llama2_inst_truthbench2_model / trainer_log.jsonl
Ogamon's picture
Initial commit
77a28b7 verified
raw
history blame
47.9 kB
{"current_steps": 1, "total_steps": 190, "loss": 8.2514, "learning_rate": 5.000000000000001e-07, "epoch": 0.025806451612903226, "percentage": 0.53, "elapsed_time": "0:00:12", "remaining_time": "0:39:32", "throughput": "545.43", "total_tokens": 6848}
{"current_steps": 2, "total_steps": 190, "loss": 8.2793, "learning_rate": 1.0000000000000002e-06, "epoch": 0.05161290322580645, "percentage": 1.05, "elapsed_time": "0:00:23", "remaining_time": "0:36:55", "throughput": "584.51", "total_tokens": 13776}
{"current_steps": 3, "total_steps": 190, "loss": 8.17, "learning_rate": 1.5e-06, "epoch": 0.07741935483870968, "percentage": 1.58, "elapsed_time": "0:00:34", "remaining_time": "0:35:54", "throughput": "598.15", "total_tokens": 20672}
{"current_steps": 4, "total_steps": 190, "loss": 7.6197, "learning_rate": 2.0000000000000003e-06, "epoch": 0.1032258064516129, "percentage": 2.11, "elapsed_time": "0:00:45", "remaining_time": "0:35:17", "throughput": "609.21", "total_tokens": 27744}
{"current_steps": 5, "total_steps": 190, "loss": 6.9491, "learning_rate": 2.5e-06, "epoch": 0.12903225806451613, "percentage": 2.63, "elapsed_time": "0:00:56", "remaining_time": "0:34:51", "throughput": "612.41", "total_tokens": 34624}
{"current_steps": 6, "total_steps": 190, "loss": 5.2054, "learning_rate": 3e-06, "epoch": 0.15483870967741936, "percentage": 3.16, "elapsed_time": "0:01:07", "remaining_time": "0:34:31", "throughput": "613.36", "total_tokens": 41424}
{"current_steps": 7, "total_steps": 190, "loss": 4.8642, "learning_rate": 3.5e-06, "epoch": 0.18064516129032257, "percentage": 3.68, "elapsed_time": "0:01:18", "remaining_time": "0:34:13", "throughput": "615.05", "total_tokens": 48304}
{"current_steps": 8, "total_steps": 190, "loss": 3.2874, "learning_rate": 4.000000000000001e-06, "epoch": 0.2064516129032258, "percentage": 4.21, "elapsed_time": "0:01:29", "remaining_time": "0:33:57", "throughput": "615.94", "total_tokens": 55152}
{"current_steps": 9, "total_steps": 190, "loss": 2.631, "learning_rate": 4.5e-06, "epoch": 0.23225806451612904, "percentage": 4.74, "elapsed_time": "0:01:40", "remaining_time": "0:33:42", "throughput": "613.25", "total_tokens": 61680}
{"current_steps": 10, "total_steps": 190, "loss": 0.6982, "learning_rate": 5e-06, "epoch": 0.25806451612903225, "percentage": 5.26, "elapsed_time": "0:01:51", "remaining_time": "0:33:28", "throughput": "613.59", "total_tokens": 68480}
{"current_steps": 11, "total_steps": 190, "loss": 0.3276, "learning_rate": 4.9996192378909785e-06, "epoch": 0.2838709677419355, "percentage": 5.79, "elapsed_time": "0:02:02", "remaining_time": "0:33:15", "throughput": "613.98", "total_tokens": 75296}
{"current_steps": 12, "total_steps": 190, "loss": 0.293, "learning_rate": 4.99847706754774e-06, "epoch": 0.3096774193548387, "percentage": 6.32, "elapsed_time": "0:02:13", "remaining_time": "0:33:02", "throughput": "615.72", "total_tokens": 82288}
{"current_steps": 13, "total_steps": 190, "loss": 0.2129, "learning_rate": 4.9965738368864345e-06, "epoch": 0.33548387096774196, "percentage": 6.84, "elapsed_time": "0:02:24", "remaining_time": "0:32:49", "throughput": "615.94", "total_tokens": 89088}
{"current_steps": 14, "total_steps": 190, "loss": 0.4712, "learning_rate": 4.993910125649561e-06, "epoch": 0.36129032258064514, "percentage": 7.37, "elapsed_time": "0:02:35", "remaining_time": "0:32:36", "throughput": "616.20", "total_tokens": 95904}
{"current_steps": 15, "total_steps": 190, "loss": 0.235, "learning_rate": 4.990486745229364e-06, "epoch": 0.3870967741935484, "percentage": 7.89, "elapsed_time": "0:02:46", "remaining_time": "0:32:23", "throughput": "617.55", "total_tokens": 102896}
{"current_steps": 16, "total_steps": 190, "loss": 0.202, "learning_rate": 4.986304738420684e-06, "epoch": 0.4129032258064516, "percentage": 8.42, "elapsed_time": "0:02:57", "remaining_time": "0:32:11", "throughput": "618.05", "total_tokens": 109792}
{"current_steps": 17, "total_steps": 190, "loss": 0.1981, "learning_rate": 4.981365379103306e-06, "epoch": 0.43870967741935485, "percentage": 8.95, "elapsed_time": "0:03:08", "remaining_time": "0:31:59", "throughput": "617.73", "total_tokens": 116528}
{"current_steps": 18, "total_steps": 190, "loss": 0.1517, "learning_rate": 4.975670171853926e-06, "epoch": 0.4645161290322581, "percentage": 9.47, "elapsed_time": "0:03:19", "remaining_time": "0:31:47", "throughput": "617.10", "total_tokens": 123200}
{"current_steps": 19, "total_steps": 190, "loss": 0.4335, "learning_rate": 4.9692208514878445e-06, "epoch": 0.49032258064516127, "percentage": 10.0, "elapsed_time": "0:03:30", "remaining_time": "0:31:35", "throughput": "617.28", "total_tokens": 130032}
{"current_steps": 20, "total_steps": 190, "loss": 0.3609, "learning_rate": 4.962019382530521e-06, "epoch": 0.5161290322580645, "percentage": 10.53, "elapsed_time": "0:03:41", "remaining_time": "0:31:24", "throughput": "617.29", "total_tokens": 136832}
{"current_steps": 21, "total_steps": 190, "loss": 0.1708, "learning_rate": 4.9540679586191605e-06, "epoch": 0.5419354838709678, "percentage": 11.05, "elapsed_time": "0:03:52", "remaining_time": "0:31:12", "throughput": "618.54", "total_tokens": 143904}
{"current_steps": 22, "total_steps": 190, "loss": 0.2277, "learning_rate": 4.9453690018345144e-06, "epoch": 0.567741935483871, "percentage": 11.58, "elapsed_time": "0:04:03", "remaining_time": "0:31:00", "throughput": "617.70", "total_tokens": 150496}
{"current_steps": 23, "total_steps": 190, "loss": 0.3437, "learning_rate": 4.935925161963089e-06, "epoch": 0.5935483870967742, "percentage": 12.11, "elapsed_time": "0:04:14", "remaining_time": "0:30:49", "throughput": "617.93", "total_tokens": 157360}
{"current_steps": 24, "total_steps": 190, "loss": 0.2229, "learning_rate": 4.925739315689991e-06, "epoch": 0.6193548387096774, "percentage": 12.63, "elapsed_time": "0:04:25", "remaining_time": "0:30:37", "throughput": "619.02", "total_tokens": 164464}
{"current_steps": 25, "total_steps": 190, "loss": 0.1242, "learning_rate": 4.914814565722671e-06, "epoch": 0.6451612903225806, "percentage": 13.16, "elapsed_time": "0:04:36", "remaining_time": "0:30:26", "throughput": "617.82", "total_tokens": 170960}
{"current_steps": 26, "total_steps": 190, "loss": 0.2117, "learning_rate": 4.903154239845798e-06, "epoch": 0.6709677419354839, "percentage": 13.68, "elapsed_time": "0:04:47", "remaining_time": "0:30:15", "throughput": "617.94", "total_tokens": 177808}
{"current_steps": 27, "total_steps": 190, "loss": 0.2706, "learning_rate": 4.890761889907589e-06, "epoch": 0.6967741935483871, "percentage": 14.21, "elapsed_time": "0:04:58", "remaining_time": "0:30:03", "throughput": "618.70", "total_tokens": 184848}
{"current_steps": 28, "total_steps": 190, "loss": 0.2084, "learning_rate": 4.8776412907378845e-06, "epoch": 0.7225806451612903, "percentage": 14.74, "elapsed_time": "0:05:09", "remaining_time": "0:29:52", "throughput": "618.27", "total_tokens": 191536}
{"current_steps": 29, "total_steps": 190, "loss": 0.0981, "learning_rate": 4.863796438998293e-06, "epoch": 0.7483870967741936, "percentage": 15.26, "elapsed_time": "0:05:20", "remaining_time": "0:29:40", "throughput": "618.39", "total_tokens": 198368}
{"current_steps": 30, "total_steps": 190, "loss": 0.16, "learning_rate": 4.849231551964771e-06, "epoch": 0.7741935483870968, "percentage": 15.79, "elapsed_time": "0:05:31", "remaining_time": "0:29:29", "throughput": "618.50", "total_tokens": 205200}
{"current_steps": 31, "total_steps": 190, "loss": 0.1614, "learning_rate": 4.833951066243004e-06, "epoch": 0.8, "percentage": 16.32, "elapsed_time": "0:05:42", "remaining_time": "0:29:18", "throughput": "617.80", "total_tokens": 211760}
{"current_steps": 32, "total_steps": 190, "loss": 0.1742, "learning_rate": 4.817959636416969e-06, "epoch": 0.8258064516129032, "percentage": 16.84, "elapsed_time": "0:05:53", "remaining_time": "0:29:06", "throughput": "617.47", "total_tokens": 218448}
{"current_steps": 33, "total_steps": 190, "loss": 0.1107, "learning_rate": 4.801262133631101e-06, "epoch": 0.8516129032258064, "percentage": 17.37, "elapsed_time": "0:06:04", "remaining_time": "0:28:55", "throughput": "617.90", "total_tokens": 225408}
{"current_steps": 34, "total_steps": 190, "loss": 0.0822, "learning_rate": 4.783863644106502e-06, "epoch": 0.8774193548387097, "percentage": 17.89, "elapsed_time": "0:06:15", "remaining_time": "0:28:44", "throughput": "617.42", "total_tokens": 232032}
{"current_steps": 35, "total_steps": 190, "loss": 0.1873, "learning_rate": 4.765769467591626e-06, "epoch": 0.9032258064516129, "percentage": 18.42, "elapsed_time": "0:06:26", "remaining_time": "0:28:33", "throughput": "617.01", "total_tokens": 238672}
{"current_steps": 36, "total_steps": 190, "loss": 0.2375, "learning_rate": 4.746985115747918e-06, "epoch": 0.9290322580645162, "percentage": 18.95, "elapsed_time": "0:06:37", "remaining_time": "0:28:21", "throughput": "616.94", "total_tokens": 245456}
{"current_steps": 37, "total_steps": 190, "loss": 0.2667, "learning_rate": 4.72751631047092e-06, "epoch": 0.9548387096774194, "percentage": 19.47, "elapsed_time": "0:06:48", "remaining_time": "0:28:10", "throughput": "617.73", "total_tokens": 252576}
{"current_steps": 38, "total_steps": 190, "loss": 0.1547, "learning_rate": 4.707368982147318e-06, "epoch": 0.9806451612903225, "percentage": 20.0, "elapsed_time": "0:06:59", "remaining_time": "0:27:59", "throughput": "618.14", "total_tokens": 259536}
{"current_steps": 39, "total_steps": 190, "loss": 0.1662, "learning_rate": 4.68654926784849e-06, "epoch": 1.0064516129032257, "percentage": 20.53, "elapsed_time": "0:07:10", "remaining_time": "0:27:48", "throughput": "618.69", "total_tokens": 266560}
{"current_steps": 40, "total_steps": 190, "loss": 0.0808, "learning_rate": 4.665063509461098e-06, "epoch": 1.032258064516129, "percentage": 21.05, "elapsed_time": "0:07:21", "remaining_time": "0:27:36", "throughput": "618.41", "total_tokens": 273248}
{"current_steps": 41, "total_steps": 190, "loss": 0.0884, "learning_rate": 4.642918251755281e-06, "epoch": 1.0580645161290323, "percentage": 21.58, "elapsed_time": "0:07:32", "remaining_time": "0:27:25", "throughput": "618.04", "total_tokens": 279888}
{"current_steps": 42, "total_steps": 190, "loss": 0.0883, "learning_rate": 4.620120240391065e-06, "epoch": 1.0838709677419356, "percentage": 22.11, "elapsed_time": "0:07:43", "remaining_time": "0:27:14", "throughput": "618.55", "total_tokens": 286944}
{"current_steps": 43, "total_steps": 190, "loss": 0.0562, "learning_rate": 4.596676419863561e-06, "epoch": 1.1096774193548387, "percentage": 22.63, "elapsed_time": "0:07:54", "remaining_time": "0:27:03", "throughput": "618.59", "total_tokens": 293792}
{"current_steps": 44, "total_steps": 190, "loss": 0.0856, "learning_rate": 4.572593931387604e-06, "epoch": 1.135483870967742, "percentage": 23.16, "elapsed_time": "0:08:05", "remaining_time": "0:26:52", "throughput": "618.38", "total_tokens": 300512}
{"current_steps": 45, "total_steps": 190, "loss": 0.0612, "learning_rate": 4.54788011072248e-06, "epoch": 1.1612903225806452, "percentage": 23.68, "elapsed_time": "0:08:16", "remaining_time": "0:26:41", "throughput": "618.26", "total_tokens": 307264}
{"current_steps": 46, "total_steps": 190, "loss": 0.0944, "learning_rate": 4.522542485937369e-06, "epoch": 1.1870967741935483, "percentage": 24.21, "elapsed_time": "0:08:27", "remaining_time": "0:26:30", "throughput": "618.35", "total_tokens": 314112}
{"current_steps": 47, "total_steps": 190, "loss": 0.0624, "learning_rate": 4.496588775118232e-06, "epoch": 1.2129032258064516, "percentage": 24.74, "elapsed_time": "0:08:39", "remaining_time": "0:26:19", "throughput": "618.23", "total_tokens": 320864}
{"current_steps": 48, "total_steps": 190, "loss": 0.0363, "learning_rate": 4.470026884016805e-06, "epoch": 1.238709677419355, "percentage": 25.26, "elapsed_time": "0:08:49", "remaining_time": "0:26:07", "throughput": "618.21", "total_tokens": 327648}
{"current_steps": 49, "total_steps": 190, "loss": 0.1039, "learning_rate": 4.442864903642428e-06, "epoch": 1.2645161290322582, "percentage": 25.79, "elapsed_time": "0:09:01", "remaining_time": "0:25:56", "throughput": "618.16", "total_tokens": 334432}
{"current_steps": 50, "total_steps": 190, "loss": 0.0488, "learning_rate": 4.415111107797445e-06, "epoch": 1.2903225806451613, "percentage": 26.32, "elapsed_time": "0:09:12", "remaining_time": "0:25:45", "throughput": "618.19", "total_tokens": 341248}
{"current_steps": 51, "total_steps": 190, "loss": 0.0613, "learning_rate": 4.386773950556931e-06, "epoch": 1.3161290322580645, "percentage": 26.84, "elapsed_time": "0:09:23", "remaining_time": "0:25:34", "throughput": "618.44", "total_tokens": 348192}
{"current_steps": 52, "total_steps": 190, "loss": 0.07, "learning_rate": 4.357862063693486e-06, "epoch": 1.3419354838709676, "percentage": 27.37, "elapsed_time": "0:09:34", "remaining_time": "0:25:23", "throughput": "618.12", "total_tokens": 354816}
{"current_steps": 53, "total_steps": 190, "loss": 0.0463, "learning_rate": 4.328384254047927e-06, "epoch": 1.367741935483871, "percentage": 27.89, "elapsed_time": "0:09:45", "remaining_time": "0:25:12", "throughput": "618.08", "total_tokens": 361600}
{"current_steps": 54, "total_steps": 190, "loss": 0.0671, "learning_rate": 4.2983495008466285e-06, "epoch": 1.3935483870967742, "percentage": 28.42, "elapsed_time": "0:09:56", "remaining_time": "0:25:01", "throughput": "618.15", "total_tokens": 368464}
{"current_steps": 55, "total_steps": 190, "loss": 0.0428, "learning_rate": 4.267766952966369e-06, "epoch": 1.4193548387096775, "percentage": 28.95, "elapsed_time": "0:10:07", "remaining_time": "0:24:50", "throughput": "618.43", "total_tokens": 375440}
{"current_steps": 56, "total_steps": 190, "loss": 0.0678, "learning_rate": 4.236645926147493e-06, "epoch": 1.4451612903225808, "percentage": 29.47, "elapsed_time": "0:10:18", "remaining_time": "0:24:38", "throughput": "618.43", "total_tokens": 382240}
{"current_steps": 57, "total_steps": 190, "loss": 0.0476, "learning_rate": 4.204995900156247e-06, "epoch": 1.4709677419354839, "percentage": 30.0, "elapsed_time": "0:10:29", "remaining_time": "0:24:27", "throughput": "618.38", "total_tokens": 389008}
{"current_steps": 58, "total_steps": 190, "loss": 0.0442, "learning_rate": 4.172826515897146e-06, "epoch": 1.4967741935483871, "percentage": 30.53, "elapsed_time": "0:10:40", "remaining_time": "0:24:16", "throughput": "618.82", "total_tokens": 396080}
{"current_steps": 59, "total_steps": 190, "loss": 0.0336, "learning_rate": 4.140147572476269e-06, "epoch": 1.5225806451612902, "percentage": 31.05, "elapsed_time": "0:10:51", "remaining_time": "0:24:05", "throughput": "619.09", "total_tokens": 403056}
{"current_steps": 60, "total_steps": 190, "loss": 0.046, "learning_rate": 4.106969024216348e-06, "epoch": 1.5483870967741935, "percentage": 31.58, "elapsed_time": "0:11:02", "remaining_time": "0:23:54", "throughput": "618.77", "total_tokens": 409664}
{"current_steps": 61, "total_steps": 190, "loss": 0.0416, "learning_rate": 4.073300977624594e-06, "epoch": 1.5741935483870968, "percentage": 32.11, "elapsed_time": "0:11:13", "remaining_time": "0:23:43", "throughput": "618.46", "total_tokens": 416272}
{"current_steps": 62, "total_steps": 190, "loss": 0.0649, "learning_rate": 4.039153688314146e-06, "epoch": 1.6, "percentage": 32.63, "elapsed_time": "0:11:24", "remaining_time": "0:23:32", "throughput": "618.87", "total_tokens": 423360}
{"current_steps": 63, "total_steps": 190, "loss": 0.0591, "learning_rate": 4.0045375578801216e-06, "epoch": 1.6258064516129034, "percentage": 33.16, "elapsed_time": "0:11:35", "remaining_time": "0:23:21", "throughput": "619.05", "total_tokens": 430304}
{"current_steps": 64, "total_steps": 190, "loss": 0.0318, "learning_rate": 3.969463130731183e-06, "epoch": 1.6516129032258065, "percentage": 33.68, "elapsed_time": "0:11:46", "remaining_time": "0:23:10", "throughput": "618.83", "total_tokens": 436960}
{"current_steps": 65, "total_steps": 190, "loss": 0.0462, "learning_rate": 3.933941090877615e-06, "epoch": 1.6774193548387095, "percentage": 34.21, "elapsed_time": "0:11:57", "remaining_time": "0:22:59", "throughput": "618.87", "total_tokens": 443792}
{"current_steps": 66, "total_steps": 190, "loss": 0.0465, "learning_rate": 3.897982258676867e-06, "epoch": 1.7032258064516128, "percentage": 34.74, "elapsed_time": "0:12:08", "remaining_time": "0:22:47", "throughput": "618.98", "total_tokens": 450672}
{"current_steps": 67, "total_steps": 190, "loss": 0.0316, "learning_rate": 3.861597587537568e-06, "epoch": 1.729032258064516, "percentage": 35.26, "elapsed_time": "0:12:19", "remaining_time": "0:22:36", "throughput": "619.15", "total_tokens": 457616}
{"current_steps": 68, "total_steps": 190, "loss": 0.1, "learning_rate": 3.824798160583012e-06, "epoch": 1.7548387096774194, "percentage": 35.79, "elapsed_time": "0:12:30", "remaining_time": "0:22:25", "throughput": "619.38", "total_tokens": 464592}
{"current_steps": 69, "total_steps": 190, "loss": 0.0711, "learning_rate": 3.787595187275136e-06, "epoch": 1.7806451612903227, "percentage": 36.32, "elapsed_time": "0:12:41", "remaining_time": "0:22:14", "throughput": "619.25", "total_tokens": 471328}
{"current_steps": 70, "total_steps": 190, "loss": 0.0494, "learning_rate": 3.7500000000000005e-06, "epoch": 1.8064516129032258, "percentage": 36.84, "elapsed_time": "0:12:52", "remaining_time": "0:22:03", "throughput": "619.69", "total_tokens": 478480}
{"current_steps": 71, "total_steps": 190, "loss": 0.0618, "learning_rate": 3.7120240506158433e-06, "epoch": 1.832258064516129, "percentage": 37.37, "elapsed_time": "0:13:03", "remaining_time": "0:21:52", "throughput": "619.64", "total_tokens": 485264}
{"current_steps": 72, "total_steps": 190, "loss": 0.0511, "learning_rate": 3.6736789069647273e-06, "epoch": 1.8580645161290321, "percentage": 37.89, "elapsed_time": "0:13:14", "remaining_time": "0:21:41", "throughput": "619.61", "total_tokens": 492064}
{"current_steps": 73, "total_steps": 190, "loss": 0.0464, "learning_rate": 3.634976249348867e-06, "epoch": 1.8838709677419354, "percentage": 38.42, "elapsed_time": "0:13:25", "remaining_time": "0:21:30", "throughput": "619.64", "total_tokens": 498896}
{"current_steps": 74, "total_steps": 190, "loss": 0.0331, "learning_rate": 3.595927866972694e-06, "epoch": 1.9096774193548387, "percentage": 38.95, "elapsed_time": "0:13:36", "remaining_time": "0:21:19", "throughput": "620.02", "total_tokens": 506016}
{"current_steps": 75, "total_steps": 190, "loss": 0.0706, "learning_rate": 3.556545654351749e-06, "epoch": 1.935483870967742, "percentage": 39.47, "elapsed_time": "0:13:47", "remaining_time": "0:21:08", "throughput": "620.04", "total_tokens": 512848}
{"current_steps": 76, "total_steps": 190, "loss": 0.0442, "learning_rate": 3.516841607689501e-06, "epoch": 1.9612903225806453, "percentage": 40.0, "elapsed_time": "0:13:58", "remaining_time": "0:20:57", "throughput": "620.14", "total_tokens": 519744}
{"current_steps": 77, "total_steps": 190, "loss": 0.042, "learning_rate": 3.476827821223184e-06, "epoch": 1.9870967741935484, "percentage": 40.53, "elapsed_time": "0:14:09", "remaining_time": "0:20:46", "throughput": "619.89", "total_tokens": 526352}
{"current_steps": 78, "total_steps": 190, "loss": 0.021, "learning_rate": 3.436516483539781e-06, "epoch": 2.0129032258064514, "percentage": 41.05, "elapsed_time": "0:14:20", "remaining_time": "0:20:35", "throughput": "619.84", "total_tokens": 533136}
{"current_steps": 79, "total_steps": 190, "loss": 0.0094, "learning_rate": 3.39591987386325e-06, "epoch": 2.0387096774193547, "percentage": 41.58, "elapsed_time": "0:14:31", "remaining_time": "0:20:23", "throughput": "619.91", "total_tokens": 540016}
{"current_steps": 80, "total_steps": 190, "loss": 0.0021, "learning_rate": 3.3550503583141726e-06, "epoch": 2.064516129032258, "percentage": 42.11, "elapsed_time": "0:14:42", "remaining_time": "0:20:12", "throughput": "620.26", "total_tokens": 547152}
{"current_steps": 81, "total_steps": 190, "loss": 0.0146, "learning_rate": 3.313920386142892e-06, "epoch": 2.0903225806451613, "percentage": 42.63, "elapsed_time": "0:14:53", "remaining_time": "0:20:01", "throughput": "620.13", "total_tokens": 553888}
{"current_steps": 82, "total_steps": 190, "loss": 0.0237, "learning_rate": 3.272542485937369e-06, "epoch": 2.1161290322580646, "percentage": 43.16, "elapsed_time": "0:15:04", "remaining_time": "0:19:50", "throughput": "620.48", "total_tokens": 561024}
{"current_steps": 83, "total_steps": 190, "loss": 0.0031, "learning_rate": 3.230929261806842e-06, "epoch": 2.141935483870968, "percentage": 43.68, "elapsed_time": "0:15:15", "remaining_time": "0:19:39", "throughput": "620.57", "total_tokens": 567936}
{"current_steps": 84, "total_steps": 190, "loss": 0.0034, "learning_rate": 3.189093389542498e-06, "epoch": 2.167741935483871, "percentage": 44.21, "elapsed_time": "0:15:26", "remaining_time": "0:19:28", "throughput": "620.54", "total_tokens": 574736}
{"current_steps": 85, "total_steps": 190, "loss": 0.0045, "learning_rate": 3.147047612756302e-06, "epoch": 2.193548387096774, "percentage": 44.74, "elapsed_time": "0:15:37", "remaining_time": "0:19:17", "throughput": "620.66", "total_tokens": 581680}
{"current_steps": 86, "total_steps": 190, "loss": 0.0031, "learning_rate": 3.1048047389991693e-06, "epoch": 2.2193548387096773, "percentage": 45.26, "elapsed_time": "0:15:48", "remaining_time": "0:19:06", "throughput": "620.62", "total_tokens": 588464}
{"current_steps": 87, "total_steps": 190, "loss": 0.0341, "learning_rate": 3.062377635859663e-06, "epoch": 2.2451612903225806, "percentage": 45.79, "elapsed_time": "0:15:59", "remaining_time": "0:18:55", "throughput": "620.63", "total_tokens": 595312}
{"current_steps": 88, "total_steps": 190, "loss": 0.0095, "learning_rate": 3.019779227044398e-06, "epoch": 2.270967741935484, "percentage": 46.32, "elapsed_time": "0:16:10", "remaining_time": "0:18:44", "throughput": "620.55", "total_tokens": 602080}
{"current_steps": 89, "total_steps": 190, "loss": 0.0459, "learning_rate": 2.9770224884413625e-06, "epoch": 2.296774193548387, "percentage": 46.84, "elapsed_time": "0:16:21", "remaining_time": "0:18:33", "throughput": "620.80", "total_tokens": 609168}
{"current_steps": 90, "total_steps": 190, "loss": 0.0104, "learning_rate": 2.9341204441673267e-06, "epoch": 2.3225806451612905, "percentage": 47.37, "elapsed_time": "0:16:32", "remaining_time": "0:18:22", "throughput": "620.80", "total_tokens": 616000}
{"current_steps": 91, "total_steps": 190, "loss": 0.0201, "learning_rate": 2.8910861626005774e-06, "epoch": 2.3483870967741938, "percentage": 47.89, "elapsed_time": "0:16:43", "remaining_time": "0:18:11", "throughput": "620.51", "total_tokens": 622544}
{"current_steps": 92, "total_steps": 190, "loss": 0.0021, "learning_rate": 2.847932752400164e-06, "epoch": 2.3741935483870966, "percentage": 48.42, "elapsed_time": "0:16:54", "remaining_time": "0:18:00", "throughput": "620.75", "total_tokens": 629600}
{"current_steps": 93, "total_steps": 190, "loss": 0.043, "learning_rate": 2.804673358512869e-06, "epoch": 2.4, "percentage": 48.95, "elapsed_time": "0:17:05", "remaining_time": "0:17:49", "throughput": "620.64", "total_tokens": 636320}
{"current_steps": 94, "total_steps": 190, "loss": 0.0207, "learning_rate": 2.761321158169134e-06, "epoch": 2.425806451612903, "percentage": 49.47, "elapsed_time": "0:17:16", "remaining_time": "0:17:38", "throughput": "620.61", "total_tokens": 643136}
{"current_steps": 95, "total_steps": 190, "loss": 0.0148, "learning_rate": 2.717889356869146e-06, "epoch": 2.4516129032258065, "percentage": 50.0, "elapsed_time": "0:17:27", "remaining_time": "0:17:27", "throughput": "620.69", "total_tokens": 650048}
{"current_steps": 96, "total_steps": 190, "loss": 0.004, "learning_rate": 2.6743911843603134e-06, "epoch": 2.47741935483871, "percentage": 50.53, "elapsed_time": "0:17:38", "remaining_time": "0:17:16", "throughput": "620.55", "total_tokens": 656736}
{"current_steps": 97, "total_steps": 190, "loss": 0.0131, "learning_rate": 2.6308398906073603e-06, "epoch": 2.5032258064516126, "percentage": 51.05, "elapsed_time": "0:17:49", "remaining_time": "0:17:05", "throughput": "620.54", "total_tokens": 663552}
{"current_steps": 98, "total_steps": 190, "loss": 0.0455, "learning_rate": 2.587248741756253e-06, "epoch": 2.5290322580645164, "percentage": 51.58, "elapsed_time": "0:18:00", "remaining_time": "0:16:54", "throughput": "620.37", "total_tokens": 670224}
{"current_steps": 99, "total_steps": 190, "loss": 0.0031, "learning_rate": 2.543631016093209e-06, "epoch": 2.554838709677419, "percentage": 52.11, "elapsed_time": "0:18:11", "remaining_time": "0:16:43", "throughput": "620.27", "total_tokens": 676960}
{"current_steps": 100, "total_steps": 190, "loss": 0.0099, "learning_rate": 2.5e-06, "epoch": 2.5806451612903225, "percentage": 52.63, "elapsed_time": "0:18:22", "remaining_time": "0:16:32", "throughput": "620.49", "total_tokens": 684016}
{"current_steps": 101, "total_steps": 190, "loss": 0.0797, "learning_rate": 2.4563689839067913e-06, "epoch": 2.606451612903226, "percentage": 53.16, "elapsed_time": "0:18:33", "remaining_time": "0:16:21", "throughput": "620.49", "total_tokens": 690832}
{"current_steps": 102, "total_steps": 190, "loss": 0.0059, "learning_rate": 2.4127512582437486e-06, "epoch": 2.632258064516129, "percentage": 53.68, "elapsed_time": "0:18:44", "remaining_time": "0:16:10", "throughput": "620.63", "total_tokens": 697808}
{"current_steps": 103, "total_steps": 190, "loss": 0.0438, "learning_rate": 2.3691601093926406e-06, "epoch": 2.6580645161290324, "percentage": 54.21, "elapsed_time": "0:18:55", "remaining_time": "0:15:58", "throughput": "620.38", "total_tokens": 704352}
{"current_steps": 104, "total_steps": 190, "loss": 0.0149, "learning_rate": 2.325608815639687e-06, "epoch": 2.6838709677419352, "percentage": 54.74, "elapsed_time": "0:19:06", "remaining_time": "0:15:47", "throughput": "620.63", "total_tokens": 711456}
{"current_steps": 105, "total_steps": 190, "loss": 0.0126, "learning_rate": 2.2821106431308546e-06, "epoch": 2.709677419354839, "percentage": 55.26, "elapsed_time": "0:19:17", "remaining_time": "0:15:36", "throughput": "620.57", "total_tokens": 718224}
{"current_steps": 106, "total_steps": 190, "loss": 0.0255, "learning_rate": 2.238678841830867e-06, "epoch": 2.735483870967742, "percentage": 55.79, "elapsed_time": "0:19:28", "remaining_time": "0:15:25", "throughput": "620.46", "total_tokens": 724928}
{"current_steps": 107, "total_steps": 190, "loss": 0.0048, "learning_rate": 2.195326641487132e-06, "epoch": 2.761290322580645, "percentage": 56.32, "elapsed_time": "0:19:39", "remaining_time": "0:15:14", "throughput": "620.34", "total_tokens": 731616}
{"current_steps": 108, "total_steps": 190, "loss": 0.0142, "learning_rate": 2.1520672475998374e-06, "epoch": 2.7870967741935484, "percentage": 56.84, "elapsed_time": "0:19:50", "remaining_time": "0:15:03", "throughput": "620.20", "total_tokens": 738272}
{"current_steps": 109, "total_steps": 190, "loss": 0.0193, "learning_rate": 2.1089138373994226e-06, "epoch": 2.8129032258064517, "percentage": 57.37, "elapsed_time": "0:20:01", "remaining_time": "0:14:52", "throughput": "620.23", "total_tokens": 745104}
{"current_steps": 110, "total_steps": 190, "loss": 0.0055, "learning_rate": 2.0658795558326745e-06, "epoch": 2.838709677419355, "percentage": 57.89, "elapsed_time": "0:20:12", "remaining_time": "0:14:41", "throughput": "620.32", "total_tokens": 752016}
{"current_steps": 111, "total_steps": 190, "loss": 0.0144, "learning_rate": 2.022977511558638e-06, "epoch": 2.864516129032258, "percentage": 58.42, "elapsed_time": "0:20:23", "remaining_time": "0:14:30", "throughput": "620.23", "total_tokens": 758720}
{"current_steps": 112, "total_steps": 190, "loss": 0.0272, "learning_rate": 1.9802207729556023e-06, "epoch": 2.8903225806451616, "percentage": 58.95, "elapsed_time": "0:20:34", "remaining_time": "0:14:19", "throughput": "620.22", "total_tokens": 765520}
{"current_steps": 113, "total_steps": 190, "loss": 0.0101, "learning_rate": 1.937622364140338e-06, "epoch": 2.9161290322580644, "percentage": 59.47, "elapsed_time": "0:20:45", "remaining_time": "0:14:08", "throughput": "620.18", "total_tokens": 772288}
{"current_steps": 114, "total_steps": 190, "loss": 0.0109, "learning_rate": 1.895195261000831e-06, "epoch": 2.9419354838709677, "percentage": 60.0, "elapsed_time": "0:20:56", "remaining_time": "0:13:57", "throughput": "620.51", "total_tokens": 779520}
{"current_steps": 115, "total_steps": 190, "loss": 0.018, "learning_rate": 1.852952387243698e-06, "epoch": 2.967741935483871, "percentage": 60.53, "elapsed_time": "0:21:07", "remaining_time": "0:13:46", "throughput": "620.55", "total_tokens": 786400}
{"current_steps": 116, "total_steps": 190, "loss": 0.0141, "learning_rate": 1.8109066104575023e-06, "epoch": 2.9935483870967743, "percentage": 61.05, "elapsed_time": "0:21:18", "remaining_time": "0:13:35", "throughput": "620.38", "total_tokens": 793008}
{"current_steps": 117, "total_steps": 190, "loss": 0.0057, "learning_rate": 1.7690707381931585e-06, "epoch": 3.0193548387096776, "percentage": 61.58, "elapsed_time": "0:21:29", "remaining_time": "0:13:24", "throughput": "620.36", "total_tokens": 799808}
{"current_steps": 118, "total_steps": 190, "loss": 0.0063, "learning_rate": 1.7274575140626318e-06, "epoch": 3.0451612903225804, "percentage": 62.11, "elapsed_time": "0:21:40", "remaining_time": "0:13:13", "throughput": "620.33", "total_tokens": 806576}
{"current_steps": 119, "total_steps": 190, "loss": 0.0138, "learning_rate": 1.686079613857109e-06, "epoch": 3.0709677419354837, "percentage": 62.63, "elapsed_time": "0:21:51", "remaining_time": "0:13:02", "throughput": "620.27", "total_tokens": 813312}
{"current_steps": 120, "total_steps": 190, "loss": 0.0011, "learning_rate": 1.6449496416858285e-06, "epoch": 3.096774193548387, "percentage": 63.16, "elapsed_time": "0:22:02", "remaining_time": "0:12:51", "throughput": "619.97", "total_tokens": 819728}
{"current_steps": 121, "total_steps": 190, "loss": 0.0006, "learning_rate": 1.6040801261367494e-06, "epoch": 3.1225806451612903, "percentage": 63.68, "elapsed_time": "0:22:13", "remaining_time": "0:12:40", "throughput": "619.94", "total_tokens": 826496}
{"current_steps": 122, "total_steps": 190, "loss": 0.0055, "learning_rate": 1.56348351646022e-06, "epoch": 3.1483870967741936, "percentage": 64.21, "elapsed_time": "0:22:24", "remaining_time": "0:12:29", "throughput": "619.97", "total_tokens": 833360}
{"current_steps": 123, "total_steps": 190, "loss": 0.0011, "learning_rate": 1.5231721787768162e-06, "epoch": 3.174193548387097, "percentage": 64.74, "elapsed_time": "0:22:35", "remaining_time": "0:12:18", "throughput": "619.90", "total_tokens": 840080}
{"current_steps": 124, "total_steps": 190, "loss": 0.0173, "learning_rate": 1.4831583923105e-06, "epoch": 3.2, "percentage": 65.26, "elapsed_time": "0:22:46", "remaining_time": "0:12:07", "throughput": "620.05", "total_tokens": 847104}
{"current_steps": 125, "total_steps": 190, "loss": 0.0027, "learning_rate": 1.443454345648252e-06, "epoch": 3.225806451612903, "percentage": 65.79, "elapsed_time": "0:22:57", "remaining_time": "0:11:56", "throughput": "619.89", "total_tokens": 853712}
{"current_steps": 126, "total_steps": 190, "loss": 0.0029, "learning_rate": 1.4040721330273063e-06, "epoch": 3.2516129032258063, "percentage": 66.32, "elapsed_time": "0:23:08", "remaining_time": "0:11:45", "throughput": "619.81", "total_tokens": 860400}
{"current_steps": 127, "total_steps": 190, "loss": 0.0003, "learning_rate": 1.3650237506511333e-06, "epoch": 3.2774193548387096, "percentage": 66.84, "elapsed_time": "0:23:19", "remaining_time": "0:11:34", "throughput": "619.97", "total_tokens": 867440}
{"current_steps": 128, "total_steps": 190, "loss": 0.0007, "learning_rate": 1.3263210930352737e-06, "epoch": 3.303225806451613, "percentage": 67.37, "elapsed_time": "0:23:30", "remaining_time": "0:11:23", "throughput": "619.98", "total_tokens": 874256}
{"current_steps": 129, "total_steps": 190, "loss": 0.008, "learning_rate": 1.2879759493841577e-06, "epoch": 3.329032258064516, "percentage": 67.89, "elapsed_time": "0:23:41", "remaining_time": "0:11:11", "throughput": "620.05", "total_tokens": 881168}
{"current_steps": 130, "total_steps": 190, "loss": 0.0004, "learning_rate": 1.2500000000000007e-06, "epoch": 3.3548387096774195, "percentage": 68.42, "elapsed_time": "0:23:52", "remaining_time": "0:11:00", "throughput": "620.16", "total_tokens": 888128}
{"current_steps": 131, "total_steps": 190, "loss": 0.0049, "learning_rate": 1.2124048127248644e-06, "epoch": 3.3806451612903228, "percentage": 68.95, "elapsed_time": "0:24:03", "remaining_time": "0:10:49", "throughput": "620.39", "total_tokens": 895296}
{"current_steps": 132, "total_steps": 190, "loss": 0.0012, "learning_rate": 1.1752018394169882e-06, "epoch": 3.4064516129032256, "percentage": 69.47, "elapsed_time": "0:24:14", "remaining_time": "0:10:38", "throughput": "620.30", "total_tokens": 901984}
{"current_steps": 133, "total_steps": 190, "loss": 0.0044, "learning_rate": 1.1384024124624324e-06, "epoch": 3.432258064516129, "percentage": 70.0, "elapsed_time": "0:24:25", "remaining_time": "0:10:27", "throughput": "620.50", "total_tokens": 909104}
{"current_steps": 134, "total_steps": 190, "loss": 0.0017, "learning_rate": 1.1020177413231334e-06, "epoch": 3.458064516129032, "percentage": 70.53, "elapsed_time": "0:24:36", "remaining_time": "0:10:16", "throughput": "620.57", "total_tokens": 916032}
{"current_steps": 135, "total_steps": 190, "loss": 0.0003, "learning_rate": 1.0660589091223854e-06, "epoch": 3.4838709677419355, "percentage": 71.05, "elapsed_time": "0:24:47", "remaining_time": "0:10:05", "throughput": "620.49", "total_tokens": 922736}
{"current_steps": 136, "total_steps": 190, "loss": 0.0099, "learning_rate": 1.0305368692688175e-06, "epoch": 3.509677419354839, "percentage": 71.58, "elapsed_time": "0:24:58", "remaining_time": "0:09:54", "throughput": "620.45", "total_tokens": 929472}
{"current_steps": 137, "total_steps": 190, "loss": 0.0068, "learning_rate": 9.95462442119879e-07, "epoch": 3.535483870967742, "percentage": 72.11, "elapsed_time": "0:25:09", "remaining_time": "0:09:43", "throughput": "620.34", "total_tokens": 936112}
{"current_steps": 138, "total_steps": 190, "loss": 0.0025, "learning_rate": 9.608463116858544e-07, "epoch": 3.5612903225806454, "percentage": 72.63, "elapsed_time": "0:25:20", "remaining_time": "0:09:32", "throughput": "620.33", "total_tokens": 942912}
{"current_steps": 139, "total_steps": 190, "loss": 0.0004, "learning_rate": 9.266990223754069e-07, "epoch": 3.587096774193548, "percentage": 73.16, "elapsed_time": "0:25:30", "remaining_time": "0:09:21", "throughput": "620.50", "total_tokens": 949984}
{"current_steps": 140, "total_steps": 190, "loss": 0.0101, "learning_rate": 8.930309757836517e-07, "epoch": 3.6129032258064515, "percentage": 73.68, "elapsed_time": "0:25:41", "remaining_time": "0:09:10", "throughput": "620.37", "total_tokens": 956608}
{"current_steps": 141, "total_steps": 190, "loss": 0.0068, "learning_rate": 8.598524275237321e-07, "epoch": 3.638709677419355, "percentage": 74.21, "elapsed_time": "0:25:52", "remaining_time": "0:08:59", "throughput": "620.41", "total_tokens": 963488}
{"current_steps": 142, "total_steps": 190, "loss": 0.0007, "learning_rate": 8.271734841028553e-07, "epoch": 3.664516129032258, "percentage": 74.74, "elapsed_time": "0:26:03", "remaining_time": "0:08:48", "throughput": "620.29", "total_tokens": 970128}
{"current_steps": 143, "total_steps": 190, "loss": 0.0161, "learning_rate": 7.950040998437541e-07, "epoch": 3.6903225806451614, "percentage": 75.26, "elapsed_time": "0:26:14", "remaining_time": "0:08:37", "throughput": "620.19", "total_tokens": 976800}
{"current_steps": 144, "total_steps": 190, "loss": 0.0115, "learning_rate": 7.633540738525066e-07, "epoch": 3.7161290322580647, "percentage": 75.79, "elapsed_time": "0:26:25", "remaining_time": "0:08:26", "throughput": "620.44", "total_tokens": 984000}
{"current_steps": 145, "total_steps": 190, "loss": 0.0052, "learning_rate": 7.322330470336314e-07, "epoch": 3.741935483870968, "percentage": 76.32, "elapsed_time": "0:26:36", "remaining_time": "0:08:15", "throughput": "620.49", "total_tokens": 990896}
{"current_steps": 146, "total_steps": 190, "loss": 0.0098, "learning_rate": 7.016504991533727e-07, "epoch": 3.767741935483871, "percentage": 76.84, "elapsed_time": "0:26:47", "remaining_time": "0:08:04", "throughput": "620.56", "total_tokens": 997824}
{"current_steps": 147, "total_steps": 190, "loss": 0.0005, "learning_rate": 6.716157459520739e-07, "epoch": 3.793548387096774, "percentage": 77.37, "elapsed_time": "0:26:58", "remaining_time": "0:07:53", "throughput": "620.74", "total_tokens": 1004928}
{"current_steps": 148, "total_steps": 190, "loss": 0.0012, "learning_rate": 6.421379363065142e-07, "epoch": 3.8193548387096774, "percentage": 77.89, "elapsed_time": "0:27:09", "remaining_time": "0:07:42", "throughput": "620.71", "total_tokens": 1011696}
{"current_steps": 149, "total_steps": 190, "loss": 0.0013, "learning_rate": 6.1322604944307e-07, "epoch": 3.8451612903225807, "percentage": 78.42, "elapsed_time": "0:27:20", "remaining_time": "0:07:31", "throughput": "620.61", "total_tokens": 1018368}
{"current_steps": 150, "total_steps": 190, "loss": 0.0003, "learning_rate": 5.848888922025553e-07, "epoch": 3.870967741935484, "percentage": 78.95, "elapsed_time": "0:27:31", "remaining_time": "0:07:20", "throughput": "620.76", "total_tokens": 1025424}
{"current_steps": 151, "total_steps": 190, "loss": 0.0026, "learning_rate": 5.571350963575728e-07, "epoch": 3.896774193548387, "percentage": 79.47, "elapsed_time": "0:27:42", "remaining_time": "0:07:09", "throughput": "620.61", "total_tokens": 1032016}
{"current_steps": 152, "total_steps": 190, "loss": 0.0097, "learning_rate": 5.299731159831953e-07, "epoch": 3.9225806451612906, "percentage": 80.0, "elapsed_time": "0:27:53", "remaining_time": "0:06:58", "throughput": "620.67", "total_tokens": 1038928}
{"current_steps": 153, "total_steps": 190, "loss": 0.0047, "learning_rate": 5.034112248817685e-07, "epoch": 3.9483870967741934, "percentage": 80.53, "elapsed_time": "0:28:04", "remaining_time": "0:06:47", "throughput": "620.62", "total_tokens": 1045664}
{"current_steps": 154, "total_steps": 190, "loss": 0.0081, "learning_rate": 4.774575140626317e-07, "epoch": 3.9741935483870967, "percentage": 81.05, "elapsed_time": "0:28:15", "remaining_time": "0:06:36", "throughput": "620.72", "total_tokens": 1052640}
{"current_steps": 155, "total_steps": 190, "loss": 0.0018, "learning_rate": 4.5211988927752026e-07, "epoch": 4.0, "percentage": 81.58, "elapsed_time": "0:28:26", "remaining_time": "0:06:25", "throughput": "620.95", "total_tokens": 1059840}
{"current_steps": 156, "total_steps": 190, "loss": 0.0053, "learning_rate": 4.27406068612396e-07, "epoch": 4.025806451612903, "percentage": 82.11, "elapsed_time": "0:28:37", "remaining_time": "0:06:14", "throughput": "620.97", "total_tokens": 1066704}
{"current_steps": 157, "total_steps": 190, "loss": 0.0005, "learning_rate": 4.033235801364402e-07, "epoch": 4.051612903225807, "percentage": 82.63, "elapsed_time": "0:28:48", "remaining_time": "0:06:03", "throughput": "621.01", "total_tokens": 1073600}
{"current_steps": 158, "total_steps": 190, "loss": 0.0001, "learning_rate": 3.798797596089351e-07, "epoch": 4.077419354838709, "percentage": 83.16, "elapsed_time": "0:28:59", "remaining_time": "0:05:52", "throughput": "620.88", "total_tokens": 1080208}
{"current_steps": 159, "total_steps": 190, "loss": 0.0018, "learning_rate": 3.5708174824471947e-07, "epoch": 4.103225806451613, "percentage": 83.68, "elapsed_time": "0:29:10", "remaining_time": "0:05:41", "throughput": "620.79", "total_tokens": 1086880}
{"current_steps": 160, "total_steps": 190, "loss": 0.001, "learning_rate": 3.3493649053890325e-07, "epoch": 4.129032258064516, "percentage": 84.21, "elapsed_time": "0:29:21", "remaining_time": "0:05:30", "throughput": "620.68", "total_tokens": 1093520}
{"current_steps": 161, "total_steps": 190, "loss": 0.0001, "learning_rate": 3.134507321515107e-07, "epoch": 4.15483870967742, "percentage": 84.74, "elapsed_time": "0:29:32", "remaining_time": "0:05:19", "throughput": "620.79", "total_tokens": 1100528}
{"current_steps": 162, "total_steps": 190, "loss": 0.0012, "learning_rate": 2.9263101785268253e-07, "epoch": 4.180645161290323, "percentage": 85.26, "elapsed_time": "0:29:43", "remaining_time": "0:05:08", "throughput": "620.89", "total_tokens": 1107520}
{"current_steps": 163, "total_steps": 190, "loss": 0.0001, "learning_rate": 2.7248368952908055e-07, "epoch": 4.2064516129032254, "percentage": 85.79, "elapsed_time": "0:29:54", "remaining_time": "0:04:57", "throughput": "620.82", "total_tokens": 1114208}
{"current_steps": 164, "total_steps": 190, "loss": 0.0002, "learning_rate": 2.53014884252083e-07, "epoch": 4.232258064516129, "percentage": 86.32, "elapsed_time": "0:30:05", "remaining_time": "0:04:46", "throughput": "620.76", "total_tokens": 1120912}
{"current_steps": 165, "total_steps": 190, "loss": 0.0001, "learning_rate": 2.3423053240837518e-07, "epoch": 4.258064516129032, "percentage": 86.84, "elapsed_time": "0:30:16", "remaining_time": "0:04:35", "throughput": "620.84", "total_tokens": 1127872}
{"current_steps": 166, "total_steps": 190, "loss": 0.0003, "learning_rate": 2.1613635589349756e-07, "epoch": 4.283870967741936, "percentage": 87.37, "elapsed_time": "0:30:27", "remaining_time": "0:04:24", "throughput": "620.65", "total_tokens": 1134352}
{"current_steps": 167, "total_steps": 190, "loss": 0.0001, "learning_rate": 1.9873786636889908e-07, "epoch": 4.309677419354839, "percentage": 87.89, "elapsed_time": "0:30:38", "remaining_time": "0:04:13", "throughput": "620.79", "total_tokens": 1141440}
{"current_steps": 168, "total_steps": 190, "loss": 0.0007, "learning_rate": 1.8204036358303173e-07, "epoch": 4.335483870967742, "percentage": 88.42, "elapsed_time": "0:30:49", "remaining_time": "0:04:02", "throughput": "620.70", "total_tokens": 1148096}
{"current_steps": 169, "total_steps": 190, "loss": 0.0003, "learning_rate": 1.6604893375699594e-07, "epoch": 4.361290322580645, "percentage": 88.95, "elapsed_time": "0:31:00", "remaining_time": "0:03:51", "throughput": "620.56", "total_tokens": 1154672}
{"current_steps": 170, "total_steps": 190, "loss": 0.0001, "learning_rate": 1.507684480352292e-07, "epoch": 4.387096774193548, "percentage": 89.47, "elapsed_time": "0:31:11", "remaining_time": "0:03:40", "throughput": "620.70", "total_tokens": 1161744}
{"current_steps": 171, "total_steps": 190, "loss": 0.0008, "learning_rate": 1.362035610017079e-07, "epoch": 4.412903225806452, "percentage": 90.0, "elapsed_time": "0:31:22", "remaining_time": "0:03:29", "throughput": "620.90", "total_tokens": 1168944}
{"current_steps": 172, "total_steps": 190, "loss": 0.0001, "learning_rate": 1.223587092621162e-07, "epoch": 4.438709677419355, "percentage": 90.53, "elapsed_time": "0:31:33", "remaining_time": "0:03:18", "throughput": "620.92", "total_tokens": 1175792}
{"current_steps": 173, "total_steps": 190, "loss": 0.0004, "learning_rate": 1.0923811009241142e-07, "epoch": 4.464516129032258, "percentage": 91.05, "elapsed_time": "0:31:44", "remaining_time": "0:03:07", "throughput": "621.02", "total_tokens": 1182800}
{"current_steps": 174, "total_steps": 190, "loss": 0.0001, "learning_rate": 9.684576015420277e-08, "epoch": 4.490322580645161, "percentage": 91.58, "elapsed_time": "0:31:55", "remaining_time": "0:02:56", "throughput": "620.99", "total_tokens": 1189568}
{"current_steps": 175, "total_steps": 190, "loss": 0.0005, "learning_rate": 8.518543427732951e-08, "epoch": 4.516129032258064, "percentage": 92.11, "elapsed_time": "0:32:06", "remaining_time": "0:02:45", "throughput": "621.03", "total_tokens": 1196480}
{"current_steps": 176, "total_steps": 190, "loss": 0.0076, "learning_rate": 7.426068431000883e-08, "epoch": 4.541935483870968, "percentage": 92.63, "elapsed_time": "0:32:17", "remaining_time": "0:02:34", "throughput": "621.25", "total_tokens": 1203728}
{"current_steps": 177, "total_steps": 190, "loss": 0.0004, "learning_rate": 6.407483803691216e-08, "epoch": 4.567741935483871, "percentage": 93.16, "elapsed_time": "0:32:28", "remaining_time": "0:02:23", "throughput": "621.12", "total_tokens": 1210320}
{"current_steps": 178, "total_steps": 190, "loss": 0.004, "learning_rate": 5.463099816548578e-08, "epoch": 4.593548387096774, "percentage": 93.68, "elapsed_time": "0:32:39", "remaining_time": "0:02:12", "throughput": "621.16", "total_tokens": 1217248}
{"current_steps": 179, "total_steps": 190, "loss": 0.0001, "learning_rate": 4.593204138084006e-08, "epoch": 4.619354838709677, "percentage": 94.21, "elapsed_time": "0:32:50", "remaining_time": "0:02:01", "throughput": "621.22", "total_tokens": 1224192}
{"current_steps": 180, "total_steps": 190, "loss": 0.0005, "learning_rate": 3.798061746947995e-08, "epoch": 4.645161290322581, "percentage": 94.74, "elapsed_time": "0:33:01", "remaining_time": "0:01:50", "throughput": "621.17", "total_tokens": 1230896}
{"current_steps": 181, "total_steps": 190, "loss": 0.0002, "learning_rate": 3.077914851215585e-08, "epoch": 4.670967741935484, "percentage": 95.26, "elapsed_time": "0:33:12", "remaining_time": "0:01:39", "throughput": "621.23", "total_tokens": 1237840}
{"current_steps": 182, "total_steps": 190, "loss": 0.0001, "learning_rate": 2.4329828146074096e-08, "epoch": 4.6967741935483875, "percentage": 95.79, "elapsed_time": "0:33:23", "remaining_time": "0:01:28", "throughput": "621.25", "total_tokens": 1244688}
{"current_steps": 183, "total_steps": 190, "loss": 0.0001, "learning_rate": 1.8634620896695044e-08, "epoch": 4.72258064516129, "percentage": 96.32, "elapsed_time": "0:33:34", "remaining_time": "0:01:17", "throughput": "621.28", "total_tokens": 1251584}
{"current_steps": 184, "total_steps": 190, "loss": 0.0001, "learning_rate": 1.3695261579316776e-08, "epoch": 4.748387096774193, "percentage": 96.84, "elapsed_time": "0:33:45", "remaining_time": "0:01:06", "throughput": "621.30", "total_tokens": 1258448}
{"current_steps": 185, "total_steps": 190, "loss": 0.0167, "learning_rate": 9.513254770636138e-09, "epoch": 4.774193548387097, "percentage": 97.37, "elapsed_time": "0:33:56", "remaining_time": "0:00:55", "throughput": "621.38", "total_tokens": 1265440}
{"current_steps": 186, "total_steps": 190, "loss": 0.0002, "learning_rate": 6.089874350439507e-09, "epoch": 4.8, "percentage": 97.89, "elapsed_time": "0:34:07", "remaining_time": "0:00:44", "throughput": "621.28", "total_tokens": 1272080}
{"current_steps": 187, "total_steps": 190, "loss": 0.0003, "learning_rate": 3.4261631135654174e-09, "epoch": 4.825806451612904, "percentage": 98.42, "elapsed_time": "0:34:18", "remaining_time": "0:00:33", "throughput": "621.31", "total_tokens": 1278976}
{"current_steps": 188, "total_steps": 190, "loss": 0.0024, "learning_rate": 1.5229324522605949e-09, "epoch": 4.851612903225806, "percentage": 98.95, "elapsed_time": "0:34:29", "remaining_time": "0:00:22", "throughput": "621.29", "total_tokens": 1285760}
{"current_steps": 189, "total_steps": 190, "loss": 0.0005, "learning_rate": 3.8076210902182607e-10, "epoch": 4.877419354838709, "percentage": 99.47, "elapsed_time": "0:34:40", "remaining_time": "0:00:11", "throughput": "621.19", "total_tokens": 1292368}
{"current_steps": 190, "total_steps": 190, "loss": 0.0017, "learning_rate": 0.0, "epoch": 4.903225806451613, "percentage": 100.0, "elapsed_time": "0:34:51", "remaining_time": "0:00:00", "throughput": "621.15", "total_tokens": 1299120}
{"current_steps": 190, "total_steps": 190, "epoch": 4.903225806451613, "percentage": 100.0, "elapsed_time": "0:35:42", "remaining_time": "0:00:00", "throughput": "606.30", "total_tokens": 1299120}