{"current_steps": 2, "total_steps": 141, "loss": 1.0015, "learning_rate": 1.3333333333333333e-05, "epoch": 0.041884816753926704, "percentage": 1.42, "elapsed_time": "0:00:07", "remaining_time": "0:08:23", "throughput": "0.00", "total_tokens": 0} {"current_steps": 4, "total_steps": 141, "loss": 0.9283, "learning_rate": 2.6666666666666667e-05, "epoch": 0.08376963350785341, "percentage": 2.84, "elapsed_time": "0:00:15", "remaining_time": "0:08:48", "throughput": "0.00", "total_tokens": 0} {"current_steps": 6, "total_steps": 141, "loss": 0.8643, "learning_rate": 4e-05, "epoch": 0.1256544502617801, "percentage": 4.26, "elapsed_time": "0:00:23", "remaining_time": "0:08:42", "throughput": "0.00", "total_tokens": 0} {"current_steps": 8, "total_steps": 141, "loss": 1.0013, "learning_rate": 5.333333333333333e-05, "epoch": 0.16753926701570682, "percentage": 5.67, "elapsed_time": "0:00:30", "remaining_time": "0:08:24", "throughput": "0.00", "total_tokens": 0} {"current_steps": 10, "total_steps": 141, "loss": 0.9341, "learning_rate": 6.666666666666667e-05, "epoch": 0.2094240837696335, "percentage": 7.09, "elapsed_time": "0:00:38", "remaining_time": "0:08:24", "throughput": "0.00", "total_tokens": 0} {"current_steps": 12, "total_steps": 141, "loss": 0.9068, "learning_rate": 8e-05, "epoch": 0.2513089005235602, "percentage": 8.51, "elapsed_time": "0:00:45", "remaining_time": "0:08:13", "throughput": "0.00", "total_tokens": 0} {"current_steps": 14, "total_steps": 141, "loss": 0.8083, "learning_rate": 9.333333333333334e-05, "epoch": 0.2931937172774869, "percentage": 9.93, "elapsed_time": "0:00:53", "remaining_time": "0:08:08", "throughput": "0.00", "total_tokens": 0} {"current_steps": 16, "total_steps": 141, "loss": 0.8985, "learning_rate": 9.998445910004082e-05, "epoch": 0.33507853403141363, "percentage": 11.35, "elapsed_time": "0:01:00", "remaining_time": "0:07:54", "throughput": "0.00", "total_tokens": 0} {"current_steps": 18, "total_steps": 141, "loss": 0.9362, "learning_rate": 9.986018985905901e-05, "epoch": 0.3769633507853403, "percentage": 12.77, "elapsed_time": "0:01:07", "remaining_time": "0:07:41", "throughput": "0.00", "total_tokens": 0} {"current_steps": 20, "total_steps": 141, "loss": 0.9174, "learning_rate": 9.961196033000861e-05, "epoch": 0.418848167539267, "percentage": 14.18, "elapsed_time": "0:01:14", "remaining_time": "0:07:30", "throughput": "0.00", "total_tokens": 0} {"current_steps": 22, "total_steps": 141, "loss": 0.8732, "learning_rate": 9.924038765061042e-05, "epoch": 0.4607329842931937, "percentage": 15.6, "elapsed_time": "0:01:22", "remaining_time": "0:07:23", "throughput": "0.00", "total_tokens": 0} {"current_steps": 24, "total_steps": 141, "loss": 0.8653, "learning_rate": 9.874639560909117e-05, "epoch": 0.5026178010471204, "percentage": 17.02, "elapsed_time": "0:01:30", "remaining_time": "0:07:20", "throughput": "0.00", "total_tokens": 0} {"current_steps": 26, "total_steps": 141, "loss": 0.8592, "learning_rate": 9.81312123475006e-05, "epoch": 0.5445026178010471, "percentage": 18.44, "elapsed_time": "0:01:36", "remaining_time": "0:07:08", "throughput": "0.00", "total_tokens": 0} {"current_steps": 28, "total_steps": 141, "loss": 0.805, "learning_rate": 9.73963673083566e-05, "epoch": 0.5863874345549738, "percentage": 19.86, "elapsed_time": "0:01:45", "remaining_time": "0:07:04", "throughput": "0.00", "total_tokens": 0} {"current_steps": 30, "total_steps": 141, "loss": 0.7464, "learning_rate": 9.654368743221022e-05, "epoch": 0.6282722513089005, "percentage": 21.28, "elapsed_time": "0:01:53", "remaining_time": "0:07:00", "throughput": "0.00", "total_tokens": 0} {"current_steps": 32, "total_steps": 141, "loss": 0.7796, "learning_rate": 9.557529261558367e-05, "epoch": 0.6701570680628273, "percentage": 22.7, "elapsed_time": "0:02:00", "remaining_time": "0:06:51", "throughput": "0.00", "total_tokens": 0} {"current_steps": 34, "total_steps": 141, "loss": 0.7768, "learning_rate": 9.449359044057345e-05, "epoch": 0.7120418848167539, "percentage": 24.11, "elapsed_time": "0:02:08", "remaining_time": "0:06:44", "throughput": "0.00", "total_tokens": 0} {"current_steps": 36, "total_steps": 141, "loss": 0.8751, "learning_rate": 9.330127018922194e-05, "epoch": 0.7539267015706806, "percentage": 25.53, "elapsed_time": "0:02:15", "remaining_time": "0:06:35", "throughput": "0.00", "total_tokens": 0} {"current_steps": 38, "total_steps": 141, "loss": 0.7966, "learning_rate": 9.200129615753859e-05, "epoch": 0.7958115183246073, "percentage": 26.95, "elapsed_time": "0:02:22", "remaining_time": "0:06:26", "throughput": "0.00", "total_tokens": 0} {"current_steps": 40, "total_steps": 141, "loss": 0.7963, "learning_rate": 9.059690028579284e-05, "epoch": 0.837696335078534, "percentage": 28.37, "elapsed_time": "0:02:29", "remaining_time": "0:06:17", "throughput": "0.00", "total_tokens": 0} {"current_steps": 42, "total_steps": 141, "loss": 0.8332, "learning_rate": 8.90915741234015e-05, "epoch": 0.8795811518324608, "percentage": 29.79, "elapsed_time": "0:02:35", "remaining_time": "0:06:07", "throughput": "0.00", "total_tokens": 0} {"current_steps": 44, "total_steps": 141, "loss": 0.7869, "learning_rate": 8.748906014838672e-05, "epoch": 0.9214659685863874, "percentage": 31.21, "elapsed_time": "0:02:42", "remaining_time": "0:05:59", "throughput": "0.00", "total_tokens": 0} {"current_steps": 46, "total_steps": 141, "loss": 0.8517, "learning_rate": 8.579334246298593e-05, "epoch": 0.9633507853403142, "percentage": 32.62, "elapsed_time": "0:02:48", "remaining_time": "0:05:48", "throughput": "0.00", "total_tokens": 0} {"current_steps": 48, "total_steps": 141, "loss": 0.8694, "learning_rate": 8.400863688854597e-05, "epoch": 1.0052356020942408, "percentage": 34.04, "elapsed_time": "0:02:55", "remaining_time": "0:05:39", "throughput": "0.00", "total_tokens": 0} {"current_steps": 50, "total_steps": 141, "loss": 0.8002, "learning_rate": 8.213938048432697e-05, "epoch": 1.0471204188481675, "percentage": 35.46, "elapsed_time": "0:03:02", "remaining_time": "0:05:31", "throughput": "0.00", "total_tokens": 0} {"current_steps": 52, "total_steps": 141, "loss": 0.7798, "learning_rate": 8.019022051627388e-05, "epoch": 1.0890052356020943, "percentage": 36.88, "elapsed_time": "0:03:09", "remaining_time": "0:05:23", "throughput": "0.00", "total_tokens": 0} {"current_steps": 54, "total_steps": 141, "loss": 0.8114, "learning_rate": 7.81660029031811e-05, "epoch": 1.130890052356021, "percentage": 38.3, "elapsed_time": "0:03:16", "remaining_time": "0:05:16", "throughput": "0.00", "total_tokens": 0} {"current_steps": 56, "total_steps": 141, "loss": 0.8206, "learning_rate": 7.60717601689749e-05, "epoch": 1.1727748691099475, "percentage": 39.72, "elapsed_time": "0:03:24", "remaining_time": "0:05:09", "throughput": "0.00", "total_tokens": 0} {"current_steps": 58, "total_steps": 141, "loss": 0.8477, "learning_rate": 7.391269893106592e-05, "epoch": 1.2146596858638743, "percentage": 41.13, "elapsed_time": "0:03:30", "remaining_time": "0:05:01", "throughput": "0.00", "total_tokens": 0} {"current_steps": 60, "total_steps": 141, "loss": 0.8213, "learning_rate": 7.169418695587791e-05, "epoch": 1.256544502617801, "percentage": 42.55, "elapsed_time": "0:03:37", "remaining_time": "0:04:53", "throughput": "0.00", "total_tokens": 0} {"current_steps": 62, "total_steps": 141, "loss": 0.8287, "learning_rate": 6.942173981373474e-05, "epoch": 1.2984293193717278, "percentage": 43.97, "elapsed_time": "0:03:43", "remaining_time": "0:04:45", "throughput": "0.00", "total_tokens": 0} {"current_steps": 64, "total_steps": 141, "loss": 0.7643, "learning_rate": 6.710100716628344e-05, "epoch": 1.3403141361256545, "percentage": 45.39, "elapsed_time": "0:03:51", "remaining_time": "0:04:39", "throughput": "0.00", "total_tokens": 0} {"current_steps": 66, "total_steps": 141, "loss": 0.7315, "learning_rate": 6.473775872054521e-05, "epoch": 1.3821989528795813, "percentage": 46.81, "elapsed_time": "0:03:59", "remaining_time": "0:04:31", "throughput": "0.00", "total_tokens": 0} {"current_steps": 68, "total_steps": 141, "loss": 0.7811, "learning_rate": 6.233786988451468e-05, "epoch": 1.4240837696335078, "percentage": 48.23, "elapsed_time": "0:04:07", "remaining_time": "0:04:25", "throughput": "0.00", "total_tokens": 0} {"current_steps": 70, "total_steps": 141, "loss": 0.754, "learning_rate": 5.9907307159969884e-05, "epoch": 1.4659685863874345, "percentage": 49.65, "elapsed_time": "0:04:15", "remaining_time": "0:04:18", "throughput": "0.00", "total_tokens": 0} {"current_steps": 72, "total_steps": 141, "loss": 0.7809, "learning_rate": 5.745211330880872e-05, "epoch": 1.5078534031413613, "percentage": 51.06, "elapsed_time": "0:04:22", "remaining_time": "0:04:11", "throughput": "0.00", "total_tokens": 0} {"current_steps": 74, "total_steps": 141, "loss": 0.8319, "learning_rate": 5.497839232979084e-05, "epoch": 1.5497382198952878, "percentage": 52.48, "elapsed_time": "0:04:30", "remaining_time": "0:04:04", "throughput": "0.00", "total_tokens": 0} {"current_steps": 76, "total_steps": 141, "loss": 0.7745, "learning_rate": 5.249229428303486e-05, "epoch": 1.5916230366492146, "percentage": 53.9, "elapsed_time": "0:04:37", "remaining_time": "0:03:57", "throughput": "0.00", "total_tokens": 0} {"current_steps": 78, "total_steps": 141, "loss": 0.8002, "learning_rate": 5e-05, "epoch": 1.6335078534031413, "percentage": 55.32, "elapsed_time": "0:04:44", "remaining_time": "0:03:50", "throughput": "0.00", "total_tokens": 0} {"current_steps": 80, "total_steps": 141, "loss": 0.7718, "learning_rate": 4.750770571696514e-05, "epoch": 1.675392670157068, "percentage": 56.74, "elapsed_time": "0:04:51", "remaining_time": "0:03:42", "throughput": "0.00", "total_tokens": 0} {"current_steps": 82, "total_steps": 141, "loss": 0.742, "learning_rate": 4.502160767020918e-05, "epoch": 1.7172774869109948, "percentage": 58.16, "elapsed_time": "0:04:58", "remaining_time": "0:03:34", "throughput": "0.00", "total_tokens": 0} {"current_steps": 84, "total_steps": 141, "loss": 0.7687, "learning_rate": 4.254788669119127e-05, "epoch": 1.7591623036649215, "percentage": 59.57, "elapsed_time": "0:05:05", "remaining_time": "0:03:27", "throughput": "0.00", "total_tokens": 0} {"current_steps": 86, "total_steps": 141, "loss": 0.7066, "learning_rate": 4.0092692840030134e-05, "epoch": 1.8010471204188483, "percentage": 60.99, "elapsed_time": "0:05:12", "remaining_time": "0:03:19", "throughput": "0.00", "total_tokens": 0} {"current_steps": 88, "total_steps": 141, "loss": 0.7098, "learning_rate": 3.7662130115485314e-05, "epoch": 1.8429319371727748, "percentage": 62.41, "elapsed_time": "0:05:20", "remaining_time": "0:03:12", "throughput": "0.00", "total_tokens": 0} {"current_steps": 90, "total_steps": 141, "loss": 0.6961, "learning_rate": 3.5262241279454785e-05, "epoch": 1.8848167539267016, "percentage": 63.83, "elapsed_time": "0:05:28", "remaining_time": "0:03:06", "throughput": "0.00", "total_tokens": 0} {"current_steps": 92, "total_steps": 141, "loss": 0.7948, "learning_rate": 3.289899283371657e-05, "epoch": 1.9267015706806283, "percentage": 65.25, "elapsed_time": "0:05:34", "remaining_time": "0:02:58", "throughput": "0.00", "total_tokens": 0} {"current_steps": 94, "total_steps": 141, "loss": 0.7264, "learning_rate": 3.0578260186265265e-05, "epoch": 1.9685863874345548, "percentage": 66.67, "elapsed_time": "0:05:41", "remaining_time": "0:02:50", "throughput": "0.00", "total_tokens": 0} {"current_steps": 96, "total_steps": 141, "loss": 0.6696, "learning_rate": 2.8305813044122097e-05, "epoch": 2.0104712041884816, "percentage": 68.09, "elapsed_time": "0:05:49", "remaining_time": "0:02:43", "throughput": "0.00", "total_tokens": 0} {"current_steps": 98, "total_steps": 141, "loss": 0.7135, "learning_rate": 2.6087301068934106e-05, "epoch": 2.0523560209424083, "percentage": 69.5, "elapsed_time": "0:05:56", "remaining_time": "0:02:36", "throughput": "0.00", "total_tokens": 0} {"current_steps": 100, "total_steps": 141, "loss": 0.7865, "learning_rate": 2.39282398310251e-05, "epoch": 2.094240837696335, "percentage": 70.92, "elapsed_time": "0:06:03", "remaining_time": "0:02:28", "throughput": "0.00", "total_tokens": 0} {"current_steps": 102, "total_steps": 141, "loss": 0.7411, "learning_rate": 2.1833997096818898e-05, "epoch": 2.136125654450262, "percentage": 72.34, "elapsed_time": "0:06:11", "remaining_time": "0:02:21", "throughput": "0.00", "total_tokens": 0} {"current_steps": 104, "total_steps": 141, "loss": 0.772, "learning_rate": 1.980977948372612e-05, "epoch": 2.1780104712041886, "percentage": 73.76, "elapsed_time": "0:06:17", "remaining_time": "0:02:14", "throughput": "0.00", "total_tokens": 0} {"current_steps": 106, "total_steps": 141, "loss": 0.7096, "learning_rate": 1.7860619515673033e-05, "epoch": 2.2198952879581153, "percentage": 75.18, "elapsed_time": "0:06:25", "remaining_time": "0:02:07", "throughput": "0.00", "total_tokens": 0} {"current_steps": 108, "total_steps": 141, "loss": 0.7378, "learning_rate": 1.599136311145402e-05, "epoch": 2.261780104712042, "percentage": 76.6, "elapsed_time": "0:06:32", "remaining_time": "0:01:59", "throughput": "0.00", "total_tokens": 0} {"current_steps": 110, "total_steps": 141, "loss": 0.6471, "learning_rate": 1.4206657537014079e-05, "epoch": 2.303664921465969, "percentage": 78.01, "elapsed_time": "0:06:39", "remaining_time": "0:01:52", "throughput": "0.00", "total_tokens": 0} {"current_steps": 112, "total_steps": 141, "loss": 0.7359, "learning_rate": 1.2510939851613285e-05, "epoch": 2.345549738219895, "percentage": 79.43, "elapsed_time": "0:06:47", "remaining_time": "0:01:45", "throughput": "0.00", "total_tokens": 0} {"current_steps": 114, "total_steps": 141, "loss": 0.7572, "learning_rate": 1.090842587659851e-05, "epoch": 2.387434554973822, "percentage": 80.85, "elapsed_time": "0:06:54", "remaining_time": "0:01:38", "throughput": "0.00", "total_tokens": 0} {"current_steps": 116, "total_steps": 141, "loss": 0.7411, "learning_rate": 9.403099714207175e-06, "epoch": 2.4293193717277486, "percentage": 82.27, "elapsed_time": "0:07:01", "remaining_time": "0:01:30", "throughput": "0.00", "total_tokens": 0} {"current_steps": 118, "total_steps": 141, "loss": 0.6692, "learning_rate": 7.998703842461431e-06, "epoch": 2.4712041884816753, "percentage": 83.69, "elapsed_time": "0:07:08", "remaining_time": "0:01:23", "throughput": "0.00", "total_tokens": 0} {"current_steps": 120, "total_steps": 141, "loss": 0.7619, "learning_rate": 6.698729810778065e-06, "epoch": 2.513089005235602, "percentage": 85.11, "elapsed_time": "0:07:15", "remaining_time": "0:01:16", "throughput": "0.00", "total_tokens": 0} {"current_steps": 122, "total_steps": 141, "loss": 0.708, "learning_rate": 5.506409559426573e-06, "epoch": 2.554973821989529, "percentage": 86.52, "elapsed_time": "0:07:22", "remaining_time": "0:01:08", "throughput": "0.00", "total_tokens": 0} {"current_steps": 124, "total_steps": 141, "loss": 0.7279, "learning_rate": 4.424707384416344e-06, "epoch": 2.5968586387434556, "percentage": 87.94, "elapsed_time": "0:07:30", "remaining_time": "0:01:01", "throughput": "0.00", "total_tokens": 0} {"current_steps": 126, "total_steps": 141, "loss": 0.7629, "learning_rate": 3.4563125677897932e-06, "epoch": 2.6387434554973823, "percentage": 89.36, "elapsed_time": "0:07:37", "remaining_time": "0:00:54", "throughput": "0.00", "total_tokens": 0} {"current_steps": 128, "total_steps": 141, "loss": 0.7334, "learning_rate": 2.603632691643415e-06, "epoch": 2.680628272251309, "percentage": 90.78, "elapsed_time": "0:07:44", "remaining_time": "0:00:47", "throughput": "0.00", "total_tokens": 0} {"current_steps": 130, "total_steps": 141, "loss": 0.6643, "learning_rate": 1.8687876524993987e-06, "epoch": 2.7225130890052354, "percentage": 92.2, "elapsed_time": "0:07:52", "remaining_time": "0:00:39", "throughput": "0.00", "total_tokens": 0} {"current_steps": 132, "total_steps": 141, "loss": 0.7363, "learning_rate": 1.2536043909088191e-06, "epoch": 2.7643979057591626, "percentage": 93.62, "elapsed_time": "0:07:58", "remaining_time": "0:00:32", "throughput": "0.00", "total_tokens": 0} {"current_steps": 134, "total_steps": 141, "loss": 0.7018, "learning_rate": 7.596123493895991e-07, "epoch": 2.806282722513089, "percentage": 95.04, "elapsed_time": "0:08:06", "remaining_time": "0:00:25", "throughput": "0.00", "total_tokens": 0} {"current_steps": 136, "total_steps": 141, "loss": 0.8282, "learning_rate": 3.8803966999139684e-07, "epoch": 2.8481675392670156, "percentage": 96.45, "elapsed_time": "0:08:14", "remaining_time": "0:00:18", "throughput": "0.00", "total_tokens": 0} {"current_steps": 138, "total_steps": 141, "loss": 0.6387, "learning_rate": 1.3981014094099353e-07, "epoch": 2.8900523560209423, "percentage": 97.87, "elapsed_time": "0:08:21", "remaining_time": "0:00:10", "throughput": "0.00", "total_tokens": 0} {"current_steps": 140, "total_steps": 141, "loss": 0.7076, "learning_rate": 1.5540899959187727e-08, "epoch": 2.931937172774869, "percentage": 99.29, "elapsed_time": "0:08:27", "remaining_time": "0:00:03", "throughput": "0.00", "total_tokens": 0} {"current_steps": 141, "total_steps": 141, "epoch": 2.9528795811518327, "percentage": 100.0, "elapsed_time": "0:08:30", "remaining_time": "0:00:00", "throughput": "0.00", "total_tokens": 0}