| {"current_steps": 2, "total_steps": 102, "loss": 0.6931, "accuracy": 0.0, "learning_rate": 9.090909090909091e-07, "epoch": 0.05755395683453238, "percentage": 1.96, "elapsed_time": "0:00:18", "remaining_time": "0:15:17", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 4, "total_steps": 102, "loss": 0.7202, "accuracy": 0.421875, "learning_rate": 1.8181818181818183e-06, "epoch": 0.11510791366906475, "percentage": 3.92, "elapsed_time": "0:00:36", "remaining_time": "0:15:04", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 6, "total_steps": 102, "loss": 0.6931, "accuracy": 0.578125, "learning_rate": 2.7272727272727272e-06, "epoch": 0.17266187050359713, "percentage": 5.88, "elapsed_time": "0:00:52", "remaining_time": "0:14:01", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 8, "total_steps": 102, "loss": 0.7227, "accuracy": 0.453125, "learning_rate": 3.6363636363636366e-06, "epoch": 0.2302158273381295, "percentage": 7.84, "elapsed_time": "0:01:08", "remaining_time": "0:13:21", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 10, "total_steps": 102, "loss": 0.7281, "accuracy": 0.46875, "learning_rate": 4.5454545454545455e-06, "epoch": 0.28776978417266186, "percentage": 9.8, "elapsed_time": "0:01:24", "remaining_time": "0:12:58", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 12, "total_steps": 102, "loss": 0.6629, "accuracy": 0.65625, "learning_rate": 4.998510351377676e-06, "epoch": 0.34532374100719426, "percentage": 11.76, "elapsed_time": "0:01:41", "remaining_time": "0:12:40", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 14, "total_steps": 102, "loss": 0.6747, "accuracy": 0.578125, "learning_rate": 4.986603811737982e-06, "epoch": 0.4028776978417266, "percentage": 13.73, "elapsed_time": "0:01:57", "remaining_time": "0:12:18", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 16, "total_steps": 102, "loss": 0.6627, "accuracy": 0.65625, "learning_rate": 4.9628474725421845e-06, "epoch": 0.460431654676259, "percentage": 15.69, "elapsed_time": "0:02:16", "remaining_time": "0:12:15", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 18, "total_steps": 102, "loss": 0.6371, "accuracy": 0.609375, "learning_rate": 4.927354543565131e-06, "epoch": 0.5179856115107914, "percentage": 17.65, "elapsed_time": "0:02:33", "remaining_time": "0:11:55", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 20, "total_steps": 102, "loss": 0.6767, "accuracy": 0.5, "learning_rate": 4.880294164776785e-06, "epoch": 0.5755395683453237, "percentage": 19.61, "elapsed_time": "0:02:48", "remaining_time": "0:11:31", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 22, "total_steps": 102, "loss": 0.6326, "accuracy": 0.59375, "learning_rate": 4.821890600313256e-06, "epoch": 0.6330935251798561, "percentage": 21.57, "elapsed_time": "0:03:05", "remaining_time": "0:11:16", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 24, "total_steps": 102, "loss": 0.6138, "accuracy": 0.6875, "learning_rate": 4.752422169756048e-06, "epoch": 0.6906474820143885, "percentage": 23.53, "elapsed_time": "0:03:26", "remaining_time": "0:11:09", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 26, "total_steps": 102, "loss": 0.6185, "accuracy": 0.65625, "learning_rate": 4.672219921812517e-06, "epoch": 0.7482014388489209, "percentage": 25.49, "elapsed_time": "0:03:43", "remaining_time": "0:10:52", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 28, "total_steps": 102, "loss": 0.6222, "accuracy": 0.640625, "learning_rate": 4.581666056718016e-06, "epoch": 0.8057553956834532, "percentage": 27.45, "elapsed_time": "0:04:02", "remaining_time": "0:10:40", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 30, "total_steps": 102, "loss": 0.4954, "accuracy": 0.875, "learning_rate": 4.481192104877727e-06, "epoch": 0.8633093525179856, "percentage": 29.41, "elapsed_time": "0:04:20", "remaining_time": "0:10:24", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 32, "total_steps": 102, "loss": 0.4999, "accuracy": 0.84375, "learning_rate": 4.3712768704277535e-06, "epoch": 0.920863309352518, "percentage": 31.37, "elapsed_time": "0:04:40", "remaining_time": "0:10:14", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 34, "total_steps": 102, "loss": 0.4695, "accuracy": 0.828125, "learning_rate": 4.252444149515374e-06, "epoch": 0.9784172661870504, "percentage": 33.33, "elapsed_time": "0:04:57", "remaining_time": "0:09:55", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 36, "total_steps": 102, "loss": 0.4663, "accuracy": 0.84375, "learning_rate": 4.125260234171861e-06, "epoch": 1.0359712230215827, "percentage": 35.29, "elapsed_time": "0:05:16", "remaining_time": "0:09:41", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 38, "total_steps": 102, "loss": 0.4458, "accuracy": 0.78125, "learning_rate": 3.990331213673064e-06, "epoch": 1.0935251798561152, "percentage": 37.25, "elapsed_time": "0:05:34", "remaining_time": "0:09:24", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 40, "total_steps": 102, "loss": 0.3395, "accuracy": 0.921875, "learning_rate": 3.848300086247998e-06, "epoch": 1.1510791366906474, "percentage": 39.22, "elapsed_time": "0:05:52", "remaining_time": "0:09:06", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 42, "total_steps": 102, "loss": 0.3934, "accuracy": 0.890625, "learning_rate": 3.6998436948994664e-06, "epoch": 1.20863309352518, "percentage": 41.18, "elapsed_time": "0:06:08", "remaining_time": "0:08:46", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 44, "total_steps": 102, "loss": 0.4418, "accuracy": 0.796875, "learning_rate": 3.545669501938913e-06, "epoch": 1.2661870503597124, "percentage": 43.14, "elapsed_time": "0:06:26", "remaining_time": "0:08:28", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 46, "total_steps": 102, "loss": 0.35, "accuracy": 0.859375, "learning_rate": 3.386512217606339e-06, "epoch": 1.3237410071942446, "percentage": 45.1, "elapsed_time": "0:06:41", "remaining_time": "0:08:08", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 48, "total_steps": 102, "loss": 0.3598, "accuracy": 0.875, "learning_rate": 3.2231302988414198e-06, "epoch": 1.381294964028777, "percentage": 47.06, "elapsed_time": "0:07:00", "remaining_time": "0:07:52", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 50, "total_steps": 102, "loss": 0.3145, "accuracy": 0.90625, "learning_rate": 3.056302334890786e-06, "epoch": 1.4388489208633093, "percentage": 49.02, "elapsed_time": "0:07:18", "remaining_time": "0:07:35", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 52, "total_steps": 102, "loss": 0.3824, "accuracy": 0.828125, "learning_rate": 2.886823336975703e-06, "epoch": 1.4964028776978417, "percentage": 50.98, "elapsed_time": "0:07:37", "remaining_time": "0:07:19", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 54, "total_steps": 102, "loss": 0.3495, "accuracy": 0.890625, "learning_rate": 2.7155009497015487e-06, "epoch": 1.5539568345323742, "percentage": 52.94, "elapsed_time": "0:07:53", "remaining_time": "0:07:00", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 56, "total_steps": 102, "loss": 0.3193, "accuracy": 0.84375, "learning_rate": 2.5431516022634718e-06, "epoch": 1.6115107913669064, "percentage": 54.9, "elapsed_time": "0:08:09", "remaining_time": "0:06:42", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 58, "total_steps": 102, "loss": 0.3311, "accuracy": 0.8125, "learning_rate": 2.3705966177894763e-06, "epoch": 1.6690647482014387, "percentage": 56.86, "elapsed_time": "0:08:28", "remaining_time": "0:06:26", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 60, "total_steps": 102, "loss": 0.2872, "accuracy": 0.90625, "learning_rate": 2.1986582993616926e-06, "epoch": 1.7266187050359711, "percentage": 58.82, "elapsed_time": "0:08:45", "remaining_time": "0:06:08", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 62, "total_steps": 102, "loss": 0.3258, "accuracy": 0.90625, "learning_rate": 2.0281560113677085e-06, "epoch": 1.7841726618705036, "percentage": 60.78, "elapsed_time": "0:09:05", "remaining_time": "0:05:52", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 64, "total_steps": 102, "loss": 0.2994, "accuracy": 0.921875, "learning_rate": 1.8599022748561324e-06, "epoch": 1.841726618705036, "percentage": 62.75, "elapsed_time": "0:09:22", "remaining_time": "0:05:33", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 66, "total_steps": 102, "loss": 0.2577, "accuracy": 0.921875, "learning_rate": 1.694698895503774e-06, "epoch": 1.8992805755395683, "percentage": 64.71, "elapsed_time": "0:09:39", "remaining_time": "0:05:16", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 68, "total_steps": 102, "loss": 0.2053, "accuracy": 0.96875, "learning_rate": 1.5333331426464532e-06, "epoch": 1.9568345323741008, "percentage": 66.67, "elapsed_time": "0:10:00", "remaining_time": "0:05:00", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 70, "total_steps": 102, "loss": 0.3402, "accuracy": 0.84375, "learning_rate": 1.3765739975820964e-06, "epoch": 2.014388489208633, "percentage": 68.63, "elapsed_time": "0:10:17", "remaining_time": "0:04:42", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 72, "total_steps": 102, "loss": 0.3119, "accuracy": 0.890625, "learning_rate": 1.225168489024661e-06, "epoch": 2.0719424460431655, "percentage": 70.59, "elapsed_time": "0:10:33", "remaining_time": "0:04:24", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 74, "total_steps": 102, "loss": 0.2232, "accuracy": 0.9375, "learning_rate": 1.079838133172111e-06, "epoch": 2.129496402877698, "percentage": 72.55, "elapsed_time": "0:10:51", "remaining_time": "0:04:06", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 76, "total_steps": 102, "loss": 0.2777, "accuracy": 0.875, "learning_rate": 9.412754953531664e-07, "epoch": 2.1870503597122304, "percentage": 74.51, "elapsed_time": "0:11:06", "remaining_time": "0:03:48", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 78, "total_steps": 102, "loss": 0.2124, "accuracy": 0.953125, "learning_rate": 8.101408896381141e-07, "epoch": 2.2446043165467624, "percentage": 76.47, "elapsed_time": "0:11:25", "remaining_time": "0:03:30", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 80, "total_steps": 102, "loss": 0.1949, "accuracy": 0.96875, "learning_rate": 6.870592321415595e-07, "epoch": 2.302158273381295, "percentage": 78.43, "elapsed_time": "0:11:44", "remaining_time": "0:03:13", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 82, "total_steps": 102, "loss": 0.2402, "accuracy": 0.90625, "learning_rate": 5.72617063012551e-07, "epoch": 2.3597122302158273, "percentage": 80.39, "elapsed_time": "0:12:01", "remaining_time": "0:02:56", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 84, "total_steps": 102, "loss": 0.2859, "accuracy": 0.875, "learning_rate": 4.673597513036684e-07, "epoch": 2.41726618705036, "percentage": 82.35, "elapsed_time": "0:12:23", "remaining_time": "0:02:39", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 86, "total_steps": 102, "loss": 0.2294, "accuracy": 0.953125, "learning_rate": 3.717888960391222e-07, "epoch": 2.4748201438848922, "percentage": 84.31, "elapsed_time": "0:12:41", "remaining_time": "0:02:21", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 88, "total_steps": 102, "loss": 0.2516, "accuracy": 0.84375, "learning_rate": 2.8635993586697555e-07, "epoch": 2.5323741007194247, "percentage": 86.27, "elapsed_time": "0:12:55", "remaining_time": "0:02:03", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 90, "total_steps": 102, "loss": 0.2254, "accuracy": 0.953125, "learning_rate": 2.1147997868658427e-07, "epoch": 2.5899280575539567, "percentage": 88.24, "elapsed_time": "0:13:09", "remaining_time": "0:01:45", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 92, "total_steps": 102, "loss": 0.3215, "accuracy": 0.84375, "learning_rate": 1.4750586159405917e-07, "epoch": 2.647482014388489, "percentage": 90.2, "elapsed_time": "0:13:26", "remaining_time": "0:01:27", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 94, "total_steps": 102, "loss": 0.2675, "accuracy": 0.890625, "learning_rate": 9.474245039099883e-08, "epoch": 2.7050359712230216, "percentage": 92.16, "elapsed_time": "0:13:47", "remaining_time": "0:01:10", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 96, "total_steps": 102, "loss": 0.2482, "accuracy": 0.875, "learning_rate": 5.344118676011173e-08, "epoch": 2.762589928057554, "percentage": 94.12, "elapsed_time": "0:14:06", "remaining_time": "0:00:52", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 98, "total_steps": 102, "loss": 0.2811, "accuracy": 0.890625, "learning_rate": 2.3798890031092037e-08, "epoch": 2.8201438848920866, "percentage": 96.08, "elapsed_time": "0:14:23", "remaining_time": "0:00:35", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 100, "total_steps": 102, "loss": 0.169, "accuracy": 0.96875, "learning_rate": 5.9568192468811844e-09, "epoch": 2.8776978417266186, "percentage": 98.04, "elapsed_time": "0:14:40", "remaining_time": "0:00:17", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 102, "total_steps": 102, "loss": 0.19, "accuracy": 0.953125, "learning_rate": 0.0, "epoch": 2.935251798561151, "percentage": 100.0, "elapsed_time": "0:14:56", "remaining_time": "0:00:00", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 102, "total_steps": 102, "epoch": 2.935251798561151, "percentage": 100.0, "elapsed_time": "0:14:56", "remaining_time": "0:00:00", "throughput": "0.00", "total_tokens": 0} | |