"loss": 0.16372932, "token_acc": 0.95967932, "grad_norm": 1.21040179, "learning_rate": 3.9e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442685, "epoch": 2.6345831, "global_step/max_steps": "2355/2679", "percentage": "87.91%", "elapsed_time": "1h 28m 36s", "remaining_time": "12m 11s"} |
| {"loss": 0.17064323, "token_acc": 0.91672063, "grad_norm": 1.20894546, "learning_rate": 3.8e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.4427, "epoch": 2.64017907, "global_step/max_steps": "2360/2679", "percentage": "88.09%", "elapsed_time": "1h 28m 47s", "remaining_time": "12m 0s"} |
| {"loss": 0.17503581, "token_acc": 0.92588128, "grad_norm": 1.11412167, "learning_rate": 3.7e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442641, "epoch": 2.64577504, "global_step/max_steps": "2365/2679", "percentage": "88.28%", "elapsed_time": "1h 28m 59s", "remaining_time": "11m 48s"} |
| {"loss": 0.15777822, "token_acc": 0.93882386, "grad_norm": 1.20056782, "learning_rate": 3.6e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442669, "epoch": 2.65137101, "global_step/max_steps": "2370/2679", "percentage": "88.47%", "elapsed_time": "1h 29m 10s", "remaining_time": "11m 37s"} |
| {"loss": 0.18190815, "token_acc": 0.92219821, "grad_norm": 1.21643673, "learning_rate": 3.5e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442655, "epoch": 2.65696698, "global_step/max_steps": "2375/2679", "percentage": "88.65%", "elapsed_time": "1h 29m 21s", "remaining_time": "11m 26s"} |
| {"loss": 0.16896079, "token_acc": 0.94248213, "grad_norm": 1.29775001, "learning_rate": 3.4e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442681, "epoch": 2.66256295, "global_step/max_steps": "2380/2679", "percentage": "88.84%", "elapsed_time": "1h 29m 32s", "remaining_time": "11m 15s"} |
| {"loss": 0.16155384, "token_acc": 0.93372982, "grad_norm": 1.2248957, "learning_rate": 3.3e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442697, "epoch": 2.66815893, "global_step/max_steps": "2385/2679", "percentage": "89.03%", "elapsed_time": "1h 29m 44s", "remaining_time": "11m 3s"} |
| {"loss": 0.16212857, "token_acc": 0.94977511, "grad_norm": 1.298028, "learning_rate": 3.1e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442704, "epoch": 2.6737549, "global_step/max_steps": "2390/2679", "percentage": "89.21%", "elapsed_time": "1h 29m 55s", "remaining_time": "10m 52s"} |
| {"loss": 0.16877029, "token_acc": 0.92798584, "grad_norm": 1.27017181, "learning_rate": 3e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442734, "epoch": 2.67935087, "global_step/max_steps": "2395/2679", "percentage": "89.40%", "elapsed_time": "1h 30m 6s", "remaining_time": "10m 41s"} |
| {"loss": 0.15284323, "token_acc": 0.92869671, "grad_norm": 1.33309448, "learning_rate": 2.9e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442698, "epoch": 2.68494684, "global_step/max_steps": "2400/2679", "percentage": "89.59%", "elapsed_time": "1h 30m 17s", "remaining_time": "10m 29s"} |
| {"eval_loss": 0.26392549, "eval_token_acc": 0.90167581, "eval_runtime": 7.0963, "eval_samples_per_second": 15.219, "eval_steps_per_second": 2.537, "epoch": 2.68494684, "global_step/max_steps": "2400/2679", "percentage": "89.59%", "elapsed_time": "1h 30m 25s", "remaining_time": "10m 30s"} |
| {"loss": 0.1815276, "token_acc": 0.94168777, "grad_norm": 1.10611318, "learning_rate": 2.8e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442089, "epoch": 2.69054281, "global_step/max_steps": "2405/2679", "percentage": "89.77%", "elapsed_time": "1h 30m 36s", "remaining_time": "10m 19s"} |
| {"loss": 0.1682732, "token_acc": 0.93883848, "grad_norm": 1.35050601, "learning_rate": 2.7e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442097, "epoch": 2.69613878, "global_step/max_steps": "2410/2679", "percentage": "89.96%", "elapsed_time": "1h 30m 47s", "remaining_time": "10m 8s"} |
| {"loss": 0.16080225, "token_acc": 0.9369645, "grad_norm": 1.21568005, "learning_rate": 2.6e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442113, "epoch": 2.70173475, "global_step/max_steps": "2415/2679", "percentage": "90.15%", "elapsed_time": "1h 30m 59s", "remaining_time": "9m 56s"} |
| {"loss": 0.15746282, "token_acc": 0.94427915, "grad_norm": 1.37953646, "learning_rate": 2.5e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442144, "epoch": 2.70733072, "global_step/max_steps": "2420/2679", "percentage": "90.33%", "elapsed_time": "1h 31m 9s", "remaining_time": "9m 45s"} |
| {"loss": 0.17066745, "token_acc": 0.92467091, "grad_norm": 1.22793674, "learning_rate": 2.4e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442176, "epoch": 2.71292669, "global_step/max_steps": "2425/2679", "percentage": "90.52%", "elapsed_time": "1h 31m 20s", "remaining_time": "9m 34s"} |
| {"loss": 0.17276361, "token_acc": 0.94611419, "grad_norm": 1.28782671, "learning_rate": 2.3e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442192, "epoch": 2.71852266, "global_step/max_steps": "2430/2679", "percentage": "90.71%", "elapsed_time": "1h 31m 31s", "remaining_time": "9m 22s"} |
| {"loss": 0.15462826, "token_acc": 0.91869919, "grad_norm": 1.26998361, "learning_rate": 2.3e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442223, "epoch": 2.72411863, "global_step/max_steps": "2435/2679", "percentage": "90.89%", "elapsed_time": "1h 31m 42s", "remaining_time": "9m 11s"} |
| {"loss": 0.16788282, "token_acc": 0.92868651, "grad_norm": 1.24201632, "learning_rate": 2.2e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442242, "epoch": 2.72971461, "global_step/max_steps": "2440/2679", "percentage": "91.08%", "elapsed_time": "1h 31m 53s", "remaining_time": "9m 0s"} |
| {"loss": 0.15652635, "token_acc": 0.92168323, "grad_norm": 1.23579484, "learning_rate": 2.1e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442267, "epoch": 2.73531058, "global_step/max_steps": "2445/2679", "percentage": "91.27%", "elapsed_time": "1h 32m 4s", "remaining_time": "8m 48s"} |
| {"loss": 0.17649339, "token_acc": 0.95203061, "grad_norm": 1.22222447, "learning_rate": 2e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442294, "epoch": 2.74090655, "global_step/max_steps": "2450/2679", "percentage": "91.45%", "elapsed_time": "1h 32m 15s", "remaining_time": "8m 37s"} |
| {"loss": 0.17051747, "token_acc": 0.95795388, "grad_norm": 1.22081634, "learning_rate": 1.9e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442301, "epoch": 2.74650252, "global_step/max_steps": "2455/2679", "percentage": "91.64%", "elapsed_time": "1h 32m 27s", "remaining_time": "8m 26s"} |
| {"loss": 0.15887477, "token_acc": 0.95137517, "grad_norm": 1.24389961, "learning_rate": 1.8e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.44232, "epoch": 2.75209849, "global_step/max_steps": "2460/2679", "percentage": "91.83%", "elapsed_time": "1h 32m 38s", "remaining_time": "8m 14s"} |
| {"loss": 0.14871559, "token_acc": 0.93847264, "grad_norm": 1.45937792, "learning_rate": 1.7e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442346, "epoch": 2.75769446, "global_step/max_steps": "2465/2679", "percentage": "92.01%", "elapsed_time": "1h 32m 49s", "remaining_time": "8m 3s"} |
| {"loss": 0.16535134, "token_acc": 0.94149954, "grad_norm": 1.25230817, "learning_rate": 1.7e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442358, "epoch": 2.76329043, "global_step/max_steps": "2470/2679", "percentage": "92.20%", "elapsed_time": "1h 33m 0s", "remaining_time": "7m 52s"} |
| {"loss": 0.15060313, "token_acc": 0.91942632, "grad_norm": 1.29740969, "learning_rate": 1.6e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442387, "epoch": 2.7688864, "global_step/max_steps": "2475/2679", "percentage": "92.39%", "elapsed_time": "1h 33m 11s", "remaining_time": "7m 40s"} |
| {"loss": 0.1718533, "token_acc": 0.92698322, "grad_norm": 1.16810634, "learning_rate": 1.5e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442423, "epoch": 2.77448237, "global_step/max_steps": "2480/2679", "percentage": "92.57%", "elapsed_time": "1h 33m 22s", "remaining_time": "7m 29s"} |
| {"loss": 0.18785089, "token_acc": 0.93242236, "grad_norm": 1.21538124, "learning_rate": 1.4e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442438, "epoch": 2.78007834, "global_step/max_steps": "2485/2679", "percentage": "92.76%", "elapsed_time": "1h 33m 33s", "remaining_time": "7m 18s"} |
| {"loss": 0.16023201, "token_acc": 0.93157702, "grad_norm": 1.2461684, "learning_rate": 1.4e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442464, "epoch": 2.78567431, "global_step/max_steps": "2490/2679", "percentage": "92.95%", "elapsed_time": "1h 33m 44s", "remaining_time": "7m 6s"} |
| {"loss": 0.14799857, "token_acc": 0.95732678, "grad_norm": 1.22283782, "learning_rate": 1.3e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.44249, "epoch": 2.79127029, "global_step/max_steps": "2495/2679", "percentage": "93.13%", "elapsed_time": "1h 33m 55s", "remaining_time": "6m 55s"} |
| {"loss": 0.20539317, "token_acc": 0.92286819, "grad_norm": 1.147499, "learning_rate": 1.2e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442523, "epoch": 2.79686626, "global_step/max_steps": "2500/2679", "percentage": "93.32%", "elapsed_time": "1h 34m 6s", "remaining_time": "6m 44s"} |
| {"loss": 0.18525865, "token_acc": 0.92442323, "grad_norm": 1.19018262, "learning_rate": 1.1e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442565, "epoch": 2.80246223, "global_step/max_steps": "2505/2679", "percentage": "93.51%", "elapsed_time": "1h 34m 16s", "remaining_time": "6m 32s"} |
| {"loss": 0.17220221, "token_acc": 0.93219686, "grad_norm": 1.30686781, "learning_rate": 1.1e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442586, "epoch": 2.8080582, "global_step/max_steps": "2510/2679", "percentage": "93.69%", "elapsed_time": "1h 34m 27s", "remaining_time": "6m 21s"} |
| {"loss": 0.16816769, "token_acc": 0.93583138, "grad_norm": 1.3368453, "learning_rate": 1e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442559, "epoch": 2.81365417, "global_step/max_steps": "2515/2679", "percentage": "93.88%", "elapsed_time": "1h 34m 39s", "remaining_time": "6m 10s"} |
| {"loss": 0.14555788, "token_acc": 0.94426327, "grad_norm": 1.15417772, "learning_rate": 1e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442593, "epoch": 2.81925014, "global_step/max_steps": "2520/2679", "percentage": "94.06%", "elapsed_time": "1h 34m 50s", "remaining_time": "5m 59s"} |
| {"loss": 0.15869925, "token_acc": 0.94099685, "grad_norm": 1.43307679, "learning_rate": 9e-08, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442606, "epoch": 2.82484611, "global_step/max_steps": "2525/2679", "percentage": "94.25%", "elapsed_time": "1h 35m 1s", "remaining_time": "5m 47s"} |
| {"loss": 0.16980503, "token_acc": 0.93390332, "grad_norm": 1.13201074, "learning_rate": 8e-08, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442626, "epoch": 2.83044208, "global_step/max_steps": "2530/2679", "percentage": "94.44%", "elapsed_time": "1h 35m 12s", "remaining_time": "5m 36s"} |
| {"loss": 0.16553295, "token_acc": 0.92041452, "grad_norm": 1.26664581, "learning_rate": 8e-08, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442626, "epoch": 2.83603805, "global_step/max_steps": "2535/2679", "percentage": "94.62%", "elapsed_time": "1h 35m 23s", "remaining_time": "5m 25s"} |
| {"loss": 0.17194555, "token_acc": 0.93642942, "grad_norm": 1.15236918, "learning_rate": 7e-08, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442576, "epoch": 2.84163402, "global_step/max_steps": "2540/2679", "percentage": "94.81%", "elapsed_time": "1h 35m 35s", "remaining_time": "5m 13s"} |
| {"loss": 0.16607561, "token_acc": 0.92838705, "grad_norm": 1.46970528, "learning_rate": 7e-08, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442603, "epoch": 2.84722999, "global_step/max_steps": "2545/2679", "percentage": "95.00%", "elapsed_time": "1h 35m 46s", "remaining_time": "5m 2s"} |
| {"loss": 0.14487417, "token_acc": 0.93286113, "grad_norm": 1.21427178, "learning_rate": 6e-08, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442628, "epoch": 2.85282597, "global_step/max_steps": "2550/2679", "percentage": "95.18%", "elapsed_time": "1h 35m 57s", "remaining_time": "4m 51s"} |
| {"loss": 0.16714262, "token_acc": 0.9251024, "grad_norm": 1.12487211, "learning_rate": 6e-08, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442651, "epoch": 2.85842194, "global_step/max_steps": "2555/2679", "percentage": "95.37%", "elapsed_time": "1h 36m 8s", "remaining_time": "4m 39s"} |
| {"loss": 0.16560882, "token_acc": 0.94222546, "grad_norm": 1.29994006, "learning_rate": 5e-08, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442683, "epoch": 2.86401791, "global_step/max_steps": "2560/2679", "percentage": "95.56%", "elapsed_time": "1h 36m 19s", "remaining_time": "4m 28s"} |
| {"loss": 0.17857795, "token_acc": 0.92386672, "grad_norm": 1.3514941, "learning_rate": 5e-08, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442669, "epoch": 2.86961388, "global_step/max_steps": "2565/2679", "percentage": "95.74%", "elapsed_time": "1h 36m 31s", "remaining_time": "4m 17s"} |
| {"loss": 0.16211841, "token_acc": 0.94589536, "grad_norm": 1.18522418, "learning_rate": 5e-08, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442613, "epoch": 2.87520985, "global_step/max_steps": "2570/2679", "percentage": "95.93%", "elapsed_time": "1h 36m 43s", "remaining_time": "4m 6s"} |
| {"loss": 0.20226593, "token_acc": 0.95256554, "grad_norm": 1.35983303, "learning_rate": 4e-08, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.44265, "epoch": 2.88080582, "global_step/max_steps": "2575/2679", "percentage": "96.12%", "elapsed_time": "1h 36m 53s", "remaining_time": "3m 54s"} |
| {"loss": 0.16548022, "token_acc": 0.92905934, "grad_norm": 1.14094479, "learning_rate": 4e-08, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.44268, "epoch": 2.88640179, "global_step/max_steps": "2580/2679", "percentage": "96.30%", "elapsed_time": "1h 37m 4s", "remaining_time": "3m 43s"} |
| {"loss": 0.17504165, "token_acc": 0.92791525, "grad_norm": 1.19324187, "learning_rate": 3e-08, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442692, "epoch": 2.89199776, "global_step/max_steps": "2585/2679", "percentage": "96.49%", "elapsed_time": "1h 37m 15s", "remaining_time": "3m 32s"} |
| {"loss": 0.12353342, "token_acc": 0.96318077, "grad_norm": 1.36187876, "learning_rate": 3e-08, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442715, "epoch": 2.89759373, "global_step/max_steps": "2590/2679", "percentage": "96.68%", "elapsed_time": "1h 37m 26s", "remaining_time": "3m 20s"} |
| {"loss": 0.17372788, "token_acc": 0.9584449, "grad_norm": 1.25548801, "learning_rate": 3e-08, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442728, "epoch": 2.9031897, "global_step/max_steps": "2595/2679", "percentage": "96.86%", "elapsed_time": "1h 37m 38s", "remaining_time": "3m 9s"} |
| {"loss": 0.14146466, "token_acc": 0.92270259, "grad_norm": 1.38427391, "learning_rate": 2e-08, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442769, "epoch": 2.90878567, "global_step/max_steps": "2600/2679", "percentage": "97.05%", "elapsed_time": "1h 37m 48s", "remaining_time": "2m 58s"} |
| {"eval_loss": 0.27052757, "eval_token_acc": 0.89954501, "eval_runtime": 6.9568, "eval_samples_per_second": 15.524, "eval_steps_per_second": 2.587, "epoch": 2.90878567, "global_step/max_steps": "2600/2679", "percentage": "97.05%", "elapsed_time": "1h 37m 55s", "remaining_time": "2m 58s"} |
| {"loss": 0.16337907, "token_acc": 0.92798152, "grad_norm": 1.16713106, "learning_rate": 2e-08, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442252, "epoch": 2.91438165, "global_step/max_steps": "2605/2679", "percentage": "97.24%", "elapsed_time": "1h 38m 6s", "remaining_time": "2m 47s"} |
| {"loss": 0.14915705, "token_acc": 0.93089145, "grad_norm": 1.30914562, "learning_rate": 2e-08, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.44227, "epoch": 2.91997762, "global_step/max_steps": "2610/2679", "percentage": "97.42%", "elapsed_time": "1h 38m 18s", "remaining_time": "2m 35s"} |
| {"loss": 0.16016901, "token_acc": 0.92600423, "grad_norm": 1.18513953, "learning_rate": 2e-08, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442296, "epoch": 2.92557359, "global_step/max_steps": "2615/2679", "percentage": "97.61%", "elapsed_time": "1h 38m 28s", "remaining_time": "2m 24s"} |
| {"loss": 0.15380819, "token_acc": 0.92095898, "grad_norm": 1.29447272, "learning_rate": 1e-08, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442322, "epoch": 2.93116956, "global_step/max_steps": "2620/2679", "percentage": "97.80%", "elapsed_time": "1h 38m 39s", "remaining_time": "2m 13s"} |
| {"loss": 0.15956333, "token_acc": 0.93549692, "grad_norm": 1.28820603, "learning_rate": 1e-08, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442314, "epoch": 2.93676553, "global_step/max_steps": "2625/2679", "percentage": "97.98%", "elapsed_time": "1h 38m 51s", "remaining_time": "2m 2s"} |
| {"loss": 0.15384411, "token_acc": 0.93980408, "grad_norm": 1.35278162, "learning_rate": 1e-08, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.44235, "epoch": 2.9423615, "global_step/max_steps": "2630/2679", "percentage": "98.17%", "elapsed_time": "1h 39m 2s", "remaining_time": "1m 50s"} |
| {"loss": 0.17564118, "token_acc": 0.94024471, "grad_norm": 1.18586829, "learning_rate": 1e-08, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442366, "epoch": 2.94795747, "global_step/max_steps": "2635/2679", "percentage": "98.36%", "elapsed_time": "1h 39m 13s", "remaining_time": "1m 39s"} |
| {"loss": 0.14418159, "token_acc": 0.95753589, "grad_norm": 1.25005964, "learning_rate": 1e-08, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442399, "epoch": 2.95355344, "global_step/max_steps": "2640/2679", "percentage": "98.54%", "elapsed_time": "1h 39m 24s", "remaining_time": "1m 28s"} |
| {"loss": 0.1636658, "token_acc": 0.91810308, "grad_norm": 1.45369825, "learning_rate": 0.0, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.4424, "epoch": 2.95914941, "global_step/max_steps": "2645/2679", "percentage": "98.73%", "elapsed_time": "1h 39m 35s", "remaining_time": "1m 16s"} |
| {"loss": 0.19950826, "token_acc": 0.90422469, "grad_norm": 1.34486929, "learning_rate": 0.0, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442399, "epoch": 2.96474538, "global_step/max_steps": "2650/2679", "percentage": "98.92%", "elapsed_time": "1h 39m 46s", "remaining_time": "1m 5s"} |
| {"loss": 0.15716251, "token_acc": 0.92965404, "grad_norm": 1.25896487, "learning_rate": 0.0, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442414, "epoch": 2.97034135, "global_step/max_steps": "2655/2679", "percentage": "99.10%", "elapsed_time": "1h 39m 57s", "remaining_time": "54s"} |
| {"loss": 0.15098288, "token_acc": 0.93120504, "grad_norm": 1.29966356, "learning_rate": 0.0, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442434, "epoch": 2.97593733, "global_step/max_steps": "2660/2679", "percentage": "99.29%", "elapsed_time": "1h 40m 8s", "remaining_time": "42s"} |
| {"loss": 0.1571296, "token_acc": 0.94081095, "grad_norm": 1.25671435, "learning_rate": 0.0, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442458, "epoch": 2.9815333, "global_step/max_steps": "2665/2679", "percentage": "99.48%", "elapsed_time": "1h 40m 19s", "remaining_time": "31s"} |
| {"loss": 0.16352346, "token_acc": 0.93164848, "grad_norm": 1.34273807, "learning_rate": 0.0, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442502, "epoch": 2.98712927, "global_step/max_steps": "2670/2679", "percentage": "99.66%", "elapsed_time": "1h 40m 30s", "remaining_time": "20s"} |
| {"loss": 0.16283302, "token_acc": 0.9286033, "grad_norm": 1.23357848, "learning_rate": 0.0, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.44253, "epoch": 2.99272524, "global_step/max_steps": "2675/2679", "percentage": "99.85%", "elapsed_time": "1h 40m 41s", "remaining_time": "9s"} |
| {"eval_loss": 0.26521888, "eval_token_acc": 0.90024022, "eval_runtime": 6.9203, "eval_samples_per_second": 15.606, "eval_steps_per_second": 2.601, "epoch": 2.99720201, "global_step/max_steps": "2679/2679", "percentage": "100.00%", "elapsed_time": "1h 40m 57s", "remaining_time": "0s"} |
| {"train_runtime": 6064.6686, "train_samples_per_second": 5.306, "train_steps_per_second": 0.442, "total_flos": 9.423481207154278e+17, "train_loss": 0.23683785, "epoch": 2.99720201, "global_step/max_steps": "2679/2679", "percentage": "100.00%", "elapsed_time": "1h 41m 4s", "remaining_time": "0s"} |
| {"model_parameter_info": "InternVLChatModel: 2088.9574M Params (1776.2831M Trainable [85.0320%]), 0.0001M Buffers.", "last_model_checkpoint": "/workspace/shinannan/R1-Multimodal-Journey-main/ms-swift-main/examples/train/full/output/InternVL3-2B-10834/v0-20250817-213019/checkpoint-2679", "best_model_checkpoint": null, "best_metric": 0.26367784, "global_step": 2679, "log_history": [{"loss": 0.6288659572601318, "token_acc": 0.7923510089160019, "grad_norm": 5.164650516332692, "learning_rate": 7.462686567164179e-08, "memory(GiB)": 20.13, "train_speed(iter/s)": 0.05631, "epoch": 0.001119194180190263, "step": 1}, {"loss": 0.6838967204093933, "token_acc": 0.7959306404730881, "grad_norm": 5.074140964945667, "learning_rate": 3.7313432835820895e-07, "memory(GiB)": 20.13, "train_speed(iter/s)": 0.186614, "epoch": 0.005595970900951315, "step": 5}, {"loss": 0.6330761909484863, "token_acc": 0.8204408135477832, "grad_norm": 4.6416361883916295, "learning_rate": 7.462686567164179e-07, "memory(GiB)": 36.34, "train_speed(iter/s)": 0.263435, "epoch": 0.01119194180190263, "step": 10}, {"loss": 0.6304532527923584, "token_acc": 0.8218135314536265, "grad_norm": 4.463406766403146, "learning_rate": 1.119402985074627e-06, "memory(GiB)": 47.65, "train_speed(iter/s)": 0.305451, "epoch": 0.016787912702853944, "step": 15}, {"loss": 0.6030900478363037, "token_acc": 0.8232171544317943, "grad_norm": 3.267272184194903, "learning_rate": 1.4925373134328358e-06, "memory(GiB)": 47.65, "train_speed(iter/s)": 0.332742, "epoch": 0.02238388360380526, "step": 20}, {"loss": 0.5528721809387207, "token_acc": 0.8158064219339406, "grad_norm": 2.5557708868369056, "learning_rate": 1.865671641791045e-06, "memory(GiB)": 47.65, "train_speed(iter/s)": 0.34915, "epoch": 0.027979854504756575, "step": 25}, {"loss": 0.47245287895202637, "token_acc": 0.8561354019746121, "grad_norm": 2.3516407718427175, "learning_rate": 2.238805970149254e-06, "memory(GiB)": 60.63, "train_speed(iter/s)": 0.362678, "epoch": 0.03357582540570789, "step": 30}, {"loss": 0.47035989761352537, "token_acc": 0.837997317836388, "grad_norm": 2.17185396933361, "learning_rate": 2.6119402985074627e-06, "memory(GiB)": 60.63, "train_speed(iter/s)": 0.374036, "epoch": 0.03917179630665921, "step": 35}, {"loss": 0.43998088836669924, "token_acc": 0.86375, "grad_norm": 1.847286094718277, "learning_rate": 2.9850746268656716e-06, "memory(GiB)": 60.63, "train_speed(iter/s)": 0.382317, "epoch": 0.04476776720761052, "step": 40}, {"loss": 0.4199844837188721, "token_acc": 0.870186745992398, "grad_norm": 1.633195215883347, "learning_rate": 3.3582089552238813e-06, "memory(GiB)": 60.63, "train_speed(iter/s)": 0.389981, "epoch": 0.05036373810856184, "step": 45}, {"loss": 0.4131132125854492, "token_acc": 0.8647862099843295, "grad_norm": 1.6001955634871525, "learning_rate": 3.73134328358209e-06, "memory(GiB)": 60.63, "train_speed(iter/s)": 0.39553, "epoch": 0.05595970900951315, "step": 50}, {"loss": 0.38757426738739015, "token_acc": 0.8864997545409916, "grad_norm": 1.4395320297243612, "learning_rate": 4.104477611940299e-06, "memory(GiB)": 60.63, "train_speed(iter/s)": 0.399908, "epoch": 0.06155567991046446, "step": 55}, {"loss": 0.36163508892059326, "token_acc": 0.8641994917407878, "grad_norm": 1.6008336224975677, "learning_rate": 4.477611940298508e-06, "memory(GiB)": 60.63, "train_speed(iter/s)": 0.404673, "epoch": 0.06715165081141578, "step": 60}, {"loss": 0.3611295700073242, "token_acc": 0.8698647399815173, "grad_norm": 1.4799587693991787, "learning_rate": 4.850746268656717e-06, "memory(GiB)": 60.63, "train_speed(iter/s)": 0.407667, "epoch": 0.0727476217123671, "step": 65}, {"loss": 0.36722731590270996, "token_acc": 0.8833816425120773, "grad_norm": 1.5714923820277997, "learning_rate": 5.2238805970149255e-06, "memory(GiB)": 60.63, "train_speed(iter/s)": 0.410585, "epoch": 0.07834359261331841, "step": 70}, {"loss": 0.37027692794799805, "token_acc": 0.8807967005331455, "grad_norm": 1.5438156564558942, "learning_rate": 5.597014925373134e-06, "memory(GiB)": 60.63, "train_speed(iter/s)": 0.41383, "epoch": 0.08393956351426973, "step": 75}, {"loss": 0.36136507987976074, "token_acc": 0.8700393624572498, "grad_norm": 1.2484571745664468, "learning_rate": 5.970149253731343e-06, "memory(GiB)": 60.63, "train_speed(iter/s)": 0.415453, "epoch": 0.08953553441522104, "step": 80}, {"loss": 0.39811656475067136, "token_acc": 0.869264135149532, "grad_norm": 1.481819133035609, "learning_rate": 6.343283582089553e-06, "memory(GiB)": 60.63, "train_speed(iter/s)": 0.417038, "epoch": 0.09513150531617236, "step": 85}, {"loss": 0.3875593900680542, "token_acc": 0.8651825328870554, "grad_norm": 1.6688988938363702, "learning_rate": 6.7164179104477625e-06, "memory(GiB)": 60.63, "train_speed(iter/s)": 0.419293, "epoch": 0.10072747621712368, "step": 90}, {"loss": 0.38646845817565917, "token_acc": 0.8667263503431811, "grad_norm": 1.4128881046310209, "learning_rate": 7.089552238805971e-06, "memory(GiB)": 60.63, "train_speed(iter/s)": 0.421241, "epoch": 0.10632344711807498, "step": 95}, {"loss": 0.3452910900115967, "token_acc": 0.8773694110837795, "grad_norm": 1.4894482509691387, "learning_rate": 7.46268656716418e-06, "memory(GiB)": 60.63, "train_speed(iter/s)": 0.421626, "epoch": 0.1119194180190263, "step": 100}, {"loss": 0.32161517143249513, "token_acc": 0.8953816131830009, "grad_norm": 1.6273281051245854, "learning_rate": 7.835820895522389e-06, "memory(GiB)": 60.63, "train_speed(iter/s)": 0.423347, "epoch": 0.11751538891997762, "step": 105}, {"loss": 0.37918944358825685, "token_acc": 0.8600061989874987, "grad_norm": 1.382419643913791, "learning_rate": 8.208955223880599e-06, "memory(GiB)": 60.63, "train_speed(iter/s)": 0.424564, "epoch": 0.12311135982092893, "step": 110}, {"loss": 0.34900507926940916, "token_acc": 0.8859086643728495, "grad_norm": 1.680949474538314, "learning_rate": 8.582089552238807e-06, "memory(GiB)": 60.63, "train_speed(iter/s)": 0.425465, "epoch": 0.12870733072188026, "step": 115}, {"loss": 0.35255160331726076, "token_acc": 0.8789230524135734, "grad_norm": 1.3929136056362328, "learning_rate": 8.955223880597016e-06, "memory(GiB)": 60.63, "train_speed(iter/s)": 0.426128, "epoch": 0.13430330162283155, "step": 120}, {"loss": 0.3469428062438965, "token_acc": 0.872209344882274, "grad_norm": 1.4562974748013175, "learning_rate": 9.328358208955226e-06, "memory(GiB)": 60.63, "train_speed(iter/s)": 0.42724, "epoch": 0.13989927252378287, "step": 125}, {"loss": 0.34943225383758547, "token_acc": 0.8839652257908718, "grad_norm": 1.5694217424160566, "learning_rate": 9.701492537313434e-06, "memory(GiB)": 60.63, "train_speed(iter/s)": 0.428067, "epoch": 0.1454952434247342, "step": 130}, {"loss": 0.3448803424835205, "token_acc": 0.8600499281337469, "grad_norm": 1.7431313401065875, "learning_rate": 9.999996190533792e-06, "memory(GiB)": 60.63, "train_speed(iter/s)": 0.428777, "epoch": 0.1510912143256855, "step": 135}, {"loss": 0.37110326290130613, "token_acc": 0.8688445600848029, "grad_norm": 1.6494726185182529, "learning_rate": 9.999862859825998e-06, "memory(GiB)": 60.63, "train_speed(iter/s)": 0.429568, "epoch": 0.15668718522663683, "step": 140}, {"loss": 0.3633245944976807, "token_acc": 0.8601999504255143, "grad_norm": 1.6355250167646298, "learning_rate": 9.999539061612546e-06, "memory(GiB)": 60.63, "train_speed(iter/s)": 0.430153, "epoch": 0.16228315612758815, "step": 145}, {"loss": 0.32439365386962893, "token_acc": 0.887977369165488, "grad_norm": 1.646233006498336, "learning_rate": 9.999024808228385e-06, "memory(GiB)": 60.63, "train_speed(iter/s)": 0.430915, "epoch": 0.16787912702853947, "step": 150}, {"loss": 0.34078292846679686, "token_acc": 0.8847544441096716, "grad_norm": 1.3250586996140854, "learning_rate": 9.998320119263767e-06, "memory(GiB)": 60.63, "train_speed(iter/s)": 0.431242, "epoch": 0.17347509792949076, "step": 155}, {"loss": 0.3333411931991577, "token_acc": 0.878690333854502, "grad_norm": 1.3767975341682235, "learning_rate": 9.997425021563492e-06, "memory(GiB)": 60.63, "train_speed(iter/s)": 0.431984, "epoch": 0.17907106883044208, "step": 160}, {"loss": 0.3438950300216675, "token_acc": 0.9045189504373178, "grad_norm": 1.6068526964616547, "learning_rate": 9.996339549225905e-06, "memory(GiB)": 60.63, "train_speed(iter/s)": 0.432638, "epoch": 0.1846670397313934, "step": 165}, {"loss": 0.3308399200439453, "token_acc": 0.8731382147692949, "grad_norm": 1.4461446157676034, "learning_rate": 9.99506374360158e-06, "memory(GiB)": 60.63, "train_speed(iter/s)": 0.433378, "epoch": 0.19026301063234471, "step": 170}, {"loss": 0.3624176740646362, "token_acc": 0.8592276895260235, "grad_norm": 1.7656512825794386, "learning_rate": 9.993597653291756e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.433466, "epoch": 0.19585898153329603, "step": 175}, {"loss": 0.3295997142791748, "token_acc": 0.872310570626754, "grad_norm": 1.6347757944943615, "learning_rate": 9.991941334146472e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.434039, "epoch": 0.20145495243424735, "step": 180}, {"loss": 0.31329002380371096, "token_acc": 0.8638476533213375, "grad_norm": 1.3351221973017842, "learning_rate": 9.99009484926246e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.434381, "epoch": 0.20705092333519864, "step": 185}, {"loss": 0.3390720129013062, "token_acc": 0.8828090869375274, "grad_norm": 1.5412873617507667, "learning_rate": 9.988058268980718e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.434814, "epoch": 0.21264689423614996, "step": 190}, {"loss": 0.34030852317810056, "token_acc": 0.8777596322506502, "grad_norm": 1.377015376381531, "learning_rate": 9.98583167088385e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.435029, "epoch": 0.21824286513710128, "step": 195}, {"loss": 0.32567343711853025, "token_acc": 0.8620039545684463, "grad_norm": 1.4412053219289966, "learning_rate": 9.9834151397931e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.435215, "epoch": 0.2238388360380526, "step": 200}, {"eval_loss": 0.33167222142219543, "eval_token_acc": 0.8766353472882968, "eval_runtime": 7.2132, "eval_samples_per_second": 14.973, "eval_steps_per_second": 2.495, "epoch": 0.2238388360380526, "step": 200}, {"loss": 0.33215861320495604, "token_acc": 0.8750806451612904, "grad_norm": 1.4840083612996842, "learning_rate": 9.980808767765122e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.428914, "epoch": 0.22943480693900392, "step": 205}, {"loss": 0.33353843688964846, "token_acc": 0.8921634293369055, "grad_norm": 1.4736071546402154, "learning_rate": 9.978012654088476e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.429533, "epoch": 0.23503077783995524, "step": 210}, {"loss": 0.3203137874603271, "token_acc": 0.8668329177057357, "grad_norm": 1.2872368388850022, "learning_rate": 9.975026905279842e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.430139, "epoch": 0.24062674874090656, "step": 215}, {"loss": 0.34436259269714353, "token_acc": 0.8826526486049333, "grad_norm": 1.5395163259156714, "learning_rate": 9.971851635079965e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.430589, "epoch": 0.24622271964185785, "step": 220}, {"loss": 0.3261665105819702, "token_acc": 0.8995698522536002, "grad_norm": 1.449845968715276, "learning_rate": 9.968486964449321e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.431069, "epoch": 0.2518186905428092, "step": 225}, {"loss": 0.35327906608581544, "token_acc": 0.861946330423537, "grad_norm": 1.4968903234054471, "learning_rate": 9.964933021563513e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.431666, "epoch": 0.2574146614437605, "step": 230}, {"loss": 0.3224783420562744, "token_acc": 0.8844088055072244, "grad_norm": 1.4516249527601746, "learning_rate": 9.961189941808379e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.432177, "epoch": 0.2630106323447118, "step": 235}, {"loss": 0.3423969268798828, "token_acc": 0.8838988946432712, "grad_norm": 1.4403516755894605, "learning_rate": 9.957257867774844e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.432663, "epoch": 0.2686066032456631, "step": 240}, {"loss": 0.31796870231628416, "token_acc": 0.8951038684577552, "grad_norm": 1.3289215279475945, "learning_rate": 9.953136949253483e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.43251, "epoch": 0.2742025741466144, "step": 245}, {"loss": 0.34756717681884763, "token_acc": 0.8748805038519935, "grad_norm": 1.4042487351871165, "learning_rate": 9.948827343228817e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.432616, "epoch": 0.27979854504756574, "step": 250}, {"loss": 0.3106792449951172, "token_acc": 0.8682758620689656, "grad_norm": 1.2344578958809012, "learning_rate": 9.944329213873329e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.432875, "epoch": 0.28539451594851706, "step": 255}, {"loss": 0.34387898445129395, "token_acc": 0.8737539766702015, "grad_norm": 1.4378554713145135, "learning_rate": 9.939642732541215e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.432668, "epoch": 0.2909904868494684, "step": 260}, {"loss": 0.32631022930145265, "token_acc": 0.8958040730337079, "grad_norm": 1.48587271650264, "learning_rate": 9.934768077761856e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.432971, "epoch": 0.2965864577504197, "step": 265}, {"loss": 0.32596919536590574, "token_acc": 0.8650042028579434, "grad_norm": 1.4649046349906265, "learning_rate": 9.92970543523301e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.433333, "epoch": 0.302182428651371, "step": 270}, {"loss": 0.32187819480895996, "token_acc": 0.8864547154688752, "grad_norm": 1.3703608800446863, "learning_rate": 9.924454997813747e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.433685, "epoch": 0.30777839955232233, "step": 275}, {"loss": 0.3592820644378662, "token_acc": 0.8470501077586207, "grad_norm": 1.4631770203727088, "learning_rate": 9.919016965517095e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.433804, "epoch": 0.31337437045327365, "step": 280}, {"loss": 0.34660048484802247, "token_acc": 0.890639589169001, "grad_norm": 1.4130519168265454, "learning_rate": 9.913391545502426e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.434237, "epoch": 0.318970341354225, "step": 285}, {"loss": 0.3402921438217163, "token_acc": 0.861886125489206, "grad_norm": 1.3391319433579545, "learning_rate": 9.907578952067565e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.434574, "epoch": 0.3245663122551763, "step": 290}, {"loss": 0.3294564723968506, "token_acc": 0.8687799043062201, "grad_norm": 1.5505517638822532, "learning_rate": 9.901579406640616e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.434805, "epoch": 0.3301622831561276, "step": 295}, {"loss": 0.3197826385498047, "token_acc": 0.8748271092669433, "grad_norm": 1.4952319330001402, "learning_rate": 9.895393137771538e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.4352, "epoch": 0.33575825405707893, "step": 300}, {"loss": 0.29167900085449217, "token_acc": 0.8764111266878182, "grad_norm": 1.3831734236900424, "learning_rate": 9.889020381123436e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.435369, "epoch": 0.3413542249580302, "step": 305}, {"loss": 0.3053152561187744, "token_acc": 0.8763576263182749, "grad_norm": 1.464652957178571, "learning_rate": 9.882461379463583e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.435737, "epoch": 0.3469501958589815, "step": 310}, {"loss": 0.3119038581848145, "token_acc": 0.8826527278667102, "grad_norm": 1.5037168892767538, "learning_rate": 9.875716382654167e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.436009, "epoch": 0.35254616675993283, "step": 315}, {"loss": 0.33403193950653076, "token_acc": 0.8776218820861678, "grad_norm": 1.3897304995758166, "learning_rate": 9.86878564764278e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.436297, "epoch": 0.35814213766088415, "step": 320}, {"loss": 0.33297195434570315, "token_acc": 0.8395671920919049, "grad_norm": 1.3057535262965767, "learning_rate": 9.861669438452625e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.436454, "epoch": 0.36373810856183547, "step": 325}, {"loss": 0.2970301389694214, "token_acc": 0.8724551705541324, "grad_norm": 1.2472601334437117, "learning_rate": 9.854368026172463e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.436574, "epoch": 0.3693340794627868, "step": 330}, {"loss": 0.2859848737716675, "token_acc": 0.8917525773195877, "grad_norm": 1.3612221203615535, "learning_rate": 9.846881688946274e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.436805, "epoch": 0.3749300503637381, "step": 335}, {"loss": 0.31956565380096436, "token_acc": 0.8891982182628062, "grad_norm": 1.3737205792759508, "learning_rate": 9.839210711962683e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.436964, "epoch": 0.38052602126468943, "step": 340}, {"loss": 0.32744243144989016, "token_acc": 0.8870775821037601, "grad_norm": 1.506637399060771, "learning_rate": 9.83135538744407e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.43725, "epoch": 0.38612199216564075, "step": 345}, {"loss": 0.30742359161376953, "token_acc": 0.8724678527391228, "grad_norm": 1.5285064810134161, "learning_rate": 9.823316014635459e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.437467, "epoch": 0.39171796306659207, "step": 350}, {"loss": 0.3286896705627441, "token_acc": 0.872442929143196, "grad_norm": 1.3633676378987347, "learning_rate": 9.815092899793107e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.437632, "epoch": 0.3973139339675434, "step": 355}, {"loss": 0.3250423908233643, "token_acc": 0.8794072143962218, "grad_norm": 1.3335038948150217, "learning_rate": 9.806686356172837e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.437831, "epoch": 0.4029099048684947, "step": 360}, {"loss": 0.34006173610687257, "token_acc": 0.8748522342186146, "grad_norm": 1.2329509220181991, "learning_rate": 9.798096704018117e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.437909, "epoch": 0.408505875769446, "step": 365}, {"loss": 0.29794697761535643, "token_acc": 0.8918630366811561, "grad_norm": 1.5850390606141938, "learning_rate": 9.789324270547841e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.437933, "epoch": 0.4141018466703973, "step": 370}, {"loss": 0.3013563632965088, "token_acc": 0.8884396250689212, "grad_norm": 1.2214505990612532, "learning_rate": 9.780369389943885e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.438112, "epoch": 0.4196978175713486, "step": 375}, {"loss": 0.30278620719909666, "token_acc": 0.8983416628805089, "grad_norm": 1.2126588169180585, "learning_rate": 9.771232403338356e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.438308, "epoch": 0.4252937884722999, "step": 380}, {"loss": 0.31080145835876466, "token_acc": 0.8811671087533156, "grad_norm": 1.2480113049509336, "learning_rate": 9.761913658800608e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.438551, "epoch": 0.43088975937325125, "step": 385}, {"loss": 0.30190391540527345, "token_acc": 0.8755247691015953, "grad_norm": 1.4745969279384732, "learning_rate": 9.752413511323989e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.438709, "epoch": 0.43648573027420257, "step": 390}, {"loss": 0.2965328931808472, "token_acc": 0.8871211241435374, "grad_norm": 1.3454129818991207, "learning_rate": 9.742732322812301e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.4389, "epoch": 0.4420817011751539, "step": 395}, {"loss": 0.28368549346923827, "token_acc": 0.9217436974789915, "grad_norm": 1.3229095654906426, "learning_rate": 9.732870462066026e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.438943, "epoch": 0.4476776720761052, "step": 400}, {"eval_loss": 0.3092662990093231, "eval_token_acc": 0.8825612682713985, "eval_runtime": 6.9665, "eval_samples_per_second": 15.503, "eval_steps_per_second": 2.584, "epoch": 0.4476776720761052, "step": 400}, {"loss": 0.3045057773590088, "token_acc": 0.901119252757871, "grad_norm": 1.5287346624969789, "learning_rate": 9.72282830476827e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.435736, "epoch": 0.4532736429770565, "step": 405}, {"loss": 0.29214427471160886, "token_acc": 0.9052513739059638, "grad_norm": 1.224867611079956, "learning_rate": 9.712606233470458e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.435701, "epoch": 0.45886961387800784, "step": 410}, {"loss": 0.29977681636810305, "token_acc": 0.889289814662949, "grad_norm": 1.4419705420525581, "learning_rate": 9.702204637577755e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.43594, "epoch": 0.46446558477895916, "step": 415}, {"loss": 0.3212217092514038, "token_acc": 0.8999187798935114, "grad_norm": 1.436603582117861, "learning_rate": 9.691623913334233e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.436145, "epoch": 0.4700615556799105, "step": 420}, {"loss": 0.33009185791015627, "token_acc": 0.8841954844241212, "grad_norm": 1.3801418005261523, "learning_rate": 9.680864463807778e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.4362, "epoch": 0.4756575265808618, "step": 425}, {"loss": 0.30348739624023435, "token_acc": 0.8896958070704303, "grad_norm": 1.4049670651602044, "learning_rate": 9.669926698874736e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.43639, "epoch": 0.4812534974818131, "step": 430}, {"loss": 0.3114774227142334, "token_acc": 0.8878697007114718, "grad_norm": 1.3942407491582895, "learning_rate": 9.658811035204297e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.436681, "epoch": 0.4868494683827644, "step": 435}, {"loss": 0.2918144941329956, "token_acc": 0.8804817994276968, "grad_norm": 1.3237093688587047, "learning_rate": 9.647517896242619e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.436873, "epoch": 0.4924454392837157, "step": 440}, {"loss": 0.3175345420837402, "token_acc": 0.8880962087240114, "grad_norm": 1.348283058850507, "learning_rate": 9.636047712196706e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.437019, "epoch": 0.498041410184667, "step": 445}, {"loss": 0.33033390045166017, "token_acc": 0.8910170625627301, "grad_norm": 1.1722563030288886, "learning_rate": 9.624400920018011e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.437217, "epoch": 0.5036373810856184, "step": 450}, {"loss": 0.30872654914855957, "token_acc": 0.9122999042276645, "grad_norm": 1.159508369060584, "learning_rate": 9.612577963385795e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.437445, "epoch": 0.5092333519865697, "step": 455}, {"loss": 0.3123885154724121, "token_acc": 0.8880212064765726, "grad_norm": 1.2400253012480726, "learning_rate": 9.600579292690219e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.437333, "epoch": 0.514829322887521, "step": 460}, {"loss": 0.32456111907958984, "token_acc": 0.8953193033381712, "grad_norm": 1.3594605142473937, "learning_rate": 9.588405365015203e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.437433, "epoch": 0.5204252937884724, "step": 465}, {"loss": 0.27809226512908936, "token_acc": 0.8954788121454789, "grad_norm": 1.3621379950694508, "learning_rate": 9.576056644120988e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.437616, "epoch": 0.5260212646894236, "step": 470}, {"loss": 0.29432024955749514, "token_acc": 0.9025830839502283, "grad_norm": 1.4149778650740406, "learning_rate": 9.563533600426494e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.437602, "epoch": 0.5316172355903749, "step": 475}, {"loss": 0.3068323850631714, "token_acc": 0.8856636026447348, "grad_norm": 1.3939803977311342, "learning_rate": 9.550836710991384e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.437622, "epoch": 0.5372132064913262, "step": 480}, {"loss": 0.28441197872161866, "token_acc": 0.894668259311543, "grad_norm": 1.3470961852354226, "learning_rate": 9.537966459497896e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.43775, "epoch": 0.5428091773922775, "step": 485}, {"loss": 0.3108638286590576, "token_acc": 0.8809775895535557, "grad_norm": 1.299840873523769, "learning_rate": 9.524923336232417e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.437894, "epoch": 0.5484051482932288, "step": 490}, {"loss": 0.3052086591720581, "token_acc": 0.9156809220503488, "grad_norm": 1.2682978849360043, "learning_rate": 9.511707838066805e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.438015, "epoch": 0.5540011191941802, "step": 495}, {"loss": 0.30751404762268064, "token_acc": 0.9094857368473004, "grad_norm": 1.3131842784404666, "learning_rate": 9.498320468439467e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.438086, "epoch": 0.5595970900951315, "step": 500}, {"loss": 0.2836303234100342, "token_acc": 0.9089347079037801, "grad_norm": 1.3091242462394421, "learning_rate": 9.484761737336168e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.438191, "epoch": 0.5651930609960828, "step": 505}, {"loss": 0.3227206230163574, "token_acc": 0.8567478702735017, "grad_norm": 1.3438835822092943, "learning_rate": 9.471032161270613e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.438392, "epoch": 0.5707890318970341, "step": 510}, {"loss": 0.2989072799682617, "token_acc": 0.8990046127700898, "grad_norm": 1.2958270881723681, "learning_rate": 9.45713226326477e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.438591, "epoch": 0.5763850027979854, "step": 515}, {"loss": 0.2774073362350464, "token_acc": 0.9048120828942747, "grad_norm": 1.2673506344824543, "learning_rate": 9.443062572828943e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.438791, "epoch": 0.5819809736989368, "step": 520}, {"loss": 0.32281246185302737, "token_acc": 0.8720700197829866, "grad_norm": 1.2176745882164097, "learning_rate": 9.428823625941598e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.438878, "epoch": 0.5875769445998881, "step": 525}, {"loss": 0.29692304134368896, "token_acc": 0.8962465344423118, "grad_norm": 1.4562038331931093, "learning_rate": 9.414415965028959e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.439094, "epoch": 0.5931729155008394, "step": 530}, {"loss": 0.30197906494140625, "token_acc": 0.9131446297014346, "grad_norm": 1.2482574733152159, "learning_rate": 9.39984013894432e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.439146, "epoch": 0.5987688864017907, "step": 535}, {"loss": 0.2776437282562256, "token_acc": 0.884635622204683, "grad_norm": 1.5242760595275333, "learning_rate": 9.385096702947163e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.439252, "epoch": 0.604364857302742, "step": 540}, {"loss": 0.32024946212768557, "token_acc": 0.8994426564094513, "grad_norm": 1.3011129001488415, "learning_rate": 9.370186218681986e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.4393, "epoch": 0.6099608282036934, "step": 545}, {"loss": 0.2718887090682983, "token_acc": 0.8605458787780129, "grad_norm": 1.1312301264797526, "learning_rate": 9.355109254156919e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.439451, "epoch": 0.6155567991046447, "step": 550}, {"loss": 0.2612948417663574, "token_acc": 0.9111170544708924, "grad_norm": 1.232540240222553, "learning_rate": 9.33986638372208e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.439623, "epoch": 0.621152770005596, "step": 555}, {"loss": 0.3251943111419678, "token_acc": 0.8738261801222663, "grad_norm": 1.1813959855507368, "learning_rate": 9.324458188047698e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.439747, "epoch": 0.6267487409065473, "step": 560}, {"loss": 0.29087398052215574, "token_acc": 0.9097278361627593, "grad_norm": 1.2245210086010445, "learning_rate": 9.308885254101992e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.439918, "epoch": 0.6323447118074986, "step": 565}, {"loss": 0.29872593879699705, "token_acc": 0.9002836569932359, "grad_norm": 1.3690831618860975, "learning_rate": 9.293148175128807e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.439995, "epoch": 0.63794068270845, "step": 570}, {"loss": 0.26016716957092284, "token_acc": 0.9074767354797304, "grad_norm": 1.3306803236593558, "learning_rate": 9.277247550625028e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.440027, "epoch": 0.6435366536094013, "step": 575}, {"loss": 0.31593778133392336, "token_acc": 0.8831472344845495, "grad_norm": 1.2861966269335297, "learning_rate": 9.261183986317721e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.440197, "epoch": 0.6491326245103526, "step": 580}, {"loss": 0.29399905204772947, "token_acc": 0.8909469530907497, "grad_norm": 1.1399057615388977, "learning_rate": 9.244958094141079e-06, "memory(GiB)": 73.92, "train_speed(iter/s)": 0.440402, "epoch": 0.6547285954113039, "step": 585}, {"loss": 0.32216219902038573, "token_acc": 0.8667805294619982, "grad_norm": 1.4435630899400433, "learning_rate": 9.228570492213093e-06, "memory(GiB)": 74.34, "train_speed(iter/s)": 0.440311, "epoch": 0.6603245663122552, "step": 590}, {"loss": 0.28130388259887695, "token_acc": 0.8738551477752518, "grad_norm": 1.200224839394651, "learning_rate": 9.212021804812024e-06, "memory(GiB)": 74.34, "train_speed(iter/s)": 0.440357, "epoch": 0.6659205372132065, "step": 595}, {"loss": 0.27870941162109375, "token_acc": 0.8820331268175496, "grad_norm": 1.4752209142131925, "learning_rate": 9.195312662352603e-06, "memory(GiB)": 74.34, "train_speed(iter/s)": 0.440536, "epoch": 0.6715165081141579, "step": 600}, {"eval_loss": 0.29483041167259216, "eval_token_acc": 0.8872909009476551, "eval_runtime": 7.0603, "eval_samples_per_second": 15.297, "eval_steps_per_second": 2.549, "epoch": 0.6715165081141579, "step": 600}, {"loss": 0.2865235090255737, "token_acc": 0.9177679882525698, "grad_norm": 1.3045832210527604, "learning_rate": 9.178443701362023e-06, "memory(GiB)": 74.34, "train_speed(iter/s)": 0.438257, "epoch": 0.6771124790151091, "step": 605}, {"loss": 0.2902667999267578, "token_acc": 0.9014307228915662, "grad_norm": 1.2692406271141943, "learning_rate": 9.161415564455698e-06, "memory(GiB)": 74.34, "train_speed(iter/s)": 0.438378, "epoch": 0.6827084499160604, "step": 610}, {"loss": 0.2846663951873779, "token_acc": 0.8956144358154409, "grad_norm": 1.3781900263699522, "learning_rate": 9.144228900312771e-06, "memory(GiB)": 74.34, "train_speed(iter/s)": 0.438524, "epoch": 0.6883044208170117, "step": 615}, {"loss": 0.28765048980712893, "token_acc": 0.8939784197702749, "grad_norm": 1.354438633478074, "learning_rate": 9.126884363651409e-06, "memory(GiB)": 74.34, "train_speed(iter/s)": 0.438652, "epoch": 0.693900391717963, "step": 620}, {"loss": 0.2981544494628906, "token_acc": 0.898406204721725, "grad_norm": 1.1389895119943678, "learning_rate": 9.109382615203864e-06, "memory(GiB)": 74.34, "train_speed(iter/s)": 0.438809, "epoch": 0.6994963626189143, "step": 625}, {"loss": 0.28049933910369873, "token_acc": 0.8890164223909589, "grad_norm": 1.1952754616766899, "learning_rate": 9.091724321691293e-06, "memory(GiB)": 74.34, "train_speed(iter/s)": 0.438978, "epoch": 0.7050923335198657, "step": 630}, {"loss": 0.2682738065719604, "token_acc": 0.9076856085347268, "grad_norm": 1.1759645692509355, "learning_rate": 9.073910155798374e-06, "memory(GiB)": 74.34, "train_speed(iter/s)": 0.439114, "epoch": 0.710688304420817, "step": 635}, {"loss": 0.2881427526473999, "token_acc": 0.9060787040824675, "grad_norm": 1.2425009914834975, "learning_rate": 9.055940796147668e-06, "memory(GiB)": 74.34, "train_speed(iter/s)": 0.439243, "epoch": 0.7162842753217683, "step": 640}, {"loss": 0.26821465492248536, "token_acc": 0.8946739274804091, "grad_norm": 1.3719293978548117, "learning_rate": 9.037816927273773e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.439225, "epoch": 0.7218802462227196, "step": 645}, {"loss": 0.286126971244812, "token_acc": 0.9088075341557236, "grad_norm": 1.3047518849464856, "learning_rate": 9.019539239597242e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.439405, "epoch": 0.7274762171236709, "step": 650}, {"loss": 0.2772322416305542, "token_acc": 0.875756527753761, "grad_norm": 1.3292513739463385, "learning_rate": 9.001108429398294e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.439539, "epoch": 0.7330721880246223, "step": 655}, {"loss": 0.2965320348739624, "token_acc": 0.8895836902518417, "grad_norm": 1.4409020129023722, "learning_rate": 8.98252519879027e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.439621, "epoch": 0.7386681589255736, "step": 660}, {"loss": 0.3238807678222656, "token_acc": 0.8777329818576524, "grad_norm": 1.3411134750002927, "learning_rate": 8.963790255692909e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.439702, "epoch": 0.7442641298265249, "step": 665}, {"loss": 0.26616921424865725, "token_acc": 0.902085308056872, "grad_norm": 1.1481208126281677, "learning_rate": 8.944904313805358e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.439783, "epoch": 0.7498601007274762, "step": 670}, {"loss": 0.2841641426086426, "token_acc": 0.8902342910367558, "grad_norm": 1.2802202296248768, "learning_rate": 8.925868092579001e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.439907, "epoch": 0.7554560716284275, "step": 675}, {"loss": 0.2816178321838379, "token_acc": 0.9059672762271415, "grad_norm": 1.2417852973094257, "learning_rate": 8.906682317190042e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.439804, "epoch": 0.7610520425293789, "step": 680}, {"loss": 0.2728067398071289, "token_acc": 0.9225755166931637, "grad_norm": 1.2614421121957997, "learning_rate": 8.887347718511885e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.43982, "epoch": 0.7666480134303302, "step": 685}, {"loss": 0.3016941547393799, "token_acc": 0.8771106169178816, "grad_norm": 1.2704340807253511, "learning_rate": 8.867865033087287e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.439933, "epoch": 0.7722439843312815, "step": 690}, {"loss": 0.28254821300506594, "token_acc": 0.8876953125, "grad_norm": 1.0763054358246116, "learning_rate": 8.848235003100305e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.439949, "epoch": 0.7778399552322328, "step": 695}, {"loss": 0.26552324295043944, "token_acc": 0.9154155386003774, "grad_norm": 1.2502761563212075, "learning_rate": 8.828458376348016e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.439982, "epoch": 0.7834359261331841, "step": 700}, {"loss": 0.293634033203125, "token_acc": 0.8976061342809052, "grad_norm": 1.3667469678317925, "learning_rate": 8.808535906212044e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.440074, "epoch": 0.7890318970341355, "step": 705}, {"loss": 0.29573874473571776, "token_acc": 0.8898115320022392, "grad_norm": 1.2202588768525482, "learning_rate": 8.78846835162984e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.440121, "epoch": 0.7946278679350868, "step": 710}, {"loss": 0.3037862777709961, "token_acc": 0.8894690265486725, "grad_norm": 1.2180477492887996, "learning_rate": 8.768256477065781e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.440276, "epoch": 0.8002238388360381, "step": 715}, {"loss": 0.2824559211730957, "token_acc": 0.8981870002375109, "grad_norm": 1.265109956600968, "learning_rate": 8.747901052482059e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.440328, "epoch": 0.8058198097369894, "step": 720}, {"loss": 0.30694236755371096, "token_acc": 0.8873165618448637, "grad_norm": 1.3142292431310703, "learning_rate": 8.727402853309329e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.440438, "epoch": 0.8114157806379407, "step": 725}, {"loss": 0.2741583585739136, "token_acc": 0.9094852854965412, "grad_norm": 1.1873483115286756, "learning_rate": 8.706762660417181e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.440501, "epoch": 0.817011751538892, "step": 730}, {"loss": 0.27101199626922606, "token_acc": 0.8793480087380272, "grad_norm": 1.3599449258080896, "learning_rate": 8.685981260084393e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.440597, "epoch": 0.8226077224398433, "step": 735}, {"loss": 0.27054176330566404, "token_acc": 0.9024995719910974, "grad_norm": 1.5107759097333584, "learning_rate": 8.665059443968976e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.4407, "epoch": 0.8282036933407946, "step": 740}, {"loss": 0.2833104133605957, "token_acc": 0.9023807416585539, "grad_norm": 1.4006177754963167, "learning_rate": 8.643998009078016e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.440837, "epoch": 0.8337996642417459, "step": 745}, {"loss": 0.267363166809082, "token_acc": 0.9018531774437286, "grad_norm": 1.3682305085364543, "learning_rate": 8.622797757737314e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.440947, "epoch": 0.8393956351426972, "step": 750}, {"loss": 0.30713891983032227, "token_acc": 0.8823120583806324, "grad_norm": 1.393782728773063, "learning_rate": 8.60145949756082e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.441058, "epoch": 0.8449916060436485, "step": 755}, {"loss": 0.26855523586273194, "token_acc": 0.9061901003495321, "grad_norm": 1.2513325739575047, "learning_rate": 8.579984041419866e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.441146, "epoch": 0.8505875769445999, "step": 760}, {"loss": 0.28615450859069824, "token_acc": 0.8924348745554167, "grad_norm": 1.1492055374811483, "learning_rate": 8.558372207412203e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.441261, "epoch": 0.8561835478455512, "step": 765}, {"loss": 0.24949636459350585, "token_acc": 0.9176990065006746, "grad_norm": 1.3533982046202395, "learning_rate": 8.536624818830839e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.441405, "epoch": 0.8617795187465025, "step": 770}, {"loss": 0.29595279693603516, "token_acc": 0.9189877324280534, "grad_norm": 1.3287940317994944, "learning_rate": 8.514742704132663e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.441471, "epoch": 0.8673754896474538, "step": 775}, {"loss": 0.2863394498825073, "token_acc": 0.9259174574139705, "grad_norm": 1.1816060993670034, "learning_rate": 8.492726696906905e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.441539, "epoch": 0.8729714605484051, "step": 780}, {"loss": 0.29375567436218264, "token_acc": 0.8926848098822621, "grad_norm": 1.4151047537292962, "learning_rate": 8.470577635843363e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.441678, "epoch": 0.8785674314493565, "step": 785}, {"loss": 0.28147799968719484, "token_acc": 0.8927141713370697, "grad_norm": 1.332428328123189, "learning_rate": 8.448296364700462e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.441774, "epoch": 0.8841634023503078, "step": 790}, {"loss": 0.29062952995300295, "token_acc": 0.912594519879665, "grad_norm": 1.294735810216212, "learning_rate": 8.42588373227311e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.441807, "epoch": 0.8897593732512591, "step": 795}, {"loss": 0.2432760238647461, "token_acc": 0.9246657245352756, "grad_norm": 1.3506652841346243, "learning_rate": 8.403340592360363e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.441924, "epoch": 0.8953553441522104, "step": 800}, {"eval_loss": 0.28589844703674316, "eval_token_acc": 0.8901815974505539, "eval_runtime": 6.807, "eval_samples_per_second": 15.866, "eval_steps_per_second": 2.644, "epoch": 0.8953553441522104, "step": 800}, {"loss": 0.2847026824951172, "token_acc": 0.8821601373497737, "grad_norm": 1.2674437732365291, "learning_rate": 8.380667803732903e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.440333, "epoch": 0.9009513150531617, "step": 805}, {"loss": 0.29183139801025393, "token_acc": 0.88401335698633, "grad_norm": 1.1228229668964222, "learning_rate": 8.357866230100319e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.44046, "epoch": 0.906547285954113, "step": 810}, {"loss": 0.3023522138595581, "token_acc": 0.916023166023166, "grad_norm": 1.1487156495952995, "learning_rate": 8.334936740078206e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.440534, "epoch": 0.9121432568550644, "step": 815}, {"loss": 0.2835411071777344, "token_acc": 0.9027477616548317, "grad_norm": 1.1744266148892926, "learning_rate": 8.311880207155073e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.440593, "epoch": 0.9177392277560157, "step": 820}, {"loss": 0.2771141767501831, "token_acc": 0.8909372579395817, "grad_norm": 1.225405472082248, "learning_rate": 8.28869750965908e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.4407, "epoch": 0.923335198656967, "step": 825}, {"loss": 0.2912137508392334, "token_acc": 0.8739354113527301, "grad_norm": 1.3464425569871379, "learning_rate": 8.265389530724557e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.440733, "epoch": 0.9289311695579183, "step": 830}, {"loss": 0.28851516246795655, "token_acc": 0.9124697010503636, "grad_norm": 1.2383021585541854, "learning_rate": 8.241957158258383e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.440867, "epoch": 0.9345271404588696, "step": 835}, {"loss": 0.26634118556976316, "token_acc": 0.9071548664300392, "grad_norm": 1.161493528645876, "learning_rate": 8.218401284906147e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.440832, "epoch": 0.940123111359821, "step": 840}, {"loss": 0.2900543689727783, "token_acc": 0.8837579617834395, "grad_norm": 1.2400159681718008, "learning_rate": 8.194722808018152e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.440898, "epoch": 0.9457190822607723, "step": 845}, {"loss": 0.2875507831573486, "token_acc": 0.924506237006237, "grad_norm": 1.1645005132819235, "learning_rate": 8.170922629615221e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.440884, "epoch": 0.9513150531617236, "step": 850}, {"loss": 0.26259241104125974, "token_acc": 0.9095591877166914, "grad_norm": 1.2592466998172376, "learning_rate": 8.147001656354348e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.44096, "epoch": 0.9569110240626749, "step": 855}, {"loss": 0.2759808301925659, "token_acc": 0.905006558810669, "grad_norm": 1.3415810657694107, "learning_rate": 8.122960799494147e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.441042, "epoch": 0.9625069949636262, "step": 860}, {"loss": 0.2864255905151367, "token_acc": 0.8875992148160792, "grad_norm": 1.3847682846995337, "learning_rate": 8.098800974860146e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.441132, "epoch": 0.9681029658645776, "step": 865}, {"loss": 0.27780890464782715, "token_acc": 0.9146428937391126, "grad_norm": 1.1008170269346917, "learning_rate": 8.074523102809896e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.441057, "epoch": 0.9736989367655288, "step": 870}, {"loss": 0.29184865951538086, "token_acc": 0.9070474535780215, "grad_norm": 1.2864756011457152, "learning_rate": 8.050128108197911e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.440924, "epoch": 0.9792949076664801, "step": 875}, {"loss": 0.26892547607421874, "token_acc": 0.90591664599355, "grad_norm": 1.2247324958155357, "learning_rate": 8.025616920340434e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.441031, "epoch": 0.9848908785674314, "step": 880}, {"loss": 0.2710403919219971, "token_acc": 0.9231757244922534, "grad_norm": 1.199829593557751, "learning_rate": 8.000990472980038e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.441122, "epoch": 0.9904868494683827, "step": 885}, {"loss": 0.28195948600769044, "token_acc": 0.8747016706443914, "grad_norm": 1.3320975580638106, "learning_rate": 7.976249704250052e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.441189, "epoch": 0.996082820369334, "step": 890}, {"loss": 0.29261341094970705, "token_acc": 0.8958440754872641, "grad_norm": 1.9343375407291328, "learning_rate": 7.951395556638834e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.441502, "epoch": 1.0011191941801902, "step": 895}, {"loss": 0.24628019332885742, "token_acc": 0.9236606739542867, "grad_norm": 1.18711027725644, "learning_rate": 7.92642897695385e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.441578, "epoch": 1.0067151650811417, "step": 900}, {"loss": 0.23440279960632324, "token_acc": 0.9254385964912281, "grad_norm": 1.2130155310565658, "learning_rate": 7.90135091628562e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.441623, "epoch": 1.0123111359820929, "step": 905}, {"loss": 0.2641316890716553, "token_acc": 0.9132357671276938, "grad_norm": 1.1413442353348675, "learning_rate": 7.876162329971475e-06, "memory(GiB)": 75.54, "train_speed(iter/s)": 0.441683, "epoch": 1.0179071068830443, "step": 910}, {"loss": 0.2040219783782959, "token_acc": 0.9264947888096544, "grad_norm": 1.133503829391007, "learning_rate": 7.850864177559178e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.441687, "epoch": 1.0235030777839955, "step": 915}, {"loss": 0.24311339855194092, "token_acc": 0.910241935483871, "grad_norm": 1.3780312570375641, "learning_rate": 7.82545742277036e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.441708, "epoch": 1.0290990486849467, "step": 920}, {"loss": 0.23109762668609618, "token_acc": 0.9180821184967233, "grad_norm": 1.15598364777028, "learning_rate": 7.799943033463806e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.441735, "epoch": 1.0346950195858982, "step": 925}, {"loss": 0.25525484085083006, "token_acc": 0.9090251663291872, "grad_norm": 1.1797280272238524, "learning_rate": 7.774321981598598e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.441814, "epoch": 1.0402909904868494, "step": 930}, {"loss": 0.24347610473632814, "token_acc": 0.8998995342040369, "grad_norm": 1.2600696364631512, "learning_rate": 7.748595243197073e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.441913, "epoch": 1.0458869613878008, "step": 935}, {"loss": 0.194050931930542, "token_acc": 0.9226053639846743, "grad_norm": 1.2247777456018079, "learning_rate": 7.722763798307647e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.44197, "epoch": 1.051482932288752, "step": 940}, {"loss": 0.20441272258758544, "token_acc": 0.9140631761142363, "grad_norm": 1.2350557577245815, "learning_rate": 7.696828630967489e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.44192, "epoch": 1.0570789031897034, "step": 945}, {"loss": 0.23828611373901368, "token_acc": 0.9278515118251671, "grad_norm": 1.1426156980522577, "learning_rate": 7.670790729165022e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.441992, "epoch": 1.0626748740906546, "step": 950}, {"loss": 0.22539873123168946, "token_acc": 0.9159352094833046, "grad_norm": 1.3785351488900761, "learning_rate": 7.644651084802295e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442055, "epoch": 1.068270844991606, "step": 955}, {"loss": 0.20619139671325684, "token_acc": 0.915081880612784, "grad_norm": 1.1794281213636433, "learning_rate": 7.61841069365719e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442084, "epoch": 1.0738668158925573, "step": 960}, {"loss": 0.21941919326782228, "token_acc": 0.9177136201015059, "grad_norm": 1.2306914457948388, "learning_rate": 7.592070555345498e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442162, "epoch": 1.0794627867935087, "step": 965}, {"loss": 0.2205348014831543, "token_acc": 0.9457587382779199, "grad_norm": 1.1943054957024757, "learning_rate": 7.565631673282827e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442247, "epoch": 1.08505875769446, "step": 970}, {"loss": 0.21462595462799072, "token_acc": 0.9223216021777173, "grad_norm": 1.2007944241224286, "learning_rate": 7.539095054646384e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442312, "epoch": 1.0906547285954113, "step": 975}, {"loss": 0.2185539960861206, "token_acc": 0.9155659915859505, "grad_norm": 1.170344020827365, "learning_rate": 7.512461710336612e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.44232, "epoch": 1.0962506994963626, "step": 980}, {"loss": 0.22841272354125977, "token_acc": 0.89678955078125, "grad_norm": 1.3471408239608222, "learning_rate": 7.485732654938667e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442341, "epoch": 1.101846670397314, "step": 985}, {"loss": 0.22382619380950927, "token_acc": 0.9109867292588246, "grad_norm": 1.288486810028764, "learning_rate": 7.4589089066837815e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.44243, "epoch": 1.1074426412982652, "step": 990}, {"loss": 0.2340932607650757, "token_acc": 0.9257302362675706, "grad_norm": 1.2923712374807843, "learning_rate": 7.431991487410466e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442512, "epoch": 1.1130386121992166, "step": 995}, {"loss": 0.2259042501449585, "token_acc": 0.9012953221336049, "grad_norm": 1.2751136630445545, "learning_rate": 7.4049814225255865e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442589, "epoch": 1.1186345831001678, "step": 1000}, {"eval_loss": 0.2782086730003357, "eval_token_acc": 0.8930693922080905, "eval_runtime": 6.9579, "eval_samples_per_second": 15.522, "eval_steps_per_second": 2.587, "epoch": 1.1186345831001678, "step": 1000}, {"loss": 0.22948970794677734, "token_acc": 0.924153213042102, "grad_norm": 1.1659131547935664, "learning_rate": 7.377879740965305e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.441179, "epoch": 1.1242305540011193, "step": 1005}, {"loss": 0.22051913738250734, "token_acc": 0.9039359573048699, "grad_norm": 1.3902882574434117, "learning_rate": 7.350687475155871e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.441266, "epoch": 1.1298265249020705, "step": 1010}, {"loss": 0.23391256332397461, "token_acc": 0.9056781255344621, "grad_norm": 1.2663179571424017, "learning_rate": 7.323405660974309e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.441356, "epoch": 1.135422495803022, "step": 1015}, {"loss": 0.22755014896392822, "token_acc": 0.9022652685503882, "grad_norm": 1.3443110229620443, "learning_rate": 7.296035337708941e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.441351, "epoch": 1.141018466703973, "step": 1020}, {"loss": 0.22950522899627684, "token_acc": 0.9084115253674334, "grad_norm": 1.3470586054978884, "learning_rate": 7.268577548019808e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.441385, "epoch": 1.1466144376049245, "step": 1025}, {"loss": 0.22843093872070314, "token_acc": 0.9301671214188267, "grad_norm": 1.1974417975580842, "learning_rate": 7.241033337898942e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.441424, "epoch": 1.1522104085058757, "step": 1030}, {"loss": 0.24183640480041504, "token_acc": 0.8994796293945932, "grad_norm": 1.2094566669384241, "learning_rate": 7.21340375663052e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.441417, "epoch": 1.1578063794068272, "step": 1035}, {"loss": 0.21626462936401367, "token_acc": 0.9179030662710188, "grad_norm": 1.023499979243188, "learning_rate": 7.185689856750897e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.441454, "epoch": 1.1634023503077784, "step": 1040}, {"loss": 0.23219399452209472, "token_acc": 0.8817243920412675, "grad_norm": 1.2295717837878086, "learning_rate": 7.157892694008508e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.441534, "epoch": 1.1689983212087296, "step": 1045}, {"loss": 0.22575864791870118, "token_acc": 0.9320476575121163, "grad_norm": 1.3818210859292883, "learning_rate": 7.130013327323648e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.441598, "epoch": 1.174594292109681, "step": 1050}, {"loss": 0.23145170211791993, "token_acc": 0.9344879518072289, "grad_norm": 1.296269411740455, "learning_rate": 7.102052818748131e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.441672, "epoch": 1.1801902630106325, "step": 1055}, {"loss": 0.2146484375, "token_acc": 0.9060156374660923, "grad_norm": 1.3488093536611714, "learning_rate": 7.074012233424836e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.441753, "epoch": 1.1857862339115837, "step": 1060}, {"loss": 0.22807834148406983, "token_acc": 0.9110867178924259, "grad_norm": 1.3282218084669626, "learning_rate": 7.045892639547133e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.441851, "epoch": 1.1913822048125349, "step": 1065}, {"loss": 0.2330177068710327, "token_acc": 0.9174842507487349, "grad_norm": 1.3604209945412253, "learning_rate": 7.017695108318185e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.441884, "epoch": 1.1969781757134863, "step": 1070}, {"loss": 0.21682214736938477, "token_acc": 0.8950133231823373, "grad_norm": 1.2546442348927167, "learning_rate": 6.9894207139101365e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.44185, "epoch": 1.2025741466144375, "step": 1075}, {"loss": 0.20190167427062988, "token_acc": 0.9373764693644023, "grad_norm": 1.3824810953694913, "learning_rate": 6.961070533423212e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.441931, "epoch": 1.208170117515389, "step": 1080}, {"loss": 0.23871922492980957, "token_acc": 0.912378661627008, "grad_norm": 1.473863018964983, "learning_rate": 6.932645646844662e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442046, "epoch": 1.2137660884163401, "step": 1085}, {"loss": 0.22519474029541015, "token_acc": 0.9090072119073194, "grad_norm": 1.1308083585508701, "learning_rate": 6.9041471370076384e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442134, "epoch": 1.2193620593172916, "step": 1090}, {"loss": 0.21806180477142334, "token_acc": 0.9130627633621645, "grad_norm": 1.2185262327499293, "learning_rate": 6.875576089549933e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442209, "epoch": 1.2249580302182428, "step": 1095}, {"loss": 0.24117612838745117, "token_acc": 0.920883164673413, "grad_norm": 1.0904436113678802, "learning_rate": 6.846933592872625e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442112, "epoch": 1.2305540011191942, "step": 1100}, {"loss": 0.2559941053390503, "token_acc": 0.9131761442441054, "grad_norm": 1.398802002038545, "learning_rate": 6.818220738098625e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442091, "epoch": 1.2361499720201454, "step": 1105}, {"loss": 0.24390604496002197, "token_acc": 0.8946233749265042, "grad_norm": 1.1005228779584435, "learning_rate": 6.789438619031099e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442118, "epoch": 1.2417459429210969, "step": 1110}, {"loss": 0.21798553466796874, "token_acc": 0.9350661625708885, "grad_norm": 1.53961582958846, "learning_rate": 6.760588332111804e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442222, "epoch": 1.247341913822048, "step": 1115}, {"loss": 0.23403940200805665, "token_acc": 0.901866381359962, "grad_norm": 1.3409634455451998, "learning_rate": 6.731670976379323e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442281, "epoch": 1.2529378847229995, "step": 1120}, {"loss": 0.21949756145477295, "token_acc": 0.9067620394244365, "grad_norm": 1.2913415922056888, "learning_rate": 6.702687653427192e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442351, "epoch": 1.2585338556239507, "step": 1125}, {"loss": 0.23506007194519044, "token_acc": 0.9012890819742183, "grad_norm": 1.3112408301666951, "learning_rate": 6.673639467361944e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442396, "epoch": 1.2641298265249021, "step": 1130}, {"loss": 0.23589205741882324, "token_acc": 0.9202514593623708, "grad_norm": 1.0574241972238565, "learning_rate": 6.644527524761035e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442451, "epoch": 1.2697257974258533, "step": 1135}, {"loss": 0.23713765144348145, "token_acc": 0.9139385418758786, "grad_norm": 1.2428077868021714, "learning_rate": 6.615352934630704e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442509, "epoch": 1.2753217683268048, "step": 1140}, {"loss": 0.2189612627029419, "token_acc": 0.907480126424672, "grad_norm": 1.3381018858593747, "learning_rate": 6.5861168083637154e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442574, "epoch": 1.280917739227756, "step": 1145}, {"loss": 0.22135844230651855, "token_acc": 0.9102111407364705, "grad_norm": 1.2034519833661497, "learning_rate": 6.5568202596970255e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442638, "epoch": 1.2865137101287074, "step": 1150}, {"loss": 0.2325753688812256, "token_acc": 0.9042232277526395, "grad_norm": 1.2636702791535477, "learning_rate": 6.527464404669355e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442662, "epoch": 1.2921096810296586, "step": 1155}, {"loss": 0.2271162748336792, "token_acc": 0.9204451393359698, "grad_norm": 1.207276387064901, "learning_rate": 6.498050361578673e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442681, "epoch": 1.29770565193061, "step": 1160}, {"loss": 0.22489440441131592, "token_acc": 0.9173960612691466, "grad_norm": 1.1808095171044612, "learning_rate": 6.468579250939598e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442681, "epoch": 1.3033016228315613, "step": 1165}, {"loss": 0.2319570541381836, "token_acc": 0.8935370955348758, "grad_norm": 1.1484006446544361, "learning_rate": 6.439052195440707e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442724, "epoch": 1.3088975937325125, "step": 1170}, {"loss": 0.2059481382369995, "token_acc": 0.9138390477882394, "grad_norm": 1.2069396652918563, "learning_rate": 6.409470319901777e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442783, "epoch": 1.314493564633464, "step": 1175}, {"loss": 0.21650776863098145, "token_acc": 0.8938825615494783, "grad_norm": 1.2593467274172607, "learning_rate": 6.379834751230925e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442813, "epoch": 1.3200895355344153, "step": 1180}, {"loss": 0.19177072048187255, "token_acc": 0.9389083022050849, "grad_norm": 1.0283655474555147, "learning_rate": 6.350146618381683e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442901, "epoch": 1.3256855064353665, "step": 1185}, {"loss": 0.19847514629364013, "token_acc": 0.937718222138341, "grad_norm": 1.2427260437265457, "learning_rate": 6.320407052309996e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442961, "epoch": 1.3312814773363177, "step": 1190}, {"loss": 0.2271047592163086, "token_acc": 0.9189399087467236, "grad_norm": 1.1983324392548087, "learning_rate": 6.290617185931127e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.443014, "epoch": 1.3368774482372692, "step": 1195}, {"loss": 0.20722079277038574, "token_acc": 0.8979670968814047, "grad_norm": 1.2311346632382048, "learning_rate": 6.260778154076516e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.443079, "epoch": 1.3424734191382206, "step": 1200}, {"eval_loss": 0.27264249324798584, "eval_token_acc": 0.8951994788883928, "eval_runtime": 6.9525, "eval_samples_per_second": 15.534, "eval_steps_per_second": 2.589, "epoch": 1.3424734191382206, "step": 1200}, {"loss": 0.20924100875854493, "token_acc": 0.9216062781766572, "grad_norm": 1.1272776752566191, "learning_rate": 6.230891093450531e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.441933, "epoch": 1.3480693900391718, "step": 1205}, {"loss": 0.23527143001556397, "token_acc": 0.9064464259611168, "grad_norm": 1.0674095635690382, "learning_rate": 6.200957142587179e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442008, "epoch": 1.353665360940123, "step": 1210}, {"loss": 0.2374746322631836, "token_acc": 0.9220827730464665, "grad_norm": 1.0334045385008415, "learning_rate": 6.170977441806726e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442044, "epoch": 1.3592613318410744, "step": 1215}, {"loss": 0.2555535316467285, "token_acc": 0.9284668683517127, "grad_norm": 1.1309583589142038, "learning_rate": 6.140953133172265e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442064, "epoch": 1.3648573027420259, "step": 1220}, {"loss": 0.2529881715774536, "token_acc": 0.9142559678738752, "grad_norm": 1.3315489545888075, "learning_rate": 6.1108853604462e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442081, "epoch": 1.370453273642977, "step": 1225}, {"loss": 0.234098482131958, "token_acc": 0.9047127622979017, "grad_norm": 1.332445805693652, "learning_rate": 6.080775269046681e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442093, "epoch": 1.3760492445439283, "step": 1230}, {"loss": 0.21449604034423828, "token_acc": 0.8922640745240988, "grad_norm": 1.214899752167624, "learning_rate": 6.050624006003972e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442158, "epoch": 1.3816452154448797, "step": 1235}, {"loss": 0.23834962844848634, "token_acc": 0.9145158337909574, "grad_norm": 1.256284665700816, "learning_rate": 6.020432719916748e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442193, "epoch": 1.387241186345831, "step": 1240}, {"loss": 0.23556227684020997, "token_acc": 0.9038773787101383, "grad_norm": 1.299905496395608, "learning_rate": 5.990202560908348e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442245, "epoch": 1.3928371572467824, "step": 1245}, {"loss": 0.2249089241027832, "token_acc": 0.9150150797070228, "grad_norm": 1.2942854733188027, "learning_rate": 5.959934680582949e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442271, "epoch": 1.3984331281477336, "step": 1250}, {"loss": 0.2471747875213623, "token_acc": 0.8972984877404199, "grad_norm": 0.9496233023559157, "learning_rate": 5.929630231981717e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442325, "epoch": 1.404029099048685, "step": 1255}, {"loss": 0.23408446311950684, "token_acc": 0.90311986863711, "grad_norm": 1.1791435604408582, "learning_rate": 5.899290369538857e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442353, "epoch": 1.4096250699496362, "step": 1260}, {"loss": 0.2351475715637207, "token_acc": 0.9307543051176328, "grad_norm": 1.2386173429738345, "learning_rate": 5.868916249037658e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.44237, "epoch": 1.4152210408505876, "step": 1265}, {"loss": 0.19895299673080444, "token_acc": 0.9216444132115249, "grad_norm": 1.3171877306059852, "learning_rate": 5.838509027566449e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442434, "epoch": 1.4208170117515388, "step": 1270}, {"loss": 0.21227779388427734, "token_acc": 0.9204231520787008, "grad_norm": 1.1605002504093953, "learning_rate": 5.808069863474526e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442486, "epoch": 1.4264129826524903, "step": 1275}, {"loss": 0.20887880325317382, "token_acc": 0.9446525679758309, "grad_norm": 1.399012554951489, "learning_rate": 5.777599916328026e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442527, "epoch": 1.4320089535534415, "step": 1280}, {"loss": 0.20969834327697753, "token_acc": 0.9014444903012794, "grad_norm": 1.3197212793079032, "learning_rate": 5.747100346865753e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442545, "epoch": 1.437604924454393, "step": 1285}, {"loss": 0.20608165264129638, "token_acc": 0.9381809278981516, "grad_norm": 1.3174476897463867, "learning_rate": 5.7165723169549555e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442591, "epoch": 1.4432008953553441, "step": 1290}, {"loss": 0.19446862936019899, "token_acc": 0.9168468782699686, "grad_norm": 1.2962679979598122, "learning_rate": 5.6860169895470765e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442634, "epoch": 1.4487968662562953, "step": 1295}, {"loss": 0.22998292446136476, "token_acc": 0.9138939011187297, "grad_norm": 1.3694120804736247, "learning_rate": 5.655435528633439e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.44269, "epoch": 1.4543928371572468, "step": 1300}, {"loss": 0.23601608276367186, "token_acc": 0.9250671708627725, "grad_norm": 1.1761056861885355, "learning_rate": 5.624829099200913e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442695, "epoch": 1.4599888080581982, "step": 1305}, {"loss": 0.2151721954345703, "token_acc": 0.9326285240464345, "grad_norm": 1.4012395702621745, "learning_rate": 5.594198867187532e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442695, "epoch": 1.4655847789591494, "step": 1310}, {"loss": 0.22861847877502442, "token_acc": 0.8996276235612729, "grad_norm": 1.2180357629546508, "learning_rate": 5.563545999438078e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442705, "epoch": 1.4711807498601006, "step": 1315}, {"loss": 0.21792027950286866, "token_acc": 0.9316926167754898, "grad_norm": 1.1919350809254627, "learning_rate": 5.5328716636596305e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442752, "epoch": 1.476776720761052, "step": 1320}, {"loss": 0.21971464157104492, "token_acc": 0.9135827165433087, "grad_norm": 1.2813693302824973, "learning_rate": 5.502177028377086e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442809, "epoch": 1.4823726916620035, "step": 1325}, {"loss": 0.2259507656097412, "token_acc": 0.9060442343407057, "grad_norm": 1.1847124337058037, "learning_rate": 5.471463262888639e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442858, "epoch": 1.4879686625629547, "step": 1330}, {"loss": 0.23206424713134766, "token_acc": 0.8917872556486418, "grad_norm": 1.2777841946997117, "learning_rate": 5.440731537221242e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442871, "epoch": 1.4935646334639059, "step": 1335}, {"loss": 0.218588924407959, "token_acc": 0.920584498094028, "grad_norm": 1.3393537888396227, "learning_rate": 5.409983022086031e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442911, "epoch": 1.4991606043648573, "step": 1340}, {"loss": 0.2211003065109253, "token_acc": 0.930855924459336, "grad_norm": 1.3550949061276751, "learning_rate": 5.379218888833729e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442919, "epoch": 1.5047565752658087, "step": 1345}, {"loss": 0.22542815208435057, "token_acc": 0.9077819229007134, "grad_norm": 1.2564741701367266, "learning_rate": 5.3484403094100265e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442918, "epoch": 1.51035254616676, "step": 1350}, {"loss": 0.247910213470459, "token_acc": 0.8992473594333059, "grad_norm": 1.2888698894674762, "learning_rate": 5.317648456310933e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442943, "epoch": 1.5159485170677112, "step": 1355}, {"loss": 0.19647455215454102, "token_acc": 0.9544097381717961, "grad_norm": 1.243616495902469, "learning_rate": 5.286844502538113e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442984, "epoch": 1.5215444879686626, "step": 1360}, {"loss": 0.21572742462158204, "token_acc": 0.9128570203276439, "grad_norm": 1.493496514669754, "learning_rate": 5.2560296215541975e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.443011, "epoch": 1.527140458869614, "step": 1365}, {"loss": 0.22728323936462402, "token_acc": 0.9280644389504745, "grad_norm": 1.2010854046949642, "learning_rate": 5.225204987238091e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.443063, "epoch": 1.5327364297705652, "step": 1370}, {"loss": 0.22756319046020507, "token_acc": 0.9305061289047054, "grad_norm": 1.255022962234977, "learning_rate": 5.19437177384024e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.443119, "epoch": 1.5383324006715164, "step": 1375}, {"loss": 0.22217469215393065, "token_acc": 0.912502696096053, "grad_norm": 1.2545154626704393, "learning_rate": 5.1635311559379105e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.443159, "epoch": 1.5439283715724679, "step": 1380}, {"loss": 0.22108981609344483, "token_acc": 0.9156757596953446, "grad_norm": 1.3570064199441148, "learning_rate": 5.132684308390442e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.443218, "epoch": 1.5495243424734193, "step": 1385}, {"loss": 0.2335721731185913, "token_acc": 0.9016964642714342, "grad_norm": 1.0515896933888347, "learning_rate": 5.101832406294484e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.443202, "epoch": 1.5551203133743705, "step": 1390}, {"loss": 0.23662757873535156, "token_acc": 0.9121441736637314, "grad_norm": 1.223912099168244, "learning_rate": 5.070976624939242e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.443184, "epoch": 1.5607162842753217, "step": 1395}, {"loss": 0.2319847822189331, "token_acc": 0.9111056187180755, "grad_norm": 0.9880429637595486, "learning_rate": 5.040118139761696e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.443156, "epoch": 1.566312255176273, "step": 1400}, {"eval_loss": 0.2671208381652832, "eval_token_acc": 0.8958707618897049, "eval_runtime": 7.0213, "eval_samples_per_second": 15.382, "eval_steps_per_second": 2.564, "epoch": 1.566312255176273, "step": 1400}, {"loss": 0.21248960494995117, "token_acc": 0.9196737518536826, "grad_norm": 0.9762868173027771, "learning_rate": 5.009258126301831e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442121, "epoch": 1.5719082260772244, "step": 1405}, {"loss": 0.20404059886932374, "token_acc": 0.9066822196300617, "grad_norm": 1.1237528422238927, "learning_rate": 4.978397760157847e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442164, "epoch": 1.5775041969781758, "step": 1410}, {"loss": 0.2393702507019043, "token_acc": 0.9099009140486981, "grad_norm": 1.2515985656960802, "learning_rate": 4.947538216941384e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.44216, "epoch": 1.583100167879127, "step": 1415}, {"loss": 0.20788743495941162, "token_acc": 0.9300936246098974, "grad_norm": 1.3059558424922046, "learning_rate": 4.9166806722327274e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.4422, "epoch": 1.5886961387800782, "step": 1420}, {"loss": 0.22498879432678223, "token_acc": 0.9034513209213334, "grad_norm": 1.116186853168441, "learning_rate": 4.885826301536034e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442238, "epoch": 1.5942921096810296, "step": 1425}, {"loss": 0.22998740673065185, "token_acc": 0.901301825385595, "grad_norm": 1.3181204681081213, "learning_rate": 4.8549762802345456e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442274, "epoch": 1.599888080581981, "step": 1430}, {"loss": 0.22384355068206788, "token_acc": 0.9350389555695936, "grad_norm": 1.240181165101517, "learning_rate": 4.824131783545822e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442293, "epoch": 1.6054840514829323, "step": 1435}, {"loss": 0.2448258876800537, "token_acc": 0.9011270006629416, "grad_norm": 1.2277702791500271, "learning_rate": 4.793293986476959e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442326, "epoch": 1.6110800223838835, "step": 1440}, {"loss": 0.19722660779953002, "token_acc": 0.9270482603815937, "grad_norm": 1.5912574249759879, "learning_rate": 4.762464063779832e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442362, "epoch": 1.616675993284835, "step": 1445}, {"loss": 0.22548329830169678, "token_acc": 0.9028498781650599, "grad_norm": 1.1897116901811948, "learning_rate": 4.731643189906353e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442326, "epoch": 1.6222719641857863, "step": 1450}, {"loss": 0.2255380392074585, "token_acc": 0.9143805834453317, "grad_norm": 1.3201360632591008, "learning_rate": 4.700832538963715e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442284, "epoch": 1.6278679350867375, "step": 1455}, {"loss": 0.2184016227722168, "token_acc": 0.9385756982376584, "grad_norm": 1.1850002691297494, "learning_rate": 4.670033284669684e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442239, "epoch": 1.6334639059876888, "step": 1460}, {"loss": 0.19763824939727784, "token_acc": 0.9146266561375801, "grad_norm": 1.3307842701039398, "learning_rate": 4.6392466003078635e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442247, "epoch": 1.6390598768886402, "step": 1465}, {"loss": 0.23901805877685547, "token_acc": 0.9181933305192064, "grad_norm": 1.2843397720927132, "learning_rate": 4.6084736586830185e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442233, "epoch": 1.6446558477895916, "step": 1470}, {"loss": 0.22745914459228517, "token_acc": 0.9043581482109547, "grad_norm": 1.3136798385290205, "learning_rate": 4.577715632076387e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442278, "epoch": 1.6502518186905428, "step": 1475}, {"loss": 0.2165836811065674, "token_acc": 0.9027646437114091, "grad_norm": 1.2082713178798956, "learning_rate": 4.546973692201034e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442293, "epoch": 1.655847789591494, "step": 1480}, {"loss": 0.23440585136413575, "token_acc": 0.9329678544729628, "grad_norm": 1.1610868009550557, "learning_rate": 4.5162490101571955e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442289, "epoch": 1.6614437604924455, "step": 1485}, {"loss": 0.22933557033538818, "token_acc": 0.9164445261513007, "grad_norm": 1.3281700749868137, "learning_rate": 4.485542756387687e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442317, "epoch": 1.667039731393397, "step": 1490}, {"loss": 0.23326985836029052, "token_acc": 0.9047209685507558, "grad_norm": 1.1129120172056912, "learning_rate": 4.454856100633306e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442334, "epoch": 1.672635702294348, "step": 1495}, {"loss": 0.2315912961959839, "token_acc": 0.8925458370904719, "grad_norm": 1.2533397634651826, "learning_rate": 4.424190211888268e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.44238, "epoch": 1.6782316731952993, "step": 1500}, {"loss": 0.21184132099151612, "token_acc": 0.9067460317460317, "grad_norm": 1.244714263184632, "learning_rate": 4.393546258355686e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.44241, "epoch": 1.6838276440962507, "step": 1505}, {"loss": 0.22453079223632813, "token_acc": 0.9076614468745956, "grad_norm": 1.2149678462332574, "learning_rate": 4.362925407403057e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442443, "epoch": 1.6894236149972022, "step": 1510}, {"loss": 0.23663246631622314, "token_acc": 0.9224715599189652, "grad_norm": 1.2440067324255226, "learning_rate": 4.332328825517793e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442483, "epoch": 1.6950195858981534, "step": 1515}, {"loss": 0.22366881370544434, "token_acc": 0.900755212608767, "grad_norm": 1.190924499589742, "learning_rate": 4.30175767826279e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442514, "epoch": 1.7006155567991046, "step": 1520}, {"loss": 0.19798750877380372, "token_acc": 0.9358589647411854, "grad_norm": 1.175250778063345, "learning_rate": 4.271213130232027e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442562, "epoch": 1.7062115277000558, "step": 1525}, {"loss": 0.21264271736145018, "token_acc": 0.9233567486201706, "grad_norm": 1.1321137159844932, "learning_rate": 4.240696345006189e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442575, "epoch": 1.7118074986010072, "step": 1530}, {"loss": 0.22446441650390625, "token_acc": 0.9287494502272394, "grad_norm": 1.2652395601180486, "learning_rate": 4.210208485108357e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442595, "epoch": 1.7174034695019587, "step": 1535}, {"loss": 0.21930482387542724, "token_acc": 0.9141625459617091, "grad_norm": 1.0302405522736506, "learning_rate": 4.179750711959711e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442641, "epoch": 1.7229994404029099, "step": 1540}, {"loss": 0.23731517791748047, "token_acc": 0.8872357086922474, "grad_norm": 1.067760679113109, "learning_rate": 4.149324185835291e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442636, "epoch": 1.728595411303861, "step": 1545}, {"loss": 0.21198184490203859, "token_acc": 0.9184515761759054, "grad_norm": 1.36346924841279, "learning_rate": 4.118930065819796e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442683, "epoch": 1.7341913822048125, "step": 1550}, {"loss": 0.2182554006576538, "token_acc": 0.905282047280955, "grad_norm": 1.0233599853448618, "learning_rate": 4.0885695097634295e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.44271, "epoch": 1.739787353105764, "step": 1555}, {"loss": 0.20367045402526857, "token_acc": 0.9006944772523268, "grad_norm": 1.1466155568430234, "learning_rate": 4.058243674237789e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442728, "epoch": 1.7453833240067151, "step": 1560}, {"loss": 0.2291868209838867, "token_acc": 0.8950943396226415, "grad_norm": 1.1318132500430367, "learning_rate": 4.027953714491811e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442772, "epoch": 1.7509792949076664, "step": 1565}, {"loss": 0.21526036262512208, "token_acc": 0.9092627599243857, "grad_norm": 1.2967206967216347, "learning_rate": 3.997700784407759e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442777, "epoch": 1.7565752658086178, "step": 1570}, {"loss": 0.2589444875717163, "token_acc": 0.9005579010856454, "grad_norm": 1.4098974268868172, "learning_rate": 3.967486036457273e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442768, "epoch": 1.7621712367095692, "step": 1575}, {"loss": 0.23918418884277343, "token_acc": 0.8968753576742589, "grad_norm": 1.0167949945873938, "learning_rate": 3.937310621657455e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442739, "epoch": 1.7677672076105204, "step": 1580}, {"loss": 0.2044771671295166, "token_acc": 0.8857057594747837, "grad_norm": 1.1481252455355528, "learning_rate": 3.907175689527033e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442745, "epoch": 1.7733631785114716, "step": 1585}, {"loss": 0.21482856273651124, "token_acc": 0.9287081775913939, "grad_norm": 1.1441550415201336, "learning_rate": 3.877082388042563e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442808, "epoch": 1.778959149412423, "step": 1590}, {"loss": 0.1964472532272339, "token_acc": 0.9372127139364304, "grad_norm": 1.2182867507427544, "learning_rate": 3.847031863594707e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442822, "epoch": 1.7845551203133745, "step": 1595}, {"loss": 0.2293701171875, "token_acc": 0.8976367319378799, "grad_norm": 0.9766986214448518, "learning_rate": 3.8170252609445465e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442818, "epoch": 1.7901510912143257, "step": 1600}, {"eval_loss": 0.26657816767692566, "eval_token_acc": 0.8966020281088775, "eval_runtime": 6.8665, "eval_samples_per_second": 15.729, "eval_steps_per_second": 2.621, "epoch": 1.7901510912143257, "step": 1600}, {"loss": 0.22518985271453856, "token_acc": 0.9124779972618815, "grad_norm": 1.3086649235091314, "learning_rate": 3.7870637231799885e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.441936, "epoch": 1.795747062115277, "step": 1605}, {"loss": 0.202821683883667, "token_acc": 0.9388393932097279, "grad_norm": 1.1169009500052414, "learning_rate": 3.7571483916722095e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.441961, "epoch": 1.8013430330162283, "step": 1610}, {"loss": 0.19543895721435547, "token_acc": 0.9390993850426502, "grad_norm": 1.040221064864985, "learning_rate": 3.727280406032181e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.441996, "epoch": 1.8069390039171798, "step": 1615}, {"loss": 0.22716264724731444, "token_acc": 0.9261504975124378, "grad_norm": 1.2755671700169964, "learning_rate": 3.697460904067258e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442058, "epoch": 1.812534974818131, "step": 1620}, {"loss": 0.18808450698852539, "token_acc": 0.9391597304795878, "grad_norm": 1.250222382202721, "learning_rate": 3.667691021737828e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442091, "epoch": 1.8181309457190822, "step": 1625}, {"loss": 0.18790140151977539, "token_acc": 0.9183053678536178, "grad_norm": 1.2212646207222784, "learning_rate": 3.637971893114043e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442136, "epoch": 1.8237269166200336, "step": 1630}, {"loss": 0.21865699291229249, "token_acc": 0.9194899124476589, "grad_norm": 1.3309622572182935, "learning_rate": 3.6083046503326146e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442152, "epoch": 1.829322887520985, "step": 1635}, {"loss": 0.22961621284484862, "token_acc": 0.9141461877756774, "grad_norm": 1.2107144740984412, "learning_rate": 3.5786904235536866e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442168, "epoch": 1.8349188584219362, "step": 1640}, {"loss": 0.22652823925018312, "token_acc": 0.9093124679322729, "grad_norm": 1.2418973648644067, "learning_rate": 3.5491303409177856e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442211, "epoch": 1.8405148293228875, "step": 1645}, {"loss": 0.22636713981628417, "token_acc": 0.9010807840263785, "grad_norm": 1.203742273232801, "learning_rate": 3.519625528502837e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442246, "epoch": 1.8461108002238389, "step": 1650}, {"loss": 0.22370562553405762, "token_acc": 0.9136438099695764, "grad_norm": 1.168213063760881, "learning_rate": 3.490177110281274e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442243, "epoch": 1.85170677112479, "step": 1655}, {"loss": 0.22471604347229004, "token_acc": 0.9090996537129665, "grad_norm": 1.0113868431043427, "learning_rate": 3.4607862080772192e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442263, "epoch": 1.8573027420257415, "step": 1660}, {"loss": 0.20516133308410645, "token_acc": 0.9268817204301075, "grad_norm": 1.318981407222853, "learning_rate": 3.431453941523749e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442289, "epoch": 1.8628987129266927, "step": 1665}, {"loss": 0.20016803741455078, "token_acc": 0.934093338083363, "grad_norm": 1.1225116121761824, "learning_rate": 3.4021814280202405e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.44233, "epoch": 1.868494683827644, "step": 1670}, {"loss": 0.2224114418029785, "token_acc": 0.9313465050639216, "grad_norm": 1.2583011507908706, "learning_rate": 3.372969782689805e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442364, "epoch": 1.8740906547285954, "step": 1675}, {"loss": 0.2007291078567505, "token_acc": 0.9357599606492868, "grad_norm": 1.2547341253064572, "learning_rate": 3.3438201183368095e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.44241, "epoch": 1.8796866256295468, "step": 1680}, {"loss": 0.20684497356414794, "token_acc": 0.9146050793128956, "grad_norm": 1.2719840334112178, "learning_rate": 3.3147335454044813e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442462, "epoch": 1.885282596530498, "step": 1685}, {"loss": 0.21820526123046874, "token_acc": 0.9030910609857978, "grad_norm": 1.087482773342334, "learning_rate": 3.2857111719326147e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442493, "epoch": 1.8908785674314492, "step": 1690}, {"loss": 0.2251755952835083, "token_acc": 0.9125040809663728, "grad_norm": 1.225705755686391, "learning_rate": 3.256754103515347e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442504, "epoch": 1.8964745383324007, "step": 1695}, {"loss": 0.21893444061279296, "token_acc": 0.9172447968285431, "grad_norm": 0.9638050363067384, "learning_rate": 3.227863443259055e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442555, "epoch": 1.902070509233352, "step": 1700}, {"loss": 0.20849003791809081, "token_acc": 0.9063286743640941, "grad_norm": 1.3805652987800299, "learning_rate": 3.1990402917403224e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442605, "epoch": 1.9076664801343033, "step": 1705}, {"loss": 0.17915595769882203, "token_acc": 0.9266568483063329, "grad_norm": 1.286425579325967, "learning_rate": 3.1702857469640223e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442658, "epoch": 1.9132624510352545, "step": 1710}, {"loss": 0.22770328521728517, "token_acc": 0.9360163875165682, "grad_norm": 1.3288534650558004, "learning_rate": 3.1416009043214825e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442699, "epoch": 1.918858421936206, "step": 1715}, {"loss": 0.21141836643218995, "token_acc": 0.9350021213406873, "grad_norm": 1.2777274288538676, "learning_rate": 3.112986856548759e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442736, "epoch": 1.9244543928371574, "step": 1720}, {"loss": 0.19971803426742554, "token_acc": 0.9248526919041085, "grad_norm": 1.0245041475644268, "learning_rate": 3.0844446936850136e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.44273, "epoch": 1.9300503637381086, "step": 1725}, {"loss": 0.23256092071533202, "token_acc": 0.9229964896556875, "grad_norm": 1.325125496923663, "learning_rate": 3.0559755030309766e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442744, "epoch": 1.9356463346390598, "step": 1730}, {"loss": 0.19755630493164061, "token_acc": 0.909935074739544, "grad_norm": 1.197214895935177, "learning_rate": 3.027580369107547e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442793, "epoch": 1.9412423055400112, "step": 1735}, {"loss": 0.2369536876678467, "token_acc": 0.9010204720465786, "grad_norm": 1.0151281883878918, "learning_rate": 2.999260373614456e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442813, "epoch": 1.9468382764409626, "step": 1740}, {"loss": 0.2143157958984375, "token_acc": 0.8924483982208007, "grad_norm": 1.1927810017954328, "learning_rate": 2.9710165953890767e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442833, "epoch": 1.9524342473419138, "step": 1745}, {"loss": 0.2051866054534912, "token_acc": 0.940868070477009, "grad_norm": 1.2028475963660856, "learning_rate": 2.9428501103653163e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.44287, "epoch": 1.958030218242865, "step": 1750}, {"loss": 0.24009857177734376, "token_acc": 0.9156408054203645, "grad_norm": 1.2323744430351997, "learning_rate": 2.9147619915326324e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442864, "epoch": 1.9636261891438165, "step": 1755}, {"loss": 0.19086207151412965, "token_acc": 0.9319941024695909, "grad_norm": 1.3694726513023645, "learning_rate": 2.8867533088951614e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442932, "epoch": 1.969222160044768, "step": 1760}, {"loss": 0.21189327239990235, "token_acc": 0.917502031969656, "grad_norm": 1.1243101097858472, "learning_rate": 2.858825129430954e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442946, "epoch": 1.9748181309457191, "step": 1765}, {"loss": 0.18747849464416505, "token_acc": 0.9306881463802705, "grad_norm": 1.314404713269285, "learning_rate": 2.8309785170513225e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442979, "epoch": 1.9804141018466703, "step": 1770}, {"loss": 0.1967552900314331, "token_acc": 0.9404498525073747, "grad_norm": 1.2259803309548771, "learning_rate": 2.8032145325603266e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.443, "epoch": 1.9860100727476218, "step": 1775}, {"loss": 0.24343225955963135, "token_acc": 0.918791887892767, "grad_norm": 1.4464000905447343, "learning_rate": 2.775534233614351e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.443018, "epoch": 1.9916060436485732, "step": 1780}, {"loss": 0.19745702743530275, "token_acc": 0.9319206965278506, "grad_norm": 1.301142136761119, "learning_rate": 2.7479386746818127e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.44305, "epoch": 1.9972020145495244, "step": 1785}, {"loss": 0.18561923503875732, "token_acc": 0.9382911392405063, "grad_norm": 1.0850219466081814, "learning_rate": 2.7204289070030055e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.443192, "epoch": 2.0022383883603805, "step": 1790}, {"loss": 0.17711580991744996, "token_acc": 0.912190491258603, "grad_norm": 1.2278778606530698, "learning_rate": 2.693005978550035e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.443214, "epoch": 2.0078343592613317, "step": 1795}, {"loss": 0.19735143184661866, "token_acc": 0.9093559210164457, "grad_norm": 1.1346108981502379, "learning_rate": 2.665670933986911e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.443215, "epoch": 2.0134303301622833, "step": 1800}, {"eval_loss": 0.26367783546447754, "eval_token_acc": 0.9001482508611088, "eval_runtime": 6.9393, "eval_samples_per_second": 15.563, "eval_steps_per_second": 2.594, "epoch": 2.0134303301622833, "step": 1800}, {"loss": 0.15310454368591309, "token_acc": 0.952543013802231, "grad_norm": 1.2400056422593364, "learning_rate": 2.638424814629751e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442444, "epoch": 2.0190263010632346, "step": 1805}, {"loss": 0.16407121419906617, "token_acc": 0.9348296908840323, "grad_norm": 1.3422159721501343, "learning_rate": 2.6112686584070945e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442487, "epoch": 2.0246222719641858, "step": 1810}, {"loss": 0.1493610382080078, "token_acc": 0.9424888448190382, "grad_norm": 1.3021240520783515, "learning_rate": 2.58420349982039e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442503, "epoch": 2.030218242865137, "step": 1815}, {"loss": 0.20290286540985109, "token_acc": 0.9229302832244008, "grad_norm": 1.1734303552654428, "learning_rate": 2.55723036990456e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442545, "epoch": 2.0358142137660886, "step": 1820}, {"loss": 0.1704019069671631, "token_acc": 0.9260758734442945, "grad_norm": 1.175514478000417, "learning_rate": 2.530350296188746e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442569, "epoch": 2.04141018466704, "step": 1825}, {"loss": 0.1619524359703064, "token_acc": 0.9424101653231316, "grad_norm": 1.2181747495652224, "learning_rate": 2.5035643026571544e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442592, "epoch": 2.047006155567991, "step": 1830}, {"loss": 0.17841706275939942, "token_acc": 0.931589089831011, "grad_norm": 1.277731000507594, "learning_rate": 2.4768734097100427e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442569, "epoch": 2.0526021264689422, "step": 1835}, {"loss": 0.14802837371826172, "token_acc": 0.9383998998372355, "grad_norm": 1.2219997962029614, "learning_rate": 2.450278634124864e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442615, "epoch": 2.0581980973698935, "step": 1840}, {"loss": 0.1637433409690857, "token_acc": 0.9260241468350897, "grad_norm": 1.2227674189010618, "learning_rate": 2.4237809890175166e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442664, "epoch": 2.063794068270845, "step": 1845}, {"loss": 0.15906648635864257, "token_acc": 0.9421514462138446, "grad_norm": 1.1797944825018591, "learning_rate": 2.3973814838037622e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442708, "epoch": 2.0693900391717963, "step": 1850}, {"loss": 0.17520735263824463, "token_acc": 0.9198778777126826, "grad_norm": 1.4128306063785532, "learning_rate": 2.3710811241607683e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442717, "epoch": 2.0749860100727475, "step": 1855}, {"loss": 0.17997454404830932, "token_acc": 0.9368106312292359, "grad_norm": 1.1216243175314227, "learning_rate": 2.344880911988791e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442756, "epoch": 2.0805819809736987, "step": 1860}, {"loss": 0.171247136592865, "token_acc": 0.9276703739643204, "grad_norm": 1.1785744948368826, "learning_rate": 2.318781845373022e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442801, "epoch": 2.0861779518746504, "step": 1865}, {"loss": 0.1540013313293457, "token_acc": 0.9361873268388596, "grad_norm": 1.270888966778523, "learning_rate": 2.2927849185455502e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442847, "epoch": 2.0917739227756016, "step": 1870}, {"loss": 0.16207342147827147, "token_acc": 0.9400119379228015, "grad_norm": 1.1930652524786638, "learning_rate": 2.2668911218475028e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442876, "epoch": 2.097369893676553, "step": 1875}, {"loss": 0.19941524267196656, "token_acc": 0.9058021670744495, "grad_norm": 1.1475435624698198, "learning_rate": 2.24110144169131e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442873, "epoch": 2.102965864577504, "step": 1880}, {"loss": 0.1726987600326538, "token_acc": 0.9099741552598832, "grad_norm": 1.247960307727673, "learning_rate": 2.215416860523125e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442924, "epoch": 2.1085618354784557, "step": 1885}, {"loss": 0.16721347570419312, "token_acc": 0.9216135995682677, "grad_norm": 1.2848658948193132, "learning_rate": 2.1898383567854113e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442938, "epoch": 2.114157806379407, "step": 1890}, {"loss": 0.17680699825286866, "token_acc": 0.9303384615384616, "grad_norm": 1.1984779495389188, "learning_rate": 2.164366904879651e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.44294, "epoch": 2.119753777280358, "step": 1895}, {"loss": 0.17396180629730223, "token_acc": 0.9202744263070736, "grad_norm": 1.193600579232686, "learning_rate": 2.139003475129242e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.44297, "epoch": 2.1253497481813093, "step": 1900}, {"loss": 0.16673849821090697, "token_acc": 0.9425412361790828, "grad_norm": 1.3422349993369314, "learning_rate": 2.1137490337425282e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442992, "epoch": 2.130945719082261, "step": 1905}, {"loss": 0.17441654205322266, "token_acc": 0.9423285109733294, "grad_norm": 1.2584208783133388, "learning_rate": 2.0886045427759855e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442995, "epoch": 2.136541689983212, "step": 1910}, {"loss": 0.16964504718780518, "token_acc": 0.9264286911345735, "grad_norm": 1.1780149589121789, "learning_rate": 2.063570960097578e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.443028, "epoch": 2.1421376608841634, "step": 1915}, {"loss": 0.17796406745910645, "token_acc": 0.9399419328079635, "grad_norm": 1.2639249158654253, "learning_rate": 2.0386492393502797e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.443046, "epoch": 2.1477336317851146, "step": 1920}, {"loss": 0.1551624655723572, "token_acc": 0.941284992379883, "grad_norm": 1.1220153973150235, "learning_rate": 2.013840329915723e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.443057, "epoch": 2.153329602686066, "step": 1925}, {"loss": 0.17658885717391967, "token_acc": 0.933706373292868, "grad_norm": 1.2637701343606473, "learning_rate": 1.989145176878052e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.443079, "epoch": 2.1589255735870174, "step": 1930}, {"loss": 0.13491592407226563, "token_acc": 0.9373566260808188, "grad_norm": 1.3530584724664532, "learning_rate": 1.964564720987908e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.443143, "epoch": 2.1645215444879686, "step": 1935}, {"loss": 0.15286178588867189, "token_acc": 0.9289142380190583, "grad_norm": 1.247257484723437, "learning_rate": 1.9400998986265953e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.443177, "epoch": 2.17011751538892, "step": 1940}, {"loss": 0.18882176876068116, "token_acc": 0.9496750793410911, "grad_norm": 1.396965184280961, "learning_rate": 1.9157516417704207e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.443164, "epoch": 2.1757134862898715, "step": 1945}, {"loss": 0.17173497676849364, "token_acc": 0.9374795631417173, "grad_norm": 1.256320640308238, "learning_rate": 1.891520877955173e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.443167, "epoch": 2.1813094571908227, "step": 1950}, {"loss": 0.14612654447555543, "token_acc": 0.946906918481403, "grad_norm": 1.2746656412590498, "learning_rate": 1.867408530240795e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.443202, "epoch": 2.186905428091774, "step": 1955}, {"loss": 0.15883901119232177, "token_acc": 0.9107088063823259, "grad_norm": 1.2563171551004302, "learning_rate": 1.843415517176229e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.443238, "epoch": 2.192501398992725, "step": 1960}, {"loss": 0.1506660223007202, "token_acc": 0.9347916666666667, "grad_norm": 1.344492615585863, "learning_rate": 1.8195427527644138e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.443271, "epoch": 2.1980973698936763, "step": 1965}, {"loss": 0.15175378322601318, "token_acc": 0.9402881271733731, "grad_norm": 1.1586443585235768, "learning_rate": 1.7957911464274724e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.443297, "epoch": 2.203693340794628, "step": 1970}, {"loss": 0.18235548734664916, "token_acc": 0.9201445214570122, "grad_norm": 1.2272708827418675, "learning_rate": 1.772161602972064e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.443305, "epoch": 2.209289311695579, "step": 1975}, {"loss": 0.15870845317840576, "token_acc": 0.9413212562764596, "grad_norm": 1.293735829731726, "learning_rate": 1.7486550225549165e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.443331, "epoch": 2.2148852825965304, "step": 1980}, {"loss": 0.17956327199935912, "token_acc": 0.9506149479659414, "grad_norm": 1.3131695568756556, "learning_rate": 1.72527230064854e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.443374, "epoch": 2.220481253497482, "step": 1985}, {"loss": 0.16729334592819214, "token_acc": 0.9163551141119357, "grad_norm": 1.2183640999801202, "learning_rate": 1.7020143280071111e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.443402, "epoch": 2.2260772243984333, "step": 1990}, {"loss": 0.17868465185165405, "token_acc": 0.9194095211188021, "grad_norm": 1.2660491929565059, "learning_rate": 1.6788819906325354e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.443423, "epoch": 2.2316731952993845, "step": 1995}, {"loss": 0.16553313732147218, "token_acc": 0.9501131733816206, "grad_norm": 1.3181964186223436, "learning_rate": 1.6558761697407061e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.44344, "epoch": 2.2372691662003357, "step": 2000}, {"eval_loss": 0.26636332273483276, "eval_token_acc": 0.9004727433889792, "eval_runtime": 6.8092, "eval_samples_per_second": 15.861, "eval_steps_per_second": 2.643, "epoch": 2.2372691662003357, "step": 2000}, {"loss": 0.1723008632659912, "token_acc": 0.915640674874601, "grad_norm": 1.266619830689515, "learning_rate": 1.632997741727922e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.441958, "epoch": 2.242865137101287, "step": 2005}, {"loss": 0.15712083578109742, "token_acc": 0.9483268185718372, "grad_norm": 1.4713250341727202, "learning_rate": 1.610247578137512e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.441992, "epoch": 2.2484611080022385, "step": 2010}, {"loss": 0.17420090436935426, "token_acc": 0.9302607640994542, "grad_norm": 1.069350669905107, "learning_rate": 1.5876265456266321e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.441994, "epoch": 2.2540570789031897, "step": 2015}, {"loss": 0.1750335454940796, "token_acc": 0.9383679067375279, "grad_norm": 1.3549867667848612, "learning_rate": 1.5651355059332412e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442019, "epoch": 2.259653049804141, "step": 2020}, {"loss": 0.15896975994110107, "token_acc": 0.9573364564162623, "grad_norm": 1.3246791560694868, "learning_rate": 1.5427753158432895e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442057, "epoch": 2.265249020705092, "step": 2025}, {"loss": 0.19799697399139404, "token_acc": 0.903164464381491, "grad_norm": 1.1760649764886135, "learning_rate": 1.5205468271580608e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442042, "epoch": 2.270844991606044, "step": 2030}, {"loss": 0.1616751194000244, "token_acc": 0.9534551056338029, "grad_norm": 1.258753479380627, "learning_rate": 1.4984508866617475e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.44208, "epoch": 2.276440962506995, "step": 2035}, {"loss": 0.16465919017791747, "token_acc": 0.9461686643835616, "grad_norm": 1.2271034969770178, "learning_rate": 1.4764883360891663e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442113, "epoch": 2.282036933407946, "step": 2040}, {"loss": 0.16746313571929933, "token_acc": 0.9308263695450325, "grad_norm": 1.2438423468682678, "learning_rate": 1.4546600120937094e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.44213, "epoch": 2.2876329043088974, "step": 2045}, {"loss": 0.19054002761840821, "token_acc": 0.9288946347769877, "grad_norm": 1.139695696210077, "learning_rate": 1.4329667462154722e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442155, "epoch": 2.293228875209849, "step": 2050}, {"loss": 0.1674778938293457, "token_acc": 0.918424317617866, "grad_norm": 1.2058648323664123, "learning_rate": 1.4114093648495658e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442162, "epoch": 2.2988248461108003, "step": 2055}, {"loss": 0.18378394842147827, "token_acc": 0.9335510755715734, "grad_norm": 1.2510242817844046, "learning_rate": 1.3899886892146474e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442144, "epoch": 2.3044208170117515, "step": 2060}, {"loss": 0.16771526336669923, "token_acc": 0.9308054481251051, "grad_norm": 1.2335649951472922, "learning_rate": 1.3687055353216328e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442179, "epoch": 2.3100167879127027, "step": 2065}, {"loss": 0.16559836864471436, "token_acc": 0.9553800389783568, "grad_norm": 1.3417762789507575, "learning_rate": 1.3475607139426027e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442233, "epoch": 2.3156127588136544, "step": 2070}, {"loss": 0.16012132167816162, "token_acc": 0.9448959365708622, "grad_norm": 1.1178366739611898, "learning_rate": 1.3265550305799307e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442251, "epoch": 2.3212087297146056, "step": 2075}, {"loss": 0.1774878740310669, "token_acc": 0.9126805191639754, "grad_norm": 1.1902532661413885, "learning_rate": 1.3056892854355853e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442274, "epoch": 2.3268047006155568, "step": 2080}, {"loss": 0.174135959148407, "token_acc": 0.946236559139785, "grad_norm": 1.2146177191052916, "learning_rate": 1.2849642733806556e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442306, "epoch": 2.332400671516508, "step": 2085}, {"loss": 0.16290172338485717, "token_acc": 0.9496350364963504, "grad_norm": 1.2321609420409616, "learning_rate": 1.2643807839250677e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442326, "epoch": 2.337996642417459, "step": 2090}, {"loss": 0.1558119535446167, "token_acc": 0.9386737317852412, "grad_norm": 1.2500344532874972, "learning_rate": 1.243939601187505e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.442336, "epoch": 2.343592613318411, "step": 2095}, {"loss": 0.18165855407714843, "token_acc": 0.926231691078562, "grad_norm": 1.3781074130334183, "learning_rate": 1.2236415038655435e-06, "memory(GiB)": 76.4, "train_speed(iter/s)": 0.44234, "epoch": 2.349188584219362, "step": 2100}, {"loss": 0.1871241807937622, "token_acc": 0.9030334579527708, "grad_norm": 1.342339986142211, "learning_rate": 1.2034872652059887e-06, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442305, "epoch": 2.3547845551203133, "step": 2105}, {"loss": 0.14789708852767944, "token_acc": 0.9666301969365426, "grad_norm": 1.2817567293316896, "learning_rate": 1.1834776529754072e-06, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442322, "epoch": 2.360380526021265, "step": 2110}, {"loss": 0.17597637176513672, "token_acc": 0.9246649463081662, "grad_norm": 1.2268430658270555, "learning_rate": 1.163613429430896e-06, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.44232, "epoch": 2.365976496922216, "step": 2115}, {"loss": 0.16379331350326537, "token_acc": 0.94415309596099, "grad_norm": 1.3986087003177086, "learning_rate": 1.14389535129103e-06, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442367, "epoch": 2.3715724678231673, "step": 2120}, {"loss": 0.17396849393844604, "token_acc": 0.9496092143150967, "grad_norm": 1.376249872397313, "learning_rate": 1.124324169707045e-06, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442403, "epoch": 2.3771684387241185, "step": 2125}, {"loss": 0.17383747100830077, "token_acc": 0.9283328030544066, "grad_norm": 1.2548992241921777, "learning_rate": 1.1049006302342185e-06, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442436, "epoch": 2.3827644096250697, "step": 2130}, {"loss": 0.1333468437194824, "token_acc": 0.9553715205889118, "grad_norm": 1.3869018709647463, "learning_rate": 1.0856254728034665e-06, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442473, "epoch": 2.3883603805260214, "step": 2135}, {"loss": 0.18759502172470094, "token_acc": 0.9157838983050848, "grad_norm": 1.3898355063513985, "learning_rate": 1.0664994316931627e-06, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.44251, "epoch": 2.3939563514269726, "step": 2140}, {"loss": 0.1732501983642578, "token_acc": 0.9391281695032998, "grad_norm": 1.4101681238504788, "learning_rate": 1.0475232355011566e-06, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442532, "epoch": 2.399552322327924, "step": 2145}, {"loss": 0.18823726177215577, "token_acc": 0.9173737893203051, "grad_norm": 1.1916671895670194, "learning_rate": 1.0286976071170285e-06, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442533, "epoch": 2.405148293228875, "step": 2150}, {"loss": 0.13603872060775757, "token_acc": 0.9596063153578019, "grad_norm": 1.38939402934436, "learning_rate": 1.0100232636945457e-06, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442574, "epoch": 2.4107442641298267, "step": 2155}, {"loss": 0.14615516662597655, "token_acc": 0.9339293501962495, "grad_norm": 1.1839108219672898, "learning_rate": 9.9150091662434e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442616, "epoch": 2.416340235030778, "step": 2160}, {"loss": 0.13922966718673707, "token_acc": 0.93811704106453, "grad_norm": 1.185201910386476, "learning_rate": 9.731312715068163e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442654, "epoch": 2.421936205931729, "step": 2165}, {"loss": 0.1840061664581299, "token_acc": 0.9225375405172984, "grad_norm": 1.2645541775953764, "learning_rate": 9.549150281252633e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442648, "epoch": 2.4275321768326803, "step": 2170}, {"loss": 0.16243042945861816, "token_acc": 0.9170923379174852, "grad_norm": 1.3518755199742414, "learning_rate": 9.368528804192029e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442638, "epoch": 2.433128147733632, "step": 2175}, {"loss": 0.1674189567565918, "token_acc": 0.9292905642706626, "grad_norm": 1.2940132287657133, "learning_rate": 9.189455164579525e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442667, "epoch": 2.438724118634583, "step": 2180}, {"loss": 0.15757845640182494, "token_acc": 0.944544906570223, "grad_norm": 1.1806228491832598, "learning_rate": 9.011936184144104e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442706, "epoch": 2.4443200895355344, "step": 2185}, {"loss": 0.15624525547027587, "token_acc": 0.9535159727029967, "grad_norm": 1.3011919485096592, "learning_rate": 8.835978625390751e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442722, "epoch": 2.4499160604364856, "step": 2190}, {"loss": 0.16322050094604493, "token_acc": 0.9319467135855222, "grad_norm": 1.2350795516270319, "learning_rate": 8.661589191342756e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442767, "epoch": 2.4555120313374372, "step": 2195}, {"loss": 0.17069439888000487, "token_acc": 0.9342807924203274, "grad_norm": 1.28774926068697, "learning_rate": 8.488774525286453e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442803, "epoch": 2.4611080022383884, "step": 2200}, {"eval_loss": 0.27052539587020874, "eval_token_acc": 0.9000036839196905, "eval_runtime": 6.8908, "eval_samples_per_second": 15.673, "eval_steps_per_second": 2.612, "epoch": 2.4611080022383884, "step": 2200}, {"loss": 0.14224891662597655, "token_acc": 0.9568543188654921, "grad_norm": 1.304693609011221, "learning_rate": 8.317541210518082e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442185, "epoch": 2.4667039731393396, "step": 2205}, {"loss": 0.16315112113952637, "token_acc": 0.9314263322884012, "grad_norm": 1.118702032334538, "learning_rate": 8.147895770093017e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442192, "epoch": 2.472299944040291, "step": 2210}, {"loss": 0.13917864561080934, "token_acc": 0.9470899470899471, "grad_norm": 1.2120903324563759, "learning_rate": 7.979844666577297e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.44221, "epoch": 2.477895914941242, "step": 2215}, {"loss": 0.18095111846923828, "token_acc": 0.9073305670816044, "grad_norm": 1.1556460595593043, "learning_rate": 7.81339430180143e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442208, "epoch": 2.4834918858421937, "step": 2220}, {"loss": 0.1651391863822937, "token_acc": 0.9439590238023501, "grad_norm": 1.3354387235357894, "learning_rate": 7.648551016616462e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442235, "epoch": 2.489087856743145, "step": 2225}, {"loss": 0.15539069175720216, "token_acc": 0.9352082296333167, "grad_norm": 1.3326219705523932, "learning_rate": 7.485321090652526e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442258, "epoch": 2.494683827644096, "step": 2230}, {"loss": 0.18741903305053711, "token_acc": 0.9260895762201246, "grad_norm": 1.321222892080106, "learning_rate": 7.323710742079538e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442295, "epoch": 2.500279798545048, "step": 2235}, {"loss": 0.16742051839828492, "token_acc": 0.9471188537264199, "grad_norm": 1.267436338458497, "learning_rate": 7.163726127370324e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.44228, "epoch": 2.505875769445999, "step": 2240}, {"loss": 0.1647175669670105, "token_acc": 0.9248651523208995, "grad_norm": 1.3375356044929705, "learning_rate": 7.005373341066197e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442281, "epoch": 2.51147174034695, "step": 2245}, {"loss": 0.1625560164451599, "token_acc": 0.9262408725390516, "grad_norm": 1.3148415778966152, "learning_rate": 6.848658415544618e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442312, "epoch": 2.5170677112479014, "step": 2250}, {"loss": 0.1868760108947754, "token_acc": 0.9265843313373253, "grad_norm": 1.6247461274101098, "learning_rate": 6.693587320789552e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442334, "epoch": 2.5226636821488526, "step": 2255}, {"loss": 0.16895049810409546, "token_acc": 0.9187955696554795, "grad_norm": 1.247703197290156, "learning_rate": 6.540165964163936e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442341, "epoch": 2.5282596530498043, "step": 2260}, {"loss": 0.17422326803207397, "token_acc": 0.9316696375519905, "grad_norm": 1.2885011880787358, "learning_rate": 6.388400190184674e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442364, "epoch": 2.5338556239507555, "step": 2265}, {"loss": 0.16969950199127198, "token_acc": 0.9239166946590527, "grad_norm": 1.4274130741706585, "learning_rate": 6.238295780300069e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442389, "epoch": 2.5394515948517067, "step": 2270}, {"loss": 0.1527194380760193, "token_acc": 0.9373237514782135, "grad_norm": 1.17324902063785, "learning_rate": 6.089858452669434e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442419, "epoch": 2.5450475657526583, "step": 2275}, {"loss": 0.16869300603866577, "token_acc": 0.9593002915451895, "grad_norm": 1.2102674424908406, "learning_rate": 5.943093861945393e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442439, "epoch": 2.5506435366536095, "step": 2280}, {"loss": 0.16076574325561524, "token_acc": 0.9468142548596112, "grad_norm": 1.1605621363843677, "learning_rate": 5.79800759905837e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442454, "epoch": 2.5562395075545608, "step": 2285}, {"loss": 0.1625348448753357, "token_acc": 0.9592737359727651, "grad_norm": 1.2439873123718215, "learning_rate": 5.654605191003698e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442484, "epoch": 2.561835478455512, "step": 2290}, {"loss": 0.16479986906051636, "token_acc": 0.9348108459165448, "grad_norm": 1.2825873051117826, "learning_rate": 5.512892100631018e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442483, "epoch": 2.567431449356463, "step": 2295}, {"loss": 0.17062801122665405, "token_acc": 0.9300467488312792, "grad_norm": 1.2758663284519018, "learning_rate": 5.372873726436146e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442503, "epoch": 2.573027420257415, "step": 2300}, {"loss": 0.1724137544631958, "token_acc": 0.9317517427479199, "grad_norm": 1.1760446280086632, "learning_rate": 5.234555402355474e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442517, "epoch": 2.578623391158366, "step": 2305}, {"loss": 0.16632583141326904, "token_acc": 0.933369785970942, "grad_norm": 1.0571014453775205, "learning_rate": 5.097942397562772e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.44252, "epoch": 2.5842193620593172, "step": 2310}, {"loss": 0.18920276165008545, "token_acc": 0.9448138957816378, "grad_norm": 1.3145687047830004, "learning_rate": 4.963039916268437e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442544, "epoch": 2.5898153329602684, "step": 2315}, {"loss": 0.1724681258201599, "token_acc": 0.934030694052073, "grad_norm": 1.404297958809576, "learning_rate": 4.829853097521242e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442567, "epoch": 2.59541130386122, "step": 2320}, {"loss": 0.1769292712211609, "token_acc": 0.93441317047265, "grad_norm": 1.2213373820989282, "learning_rate": 4.6983870150125846e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442561, "epoch": 2.6010072747621713, "step": 2325}, {"loss": 0.1712023973464966, "token_acc": 0.9342925219941349, "grad_norm": 1.0862616572032477, "learning_rate": 4.568646676883165e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442578, "epoch": 2.6066032456631225, "step": 2330}, {"loss": 0.16326529979705812, "token_acc": 0.9279852125693161, "grad_norm": 1.173066789519362, "learning_rate": 4.4406370255323015e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442595, "epoch": 2.6121992165640737, "step": 2335}, {"loss": 0.17463016510009766, "token_acc": 0.930327868852459, "grad_norm": 1.309932861479588, "learning_rate": 4.3143629374295224e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442605, "epoch": 2.617795187465025, "step": 2340}, {"loss": 0.15369285345077516, "token_acc": 0.9530141843971631, "grad_norm": 1.2955058188307895, "learning_rate": 4.189829222928876e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442635, "epoch": 2.6233911583659766, "step": 2345}, {"loss": 0.15233397483825684, "token_acc": 0.9395528366470032, "grad_norm": 1.350369176452996, "learning_rate": 4.0670406260856943e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442672, "epoch": 2.628987129266928, "step": 2350}, {"loss": 0.16372932195663453, "token_acc": 0.9596793209148786, "grad_norm": 1.210401786079074, "learning_rate": 3.9460018244758033e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442685, "epoch": 2.634583100167879, "step": 2355}, {"loss": 0.17064323425292968, "token_acc": 0.9167206320424816, "grad_norm": 1.2089454635788595, "learning_rate": 3.826717429017429e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.4427, "epoch": 2.6401790710688307, "step": 2360}, {"loss": 0.17503581047058106, "token_acc": 0.9258812750156725, "grad_norm": 1.1141216679426227, "learning_rate": 3.709191983795446e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442641, "epoch": 2.645775041969782, "step": 2365}, {"loss": 0.1577782154083252, "token_acc": 0.9388238573021181, "grad_norm": 1.200567824072627, "learning_rate": 3.5934299658883174e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442669, "epoch": 2.651371012870733, "step": 2370}, {"loss": 0.18190815448760986, "token_acc": 0.9221982093238654, "grad_norm": 1.2164367300604706, "learning_rate": 3.4794357851975825e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442655, "epoch": 2.6569669837716843, "step": 2375}, {"loss": 0.1689607858657837, "token_acc": 0.9424821257069683, "grad_norm": 1.2977500077226098, "learning_rate": 3.3672137842797714e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442681, "epoch": 2.6625629546726355, "step": 2380}, {"loss": 0.16155383586883545, "token_acc": 0.9337298215802888, "grad_norm": 1.2248957028318568, "learning_rate": 3.2567682381810964e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442697, "epoch": 2.668158925573587, "step": 2385}, {"loss": 0.16212856769561768, "token_acc": 0.9497751124437781, "grad_norm": 1.2980279961014698, "learning_rate": 3.1481033542744675e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442704, "epoch": 2.6737548964745383, "step": 2390}, {"loss": 0.16877028942108155, "token_acc": 0.9279858393888578, "grad_norm": 1.2701718081318778, "learning_rate": 3.041223272099303e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442734, "epoch": 2.6793508673754896, "step": 2395}, {"loss": 0.1528432250022888, "token_acc": 0.9286967080410146, "grad_norm": 1.3330944758304843, "learning_rate": 2.9361320632038114e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442698, "epoch": 2.684946838276441, "step": 2400}, {"eval_loss": 0.2639254927635193, "eval_token_acc": 0.90167581304556, "eval_runtime": 7.0963, "eval_samples_per_second": 15.219, "eval_steps_per_second": 2.537, "epoch": 2.684946838276441, "step": 2400}, {"loss": 0.1815276026725769, "token_acc": 0.9416877734285056, "grad_norm": 1.1061131787920164, "learning_rate": 2.8328337309898923e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442089, "epoch": 2.6905428091773924, "step": 2405}, {"loss": 0.16827319860458373, "token_acc": 0.9388384754990926, "grad_norm": 1.3505060127636601, "learning_rate": 2.7313322105605997e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442097, "epoch": 2.6961387800783436, "step": 2410}, {"loss": 0.16080224514007568, "token_acc": 0.9369645042839657, "grad_norm": 1.2156800536319636, "learning_rate": 2.631631368570281e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442113, "epoch": 2.701734750979295, "step": 2415}, {"loss": 0.15746282339096068, "token_acc": 0.9442791452529078, "grad_norm": 1.3795364584714653, "learning_rate": 2.5337350030772367e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442144, "epoch": 2.707330721880246, "step": 2420}, {"loss": 0.17066744565963746, "token_acc": 0.9246709129511678, "grad_norm": 1.2279367417162175, "learning_rate": 2.437646843399072e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442176, "epoch": 2.7129266927811977, "step": 2425}, {"loss": 0.17276360988616943, "token_acc": 0.9461141912265344, "grad_norm": 1.28782671386308, "learning_rate": 2.3433705499706083e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442192, "epoch": 2.718522663682149, "step": 2430}, {"loss": 0.1546282649040222, "token_acc": 0.9186991869918699, "grad_norm": 1.2699836055082525, "learning_rate": 2.25090971420443e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442223, "epoch": 2.7241186345831, "step": 2435}, {"loss": 0.1678828239440918, "token_acc": 0.9286865089459849, "grad_norm": 1.2420163247674112, "learning_rate": 2.160267858354115e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442242, "epoch": 2.7297146054840518, "step": 2440}, {"loss": 0.15652635097503662, "token_acc": 0.9216832261835184, "grad_norm": 1.2357948377184067, "learning_rate": 2.0714484353799857e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442267, "epoch": 2.735310576385003, "step": 2445}, {"loss": 0.1764933943748474, "token_acc": 0.9520306062389641, "grad_norm": 1.2222244682157668, "learning_rate": 1.98445482881765e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442294, "epoch": 2.740906547285954, "step": 2450}, {"loss": 0.1705174684524536, "token_acc": 0.957953884906026, "grad_norm": 1.2208163413271533, "learning_rate": 1.899290352649058e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442301, "epoch": 2.7465025181869054, "step": 2455}, {"loss": 0.158874773979187, "token_acc": 0.9513751709466647, "grad_norm": 1.2438996089905598, "learning_rate": 1.8159582511762475e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.44232, "epoch": 2.7520984890878566, "step": 2460}, {"loss": 0.14871559143066407, "token_acc": 0.9384726373286613, "grad_norm": 1.4593779229475397, "learning_rate": 1.7344616988978101e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442346, "epoch": 2.757694459988808, "step": 2465}, {"loss": 0.16535134315490724, "token_acc": 0.9414995423150537, "grad_norm": 1.2523081658329125, "learning_rate": 1.6548038003878887e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442358, "epoch": 2.7632904308897595, "step": 2470}, {"loss": 0.15060312747955323, "token_acc": 0.919426320325003, "grad_norm": 1.2974096910420287, "learning_rate": 1.5769875901779697e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442387, "epoch": 2.7688864017907107, "step": 2475}, {"loss": 0.17185330390930176, "token_acc": 0.9269832161813226, "grad_norm": 1.1681063388797248, "learning_rate": 1.501016032641256e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442423, "epoch": 2.774482372691662, "step": 2480}, {"loss": 0.18785089254379272, "token_acc": 0.9324223602484472, "grad_norm": 1.2153812447756143, "learning_rate": 1.426892021879722e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442438, "epoch": 2.7800783435926135, "step": 2485}, {"loss": 0.16023200750350952, "token_acc": 0.9315770215879985, "grad_norm": 1.2461683962637302, "learning_rate": 1.3546183816139257e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442464, "epoch": 2.7856743144935647, "step": 2490}, {"loss": 0.14799857139587402, "token_acc": 0.9573267756400984, "grad_norm": 1.2228378212644044, "learning_rate": 1.2841978650753706e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.44249, "epoch": 2.791270285394516, "step": 2495}, {"loss": 0.2053931713104248, "token_acc": 0.9228681851821396, "grad_norm": 1.1474990035637709, "learning_rate": 1.2156331549016576e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442523, "epoch": 2.796866256295467, "step": 2500}, {"loss": 0.18525865077972412, "token_acc": 0.92442322991249, "grad_norm": 1.1901826168902156, "learning_rate": 1.1489268630342997e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442565, "epoch": 2.8024622271964184, "step": 2505}, {"loss": 0.172202205657959, "token_acc": 0.9321968602523355, "grad_norm": 1.3068678073171385, "learning_rate": 1.0840815306191966e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442586, "epoch": 2.80805819809737, "step": 2510}, {"loss": 0.16816768646240235, "token_acc": 0.935831381733021, "grad_norm": 1.336845300654527, "learning_rate": 1.021099627909844e-07, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442559, "epoch": 2.813654168998321, "step": 2515}, {"loss": 0.14555788040161133, "token_acc": 0.9442632671212571, "grad_norm": 1.1541777235037767, "learning_rate": 9.599835541732383e-08, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442593, "epoch": 2.8192501398992724, "step": 2520}, {"loss": 0.15869925022125245, "token_acc": 0.9409968479117415, "grad_norm": 1.433076786845026, "learning_rate": 9.007356375984544e-08, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442606, "epoch": 2.824846110800224, "step": 2525}, {"loss": 0.16980502605438233, "token_acc": 0.933903321275896, "grad_norm": 1.1320107449233108, "learning_rate": 8.433581352079833e-08, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442626, "epoch": 2.8304420817011753, "step": 2530}, {"loss": 0.1655329465866089, "token_acc": 0.9204145218098077, "grad_norm": 1.2666458142424961, "learning_rate": 7.87853232771718e-08, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442626, "epoch": 2.8360380526021265, "step": 2535}, {"loss": 0.17194554805755616, "token_acc": 0.9364294220023817, "grad_norm": 1.1523691803015328, "learning_rate": 7.342230447237197e-08, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442576, "epoch": 2.8416340235030777, "step": 2540}, {"loss": 0.16607561111450195, "token_acc": 0.9283870491924183, "grad_norm": 1.4697052778996835, "learning_rate": 6.8246961408166e-08, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442603, "epoch": 2.847229994404029, "step": 2545}, {"loss": 0.1448741674423218, "token_acc": 0.9328611332801277, "grad_norm": 1.2142717819755466, "learning_rate": 6.325949123689723e-08, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442628, "epoch": 2.8528259653049806, "step": 2550}, {"loss": 0.16714261770248412, "token_acc": 0.92510239906378, "grad_norm": 1.1248721103309427, "learning_rate": 5.8460083953978955e-08, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442651, "epoch": 2.8584219362059318, "step": 2555}, {"loss": 0.16560882329940796, "token_acc": 0.9422254571922482, "grad_norm": 1.2999400568749204, "learning_rate": 5.3848922390651314e-08, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442683, "epoch": 2.864017907106883, "step": 2560}, {"loss": 0.17857794761657714, "token_acc": 0.9238667183262301, "grad_norm": 1.3514941033773715, "learning_rate": 4.9426182207020775e-08, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442669, "epoch": 2.8696138780078346, "step": 2565}, {"loss": 0.16211841106414795, "token_acc": 0.9458953560923433, "grad_norm": 1.185224184542901, "learning_rate": 4.5192031885367136e-08, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442613, "epoch": 2.875209848908786, "step": 2570}, {"loss": 0.20226593017578126, "token_acc": 0.9525655411608691, "grad_norm": 1.3598330316054918, "learning_rate": 4.114663272372421e-08, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.44265, "epoch": 2.880805819809737, "step": 2575}, {"loss": 0.16548022031784057, "token_acc": 0.9290593425359328, "grad_norm": 1.1409447853455221, "learning_rate": 3.7290138829736425e-08, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.44268, "epoch": 2.8864017907106883, "step": 2580}, {"loss": 0.17504165172576905, "token_acc": 0.9279152467032153, "grad_norm": 1.1932418687223627, "learning_rate": 3.362269711478794e-08, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442692, "epoch": 2.8919977616116395, "step": 2585}, {"loss": 0.12353341579437256, "token_acc": 0.9631807721810278, "grad_norm": 1.3618787602920703, "learning_rate": 3.014444728840549e-08, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442715, "epoch": 2.8975937325125907, "step": 2590}, {"loss": 0.17372788190841676, "token_acc": 0.9584448966477456, "grad_norm": 1.2554880116449778, "learning_rate": 2.6855521852937606e-08, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442728, "epoch": 2.9031897034135423, "step": 2595}, {"loss": 0.1414646625518799, "token_acc": 0.9227025883348614, "grad_norm": 1.3842739136612618, "learning_rate": 2.3756046098504793e-08, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442769, "epoch": 2.9087856743144935, "step": 2600}, {"eval_loss": 0.27052757143974304, "eval_token_acc": 0.899545007202864, "eval_runtime": 6.9568, "eval_samples_per_second": 15.524, "eval_steps_per_second": 2.587, "epoch": 2.9087856743144935, "step": 2600}, {"loss": 0.16337907314300537, "token_acc": 0.927981522956327, "grad_norm": 1.1671310615595727, "learning_rate": 2.0846138098229995e-08, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442252, "epoch": 2.9143816452154447, "step": 2605}, {"loss": 0.14915704727172852, "token_acc": 0.9308914510686164, "grad_norm": 1.3091456222811118, "learning_rate": 1.812590870373554e-08, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.44227, "epoch": 2.9199776161163964, "step": 2610}, {"loss": 0.16016900539398193, "token_acc": 0.9260042283298098, "grad_norm": 1.1851395349392027, "learning_rate": 1.5595461540926503e-08, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442296, "epoch": 2.9255735870173476, "step": 2615}, {"loss": 0.15380818843841554, "token_acc": 0.9209589810825998, "grad_norm": 1.2944727183719047, "learning_rate": 1.3254893006038883e-08, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442322, "epoch": 2.931169557918299, "step": 2620}, {"loss": 0.15956332683563232, "token_acc": 0.9354969163886361, "grad_norm": 1.2882060323850986, "learning_rate": 1.110429226196752e-08, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442314, "epoch": 2.93676552881925, "step": 2625}, {"loss": 0.15384410619735717, "token_acc": 0.9398040828535108, "grad_norm": 1.352781615539, "learning_rate": 9.143741234871606e-09, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.44235, "epoch": 2.9423614997202012, "step": 2630}, {"loss": 0.17564117908477783, "token_acc": 0.9402447121312719, "grad_norm": 1.185868294588732, "learning_rate": 7.373314611052174e-09, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442366, "epoch": 2.947957470621153, "step": 2635}, {"loss": 0.14418158531188965, "token_acc": 0.9575358851674641, "grad_norm": 1.2500596359439817, "learning_rate": 5.7930798341082615e-09, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442399, "epoch": 2.953553441522104, "step": 2640}, {"loss": 0.1636657953262329, "token_acc": 0.9181030786381957, "grad_norm": 1.4536982518875539, "learning_rate": 4.403097102366194e-09, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.4424, "epoch": 2.9591494124230553, "step": 2645}, {"loss": 0.19950826168060304, "token_acc": 0.9042246900522944, "grad_norm": 1.3448692858368538, "learning_rate": 3.2034193665869684e-09, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442399, "epoch": 2.964745383324007, "step": 2650}, {"loss": 0.15716251134872436, "token_acc": 0.929654036243822, "grad_norm": 1.2589648663588275, "learning_rate": 2.194092327948982e-09, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442414, "epoch": 2.970341354224958, "step": 2655}, {"loss": 0.15098288059234619, "token_acc": 0.9312050359712231, "grad_norm": 1.2996635592171242, "learning_rate": 1.3751544363077574e-09, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442434, "epoch": 2.9759373251259094, "step": 2660}, {"loss": 0.1571295976638794, "token_acc": 0.940810953133228, "grad_norm": 1.2567143547738586, "learning_rate": 7.466368887304454e-10, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442458, "epoch": 2.9815332960268606, "step": 2665}, {"loss": 0.16352345943450927, "token_acc": 0.9316484778862723, "grad_norm": 1.3427380726944973, "learning_rate": 3.0856362830733453e-10, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.442502, "epoch": 2.9871292669278118, "step": 2670}, {"loss": 0.16283302307128905, "token_acc": 0.928603302097278, "grad_norm": 1.233578482321699, "learning_rate": 6.095134324091145e-11, "memory(GiB)": 76.69, "train_speed(iter/s)": 0.44253, "epoch": 2.9927252378287634, "step": 2675}, {"eval_loss": 0.2652188837528229, "eval_token_acc": 0.9002402198769324, "eval_runtime": 6.9203, "eval_samples_per_second": 15.606, "eval_steps_per_second": 2.601, "epoch": 2.9972020145495244, "step": 2679}, {"train_runtime": 6064.6686, "train_samples_per_second": 5.306, "train_steps_per_second": 0.442, "total_flos": 9.423481207154278e+17, "train_loss": 0.23683785317592898, "epoch": 2.9972020145495244, "step": 2679}], "memory": 76.689453125} |
|
|
