{"current_steps": 1, "total_steps": 3345, "loss": 2.2531, "lr": 2.4999994487006423e-06, "epoch": 0.0014947683109118087, "percentage": 0.03, "elapsed_time": "0:00:03", "remaining_time": "3:11:28", "throughput": 2384.55, "total_tokens": 8192} {"current_steps": 2, "total_steps": 3345, "loss": 2.402, "lr": 2.499997794803055e-06, "epoch": 0.0029895366218236174, "percentage": 0.06, "elapsed_time": "0:00:04", "remaining_time": "2:12:33", "throughput": 3443.08, "total_tokens": 16384} {"current_steps": 3, "total_steps": 3345, "loss": 2.0147, "lr": 2.4999950383086976e-06, "epoch": 0.004484304932735426, "percentage": 0.09, "elapsed_time": "0:00:05", "remaining_time": "1:49:48", "throughput": 4155.55, "total_tokens": 24576} {"current_steps": 4, "total_steps": 3345, "loss": 1.9146, "lr": 2.499991179220001e-06, "epoch": 0.005979073243647235, "percentage": 0.12, "elapsed_time": "0:00:07", "remaining_time": "1:38:26", "throughput": 4634.03, "total_tokens": 32768} {"current_steps": 5, "total_steps": 3345, "loss": 1.7463, "lr": 2.499986217540369e-06, "epoch": 0.007473841554559043, "percentage": 0.15, "elapsed_time": "0:00:08", "remaining_time": "1:31:42", "throughput": 4972.76, "total_tokens": 40960} {"current_steps": 6, "total_steps": 3345, "loss": 1.7718, "lr": 2.4999801532741787e-06, "epoch": 0.008968609865470852, "percentage": 0.18, "elapsed_time": "0:00:09", "remaining_time": "1:27:07", "throughput": 5232.38, "total_tokens": 49152} {"current_steps": 7, "total_steps": 3345, "loss": 2.2407, "lr": 2.499972986426779e-06, "epoch": 0.01046337817638266, "percentage": 0.21, "elapsed_time": "0:00:10", "remaining_time": "1:23:48", "throughput": 5438.01, "total_tokens": 57344} {"current_steps": 8, "total_steps": 3345, "loss": 1.9477, "lr": 2.4999647170044923e-06, "epoch": 0.01195814648729447, "percentage": 0.24, "elapsed_time": "0:00:11", "remaining_time": "1:21:20", "throughput": 5601.71, "total_tokens": 65536} {"current_steps": 9, "total_steps": 3345, "loss": 2.0326, "lr": 2.4999553450146116e-06, "epoch": 0.013452914798206279, "percentage": 0.27, "elapsed_time": "0:00:12", "remaining_time": "1:19:24", "throughput": 5735.77, "total_tokens": 73728} {"current_steps": 10, "total_steps": 3345, "loss": 1.8658, "lr": 2.499944870465405e-06, "epoch": 0.014947683109118086, "percentage": 0.3, "elapsed_time": "0:00:14", "remaining_time": "1:17:52", "throughput": 5846.89, "total_tokens": 81920} {"current_steps": 11, "total_steps": 3345, "loss": 1.7791, "lr": 2.499933293366111e-06, "epoch": 0.016442451420029897, "percentage": 0.33, "elapsed_time": "0:00:15", "remaining_time": "1:16:37", "throughput": 5940.68, "total_tokens": 90112} {"current_steps": 12, "total_steps": 3345, "loss": 1.5517, "lr": 2.499920613726942e-06, "epoch": 0.017937219730941704, "percentage": 0.36, "elapsed_time": "0:00:16", "remaining_time": "1:15:34", "throughput": 6021.65, "total_tokens": 98304} {"current_steps": 13, "total_steps": 3345, "loss": 1.8122, "lr": 2.4999068315590823e-06, "epoch": 0.01943198804185351, "percentage": 0.39, "elapsed_time": "0:00:17", "remaining_time": "1:14:43", "throughput": 6088.68, "total_tokens": 106496} {"current_steps": 14, "total_steps": 3345, "loss": 1.7822, "lr": 2.499891946874689e-06, "epoch": 0.02092675635276532, "percentage": 0.42, "elapsed_time": "0:00:18", "remaining_time": "1:13:56", "throughput": 6150.62, "total_tokens": 114688} {"current_steps": 15, "total_steps": 3345, "loss": 1.9233, "lr": 2.499875959686891e-06, "epoch": 0.02242152466367713, "percentage": 0.45, "elapsed_time": "0:00:19", "remaining_time": "1:13:16", "throughput": 6205.42, "total_tokens": 122880} {"current_steps": 16, "total_steps": 3345, "loss": 1.6661, "lr": 2.4998588700097914e-06, "epoch": 0.02391629297458894, "percentage": 0.48, "elapsed_time": "0:00:20", "remaining_time": "1:12:41", "throughput": 6252.89, "total_tokens": 131072} {"current_steps": 17, "total_steps": 3345, "loss": 2.0675, "lr": 2.4998406778584635e-06, "epoch": 0.025411061285500747, "percentage": 0.51, "elapsed_time": "0:00:22", "remaining_time": "1:12:10", "throughput": 6295.74, "total_tokens": 139264} {"current_steps": 18, "total_steps": 3345, "loss": 2.0639, "lr": 2.4998213832489544e-06, "epoch": 0.026905829596412557, "percentage": 0.54, "elapsed_time": "0:00:23", "remaining_time": "1:11:43", "throughput": 6333.56, "total_tokens": 147456} {"current_steps": 19, "total_steps": 3345, "loss": 2.0295, "lr": 2.4998009861982842e-06, "epoch": 0.028400597907324365, "percentage": 0.57, "elapsed_time": "0:00:24", "remaining_time": "1:11:17", "throughput": 6369.6, "total_tokens": 155648} {"current_steps": 20, "total_steps": 3345, "loss": 1.8815, "lr": 2.4997794867244437e-06, "epoch": 0.029895366218236172, "percentage": 0.6, "elapsed_time": "0:00:25", "remaining_time": "1:10:55", "throughput": 6400.28, "total_tokens": 163840} {"current_steps": 21, "total_steps": 3345, "loss": 1.8903, "lr": 2.499756884846398e-06, "epoch": 0.03139013452914798, "percentage": 0.63, "elapsed_time": "0:00:26", "remaining_time": "1:10:35", "throughput": 6429.1, "total_tokens": 172032} {"current_steps": 22, "total_steps": 3345, "loss": 1.9163, "lr": 2.4997331805840835e-06, "epoch": 0.03288490284005979, "percentage": 0.66, "elapsed_time": "0:00:27", "remaining_time": "1:10:16", "throughput": 6455.55, "total_tokens": 180224} {"current_steps": 23, "total_steps": 3345, "loss": 1.7741, "lr": 2.4997083739584086e-06, "epoch": 0.0343796711509716, "percentage": 0.69, "elapsed_time": "0:00:29", "remaining_time": "1:09:59", "throughput": 6479.53, "total_tokens": 188416} {"current_steps": 24, "total_steps": 3345, "loss": 1.6643, "lr": 2.499682464991256e-06, "epoch": 0.03587443946188341, "percentage": 0.72, "elapsed_time": "0:00:30", "remaining_time": "1:09:43", "throughput": 6502.63, "total_tokens": 196608} {"current_steps": 25, "total_steps": 3345, "loss": 1.7719, "lr": 2.4996554537054785e-06, "epoch": 0.03736920777279522, "percentage": 0.75, "elapsed_time": "0:00:31", "remaining_time": "1:09:29", "throughput": 6523.06, "total_tokens": 204800} {"current_steps": 26, "total_steps": 3345, "loss": 1.9136, "lr": 2.499627340124902e-06, "epoch": 0.03886397608370702, "percentage": 0.78, "elapsed_time": "0:00:32", "remaining_time": "1:09:14", "throughput": 6543.94, "total_tokens": 212992} {"current_steps": 27, "total_steps": 3345, "loss": 1.942, "lr": 2.4995981242743257e-06, "epoch": 0.04035874439461883, "percentage": 0.81, "elapsed_time": "0:00:33", "remaining_time": "1:09:02", "throughput": 6561.29, "total_tokens": 221184} {"current_steps": 28, "total_steps": 3345, "loss": 1.5864, "lr": 2.4995678061795194e-06, "epoch": 0.04185351270553064, "percentage": 0.84, "elapsed_time": "0:00:34", "remaining_time": "1:08:50", "throughput": 6579.04, "total_tokens": 229376} {"current_steps": 29, "total_steps": 3345, "loss": 1.6736, "lr": 2.4995363858672268e-06, "epoch": 0.043348281016442454, "percentage": 0.87, "elapsed_time": "0:00:36", "remaining_time": "1:08:38", "throughput": 6595.26, "total_tokens": 237568} {"current_steps": 30, "total_steps": 3345, "loss": 1.7478, "lr": 2.4995038633651628e-06, "epoch": 0.04484304932735426, "percentage": 0.9, "elapsed_time": "0:00:37", "remaining_time": "1:08:28", "throughput": 6610.58, "total_tokens": 245760} {"current_steps": 31, "total_steps": 3345, "loss": 2.0641, "lr": 2.4994702387020148e-06, "epoch": 0.04633781763826607, "percentage": 0.93, "elapsed_time": "0:00:38", "remaining_time": "1:08:18", "throughput": 6624.74, "total_tokens": 253952} {"current_steps": 32, "total_steps": 3345, "loss": 1.4719, "lr": 2.4994355119074424e-06, "epoch": 0.04783258594917788, "percentage": 0.96, "elapsed_time": "0:00:39", "remaining_time": "1:08:08", "throughput": 6638.36, "total_tokens": 262144} {"current_steps": 33, "total_steps": 3345, "loss": 1.7285, "lr": 2.4993996830120774e-06, "epoch": 0.04932735426008968, "percentage": 0.99, "elapsed_time": "0:00:40", "remaining_time": "1:07:59", "throughput": 6650.96, "total_tokens": 270336} {"current_steps": 34, "total_steps": 3345, "loss": 1.4259, "lr": 2.4993627520475238e-06, "epoch": 0.05082212257100149, "percentage": 1.02, "elapsed_time": "0:00:41", "remaining_time": "1:07:50", "throughput": 6662.78, "total_tokens": 278528} {"current_steps": 35, "total_steps": 3345, "loss": 1.4831, "lr": 2.4993247190463576e-06, "epoch": 0.052316890881913304, "percentage": 1.05, "elapsed_time": "0:00:42", "remaining_time": "1:07:42", "throughput": 6673.93, "total_tokens": 286720} {"current_steps": 36, "total_steps": 3345, "loss": 1.775, "lr": 2.499285584042127e-06, "epoch": 0.053811659192825115, "percentage": 1.08, "elapsed_time": "0:00:44", "remaining_time": "1:07:35", "throughput": 6684.62, "total_tokens": 294912} {"current_steps": 37, "total_steps": 3345, "loss": 1.6792, "lr": 2.4992453470693517e-06, "epoch": 0.05530642750373692, "percentage": 1.11, "elapsed_time": "0:00:45", "remaining_time": "1:07:28", "throughput": 6694.34, "total_tokens": 303104} {"current_steps": 38, "total_steps": 3345, "loss": 1.6426, "lr": 2.4992040081635242e-06, "epoch": 0.05680119581464873, "percentage": 1.14, "elapsed_time": "0:00:46", "remaining_time": "1:07:20", "throughput": 6704.07, "total_tokens": 311296} {"current_steps": 39, "total_steps": 3345, "loss": 1.6024, "lr": 2.499161567361109e-06, "epoch": 0.05829596412556054, "percentage": 1.17, "elapsed_time": "0:00:47", "remaining_time": "1:07:14", "throughput": 6712.43, "total_tokens": 319488} {"current_steps": 40, "total_steps": 3345, "loss": 1.3827, "lr": 2.499118024699542e-06, "epoch": 0.059790732436472344, "percentage": 1.2, "elapsed_time": "0:00:48", "remaining_time": "1:07:08", "throughput": 6720.6, "total_tokens": 327680} {"current_steps": 41, "total_steps": 3345, "loss": 1.7409, "lr": 2.4990733802172313e-06, "epoch": 0.061285500747384154, "percentage": 1.23, "elapsed_time": "0:00:49", "remaining_time": "1:07:02", "throughput": 6728.93, "total_tokens": 335872} {"current_steps": 42, "total_steps": 3345, "loss": 1.205, "lr": 2.499027633953556e-06, "epoch": 0.06278026905829596, "percentage": 1.26, "elapsed_time": "0:00:51", "remaining_time": "1:06:56", "throughput": 6736.81, "total_tokens": 344064} {"current_steps": 43, "total_steps": 3345, "loss": 1.6824, "lr": 2.49898078594887e-06, "epoch": 0.06427503736920777, "percentage": 1.29, "elapsed_time": "0:00:52", "remaining_time": "1:06:51", "throughput": 6743.83, "total_tokens": 352256} {"current_steps": 44, "total_steps": 3345, "loss": 1.4352, "lr": 2.4989328362444944e-06, "epoch": 0.06576980568011959, "percentage": 1.32, "elapsed_time": "0:00:53", "remaining_time": "1:06:45", "throughput": 6751.32, "total_tokens": 360448} {"current_steps": 45, "total_steps": 3345, "loss": 1.5861, "lr": 2.498883784882726e-06, "epoch": 0.06726457399103139, "percentage": 1.35, "elapsed_time": "0:00:54", "remaining_time": "1:06:39", "throughput": 6758.43, "total_tokens": 368640} {"current_steps": 46, "total_steps": 3345, "loss": 1.4885, "lr": 2.498833631906832e-06, "epoch": 0.0687593423019432, "percentage": 1.38, "elapsed_time": "0:00:55", "remaining_time": "1:06:34", "throughput": 6765.13, "total_tokens": 376832} {"current_steps": 47, "total_steps": 3345, "loss": 1.7831, "lr": 2.4987823773610516e-06, "epoch": 0.07025411061285501, "percentage": 1.41, "elapsed_time": "0:00:56", "remaining_time": "1:06:29", "throughput": 6771.38, "total_tokens": 385024} {"current_steps": 48, "total_steps": 3345, "loss": 1.6712, "lr": 2.498730021290594e-06, "epoch": 0.07174887892376682, "percentage": 1.43, "elapsed_time": "0:00:58", "remaining_time": "1:06:25", "throughput": 6777.29, "total_tokens": 393216} {"current_steps": 49, "total_steps": 3345, "loss": 1.505, "lr": 2.4986765637416427e-06, "epoch": 0.07324364723467862, "percentage": 1.46, "elapsed_time": "0:00:59", "remaining_time": "1:06:20", "throughput": 6783.31, "total_tokens": 401408} {"current_steps": 50, "total_steps": 3345, "loss": 1.4856, "lr": 2.498622004761351e-06, "epoch": 0.07473841554559044, "percentage": 1.49, "elapsed_time": "0:01:00", "remaining_time": "1:06:15", "throughput": 6788.95, "total_tokens": 409600} {"current_steps": 51, "total_steps": 3345, "loss": 1.6896, "lr": 2.4985663443978446e-06, "epoch": 0.07623318385650224, "percentage": 1.52, "elapsed_time": "0:01:01", "remaining_time": "1:06:11", "throughput": 6794.19, "total_tokens": 417792} {"current_steps": 52, "total_steps": 3345, "loss": 1.4315, "lr": 2.4985095827002194e-06, "epoch": 0.07772795216741404, "percentage": 1.55, "elapsed_time": "0:01:02", "remaining_time": "1:06:07", "throughput": 6799.4, "total_tokens": 425984} {"current_steps": 53, "total_steps": 3345, "loss": 2.0576, "lr": 2.498451719718545e-06, "epoch": 0.07922272047832586, "percentage": 1.58, "elapsed_time": "0:01:03", "remaining_time": "1:06:03", "throughput": 6804.87, "total_tokens": 434176} {"current_steps": 54, "total_steps": 3345, "loss": 1.6303, "lr": 2.4983927555038594e-06, "epoch": 0.08071748878923767, "percentage": 1.61, "elapsed_time": "0:01:04", "remaining_time": "1:05:59", "throughput": 6809.68, "total_tokens": 442368} {"current_steps": 55, "total_steps": 3345, "loss": 1.7331, "lr": 2.4983326901081755e-06, "epoch": 0.08221225710014948, "percentage": 1.64, "elapsed_time": "0:01:06", "remaining_time": "1:05:55", "throughput": 6814.54, "total_tokens": 450560} {"current_steps": 56, "total_steps": 3345, "loss": 1.6948, "lr": 2.4982715235844748e-06, "epoch": 0.08370702541106129, "percentage": 1.67, "elapsed_time": "0:01:07", "remaining_time": "1:05:51", "throughput": 6819.03, "total_tokens": 458752} {"current_steps": 57, "total_steps": 3345, "loss": 1.5503, "lr": 2.498209255986711e-06, "epoch": 0.08520179372197309, "percentage": 1.7, "elapsed_time": "0:01:08", "remaining_time": "1:05:47", "throughput": 6822.8, "total_tokens": 466944} {"current_steps": 58, "total_steps": 3345, "loss": 1.7984, "lr": 2.4981458873698095e-06, "epoch": 0.08669656203288491, "percentage": 1.73, "elapsed_time": "0:01:09", "remaining_time": "1:05:44", "throughput": 6827.29, "total_tokens": 475136} {"current_steps": 59, "total_steps": 3345, "loss": 1.6344, "lr": 2.4980814177896656e-06, "epoch": 0.08819133034379671, "percentage": 1.76, "elapsed_time": "0:01:10", "remaining_time": "1:05:40", "throughput": 6831.73, "total_tokens": 483328} {"current_steps": 60, "total_steps": 3345, "loss": 1.732, "lr": 2.498015847303147e-06, "epoch": 0.08968609865470852, "percentage": 1.79, "elapsed_time": "0:01:11", "remaining_time": "1:05:36", "throughput": 6835.91, "total_tokens": 491520} {"current_steps": 61, "total_steps": 3345, "loss": 1.5801, "lr": 2.497949175968093e-06, "epoch": 0.09118086696562033, "percentage": 1.82, "elapsed_time": "0:01:13", "remaining_time": "1:05:33", "throughput": 6839.86, "total_tokens": 499712} {"current_steps": 62, "total_steps": 3345, "loss": 1.7174, "lr": 2.4978814038433113e-06, "epoch": 0.09267563527653214, "percentage": 1.85, "elapsed_time": "0:01:14", "remaining_time": "1:05:29", "throughput": 6843.57, "total_tokens": 507904} {"current_steps": 63, "total_steps": 3345, "loss": 1.3201, "lr": 2.4978125309885836e-06, "epoch": 0.09417040358744394, "percentage": 1.88, "elapsed_time": "0:01:15", "remaining_time": "1:05:26", "throughput": 6847.13, "total_tokens": 516096} {"current_steps": 64, "total_steps": 3345, "loss": 1.6244, "lr": 2.49774255746466e-06, "epoch": 0.09566517189835576, "percentage": 1.91, "elapsed_time": "0:01:16", "remaining_time": "1:05:23", "throughput": 6850.88, "total_tokens": 524288} {"current_steps": 65, "total_steps": 3345, "loss": 1.7402, "lr": 2.4976714833332637e-06, "epoch": 0.09715994020926756, "percentage": 1.94, "elapsed_time": "0:01:17", "remaining_time": "1:05:20", "throughput": 6854.18, "total_tokens": 532480} {"current_steps": 66, "total_steps": 3345, "loss": 1.5963, "lr": 2.4975993086570876e-06, "epoch": 0.09865470852017937, "percentage": 1.97, "elapsed_time": "0:01:18", "remaining_time": "1:05:17", "throughput": 6857.45, "total_tokens": 540672} {"current_steps": 67, "total_steps": 3345, "loss": 1.6819, "lr": 2.497526033499795e-06, "epoch": 0.10014947683109118, "percentage": 2.0, "elapsed_time": "0:01:20", "remaining_time": "1:05:14", "throughput": 6860.51, "total_tokens": 548864} {"current_steps": 68, "total_steps": 3345, "loss": 1.3257, "lr": 2.49745165792602e-06, "epoch": 0.10164424514200299, "percentage": 2.03, "elapsed_time": "0:01:21", "remaining_time": "1:05:11", "throughput": 6863.76, "total_tokens": 557056} {"current_steps": 69, "total_steps": 3345, "loss": 1.264, "lr": 2.4973761820013686e-06, "epoch": 0.1031390134529148, "percentage": 2.06, "elapsed_time": "0:01:22", "remaining_time": "1:05:08", "throughput": 6866.62, "total_tokens": 565248} {"current_steps": 70, "total_steps": 3345, "loss": 1.6961, "lr": 2.4972996057924166e-06, "epoch": 0.10463378176382661, "percentage": 2.09, "elapsed_time": "0:01:23", "remaining_time": "1:05:05", "throughput": 6869.44, "total_tokens": 573440} {"current_steps": 71, "total_steps": 3345, "loss": 1.7499, "lr": 2.4972219293667096e-06, "epoch": 0.10612855007473841, "percentage": 2.12, "elapsed_time": "0:01:24", "remaining_time": "1:05:02", "throughput": 6872.18, "total_tokens": 581632} {"current_steps": 72, "total_steps": 3345, "loss": 1.6704, "lr": 2.497143152792765e-06, "epoch": 0.10762331838565023, "percentage": 2.15, "elapsed_time": "0:01:25", "remaining_time": "1:04:59", "throughput": 6875.05, "total_tokens": 589824} {"current_steps": 73, "total_steps": 3345, "loss": 1.6915, "lr": 2.497063276140069e-06, "epoch": 0.10911808669656203, "percentage": 2.18, "elapsed_time": "0:01:26", "remaining_time": "1:04:57", "throughput": 6877.75, "total_tokens": 598016} {"current_steps": 74, "total_steps": 3345, "loss": 1.6635, "lr": 2.49698229947908e-06, "epoch": 0.11061285500747384, "percentage": 2.21, "elapsed_time": "0:01:28", "remaining_time": "1:04:54", "throughput": 6879.79, "total_tokens": 606208} {"current_steps": 75, "total_steps": 3345, "loss": 1.5452, "lr": 2.4969002228812255e-06, "epoch": 0.11210762331838565, "percentage": 2.24, "elapsed_time": "0:01:29", "remaining_time": "1:04:52", "throughput": 6881.9, "total_tokens": 614400} {"current_steps": 76, "total_steps": 3345, "loss": 1.5596, "lr": 2.4968170464189033e-06, "epoch": 0.11360239162929746, "percentage": 2.27, "elapsed_time": "0:01:30", "remaining_time": "1:04:49", "throughput": 6884.43, "total_tokens": 622592} {"current_steps": 77, "total_steps": 3345, "loss": 1.2998, "lr": 2.496732770165482e-06, "epoch": 0.11509715994020926, "percentage": 2.3, "elapsed_time": "0:01:31", "remaining_time": "1:04:47", "throughput": 6886.89, "total_tokens": 630784} {"current_steps": 78, "total_steps": 3345, "loss": 1.3934, "lr": 2.4966473941953e-06, "epoch": 0.11659192825112108, "percentage": 2.33, "elapsed_time": "0:01:32", "remaining_time": "1:04:44", "throughput": 6889.27, "total_tokens": 638976} {"current_steps": 79, "total_steps": 3345, "loss": 1.4253, "lr": 2.4965609185836653e-06, "epoch": 0.11808669656203288, "percentage": 2.36, "elapsed_time": "0:01:33", "remaining_time": "1:04:42", "throughput": 6891.44, "total_tokens": 647168} {"current_steps": 80, "total_steps": 3345, "loss": 1.8576, "lr": 2.4964733434068567e-06, "epoch": 0.11958146487294469, "percentage": 2.39, "elapsed_time": "0:01:35", "remaining_time": "1:04:39", "throughput": 6893.67, "total_tokens": 655360} {"current_steps": 81, "total_steps": 3345, "loss": 1.5174, "lr": 2.4963846687421218e-06, "epoch": 0.1210762331838565, "percentage": 2.42, "elapsed_time": "0:01:36", "remaining_time": "1:04:37", "throughput": 6895.87, "total_tokens": 663552} {"current_steps": 82, "total_steps": 3345, "loss": 1.6566, "lr": 2.4962948946676784e-06, "epoch": 0.12257100149476831, "percentage": 2.45, "elapsed_time": "0:01:37", "remaining_time": "1:04:35", "throughput": 6898.07, "total_tokens": 671744} {"current_steps": 83, "total_steps": 3345, "loss": 1.6836, "lr": 2.4962040212627153e-06, "epoch": 0.12406576980568013, "percentage": 2.48, "elapsed_time": "0:01:38", "remaining_time": "1:04:32", "throughput": 6900.17, "total_tokens": 679936} {"current_steps": 84, "total_steps": 3345, "loss": 1.7189, "lr": 2.4961120486073897e-06, "epoch": 0.12556053811659193, "percentage": 2.51, "elapsed_time": "0:01:39", "remaining_time": "1:04:30", "throughput": 6902.15, "total_tokens": 688128} {"current_steps": 85, "total_steps": 3345, "loss": 1.5108, "lr": 2.4960189767828284e-06, "epoch": 0.12705530642750373, "percentage": 2.54, "elapsed_time": "0:01:40", "remaining_time": "1:04:28", "throughput": 6903.97, "total_tokens": 696320} {"current_steps": 86, "total_steps": 3345, "loss": 1.4172, "lr": 2.4959248058711283e-06, "epoch": 0.12855007473841554, "percentage": 2.57, "elapsed_time": "0:01:42", "remaining_time": "1:04:25", "throughput": 6905.93, "total_tokens": 704512} {"current_steps": 87, "total_steps": 3345, "loss": 1.4983, "lr": 2.4958295359553557e-06, "epoch": 0.13004484304932734, "percentage": 2.6, "elapsed_time": "0:01:43", "remaining_time": "1:04:23", "throughput": 6907.81, "total_tokens": 712704} {"current_steps": 88, "total_steps": 3345, "loss": 1.3436, "lr": 2.4957331671195462e-06, "epoch": 0.13153961136023917, "percentage": 2.63, "elapsed_time": "0:01:44", "remaining_time": "1:04:21", "throughput": 6909.62, "total_tokens": 720896} {"current_steps": 89, "total_steps": 3345, "loss": 1.3153, "lr": 2.495635699448704e-06, "epoch": 0.13303437967115098, "percentage": 2.66, "elapsed_time": "0:01:45", "remaining_time": "1:04:19", "throughput": 6911.16, "total_tokens": 729088} {"current_steps": 90, "total_steps": 3345, "loss": 1.3699, "lr": 2.4955371330288046e-06, "epoch": 0.13452914798206278, "percentage": 2.69, "elapsed_time": "0:01:46", "remaining_time": "1:04:17", "throughput": 6912.97, "total_tokens": 737280} {"current_steps": 91, "total_steps": 3345, "loss": 1.8896, "lr": 2.49543746794679e-06, "epoch": 0.13602391629297458, "percentage": 2.72, "elapsed_time": "0:01:47", "remaining_time": "1:04:15", "throughput": 6914.67, "total_tokens": 745472} {"current_steps": 92, "total_steps": 3345, "loss": 1.9526, "lr": 2.495336704290574e-06, "epoch": 0.1375186846038864, "percentage": 2.75, "elapsed_time": "0:01:48", "remaining_time": "1:04:12", "throughput": 6916.48, "total_tokens": 753664} {"current_steps": 93, "total_steps": 3345, "loss": 1.7065, "lr": 2.495234842149037e-06, "epoch": 0.13901345291479822, "percentage": 2.78, "elapsed_time": "0:01:50", "remaining_time": "1:04:10", "throughput": 6918.12, "total_tokens": 761856} {"current_steps": 94, "total_steps": 3345, "loss": 1.7117, "lr": 2.49513188161203e-06, "epoch": 0.14050822122571002, "percentage": 2.81, "elapsed_time": "0:01:51", "remaining_time": "1:04:08", "throughput": 6919.87, "total_tokens": 770048} {"current_steps": 95, "total_steps": 3345, "loss": 1.7057, "lr": 2.4950278227703724e-06, "epoch": 0.14200298953662183, "percentage": 2.84, "elapsed_time": "0:01:52", "remaining_time": "1:04:06", "throughput": 6921.6, "total_tokens": 778240} {"current_steps": 96, "total_steps": 3345, "loss": 1.7008, "lr": 2.4949226657158517e-06, "epoch": 0.14349775784753363, "percentage": 2.87, "elapsed_time": "0:01:53", "remaining_time": "1:04:04", "throughput": 6923.29, "total_tokens": 786432} {"current_steps": 97, "total_steps": 3345, "loss": 1.3791, "lr": 2.4948164105412255e-06, "epoch": 0.14499252615844543, "percentage": 2.9, "elapsed_time": "0:01:54", "remaining_time": "1:04:02", "throughput": 6925.04, "total_tokens": 794624} {"current_steps": 98, "total_steps": 3345, "loss": 1.7529, "lr": 2.494709057340218e-06, "epoch": 0.14648729446935724, "percentage": 2.93, "elapsed_time": "0:01:55", "remaining_time": "1:04:00", "throughput": 6926.82, "total_tokens": 802816} {"current_steps": 99, "total_steps": 3345, "loss": 1.5625, "lr": 2.4946006062075253e-06, "epoch": 0.14798206278026907, "percentage": 2.96, "elapsed_time": "0:01:57", "remaining_time": "1:03:58", "throughput": 6928.39, "total_tokens": 811008} {"current_steps": 100, "total_steps": 3345, "loss": 1.5933, "lr": 2.4944910572388083e-06, "epoch": 0.14947683109118087, "percentage": 2.99, "elapsed_time": "0:01:58", "remaining_time": "1:03:55", "throughput": 6929.88, "total_tokens": 819200} {"current_steps": 101, "total_steps": 3345, "loss": 1.5557, "lr": 2.494380410530698e-06, "epoch": 0.15097159940209268, "percentage": 3.02, "elapsed_time": "0:01:59", "remaining_time": "1:03:54", "throughput": 6931.17, "total_tokens": 827392} {"current_steps": 102, "total_steps": 3345, "loss": 1.6925, "lr": 2.494268666180794e-06, "epoch": 0.15246636771300448, "percentage": 3.05, "elapsed_time": "0:02:00", "remaining_time": "1:03:52", "throughput": 6932.52, "total_tokens": 835584} {"current_steps": 103, "total_steps": 3345, "loss": 1.7684, "lr": 2.494155824287663e-06, "epoch": 0.15396113602391628, "percentage": 3.08, "elapsed_time": "0:02:01", "remaining_time": "1:03:50", "throughput": 6933.55, "total_tokens": 843776} {"current_steps": 104, "total_steps": 3345, "loss": 1.2722, "lr": 2.494041884950841e-06, "epoch": 0.1554559043348281, "percentage": 3.11, "elapsed_time": "0:02:02", "remaining_time": "1:03:48", "throughput": 6934.91, "total_tokens": 851968} {"current_steps": 105, "total_steps": 3345, "loss": 1.5557, "lr": 2.493926848270832e-06, "epoch": 0.15695067264573992, "percentage": 3.14, "elapsed_time": "0:02:04", "remaining_time": "1:03:46", "throughput": 6936.3, "total_tokens": 860160} {"current_steps": 106, "total_steps": 3345, "loss": 1.7449, "lr": 2.4938107143491058e-06, "epoch": 0.15844544095665172, "percentage": 3.17, "elapsed_time": "0:02:05", "remaining_time": "1:03:44", "throughput": 6937.61, "total_tokens": 868352} {"current_steps": 107, "total_steps": 3345, "loss": 1.7394, "lr": 2.493693483288103e-06, "epoch": 0.15994020926756353, "percentage": 3.2, "elapsed_time": "0:02:06", "remaining_time": "1:03:42", "throughput": 6938.89, "total_tokens": 876544} {"current_steps": 108, "total_steps": 3345, "loss": 1.7117, "lr": 2.4935751551912307e-06, "epoch": 0.16143497757847533, "percentage": 3.23, "elapsed_time": "0:02:07", "remaining_time": "1:03:40", "throughput": 6940.14, "total_tokens": 884736} {"current_steps": 109, "total_steps": 3345, "loss": 1.5558, "lr": 2.493455730162863e-06, "epoch": 0.16292974588938713, "percentage": 3.26, "elapsed_time": "0:02:08", "remaining_time": "1:03:39", "throughput": 6941.43, "total_tokens": 892928} {"current_steps": 110, "total_steps": 3345, "loss": 1.702, "lr": 2.493335208308342e-06, "epoch": 0.16442451420029897, "percentage": 3.29, "elapsed_time": "0:02:09", "remaining_time": "1:03:37", "throughput": 6942.25, "total_tokens": 901120} {"current_steps": 111, "total_steps": 3345, "loss": 1.579, "lr": 2.4932135897339784e-06, "epoch": 0.16591928251121077, "percentage": 3.32, "elapsed_time": "0:02:10", "remaining_time": "1:03:35", "throughput": 6943.04, "total_tokens": 909312} {"current_steps": 112, "total_steps": 3345, "loss": 1.7089, "lr": 2.493090874547049e-06, "epoch": 0.16741405082212257, "percentage": 3.35, "elapsed_time": "0:02:12", "remaining_time": "1:03:33", "throughput": 6944.42, "total_tokens": 917504} {"current_steps": 113, "total_steps": 3345, "loss": 1.713, "lr": 2.492967062855798e-06, "epoch": 0.16890881913303438, "percentage": 3.38, "elapsed_time": "0:02:13", "remaining_time": "1:03:31", "throughput": 6945.6, "total_tokens": 925696} {"current_steps": 114, "total_steps": 3345, "loss": 1.4648, "lr": 2.4928421547694374e-06, "epoch": 0.17040358744394618, "percentage": 3.41, "elapsed_time": "0:02:14", "remaining_time": "1:03:30", "throughput": 6946.59, "total_tokens": 933888} {"current_steps": 115, "total_steps": 3345, "loss": 1.683, "lr": 2.492716150398146e-06, "epoch": 0.17189835575485798, "percentage": 3.44, "elapsed_time": "0:02:15", "remaining_time": "1:03:28", "throughput": 6947.63, "total_tokens": 942080} {"current_steps": 116, "total_steps": 3345, "loss": 1.4621, "lr": 2.4925890498530694e-06, "epoch": 0.17339312406576982, "percentage": 3.47, "elapsed_time": "0:02:16", "remaining_time": "1:03:26", "throughput": 6948.73, "total_tokens": 950272} {"current_steps": 117, "total_steps": 3345, "loss": 1.3744, "lr": 2.4924608532463206e-06, "epoch": 0.17488789237668162, "percentage": 3.5, "elapsed_time": "0:02:17", "remaining_time": "1:03:24", "throughput": 6949.79, "total_tokens": 958464} {"current_steps": 118, "total_steps": 3345, "loss": 1.2774, "lr": 2.4923315606909785e-06, "epoch": 0.17638266068759342, "percentage": 3.53, "elapsed_time": "0:02:19", "remaining_time": "1:03:23", "throughput": 6950.77, "total_tokens": 966656} {"current_steps": 119, "total_steps": 3345, "loss": 1.1184, "lr": 2.49220117230109e-06, "epoch": 0.17787742899850523, "percentage": 3.56, "elapsed_time": "0:02:20", "remaining_time": "1:03:21", "throughput": 6951.86, "total_tokens": 974848} {"current_steps": 120, "total_steps": 3345, "loss": 1.5893, "lr": 2.4920696881916683e-06, "epoch": 0.17937219730941703, "percentage": 3.59, "elapsed_time": "0:02:21", "remaining_time": "1:03:19", "throughput": 6952.93, "total_tokens": 983040} {"current_steps": 121, "total_steps": 3345, "loss": 1.5717, "lr": 2.4919371084786915e-06, "epoch": 0.18086696562032886, "percentage": 3.62, "elapsed_time": "0:02:22", "remaining_time": "1:03:17", "throughput": 6953.95, "total_tokens": 991232} {"current_steps": 122, "total_steps": 3345, "loss": 1.4805, "lr": 2.4918034332791063e-06, "epoch": 0.18236173393124067, "percentage": 3.65, "elapsed_time": "0:02:23", "remaining_time": "1:03:16", "throughput": 6954.95, "total_tokens": 999424} {"current_steps": 123, "total_steps": 3345, "loss": 1.7121, "lr": 2.491668662710825e-06, "epoch": 0.18385650224215247, "percentage": 3.68, "elapsed_time": "0:02:24", "remaining_time": "1:03:14", "throughput": 6955.9, "total_tokens": 1007616} {"current_steps": 124, "total_steps": 3345, "loss": 1.5501, "lr": 2.491532796892725e-06, "epoch": 0.18535127055306427, "percentage": 3.71, "elapsed_time": "0:02:26", "remaining_time": "1:03:12", "throughput": 6956.91, "total_tokens": 1015808} {"current_steps": 125, "total_steps": 3345, "loss": 1.6781, "lr": 2.491395835944651e-06, "epoch": 0.18684603886397608, "percentage": 3.74, "elapsed_time": "0:02:27", "remaining_time": "1:03:11", "throughput": 6957.84, "total_tokens": 1024000} {"current_steps": 126, "total_steps": 3345, "loss": 1.6426, "lr": 2.4912577799874143e-06, "epoch": 0.18834080717488788, "percentage": 3.77, "elapsed_time": "0:02:28", "remaining_time": "1:03:09", "throughput": 6958.67, "total_tokens": 1032192} {"current_steps": 127, "total_steps": 3345, "loss": 1.6133, "lr": 2.4911186291427897e-06, "epoch": 0.1898355754857997, "percentage": 3.8, "elapsed_time": "0:02:29", "remaining_time": "1:03:07", "throughput": 6959.33, "total_tokens": 1040384} {"current_steps": 128, "total_steps": 3345, "loss": 1.1921, "lr": 2.49097838353352e-06, "epoch": 0.19133034379671152, "percentage": 3.83, "elapsed_time": "0:02:30", "remaining_time": "1:03:06", "throughput": 6960.19, "total_tokens": 1048576} {"current_steps": 129, "total_steps": 3345, "loss": 1.1637, "lr": 2.4908370432833136e-06, "epoch": 0.19282511210762332, "percentage": 3.86, "elapsed_time": "0:02:31", "remaining_time": "1:03:04", "throughput": 6961.08, "total_tokens": 1056768} {"current_steps": 130, "total_steps": 3345, "loss": 1.5713, "lr": 2.490694608516842e-06, "epoch": 0.19431988041853512, "percentage": 3.89, "elapsed_time": "0:02:32", "remaining_time": "1:03:02", "throughput": 6962.15, "total_tokens": 1064960} {"current_steps": 131, "total_steps": 3345, "loss": 1.549, "lr": 2.4905510793597455e-06, "epoch": 0.19581464872944693, "percentage": 3.92, "elapsed_time": "0:02:34", "remaining_time": "1:03:01", "throughput": 6962.92, "total_tokens": 1073152} {"current_steps": 132, "total_steps": 3345, "loss": 1.619, "lr": 2.490406455938627e-06, "epoch": 0.19730941704035873, "percentage": 3.95, "elapsed_time": "0:02:35", "remaining_time": "1:03:00", "throughput": 6963.16, "total_tokens": 1081344} {"current_steps": 133, "total_steps": 3345, "loss": 1.5875, "lr": 2.4902607383810566e-06, "epoch": 0.19880418535127056, "percentage": 3.98, "elapsed_time": "0:02:36", "remaining_time": "1:02:58", "throughput": 6964.04, "total_tokens": 1089536} {"current_steps": 134, "total_steps": 3345, "loss": 1.5687, "lr": 2.4901139268155686e-06, "epoch": 0.20029895366218237, "percentage": 4.01, "elapsed_time": "0:02:37", "remaining_time": "1:02:56", "throughput": 6964.93, "total_tokens": 1097728} {"current_steps": 135, "total_steps": 3345, "loss": 1.5267, "lr": 2.489966021371662e-06, "epoch": 0.20179372197309417, "percentage": 4.04, "elapsed_time": "0:02:38", "remaining_time": "1:02:55", "throughput": 6965.68, "total_tokens": 1105920} {"current_steps": 136, "total_steps": 3345, "loss": 1.595, "lr": 2.4898170221798014e-06, "epoch": 0.20328849028400597, "percentage": 4.07, "elapsed_time": "0:02:39", "remaining_time": "1:02:53", "throughput": 6966.62, "total_tokens": 1114112} {"current_steps": 137, "total_steps": 3345, "loss": 1.4933, "lr": 2.4896669293714158e-06, "epoch": 0.20478325859491778, "percentage": 4.1, "elapsed_time": "0:02:41", "remaining_time": "1:02:51", "throughput": 6967.54, "total_tokens": 1122304} {"current_steps": 138, "total_steps": 3345, "loss": 1.393, "lr": 2.4895157430788987e-06, "epoch": 0.2062780269058296, "percentage": 4.13, "elapsed_time": "0:02:42", "remaining_time": "1:02:50", "throughput": 6968.45, "total_tokens": 1130496} {"current_steps": 139, "total_steps": 3345, "loss": 1.7965, "lr": 2.4893634634356083e-06, "epoch": 0.2077727952167414, "percentage": 4.16, "elapsed_time": "0:02:43", "remaining_time": "1:02:48", "throughput": 6969.3, "total_tokens": 1138688} {"current_steps": 140, "total_steps": 3345, "loss": 1.602, "lr": 2.4892100905758683e-06, "epoch": 0.20926756352765322, "percentage": 4.19, "elapsed_time": "0:02:44", "remaining_time": "1:02:46", "throughput": 6970.14, "total_tokens": 1146880} {"current_steps": 141, "total_steps": 3345, "loss": 1.3733, "lr": 2.489055624634964e-06, "epoch": 0.21076233183856502, "percentage": 4.22, "elapsed_time": "0:02:45", "remaining_time": "1:02:45", "throughput": 6970.9, "total_tokens": 1155072} {"current_steps": 142, "total_steps": 3345, "loss": 1.3091, "lr": 2.488900065749148e-06, "epoch": 0.21225710014947682, "percentage": 4.25, "elapsed_time": "0:02:46", "remaining_time": "1:02:43", "throughput": 6971.79, "total_tokens": 1163264} {"current_steps": 143, "total_steps": 3345, "loss": 1.0714, "lr": 2.4887434140556345e-06, "epoch": 0.21375186846038863, "percentage": 4.28, "elapsed_time": "0:02:48", "remaining_time": "1:02:41", "throughput": 6972.57, "total_tokens": 1171456} {"current_steps": 144, "total_steps": 3345, "loss": 1.468, "lr": 2.488585669692603e-06, "epoch": 0.21524663677130046, "percentage": 4.3, "elapsed_time": "0:02:49", "remaining_time": "1:02:40", "throughput": 6973.4, "total_tokens": 1179648} {"current_steps": 145, "total_steps": 3345, "loss": 1.8498, "lr": 2.488426832799197e-06, "epoch": 0.21674140508221226, "percentage": 4.33, "elapsed_time": "0:02:50", "remaining_time": "1:02:38", "throughput": 6973.97, "total_tokens": 1187840} {"current_steps": 146, "total_steps": 3345, "loss": 1.4059, "lr": 2.4882669035155227e-06, "epoch": 0.21823617339312407, "percentage": 4.36, "elapsed_time": "0:02:51", "remaining_time": "1:02:37", "throughput": 6974.68, "total_tokens": 1196032} {"current_steps": 147, "total_steps": 3345, "loss": 1.4303, "lr": 2.4881058819826505e-06, "epoch": 0.21973094170403587, "percentage": 4.39, "elapsed_time": "0:02:52", "remaining_time": "1:02:35", "throughput": 6975.34, "total_tokens": 1204224} {"current_steps": 148, "total_steps": 3345, "loss": 1.6711, "lr": 2.4879437683426137e-06, "epoch": 0.22122571001494767, "percentage": 4.42, "elapsed_time": "0:02:53", "remaining_time": "1:02:34", "throughput": 6976.04, "total_tokens": 1212416} {"current_steps": 149, "total_steps": 3345, "loss": 1.2693, "lr": 2.48778056273841e-06, "epoch": 0.2227204783258595, "percentage": 4.45, "elapsed_time": "0:02:54", "remaining_time": "1:02:32", "throughput": 6976.81, "total_tokens": 1220608} {"current_steps": 150, "total_steps": 3345, "loss": 1.3479, "lr": 2.487616265313999e-06, "epoch": 0.2242152466367713, "percentage": 4.48, "elapsed_time": "0:02:56", "remaining_time": "1:02:31", "throughput": 6977.36, "total_tokens": 1228800} {"current_steps": 151, "total_steps": 3345, "loss": 1.4785, "lr": 2.4874508762143044e-06, "epoch": 0.2257100149476831, "percentage": 4.51, "elapsed_time": "0:02:57", "remaining_time": "1:02:29", "throughput": 6977.97, "total_tokens": 1236992} {"current_steps": 152, "total_steps": 3345, "loss": 1.3335, "lr": 2.4872843955852127e-06, "epoch": 0.22720478325859492, "percentage": 4.54, "elapsed_time": "0:02:58", "remaining_time": "1:02:28", "throughput": 6978.67, "total_tokens": 1245184} {"current_steps": 153, "total_steps": 3345, "loss": 1.5227, "lr": 2.487116823573572e-06, "epoch": 0.22869955156950672, "percentage": 4.57, "elapsed_time": "0:02:59", "remaining_time": "1:02:26", "throughput": 6979.29, "total_tokens": 1253376} {"current_steps": 154, "total_steps": 3345, "loss": 1.1676, "lr": 2.486948160327195e-06, "epoch": 0.23019431988041852, "percentage": 4.6, "elapsed_time": "0:03:00", "remaining_time": "1:02:25", "throughput": 6979.99, "total_tokens": 1261568} {"current_steps": 155, "total_steps": 3345, "loss": 1.5164, "lr": 2.486778405994856e-06, "epoch": 0.23168908819133036, "percentage": 4.63, "elapsed_time": "0:03:01", "remaining_time": "1:02:23", "throughput": 6980.74, "total_tokens": 1269760} {"current_steps": 156, "total_steps": 3345, "loss": 1.2197, "lr": 2.486607560726291e-06, "epoch": 0.23318385650224216, "percentage": 4.66, "elapsed_time": "0:03:03", "remaining_time": "1:02:21", "throughput": 6981.5, "total_tokens": 1277952} {"current_steps": 157, "total_steps": 3345, "loss": 1.6215, "lr": 2.4864356246721995e-06, "epoch": 0.23467862481315396, "percentage": 4.69, "elapsed_time": "0:03:04", "remaining_time": "1:02:20", "throughput": 6981.97, "total_tokens": 1286144} {"current_steps": 158, "total_steps": 3345, "loss": 1.5104, "lr": 2.4862625979842425e-06, "epoch": 0.23617339312406577, "percentage": 4.72, "elapsed_time": "0:03:05", "remaining_time": "1:02:18", "throughput": 6982.61, "total_tokens": 1294336} {"current_steps": 159, "total_steps": 3345, "loss": 1.4482, "lr": 2.486088480815043e-06, "epoch": 0.23766816143497757, "percentage": 4.75, "elapsed_time": "0:03:06", "remaining_time": "1:02:17", "throughput": 6983.16, "total_tokens": 1302528} {"current_steps": 160, "total_steps": 3345, "loss": 1.7395, "lr": 2.485913273318187e-06, "epoch": 0.23916292974588937, "percentage": 4.78, "elapsed_time": "0:03:07", "remaining_time": "1:02:16", "throughput": 6983.69, "total_tokens": 1310720} {"current_steps": 161, "total_steps": 3345, "loss": 1.3714, "lr": 2.4857369756482205e-06, "epoch": 0.2406576980568012, "percentage": 4.81, "elapsed_time": "0:03:08", "remaining_time": "1:02:14", "throughput": 6984.26, "total_tokens": 1318912} {"current_steps": 162, "total_steps": 3345, "loss": 1.3399, "lr": 2.4855595879606523e-06, "epoch": 0.242152466367713, "percentage": 4.84, "elapsed_time": "0:03:09", "remaining_time": "1:02:13", "throughput": 6984.84, "total_tokens": 1327104} {"current_steps": 163, "total_steps": 3345, "loss": 1.4107, "lr": 2.485381110411952e-06, "epoch": 0.2436472346786248, "percentage": 4.87, "elapsed_time": "0:03:11", "remaining_time": "1:02:11", "throughput": 6984.99, "total_tokens": 1335296} {"current_steps": 164, "total_steps": 3345, "loss": 1.3479, "lr": 2.4852015431595515e-06, "epoch": 0.24514200298953662, "percentage": 4.9, "elapsed_time": "0:03:12", "remaining_time": "1:02:10", "throughput": 6985.49, "total_tokens": 1343488} {"current_steps": 165, "total_steps": 3345, "loss": 1.4561, "lr": 2.4850208863618424e-06, "epoch": 0.24663677130044842, "percentage": 4.93, "elapsed_time": "0:03:13", "remaining_time": "1:02:08", "throughput": 6986.08, "total_tokens": 1351680} {"current_steps": 166, "total_steps": 3345, "loss": 1.5962, "lr": 2.4848391401781793e-06, "epoch": 0.24813153961136025, "percentage": 4.96, "elapsed_time": "0:03:14", "remaining_time": "1:02:07", "throughput": 6986.67, "total_tokens": 1359872} {"current_steps": 167, "total_steps": 3345, "loss": 1.5748, "lr": 2.484656304768876e-06, "epoch": 0.24962630792227206, "percentage": 4.99, "elapsed_time": "0:03:15", "remaining_time": "1:02:06", "throughput": 6987.13, "total_tokens": 1368064} {"current_steps": 168, "total_steps": 3345, "loss": 1.7524, "lr": 2.484472380295208e-06, "epoch": 0.25112107623318386, "percentage": 5.02, "elapsed_time": "0:03:16", "remaining_time": "1:02:04", "throughput": 6987.51, "total_tokens": 1376256} {"current_steps": 169, "total_steps": 3345, "loss": 1.3243, "lr": 2.4842873669194113e-06, "epoch": 0.2526158445440957, "percentage": 5.05, "elapsed_time": "0:03:18", "remaining_time": "1:02:03", "throughput": 6987.84, "total_tokens": 1384448} {"current_steps": 170, "total_steps": 3345, "loss": 1.3097, "lr": 2.484101264804682e-06, "epoch": 0.25411061285500747, "percentage": 5.08, "elapsed_time": "0:03:19", "remaining_time": "1:02:01", "throughput": 6988.36, "total_tokens": 1392640} {"current_steps": 171, "total_steps": 3345, "loss": 1.6839, "lr": 2.483914074115177e-06, "epoch": 0.2556053811659193, "percentage": 5.11, "elapsed_time": "0:03:20", "remaining_time": "1:02:00", "throughput": 6988.5, "total_tokens": 1400832} {"current_steps": 172, "total_steps": 3345, "loss": 1.5036, "lr": 2.4837257950160133e-06, "epoch": 0.2571001494768311, "percentage": 5.14, "elapsed_time": "0:03:21", "remaining_time": "1:01:59", "throughput": 6988.62, "total_tokens": 1409024} {"current_steps": 173, "total_steps": 3345, "loss": 1.2148, "lr": 2.483536427673268e-06, "epoch": 0.2585949177877429, "percentage": 5.17, "elapsed_time": "0:03:22", "remaining_time": "1:01:58", "throughput": 6988.92, "total_tokens": 1417216} {"current_steps": 174, "total_steps": 3345, "loss": 1.6327, "lr": 2.483345972253978e-06, "epoch": 0.2600896860986547, "percentage": 5.2, "elapsed_time": "0:03:23", "remaining_time": "1:01:56", "throughput": 6989.38, "total_tokens": 1425408} {"current_steps": 175, "total_steps": 3345, "loss": 1.392, "lr": 2.4831544289261404e-06, "epoch": 0.2615844544095665, "percentage": 5.23, "elapsed_time": "0:03:25", "remaining_time": "1:01:55", "throughput": 6989.91, "total_tokens": 1433600} {"current_steps": 176, "total_steps": 3345, "loss": 1.2482, "lr": 2.4829617978587106e-06, "epoch": 0.26307922272047835, "percentage": 5.26, "elapsed_time": "0:03:26", "remaining_time": "1:01:53", "throughput": 6990.4, "total_tokens": 1441792} {"current_steps": 177, "total_steps": 3345, "loss": 1.3852, "lr": 2.482768079221605e-06, "epoch": 0.2645739910313901, "percentage": 5.29, "elapsed_time": "0:03:27", "remaining_time": "1:01:52", "throughput": 6990.79, "total_tokens": 1449984} {"current_steps": 178, "total_steps": 3345, "loss": 1.7573, "lr": 2.4825732731856994e-06, "epoch": 0.26606875934230195, "percentage": 5.32, "elapsed_time": "0:03:28", "remaining_time": "1:01:50", "throughput": 6991.2, "total_tokens": 1458176} {"current_steps": 179, "total_steps": 3345, "loss": 1.3852, "lr": 2.4823773799228267e-06, "epoch": 0.26756352765321373, "percentage": 5.35, "elapsed_time": "0:03:29", "remaining_time": "1:01:49", "throughput": 6991.62, "total_tokens": 1466368} {"current_steps": 180, "total_steps": 3345, "loss": 1.5143, "lr": 2.4821803996057813e-06, "epoch": 0.26905829596412556, "percentage": 5.38, "elapsed_time": "0:03:30", "remaining_time": "1:01:48", "throughput": 6992.06, "total_tokens": 1474560} {"current_steps": 181, "total_steps": 3345, "loss": 1.5158, "lr": 2.481982332408315e-06, "epoch": 0.2705530642750374, "percentage": 5.41, "elapsed_time": "0:03:32", "remaining_time": "1:01:46", "throughput": 6992.49, "total_tokens": 1482752} {"current_steps": 182, "total_steps": 3345, "loss": 1.4692, "lr": 2.481783178505139e-06, "epoch": 0.27204783258594917, "percentage": 5.44, "elapsed_time": "0:03:33", "remaining_time": "1:01:45", "throughput": 6992.99, "total_tokens": 1490944} {"current_steps": 183, "total_steps": 3345, "loss": 1.5048, "lr": 2.481582938071922e-06, "epoch": 0.273542600896861, "percentage": 5.47, "elapsed_time": "0:03:34", "remaining_time": "1:01:43", "throughput": 6993.38, "total_tokens": 1499136} {"current_steps": 184, "total_steps": 3345, "loss": 1.3271, "lr": 2.4813816112852925e-06, "epoch": 0.2750373692077728, "percentage": 5.5, "elapsed_time": "0:03:35", "remaining_time": "1:01:42", "throughput": 6993.8, "total_tokens": 1507328} {"current_steps": 185, "total_steps": 3345, "loss": 1.7256, "lr": 2.4811791983228366e-06, "epoch": 0.2765321375186846, "percentage": 5.53, "elapsed_time": "0:03:36", "remaining_time": "1:01:41", "throughput": 6994.19, "total_tokens": 1515520} {"current_steps": 186, "total_steps": 3345, "loss": 1.5838, "lr": 2.4809756993630986e-06, "epoch": 0.27802690582959644, "percentage": 5.56, "elapsed_time": "0:03:37", "remaining_time": "1:01:39", "throughput": 6994.55, "total_tokens": 1523712} {"current_steps": 187, "total_steps": 3345, "loss": 1.4504, "lr": 2.48077111458558e-06, "epoch": 0.2795216741405082, "percentage": 5.59, "elapsed_time": "0:03:39", "remaining_time": "1:01:38", "throughput": 6994.75, "total_tokens": 1531904} {"current_steps": 188, "total_steps": 3345, "loss": 1.4268, "lr": 2.480565444170742e-06, "epoch": 0.28101644245142005, "percentage": 5.62, "elapsed_time": "0:03:40", "remaining_time": "1:01:37", "throughput": 6995.17, "total_tokens": 1540096} {"current_steps": 189, "total_steps": 3345, "loss": 1.6037, "lr": 2.480358688300001e-06, "epoch": 0.2825112107623318, "percentage": 5.65, "elapsed_time": "0:03:41", "remaining_time": "1:01:35", "throughput": 6995.42, "total_tokens": 1548288} {"current_steps": 190, "total_steps": 3345, "loss": 1.1135, "lr": 2.480150847155732e-06, "epoch": 0.28400597907324365, "percentage": 5.68, "elapsed_time": "0:03:42", "remaining_time": "1:01:34", "throughput": 6996.01, "total_tokens": 1556480} {"current_steps": 191, "total_steps": 3345, "loss": 1.3593, "lr": 2.4799419209212684e-06, "epoch": 0.28550074738415543, "percentage": 5.71, "elapsed_time": "0:03:43", "remaining_time": "1:01:33", "throughput": 6996.31, "total_tokens": 1564672} {"current_steps": 192, "total_steps": 3345, "loss": 1.3736, "lr": 2.4797319097808985e-06, "epoch": 0.28699551569506726, "percentage": 5.74, "elapsed_time": "0:03:44", "remaining_time": "1:01:31", "throughput": 6996.63, "total_tokens": 1572864} {"current_steps": 193, "total_steps": 3345, "loss": 1.6823, "lr": 2.4795208139198695e-06, "epoch": 0.2884902840059791, "percentage": 5.77, "elapsed_time": "0:03:45", "remaining_time": "1:01:30", "throughput": 6996.91, "total_tokens": 1581056} {"current_steps": 194, "total_steps": 3345, "loss": 1.5062, "lr": 2.4793086335243837e-06, "epoch": 0.28998505231689087, "percentage": 5.8, "elapsed_time": "0:03:47", "remaining_time": "1:01:29", "throughput": 6997.0, "total_tokens": 1589248} {"current_steps": 195, "total_steps": 3345, "loss": 1.4775, "lr": 2.4790953687816016e-06, "epoch": 0.2914798206278027, "percentage": 5.83, "elapsed_time": "0:03:48", "remaining_time": "1:01:27", "throughput": 6997.32, "total_tokens": 1597440} {"current_steps": 196, "total_steps": 3345, "loss": 1.4649, "lr": 2.47888101987964e-06, "epoch": 0.2929745889387145, "percentage": 5.86, "elapsed_time": "0:03:49", "remaining_time": "1:01:26", "throughput": 6997.63, "total_tokens": 1605632} {"current_steps": 197, "total_steps": 3345, "loss": 1.5072, "lr": 2.4786655870075702e-06, "epoch": 0.2944693572496263, "percentage": 5.89, "elapsed_time": "0:03:50", "remaining_time": "1:01:25", "throughput": 6997.97, "total_tokens": 1613824} {"current_steps": 198, "total_steps": 3345, "loss": 1.696, "lr": 2.4784490703554224e-06, "epoch": 0.29596412556053814, "percentage": 5.92, "elapsed_time": "0:03:51", "remaining_time": "1:01:23", "throughput": 6998.31, "total_tokens": 1622016} {"current_steps": 199, "total_steps": 3345, "loss": 1.7654, "lr": 2.4782314701141807e-06, "epoch": 0.2974588938714499, "percentage": 5.95, "elapsed_time": "0:03:52", "remaining_time": "1:01:22", "throughput": 6998.62, "total_tokens": 1630208} {"current_steps": 200, "total_steps": 3345, "loss": 1.4032, "lr": 2.4780127864757863e-06, "epoch": 0.29895366218236175, "percentage": 5.98, "elapsed_time": "0:03:54", "remaining_time": "1:01:21", "throughput": 6999.08, "total_tokens": 1638400} {"current_steps": 201, "total_steps": 3345, "loss": 1.3348, "lr": 2.4777930196331343e-06, "epoch": 0.3004484304932735, "percentage": 6.01, "elapsed_time": "0:03:55", "remaining_time": "1:01:19", "throughput": 6999.43, "total_tokens": 1646592} {"current_steps": 202, "total_steps": 3345, "loss": 1.4461, "lr": 2.477572169780077e-06, "epoch": 0.30194319880418535, "percentage": 6.04, "elapsed_time": "0:03:56", "remaining_time": "1:01:18", "throughput": 6999.83, "total_tokens": 1654784} {"current_steps": 203, "total_steps": 3345, "loss": 1.2494, "lr": 2.477350237111422e-06, "epoch": 0.3034379671150972, "percentage": 6.07, "elapsed_time": "0:03:57", "remaining_time": "1:01:17", "throughput": 7000.01, "total_tokens": 1662976} {"current_steps": 204, "total_steps": 3345, "loss": 1.1899, "lr": 2.4771272218229305e-06, "epoch": 0.30493273542600896, "percentage": 6.1, "elapsed_time": "0:03:58", "remaining_time": "1:01:15", "throughput": 7000.34, "total_tokens": 1671168} {"current_steps": 205, "total_steps": 3345, "loss": 1.2262, "lr": 2.47690312411132e-06, "epoch": 0.3064275037369208, "percentage": 6.13, "elapsed_time": "0:03:59", "remaining_time": "1:01:14", "throughput": 7000.69, "total_tokens": 1679360} {"current_steps": 206, "total_steps": 3345, "loss": 1.1356, "lr": 2.4766779441742626e-06, "epoch": 0.30792227204783257, "percentage": 6.16, "elapsed_time": "0:04:01", "remaining_time": "1:01:12", "throughput": 7001.06, "total_tokens": 1687552} {"current_steps": 207, "total_steps": 3345, "loss": 1.4179, "lr": 2.4764516822103845e-06, "epoch": 0.3094170403587444, "percentage": 6.19, "elapsed_time": "0:04:02", "remaining_time": "1:01:11", "throughput": 7001.43, "total_tokens": 1695744} {"current_steps": 208, "total_steps": 3345, "loss": 1.4086, "lr": 2.476224338419267e-06, "epoch": 0.3109118086696562, "percentage": 6.22, "elapsed_time": "0:04:03", "remaining_time": "1:01:10", "throughput": 7001.77, "total_tokens": 1703936} {"current_steps": 209, "total_steps": 3345, "loss": 1.6429, "lr": 2.475995913001444e-06, "epoch": 0.312406576980568, "percentage": 6.25, "elapsed_time": "0:04:04", "remaining_time": "1:01:08", "throughput": 7002.12, "total_tokens": 1712128} {"current_steps": 210, "total_steps": 3345, "loss": 1.296, "lr": 2.475766406158407e-06, "epoch": 0.31390134529147984, "percentage": 6.28, "elapsed_time": "0:04:05", "remaining_time": "1:01:07", "throughput": 7002.4, "total_tokens": 1720320} {"current_steps": 211, "total_steps": 3345, "loss": 1.5798, "lr": 2.475535818092597e-06, "epoch": 0.3153961136023916, "percentage": 6.31, "elapsed_time": "0:04:06", "remaining_time": "1:01:06", "throughput": 7002.68, "total_tokens": 1728512} {"current_steps": 212, "total_steps": 3345, "loss": 1.2757, "lr": 2.4753041490074123e-06, "epoch": 0.31689088191330345, "percentage": 6.34, "elapsed_time": "0:04:07", "remaining_time": "1:01:04", "throughput": 7003.08, "total_tokens": 1736704} {"current_steps": 213, "total_steps": 3345, "loss": 1.5177, "lr": 2.475071399107203e-06, "epoch": 0.3183856502242152, "percentage": 6.37, "elapsed_time": "0:04:09", "remaining_time": "1:01:03", "throughput": 7003.48, "total_tokens": 1744896} {"current_steps": 214, "total_steps": 3345, "loss": 1.4427, "lr": 2.474837568597272e-06, "epoch": 0.31988041853512705, "percentage": 6.4, "elapsed_time": "0:04:10", "remaining_time": "1:01:02", "throughput": 7003.84, "total_tokens": 1753088} {"current_steps": 215, "total_steps": 3345, "loss": 1.4988, "lr": 2.4746026576838772e-06, "epoch": 0.3213751868460389, "percentage": 6.43, "elapsed_time": "0:04:11", "remaining_time": "1:01:00", "throughput": 7004.18, "total_tokens": 1761280} {"current_steps": 216, "total_steps": 3345, "loss": 1.5623, "lr": 2.474366666574228e-06, "epoch": 0.32286995515695066, "percentage": 6.46, "elapsed_time": "0:04:12", "remaining_time": "1:00:59", "throughput": 7004.48, "total_tokens": 1769472} {"current_steps": 217, "total_steps": 3345, "loss": 1.3899, "lr": 2.4741295954764883e-06, "epoch": 0.3243647234678625, "percentage": 6.49, "elapsed_time": "0:04:13", "remaining_time": "1:00:58", "throughput": 7004.65, "total_tokens": 1777664} {"current_steps": 218, "total_steps": 3345, "loss": 1.8362, "lr": 2.4738914445997726e-06, "epoch": 0.32585949177877427, "percentage": 6.52, "elapsed_time": "0:04:14", "remaining_time": "1:00:56", "throughput": 7004.98, "total_tokens": 1785856} {"current_steps": 219, "total_steps": 3345, "loss": 1.2491, "lr": 2.4736522141541488e-06, "epoch": 0.3273542600896861, "percentage": 6.55, "elapsed_time": "0:04:16", "remaining_time": "1:00:55", "throughput": 7005.21, "total_tokens": 1794048} {"current_steps": 220, "total_steps": 3345, "loss": 1.2778, "lr": 2.4734119043506372e-06, "epoch": 0.32884902840059793, "percentage": 6.58, "elapsed_time": "0:04:17", "remaining_time": "1:00:54", "throughput": 7005.44, "total_tokens": 1802240} {"current_steps": 221, "total_steps": 3345, "loss": 1.6311, "lr": 2.47317051540121e-06, "epoch": 0.3303437967115097, "percentage": 6.61, "elapsed_time": "0:04:18", "remaining_time": "1:00:52", "throughput": 7005.72, "total_tokens": 1810432} {"current_steps": 222, "total_steps": 3345, "loss": 1.1312, "lr": 2.472928047518792e-06, "epoch": 0.33183856502242154, "percentage": 6.64, "elapsed_time": "0:04:19", "remaining_time": "1:00:51", "throughput": 7005.98, "total_tokens": 1818624} {"current_steps": 223, "total_steps": 3345, "loss": 1.5484, "lr": 2.4726845009172572e-06, "epoch": 0.3333333333333333, "percentage": 6.67, "elapsed_time": "0:04:20", "remaining_time": "1:00:50", "throughput": 7006.03, "total_tokens": 1826816} {"current_steps": 224, "total_steps": 3345, "loss": 1.4286, "lr": 2.472439875811435e-06, "epoch": 0.33482810164424515, "percentage": 6.7, "elapsed_time": "0:04:21", "remaining_time": "1:00:49", "throughput": 7006.28, "total_tokens": 1835008} {"current_steps": 225, "total_steps": 3345, "loss": 1.9832, "lr": 2.4721941724171026e-06, "epoch": 0.336322869955157, "percentage": 6.73, "elapsed_time": "0:04:23", "remaining_time": "1:00:47", "throughput": 7006.6, "total_tokens": 1843200} {"current_steps": 226, "total_steps": 3345, "loss": 1.4192, "lr": 2.4719473909509907e-06, "epoch": 0.33781763826606875, "percentage": 6.76, "elapsed_time": "0:04:24", "remaining_time": "1:00:46", "throughput": 7006.83, "total_tokens": 1851392} {"current_steps": 227, "total_steps": 3345, "loss": 1.592, "lr": 2.4716995316307796e-06, "epoch": 0.3393124065769806, "percentage": 6.79, "elapsed_time": "0:04:25", "remaining_time": "1:00:45", "throughput": 7006.97, "total_tokens": 1859584} {"current_steps": 228, "total_steps": 3345, "loss": 1.7227, "lr": 2.4714505946751006e-06, "epoch": 0.34080717488789236, "percentage": 6.82, "elapsed_time": "0:04:26", "remaining_time": "1:00:44", "throughput": 7007.15, "total_tokens": 1867776} {"current_steps": 229, "total_steps": 3345, "loss": 1.4856, "lr": 2.4712005803035365e-06, "epoch": 0.3423019431988042, "percentage": 6.85, "elapsed_time": "0:04:27", "remaining_time": "1:00:42", "throughput": 7007.44, "total_tokens": 1875968} {"current_steps": 230, "total_steps": 3345, "loss": 1.4689, "lr": 2.470949488736619e-06, "epoch": 0.34379671150971597, "percentage": 6.88, "elapsed_time": "0:04:28", "remaining_time": "1:00:41", "throughput": 7007.76, "total_tokens": 1884160} {"current_steps": 231, "total_steps": 3345, "loss": 1.234, "lr": 2.4706973201958314e-06, "epoch": 0.3452914798206278, "percentage": 6.91, "elapsed_time": "0:04:30", "remaining_time": "1:00:40", "throughput": 7008.12, "total_tokens": 1892352} {"current_steps": 232, "total_steps": 3345, "loss": 1.4724, "lr": 2.470444074903605e-06, "epoch": 0.34678624813153963, "percentage": 6.94, "elapsed_time": "0:04:31", "remaining_time": "1:00:38", "throughput": 7008.41, "total_tokens": 1900544} {"current_steps": 233, "total_steps": 3345, "loss": 1.4742, "lr": 2.470189753083324e-06, "epoch": 0.3482810164424514, "percentage": 6.97, "elapsed_time": "0:04:32", "remaining_time": "1:00:37", "throughput": 7008.67, "total_tokens": 1908736} {"current_steps": 234, "total_steps": 3345, "loss": 1.3692, "lr": 2.4699343549593183e-06, "epoch": 0.34977578475336324, "percentage": 7.0, "elapsed_time": "0:04:33", "remaining_time": "1:00:36", "throughput": 7008.64, "total_tokens": 1916928} {"current_steps": 235, "total_steps": 3345, "loss": 1.313, "lr": 2.469677880756871e-06, "epoch": 0.351270553064275, "percentage": 7.03, "elapsed_time": "0:04:34", "remaining_time": "1:00:35", "throughput": 7008.8, "total_tokens": 1925120} {"current_steps": 236, "total_steps": 3345, "loss": 1.4625, "lr": 2.4694203307022118e-06, "epoch": 0.35276532137518685, "percentage": 7.06, "elapsed_time": "0:04:35", "remaining_time": "1:00:33", "throughput": 7009.1, "total_tokens": 1933312} {"current_steps": 237, "total_steps": 3345, "loss": 1.5025, "lr": 2.4691617050225195e-06, "epoch": 0.3542600896860987, "percentage": 7.09, "elapsed_time": "0:04:36", "remaining_time": "1:00:32", "throughput": 7009.35, "total_tokens": 1941504} {"current_steps": 238, "total_steps": 3345, "loss": 1.0648, "lr": 2.468902003945924e-06, "epoch": 0.35575485799701045, "percentage": 7.12, "elapsed_time": "0:04:38", "remaining_time": "1:00:31", "throughput": 7009.7, "total_tokens": 1949696} {"current_steps": 239, "total_steps": 3345, "loss": 1.5389, "lr": 2.4686412277015005e-06, "epoch": 0.3572496263079223, "percentage": 7.14, "elapsed_time": "0:04:39", "remaining_time": "1:00:29", "throughput": 7009.98, "total_tokens": 1957888} {"current_steps": 240, "total_steps": 3345, "loss": 1.522, "lr": 2.4683793765192753e-06, "epoch": 0.35874439461883406, "percentage": 7.17, "elapsed_time": "0:04:40", "remaining_time": "1:00:28", "throughput": 7010.27, "total_tokens": 1966080} {"current_steps": 241, "total_steps": 3345, "loss": 1.597, "lr": 2.468116450630222e-06, "epoch": 0.3602391629297459, "percentage": 7.2, "elapsed_time": "0:04:41", "remaining_time": "1:00:27", "throughput": 7010.57, "total_tokens": 1974272} {"current_steps": 242, "total_steps": 3345, "loss": 1.456, "lr": 2.467852450266261e-06, "epoch": 0.3617339312406577, "percentage": 7.23, "elapsed_time": "0:04:42", "remaining_time": "1:00:25", "throughput": 7010.83, "total_tokens": 1982464} {"current_steps": 243, "total_steps": 3345, "loss": 1.5926, "lr": 2.4675873756602617e-06, "epoch": 0.3632286995515695, "percentage": 7.26, "elapsed_time": "0:04:43", "remaining_time": "1:00:24", "throughput": 7011.1, "total_tokens": 1990656} {"current_steps": 244, "total_steps": 3345, "loss": 1.5448, "lr": 2.4673212270460414e-06, "epoch": 0.36472346786248133, "percentage": 7.29, "elapsed_time": "0:04:45", "remaining_time": "1:00:23", "throughput": 7011.12, "total_tokens": 1998848} {"current_steps": 245, "total_steps": 3345, "loss": 1.3419, "lr": 2.467054004658364e-06, "epoch": 0.3662182361733931, "percentage": 7.32, "elapsed_time": "0:04:46", "remaining_time": "1:00:22", "throughput": 7011.26, "total_tokens": 2007040} {"current_steps": 246, "total_steps": 3345, "loss": 1.2337, "lr": 2.4667857087329407e-06, "epoch": 0.36771300448430494, "percentage": 7.35, "elapsed_time": "0:04:47", "remaining_time": "1:00:20", "throughput": 7011.54, "total_tokens": 2015232} {"current_steps": 247, "total_steps": 3345, "loss": 1.1224, "lr": 2.4665163395064292e-06, "epoch": 0.3692077727952167, "percentage": 7.38, "elapsed_time": "0:04:48", "remaining_time": "1:00:19", "throughput": 7011.84, "total_tokens": 2023424} {"current_steps": 248, "total_steps": 3345, "loss": 1.6821, "lr": 2.4662458972164353e-06, "epoch": 0.37070254110612855, "percentage": 7.41, "elapsed_time": "0:04:49", "remaining_time": "1:00:18", "throughput": 7012.02, "total_tokens": 2031616} {"current_steps": 249, "total_steps": 3345, "loss": 1.5955, "lr": 2.46597438210151e-06, "epoch": 0.3721973094170404, "percentage": 7.44, "elapsed_time": "0:04:50", "remaining_time": "1:00:16", "throughput": 7012.29, "total_tokens": 2039808} {"current_steps": 250, "total_steps": 3345, "loss": 1.4579, "lr": 2.465701794401151e-06, "epoch": 0.37369207772795215, "percentage": 7.47, "elapsed_time": "0:04:52", "remaining_time": "1:00:15", "throughput": 7012.59, "total_tokens": 2048000} {"current_steps": 251, "total_steps": 3345, "loss": 1.6388, "lr": 2.4654281343558025e-06, "epoch": 0.375186846038864, "percentage": 7.5, "elapsed_time": "0:04:53", "remaining_time": "1:00:14", "throughput": 7012.83, "total_tokens": 2056192} {"current_steps": 252, "total_steps": 3345, "loss": 1.0733, "lr": 2.4651534022068534e-06, "epoch": 0.37668161434977576, "percentage": 7.53, "elapsed_time": "0:04:54", "remaining_time": "1:00:12", "throughput": 7013.07, "total_tokens": 2064384} {"current_steps": 253, "total_steps": 3345, "loss": 1.2628, "lr": 2.4648775981966406e-06, "epoch": 0.3781763826606876, "percentage": 7.56, "elapsed_time": "0:04:55", "remaining_time": "1:00:11", "throughput": 7013.31, "total_tokens": 2072576} {"current_steps": 254, "total_steps": 3345, "loss": 1.3199, "lr": 2.464600722568444e-06, "epoch": 0.3796711509715994, "percentage": 7.59, "elapsed_time": "0:04:56", "remaining_time": "1:00:10", "throughput": 7013.51, "total_tokens": 2080768} {"current_steps": 255, "total_steps": 3345, "loss": 1.4492, "lr": 2.46432277556649e-06, "epoch": 0.3811659192825112, "percentage": 7.62, "elapsed_time": "0:04:57", "remaining_time": "1:00:09", "throughput": 7013.83, "total_tokens": 2088960} {"current_steps": 256, "total_steps": 3345, "loss": 1.408, "lr": 2.4640437574359495e-06, "epoch": 0.38266068759342303, "percentage": 7.65, "elapsed_time": "0:04:58", "remaining_time": "1:00:07", "throughput": 7014.19, "total_tokens": 2097152} {"current_steps": 257, "total_steps": 3345, "loss": 1.6123, "lr": 2.463763668422939e-06, "epoch": 0.3841554559043348, "percentage": 7.68, "elapsed_time": "0:05:00", "remaining_time": "1:00:06", "throughput": 7014.34, "total_tokens": 2105344} {"current_steps": 258, "total_steps": 3345, "loss": 1.5519, "lr": 2.4634825087745196e-06, "epoch": 0.38565022421524664, "percentage": 7.71, "elapsed_time": "0:05:01", "remaining_time": "1:00:05", "throughput": 7014.49, "total_tokens": 2113536} {"current_steps": 259, "total_steps": 3345, "loss": 1.4371, "lr": 2.463200278738695e-06, "epoch": 0.38714499252615847, "percentage": 7.74, "elapsed_time": "0:05:02", "remaining_time": "1:00:03", "throughput": 7014.73, "total_tokens": 2121728} {"current_steps": 260, "total_steps": 3345, "loss": 1.351, "lr": 2.4629169785644155e-06, "epoch": 0.38863976083707025, "percentage": 7.77, "elapsed_time": "0:05:03", "remaining_time": "1:00:02", "throughput": 7014.97, "total_tokens": 2129920} {"current_steps": 261, "total_steps": 3345, "loss": 1.2122, "lr": 2.462632608501573e-06, "epoch": 0.3901345291479821, "percentage": 7.8, "elapsed_time": "0:05:04", "remaining_time": "1:00:01", "throughput": 7015.14, "total_tokens": 2138112} {"current_steps": 262, "total_steps": 3345, "loss": 1.4526, "lr": 2.4623471688010057e-06, "epoch": 0.39162929745889385, "percentage": 7.83, "elapsed_time": "0:05:05", "remaining_time": "1:00:00", "throughput": 7015.44, "total_tokens": 2146304} {"current_steps": 263, "total_steps": 3345, "loss": 1.3306, "lr": 2.4620606597144933e-06, "epoch": 0.3931240657698057, "percentage": 7.86, "elapsed_time": "0:05:07", "remaining_time": "0:59:58", "throughput": 7015.71, "total_tokens": 2154496} {"current_steps": 264, "total_steps": 3345, "loss": 1.2806, "lr": 2.4617730814947595e-06, "epoch": 0.39461883408071746, "percentage": 7.89, "elapsed_time": "0:05:08", "remaining_time": "0:59:57", "throughput": 7015.49, "total_tokens": 2162688} {"current_steps": 265, "total_steps": 3345, "loss": 1.2858, "lr": 2.4614844343954714e-06, "epoch": 0.3961136023916293, "percentage": 7.92, "elapsed_time": "0:05:09", "remaining_time": "0:59:56", "throughput": 7015.47, "total_tokens": 2170880} {"current_steps": 266, "total_steps": 3345, "loss": 1.3114, "lr": 2.4611947186712376e-06, "epoch": 0.3976083707025411, "percentage": 7.95, "elapsed_time": "0:05:10", "remaining_time": "0:59:55", "throughput": 7015.66, "total_tokens": 2179072} {"current_steps": 267, "total_steps": 3345, "loss": 1.488, "lr": 2.4609039345776114e-06, "epoch": 0.3991031390134529, "percentage": 7.98, "elapsed_time": "0:05:11", "remaining_time": "0:59:54", "throughput": 7015.69, "total_tokens": 2187264} {"current_steps": 268, "total_steps": 3345, "loss": 1.5806, "lr": 2.460612082371086e-06, "epoch": 0.40059790732436473, "percentage": 8.01, "elapsed_time": "0:05:12", "remaining_time": "0:59:52", "throughput": 7015.87, "total_tokens": 2195456} {"current_steps": 269, "total_steps": 3345, "loss": 1.494, "lr": 2.4603191623090995e-06, "epoch": 0.4020926756352765, "percentage": 8.04, "elapsed_time": "0:05:14", "remaining_time": "0:59:51", "throughput": 7015.97, "total_tokens": 2203648} {"current_steps": 270, "total_steps": 3345, "loss": 1.3477, "lr": 2.46002517465003e-06, "epoch": 0.40358744394618834, "percentage": 8.07, "elapsed_time": "0:05:15", "remaining_time": "0:59:50", "throughput": 7015.96, "total_tokens": 2211840} {"current_steps": 271, "total_steps": 3345, "loss": 1.0195, "lr": 2.459730119653197e-06, "epoch": 0.40508221225710017, "percentage": 8.1, "elapsed_time": "0:05:16", "remaining_time": "0:59:49", "throughput": 7016.12, "total_tokens": 2220032} {"current_steps": 272, "total_steps": 3345, "loss": 1.7124, "lr": 2.4594339975788633e-06, "epoch": 0.40657698056801195, "percentage": 8.13, "elapsed_time": "0:05:17", "remaining_time": "0:59:47", "throughput": 7016.44, "total_tokens": 2228224} {"current_steps": 273, "total_steps": 3345, "loss": 1.5715, "lr": 2.4591368086882316e-06, "epoch": 0.4080717488789238, "percentage": 8.16, "elapsed_time": "0:05:18", "remaining_time": "0:59:46", "throughput": 7016.65, "total_tokens": 2236416} {"current_steps": 274, "total_steps": 3345, "loss": 1.4305, "lr": 2.4588385532434462e-06, "epoch": 0.40956651718983555, "percentage": 8.19, "elapsed_time": "0:05:19", "remaining_time": "0:59:45", "throughput": 7016.84, "total_tokens": 2244608} {"current_steps": 275, "total_steps": 3345, "loss": 1.3191, "lr": 2.458539231507592e-06, "epoch": 0.4110612855007474, "percentage": 8.22, "elapsed_time": "0:05:21", "remaining_time": "0:59:44", "throughput": 7017.04, "total_tokens": 2252800} {"current_steps": 276, "total_steps": 3345, "loss": 1.3912, "lr": 2.458238843744694e-06, "epoch": 0.4125560538116592, "percentage": 8.25, "elapsed_time": "0:05:22", "remaining_time": "0:59:42", "throughput": 7017.2, "total_tokens": 2260992} {"current_steps": 277, "total_steps": 3345, "loss": 1.6153, "lr": 2.4579373902197183e-06, "epoch": 0.414050822122571, "percentage": 8.28, "elapsed_time": "0:05:23", "remaining_time": "0:59:41", "throughput": 7017.36, "total_tokens": 2269184} {"current_steps": 278, "total_steps": 3345, "loss": 1.377, "lr": 2.4576348711985703e-06, "epoch": 0.4155455904334828, "percentage": 8.31, "elapsed_time": "0:05:24", "remaining_time": "0:59:40", "throughput": 7017.52, "total_tokens": 2277376} {"current_steps": 279, "total_steps": 3345, "loss": 1.2891, "lr": 2.457331286948096e-06, "epoch": 0.4170403587443946, "percentage": 8.34, "elapsed_time": "0:05:25", "remaining_time": "0:59:39", "throughput": 7017.73, "total_tokens": 2285568} {"current_steps": 280, "total_steps": 3345, "loss": 1.4379, "lr": 2.457026637736081e-06, "epoch": 0.41853512705530643, "percentage": 8.37, "elapsed_time": "0:05:26", "remaining_time": "0:59:37", "throughput": 7017.95, "total_tokens": 2293760} {"current_steps": 281, "total_steps": 3345, "loss": 1.5818, "lr": 2.456720923831249e-06, "epoch": 0.4200298953662182, "percentage": 8.4, "elapsed_time": "0:05:28", "remaining_time": "0:59:36", "throughput": 7018.14, "total_tokens": 2301952} {"current_steps": 282, "total_steps": 3345, "loss": 1.3242, "lr": 2.456414145503265e-06, "epoch": 0.42152466367713004, "percentage": 8.43, "elapsed_time": "0:05:29", "remaining_time": "0:59:35", "throughput": 7018.33, "total_tokens": 2310144} {"current_steps": 283, "total_steps": 3345, "loss": 1.3761, "lr": 2.4561063030227303e-06, "epoch": 0.42301943198804187, "percentage": 8.46, "elapsed_time": "0:05:30", "remaining_time": "0:59:33", "throughput": 7018.54, "total_tokens": 2318336} {"current_steps": 284, "total_steps": 3345, "loss": 1.242, "lr": 2.4557973966611877e-06, "epoch": 0.42451420029895365, "percentage": 8.49, "elapsed_time": "0:05:31", "remaining_time": "0:59:32", "throughput": 7018.59, "total_tokens": 2326528} {"current_steps": 285, "total_steps": 3345, "loss": 1.3745, "lr": 2.4554874266911157e-06, "epoch": 0.4260089686098655, "percentage": 8.52, "elapsed_time": "0:05:32", "remaining_time": "0:59:31", "throughput": 7018.76, "total_tokens": 2334720} {"current_steps": 286, "total_steps": 3345, "loss": 1.2752, "lr": 2.4551763933859337e-06, "epoch": 0.42750373692077726, "percentage": 8.55, "elapsed_time": "0:05:33", "remaining_time": "0:59:30", "throughput": 7018.82, "total_tokens": 2342912} {"current_steps": 287, "total_steps": 3345, "loss": 1.4057, "lr": 2.4548642970199963e-06, "epoch": 0.4289985052316891, "percentage": 8.58, "elapsed_time": "0:05:34", "remaining_time": "0:59:29", "throughput": 7018.9, "total_tokens": 2351104} {"current_steps": 288, "total_steps": 3345, "loss": 1.3236, "lr": 2.4545511378685983e-06, "epoch": 0.4304932735426009, "percentage": 8.61, "elapsed_time": "0:05:36", "remaining_time": "0:59:27", "throughput": 7019.08, "total_tokens": 2359296} {"current_steps": 289, "total_steps": 3345, "loss": 1.3679, "lr": 2.4542369162079697e-06, "epoch": 0.4319880418535127, "percentage": 8.64, "elapsed_time": "0:05:37", "remaining_time": "0:59:26", "throughput": 7019.3, "total_tokens": 2367488} {"current_steps": 290, "total_steps": 3345, "loss": 1.5813, "lr": 2.4539216323152797e-06, "epoch": 0.4334828101644245, "percentage": 8.67, "elapsed_time": "0:05:38", "remaining_time": "0:59:25", "throughput": 7019.55, "total_tokens": 2375680} {"current_steps": 291, "total_steps": 3345, "loss": 1.1405, "lr": 2.4536052864686333e-06, "epoch": 0.4349775784753363, "percentage": 8.7, "elapsed_time": "0:05:39", "remaining_time": "0:59:24", "throughput": 7019.71, "total_tokens": 2383872} {"current_steps": 292, "total_steps": 3345, "loss": 1.3261, "lr": 2.4532878789470724e-06, "epoch": 0.43647234678624813, "percentage": 8.73, "elapsed_time": "0:05:40", "remaining_time": "0:59:22", "throughput": 7019.91, "total_tokens": 2392064} {"current_steps": 293, "total_steps": 3345, "loss": 1.4329, "lr": 2.4529694100305756e-06, "epoch": 0.43796711509715996, "percentage": 8.76, "elapsed_time": "0:05:41", "remaining_time": "0:59:21", "throughput": 7019.92, "total_tokens": 2400256} {"current_steps": 294, "total_steps": 3345, "loss": 1.2262, "lr": 2.4526498800000577e-06, "epoch": 0.43946188340807174, "percentage": 8.79, "elapsed_time": "0:05:43", "remaining_time": "0:59:20", "throughput": 7020.14, "total_tokens": 2408448} {"current_steps": 295, "total_steps": 3345, "loss": 1.2749, "lr": 2.452329289137369e-06, "epoch": 0.44095665171898357, "percentage": 8.82, "elapsed_time": "0:05:44", "remaining_time": "0:59:18", "throughput": 7020.41, "total_tokens": 2416640} {"current_steps": 296, "total_steps": 3345, "loss": 1.1285, "lr": 2.4520076377252966e-06, "epoch": 0.44245142002989535, "percentage": 8.85, "elapsed_time": "0:05:45", "remaining_time": "0:59:17", "throughput": 7020.57, "total_tokens": 2424832} {"current_steps": 297, "total_steps": 3345, "loss": 1.6215, "lr": 2.451684926047562e-06, "epoch": 0.4439461883408072, "percentage": 8.88, "elapsed_time": "0:05:46", "remaining_time": "0:59:16", "throughput": 7020.69, "total_tokens": 2433024} {"current_steps": 298, "total_steps": 3345, "loss": 1.3884, "lr": 2.4513611543888227e-06, "epoch": 0.445440956651719, "percentage": 8.91, "elapsed_time": "0:05:47", "remaining_time": "0:59:15", "throughput": 7020.71, "total_tokens": 2441216} {"current_steps": 299, "total_steps": 3345, "loss": 1.7389, "lr": 2.451036323034671e-06, "epoch": 0.4469357249626308, "percentage": 8.94, "elapsed_time": "0:05:48", "remaining_time": "0:59:14", "throughput": 7020.85, "total_tokens": 2449408} {"current_steps": 300, "total_steps": 3345, "loss": 1.4761, "lr": 2.4507104322716327e-06, "epoch": 0.4484304932735426, "percentage": 8.97, "elapsed_time": "0:05:50", "remaining_time": "0:59:12", "throughput": 7020.99, "total_tokens": 2457600} {"current_steps": 301, "total_steps": 3345, "loss": 1.5698, "lr": 2.45038348238717e-06, "epoch": 0.4499252615844544, "percentage": 9.0, "elapsed_time": "0:05:51", "remaining_time": "0:59:11", "throughput": 7020.67, "total_tokens": 2465792} {"current_steps": 302, "total_steps": 3345, "loss": 1.1018, "lr": 2.4500554736696793e-06, "epoch": 0.4514200298953662, "percentage": 9.03, "elapsed_time": "0:05:52", "remaining_time": "0:59:10", "throughput": 7020.92, "total_tokens": 2473984} {"current_steps": 303, "total_steps": 3345, "loss": 1.4443, "lr": 2.449726406408489e-06, "epoch": 0.452914798206278, "percentage": 9.06, "elapsed_time": "0:05:53", "remaining_time": "0:59:09", "throughput": 7021.18, "total_tokens": 2482176} {"current_steps": 304, "total_steps": 3345, "loss": 1.3105, "lr": 2.4493962808938627e-06, "epoch": 0.45440956651718983, "percentage": 9.09, "elapsed_time": "0:05:54", "remaining_time": "0:59:07", "throughput": 7021.41, "total_tokens": 2490368} {"current_steps": 305, "total_steps": 3345, "loss": 1.2813, "lr": 2.4490650974169976e-06, "epoch": 0.45590433482810166, "percentage": 9.12, "elapsed_time": "0:05:55", "remaining_time": "0:59:06", "throughput": 7021.57, "total_tokens": 2498560} {"current_steps": 306, "total_steps": 3345, "loss": 1.1712, "lr": 2.4487328562700232e-06, "epoch": 0.45739910313901344, "percentage": 9.15, "elapsed_time": "0:05:56", "remaining_time": "0:59:05", "throughput": 7021.78, "total_tokens": 2506752} {"current_steps": 307, "total_steps": 3345, "loss": 1.396, "lr": 2.448399557746003e-06, "epoch": 0.4588938714499253, "percentage": 9.18, "elapsed_time": "0:05:58", "remaining_time": "0:59:04", "throughput": 7021.98, "total_tokens": 2514944} {"current_steps": 308, "total_steps": 3345, "loss": 1.5844, "lr": 2.4480652021389317e-06, "epoch": 0.46038863976083705, "percentage": 9.21, "elapsed_time": "0:05:59", "remaining_time": "0:59:02", "throughput": 7022.15, "total_tokens": 2523136} {"current_steps": 309, "total_steps": 3345, "loss": 1.179, "lr": 2.447729789743738e-06, "epoch": 0.4618834080717489, "percentage": 9.24, "elapsed_time": "0:06:00", "remaining_time": "0:59:01", "throughput": 7022.36, "total_tokens": 2531328} {"current_steps": 310, "total_steps": 3345, "loss": 1.2915, "lr": 2.4473933208562817e-06, "epoch": 0.4633781763826607, "percentage": 9.27, "elapsed_time": "0:06:01", "remaining_time": "0:59:00", "throughput": 7022.48, "total_tokens": 2539520} {"current_steps": 311, "total_steps": 3345, "loss": 1.526, "lr": 2.4470557957733556e-06, "epoch": 0.4648729446935725, "percentage": 9.3, "elapsed_time": "0:06:02", "remaining_time": "0:58:59", "throughput": 7022.58, "total_tokens": 2547712} {"current_steps": 312, "total_steps": 3345, "loss": 1.256, "lr": 2.4467172147926833e-06, "epoch": 0.4663677130044843, "percentage": 9.33, "elapsed_time": "0:06:03", "remaining_time": "0:58:57", "throughput": 7022.78, "total_tokens": 2555904} {"current_steps": 313, "total_steps": 3345, "loss": 1.2324, "lr": 2.4463775782129193e-06, "epoch": 0.4678624813153961, "percentage": 9.36, "elapsed_time": "0:06:05", "remaining_time": "0:58:56", "throughput": 7022.99, "total_tokens": 2564096} {"current_steps": 314, "total_steps": 3345, "loss": 1.4992, "lr": 2.4460368863336507e-06, "epoch": 0.4693572496263079, "percentage": 9.39, "elapsed_time": "0:06:06", "remaining_time": "0:58:55", "throughput": 7023.13, "total_tokens": 2572288} {"current_steps": 315, "total_steps": 3345, "loss": 1.5728, "lr": 2.445695139455394e-06, "epoch": 0.47085201793721976, "percentage": 9.42, "elapsed_time": "0:06:07", "remaining_time": "0:58:54", "throughput": 7023.21, "total_tokens": 2580480} {"current_steps": 316, "total_steps": 3345, "loss": 1.1954, "lr": 2.4453523378795973e-06, "epoch": 0.47234678624813153, "percentage": 9.45, "elapsed_time": "0:06:08", "remaining_time": "0:58:53", "throughput": 7023.36, "total_tokens": 2588672} {"current_steps": 317, "total_steps": 3345, "loss": 1.5155, "lr": 2.445008481908639e-06, "epoch": 0.47384155455904337, "percentage": 9.48, "elapsed_time": "0:06:09", "remaining_time": "0:58:51", "throughput": 7023.45, "total_tokens": 2596864} {"current_steps": 318, "total_steps": 3345, "loss": 1.1073, "lr": 2.444663571845826e-06, "epoch": 0.47533632286995514, "percentage": 9.51, "elapsed_time": "0:06:10", "remaining_time": "0:58:50", "throughput": 7023.61, "total_tokens": 2605056} {"current_steps": 319, "total_steps": 3345, "loss": 1.2764, "lr": 2.444317607995398e-06, "epoch": 0.476831091180867, "percentage": 9.54, "elapsed_time": "0:06:12", "remaining_time": "0:58:49", "throughput": 7023.8, "total_tokens": 2613248} {"current_steps": 320, "total_steps": 3345, "loss": 1.3354, "lr": 2.443970590662521e-06, "epoch": 0.47832585949177875, "percentage": 9.57, "elapsed_time": "0:06:13", "remaining_time": "0:58:48", "throughput": 7023.96, "total_tokens": 2621440} {"current_steps": 321, "total_steps": 3345, "loss": 1.2467, "lr": 2.443622520153292e-06, "epoch": 0.4798206278026906, "percentage": 9.6, "elapsed_time": "0:06:14", "remaining_time": "0:58:46", "throughput": 7023.95, "total_tokens": 2629632} {"current_steps": 322, "total_steps": 3345, "loss": 1.5117, "lr": 2.443273396774737e-06, "epoch": 0.4813153961136024, "percentage": 9.63, "elapsed_time": "0:06:15", "remaining_time": "0:58:45", "throughput": 7024.11, "total_tokens": 2637824} {"current_steps": 323, "total_steps": 3345, "loss": 1.4328, "lr": 2.44292322083481e-06, "epoch": 0.4828101644245142, "percentage": 9.66, "elapsed_time": "0:06:16", "remaining_time": "0:58:44", "throughput": 7024.23, "total_tokens": 2646016} {"current_steps": 324, "total_steps": 3345, "loss": 1.4088, "lr": 2.442571992642394e-06, "epoch": 0.484304932735426, "percentage": 9.69, "elapsed_time": "0:06:17", "remaining_time": "0:58:43", "throughput": 7024.33, "total_tokens": 2654208} {"current_steps": 325, "total_steps": 3345, "loss": 1.3187, "lr": 2.4422197125073003e-06, "epoch": 0.4857997010463378, "percentage": 9.72, "elapsed_time": "0:06:19", "remaining_time": "0:58:41", "throughput": 7024.48, "total_tokens": 2662400} {"current_steps": 326, "total_steps": 3345, "loss": 1.5883, "lr": 2.4418663807402677e-06, "epoch": 0.4872944693572496, "percentage": 9.75, "elapsed_time": "0:06:20", "remaining_time": "0:58:40", "throughput": 7024.64, "total_tokens": 2670592} {"current_steps": 327, "total_steps": 3345, "loss": 1.3345, "lr": 2.441511997652963e-06, "epoch": 0.48878923766816146, "percentage": 9.78, "elapsed_time": "0:06:21", "remaining_time": "0:58:39", "throughput": 7024.87, "total_tokens": 2678784} {"current_steps": 328, "total_steps": 3345, "loss": 1.431, "lr": 2.441156563557979e-06, "epoch": 0.49028400597907323, "percentage": 9.81, "elapsed_time": "0:06:22", "remaining_time": "0:58:38", "throughput": 7025.07, "total_tokens": 2686976} {"current_steps": 329, "total_steps": 3345, "loss": 1.5663, "lr": 2.4408000787688375e-06, "epoch": 0.49177877428998507, "percentage": 9.84, "elapsed_time": "0:06:23", "remaining_time": "0:58:36", "throughput": 7025.1, "total_tokens": 2695168} {"current_steps": 330, "total_steps": 3345, "loss": 1.4985, "lr": 2.440442543599986e-06, "epoch": 0.49327354260089684, "percentage": 9.87, "elapsed_time": "0:06:24", "remaining_time": "0:58:35", "throughput": 7025.11, "total_tokens": 2703360} {"current_steps": 331, "total_steps": 3345, "loss": 1.2116, "lr": 2.4400839583667985e-06, "epoch": 0.4947683109118087, "percentage": 9.9, "elapsed_time": "0:06:25", "remaining_time": "0:58:34", "throughput": 7025.28, "total_tokens": 2711552} {"current_steps": 332, "total_steps": 3345, "loss": 1.3338, "lr": 2.439724323385576e-06, "epoch": 0.4962630792227205, "percentage": 9.93, "elapsed_time": "0:06:27", "remaining_time": "0:58:33", "throughput": 7025.49, "total_tokens": 2719744} {"current_steps": 333, "total_steps": 3345, "loss": 1.5811, "lr": 2.439363638973545e-06, "epoch": 0.4977578475336323, "percentage": 9.96, "elapsed_time": "0:06:28", "remaining_time": "0:58:32", "throughput": 7025.6, "total_tokens": 2727936} {"current_steps": 334, "total_steps": 3345, "loss": 1.3161, "lr": 2.4390019054488566e-06, "epoch": 0.4992526158445441, "percentage": 9.99, "elapsed_time": "0:06:29", "remaining_time": "0:58:30", "throughput": 7025.76, "total_tokens": 2736128} {"current_steps": 335, "total_steps": 3345, "loss": 1.1632, "lr": 2.4386391231305896e-06, "epoch": 0.5007473841554559, "percentage": 10.01, "elapsed_time": "0:06:30", "remaining_time": "0:58:29", "throughput": 7025.94, "total_tokens": 2744320} {"current_steps": 336, "total_steps": 3345, "loss": 1.1303, "lr": 2.4382752923387464e-06, "epoch": 0.5022421524663677, "percentage": 10.04, "elapsed_time": "0:06:31", "remaining_time": "0:58:28", "throughput": 7026.14, "total_tokens": 2752512} {"current_steps": 337, "total_steps": 3345, "loss": 1.3414, "lr": 2.437910413394254e-06, "epoch": 0.5037369207772795, "percentage": 10.07, "elapsed_time": "0:06:32", "remaining_time": "0:58:27", "throughput": 7026.27, "total_tokens": 2760704} {"current_steps": 338, "total_steps": 3345, "loss": 1.2798, "lr": 2.4375444866189644e-06, "epoch": 0.5052316890881914, "percentage": 10.1, "elapsed_time": "0:06:34", "remaining_time": "0:58:25", "throughput": 7026.45, "total_tokens": 2768896} {"current_steps": 339, "total_steps": 3345, "loss": 1.4489, "lr": 2.437177512335655e-06, "epoch": 0.5067264573991032, "percentage": 10.13, "elapsed_time": "0:06:35", "remaining_time": "0:58:24", "throughput": 7026.62, "total_tokens": 2777088} {"current_steps": 340, "total_steps": 3345, "loss": 1.7605, "lr": 2.4368094908680246e-06, "epoch": 0.5082212257100149, "percentage": 10.16, "elapsed_time": "0:06:36", "remaining_time": "0:58:23", "throughput": 7026.83, "total_tokens": 2785280} {"current_steps": 341, "total_steps": 3345, "loss": 1.4053, "lr": 2.4364404225406984e-06, "epoch": 0.5097159940209267, "percentage": 10.19, "elapsed_time": "0:06:37", "remaining_time": "0:58:22", "throughput": 7026.95, "total_tokens": 2793472} {"current_steps": 342, "total_steps": 3345, "loss": 1.3494, "lr": 2.436070307679223e-06, "epoch": 0.5112107623318386, "percentage": 10.22, "elapsed_time": "0:06:38", "remaining_time": "0:58:20", "throughput": 7027.11, "total_tokens": 2801664} {"current_steps": 343, "total_steps": 3345, "loss": 1.6992, "lr": 2.4356991466100695e-06, "epoch": 0.5127055306427504, "percentage": 10.25, "elapsed_time": "0:06:39", "remaining_time": "0:58:19", "throughput": 7027.28, "total_tokens": 2809856} {"current_steps": 344, "total_steps": 3345, "loss": 1.1243, "lr": 2.4353269396606304e-06, "epoch": 0.5142002989536621, "percentage": 10.28, "elapsed_time": "0:06:41", "remaining_time": "0:58:18", "throughput": 7027.43, "total_tokens": 2818048} {"current_steps": 345, "total_steps": 3345, "loss": 1.3991, "lr": 2.434953687159223e-06, "epoch": 0.515695067264574, "percentage": 10.31, "elapsed_time": "0:06:42", "remaining_time": "0:58:17", "throughput": 7027.57, "total_tokens": 2826240} {"current_steps": 346, "total_steps": 3345, "loss": 1.3068, "lr": 2.4345793894350844e-06, "epoch": 0.5171898355754858, "percentage": 10.34, "elapsed_time": "0:06:43", "remaining_time": "0:58:15", "throughput": 7027.65, "total_tokens": 2834432} {"current_steps": 347, "total_steps": 3345, "loss": 1.6695, "lr": 2.4342040468183753e-06, "epoch": 0.5186846038863976, "percentage": 10.37, "elapsed_time": "0:06:44", "remaining_time": "0:58:14", "throughput": 7027.7, "total_tokens": 2842624} {"current_steps": 348, "total_steps": 3345, "loss": 1.627, "lr": 2.433827659640177e-06, "epoch": 0.5201793721973094, "percentage": 10.4, "elapsed_time": "0:06:45", "remaining_time": "0:58:13", "throughput": 7027.79, "total_tokens": 2850816} {"current_steps": 349, "total_steps": 3345, "loss": 1.4229, "lr": 2.433450228232493e-06, "epoch": 0.5216741405082213, "percentage": 10.43, "elapsed_time": "0:06:46", "remaining_time": "0:58:12", "throughput": 7027.92, "total_tokens": 2859008} {"current_steps": 350, "total_steps": 3345, "loss": 1.4824, "lr": 2.433071752928248e-06, "epoch": 0.523168908819133, "percentage": 10.46, "elapsed_time": "0:06:47", "remaining_time": "0:58:11", "throughput": 7028.04, "total_tokens": 2867200} {"current_steps": 351, "total_steps": 3345, "loss": 1.4924, "lr": 2.4326922340612867e-06, "epoch": 0.5246636771300448, "percentage": 10.49, "elapsed_time": "0:06:49", "remaining_time": "0:58:09", "throughput": 7028.25, "total_tokens": 2875392} {"current_steps": 352, "total_steps": 3345, "loss": 1.2732, "lr": 2.4323116719663745e-06, "epoch": 0.5261584454409567, "percentage": 10.52, "elapsed_time": "0:06:50", "remaining_time": "0:58:08", "throughput": 7028.38, "total_tokens": 2883584} {"current_steps": 353, "total_steps": 3345, "loss": 1.171, "lr": 2.4319300669791976e-06, "epoch": 0.5276532137518685, "percentage": 10.55, "elapsed_time": "0:06:51", "remaining_time": "0:58:07", "throughput": 7028.54, "total_tokens": 2891776} {"current_steps": 354, "total_steps": 3345, "loss": 1.113, "lr": 2.4315474194363614e-06, "epoch": 0.5291479820627802, "percentage": 10.58, "elapsed_time": "0:06:52", "remaining_time": "0:58:06", "throughput": 7028.55, "total_tokens": 2899968} {"current_steps": 355, "total_steps": 3345, "loss": 1.3451, "lr": 2.431163729675392e-06, "epoch": 0.5306427503736921, "percentage": 10.61, "elapsed_time": "0:06:53", "remaining_time": "0:58:04", "throughput": 7028.68, "total_tokens": 2908160} {"current_steps": 356, "total_steps": 3345, "loss": 1.2737, "lr": 2.430778998034733e-06, "epoch": 0.5321375186846039, "percentage": 10.64, "elapsed_time": "0:06:54", "remaining_time": "0:58:03", "throughput": 7028.8, "total_tokens": 2916352} {"current_steps": 357, "total_steps": 3345, "loss": 1.4497, "lr": 2.430393224853749e-06, "epoch": 0.5336322869955157, "percentage": 10.67, "elapsed_time": "0:06:56", "remaining_time": "0:58:02", "throughput": 7028.91, "total_tokens": 2924544} {"current_steps": 358, "total_steps": 3345, "loss": 1.4728, "lr": 2.430006410472722e-06, "epoch": 0.5351270553064275, "percentage": 10.7, "elapsed_time": "0:06:57", "remaining_time": "0:58:01", "throughput": 7029.05, "total_tokens": 2932736} {"current_steps": 359, "total_steps": 3345, "loss": 1.1206, "lr": 2.429618555232853e-06, "epoch": 0.5366218236173393, "percentage": 10.73, "elapsed_time": "0:06:58", "remaining_time": "0:57:59", "throughput": 7029.2, "total_tokens": 2940928} {"current_steps": 360, "total_steps": 3345, "loss": 1.5419, "lr": 2.4292296594762605e-06, "epoch": 0.5381165919282511, "percentage": 10.76, "elapsed_time": "0:06:59", "remaining_time": "0:57:58", "throughput": 7029.23, "total_tokens": 2949120} {"current_steps": 361, "total_steps": 3345, "loss": 1.5466, "lr": 2.4288397235459815e-06, "epoch": 0.5396113602391629, "percentage": 10.79, "elapsed_time": "0:07:00", "remaining_time": "0:57:57", "throughput": 7029.28, "total_tokens": 2957312} {"current_steps": 362, "total_steps": 3345, "loss": 1.1741, "lr": 2.4284487477859706e-06, "epoch": 0.5411061285500748, "percentage": 10.82, "elapsed_time": "0:07:01", "remaining_time": "0:57:56", "throughput": 7029.36, "total_tokens": 2965504} {"current_steps": 363, "total_steps": 3345, "loss": 1.5147, "lr": 2.4280567325410993e-06, "epoch": 0.5426008968609866, "percentage": 10.85, "elapsed_time": "0:07:03", "remaining_time": "0:57:55", "throughput": 7029.46, "total_tokens": 2973696} {"current_steps": 364, "total_steps": 3345, "loss": 1.5558, "lr": 2.4276636781571553e-06, "epoch": 0.5440956651718983, "percentage": 10.88, "elapsed_time": "0:07:04", "remaining_time": "0:57:53", "throughput": 7029.5, "total_tokens": 2981888} {"current_steps": 365, "total_steps": 3345, "loss": 1.3384, "lr": 2.427269584980844e-06, "epoch": 0.5455904334828101, "percentage": 10.91, "elapsed_time": "0:07:05", "remaining_time": "0:57:52", "throughput": 7029.62, "total_tokens": 2990080} {"current_steps": 366, "total_steps": 3345, "loss": 1.3373, "lr": 2.4268744533597874e-06, "epoch": 0.547085201793722, "percentage": 10.94, "elapsed_time": "0:07:06", "remaining_time": "0:57:51", "throughput": 7029.76, "total_tokens": 2998272} {"current_steps": 367, "total_steps": 3345, "loss": 1.3545, "lr": 2.426478283642522e-06, "epoch": 0.5485799701046338, "percentage": 10.97, "elapsed_time": "0:07:07", "remaining_time": "0:57:50", "throughput": 7029.88, "total_tokens": 3006464} {"current_steps": 368, "total_steps": 3345, "loss": 1.5778, "lr": 2.4260810761785007e-06, "epoch": 0.5500747384155455, "percentage": 11.0, "elapsed_time": "0:07:08", "remaining_time": "0:57:49", "throughput": 7029.97, "total_tokens": 3014656} {"current_steps": 369, "total_steps": 3345, "loss": 1.3254, "lr": 2.425682831318092e-06, "epoch": 0.5515695067264574, "percentage": 11.03, "elapsed_time": "0:07:09", "remaining_time": "0:57:47", "throughput": 7030.04, "total_tokens": 3022848} {"current_steps": 370, "total_steps": 3345, "loss": 1.4321, "lr": 2.42528354941258e-06, "epoch": 0.5530642750373692, "percentage": 11.06, "elapsed_time": "0:07:11", "remaining_time": "0:57:46", "throughput": 7030.13, "total_tokens": 3031040} {"current_steps": 371, "total_steps": 3345, "loss": 1.6006, "lr": 2.424883230814162e-06, "epoch": 0.554559043348281, "percentage": 11.09, "elapsed_time": "0:07:12", "remaining_time": "0:57:45", "throughput": 7030.23, "total_tokens": 3039232} {"current_steps": 372, "total_steps": 3345, "loss": 1.3241, "lr": 2.424481875875951e-06, "epoch": 0.5560538116591929, "percentage": 11.12, "elapsed_time": "0:07:13", "remaining_time": "0:57:44", "throughput": 7030.34, "total_tokens": 3047424} {"current_steps": 373, "total_steps": 3345, "loss": 1.222, "lr": 2.4240794849519735e-06, "epoch": 0.5575485799701047, "percentage": 11.15, "elapsed_time": "0:07:14", "remaining_time": "0:57:43", "throughput": 7030.46, "total_tokens": 3055616} {"current_steps": 374, "total_steps": 3345, "loss": 1.274, "lr": 2.4236760583971703e-06, "epoch": 0.5590433482810164, "percentage": 11.18, "elapsed_time": "0:07:15", "remaining_time": "0:57:41", "throughput": 7030.63, "total_tokens": 3063808} {"current_steps": 375, "total_steps": 3345, "loss": 1.2876, "lr": 2.4232715965673952e-06, "epoch": 0.5605381165919282, "percentage": 11.21, "elapsed_time": "0:07:16", "remaining_time": "0:57:40", "throughput": 7030.77, "total_tokens": 3072000} {"current_steps": 376, "total_steps": 3345, "loss": 1.3742, "lr": 2.4228660998194164e-06, "epoch": 0.5620328849028401, "percentage": 11.24, "elapsed_time": "0:07:18", "remaining_time": "0:57:39", "throughput": 7030.95, "total_tokens": 3080192} {"current_steps": 377, "total_steps": 3345, "loss": 1.2984, "lr": 2.4224595685109125e-06, "epoch": 0.5635276532137519, "percentage": 11.27, "elapsed_time": "0:07:19", "remaining_time": "0:57:38", "throughput": 7031.1, "total_tokens": 3088384} {"current_steps": 378, "total_steps": 3345, "loss": 1.4507, "lr": 2.422052003000478e-06, "epoch": 0.5650224215246636, "percentage": 11.3, "elapsed_time": "0:07:20", "remaining_time": "0:57:36", "throughput": 7031.24, "total_tokens": 3096576} {"current_steps": 379, "total_steps": 3345, "loss": 1.3074, "lr": 2.4216434036476162e-06, "epoch": 0.5665171898355755, "percentage": 11.33, "elapsed_time": "0:07:21", "remaining_time": "0:57:35", "throughput": 7031.37, "total_tokens": 3104768} {"current_steps": 380, "total_steps": 3345, "loss": 1.0148, "lr": 2.4212337708127447e-06, "epoch": 0.5680119581464873, "percentage": 11.36, "elapsed_time": "0:07:22", "remaining_time": "0:57:34", "throughput": 7031.55, "total_tokens": 3112960} {"current_steps": 381, "total_steps": 3345, "loss": 1.329, "lr": 2.4208231048571924e-06, "epoch": 0.5695067264573991, "percentage": 11.39, "elapsed_time": "0:07:23", "remaining_time": "0:57:33", "throughput": 7031.62, "total_tokens": 3121152} {"current_steps": 382, "total_steps": 3345, "loss": 1.4917, "lr": 2.4204114061431988e-06, "epoch": 0.5710014947683109, "percentage": 11.42, "elapsed_time": "0:07:25", "remaining_time": "0:57:31", "throughput": 7031.71, "total_tokens": 3129344} {"current_steps": 383, "total_steps": 3345, "loss": 1.2924, "lr": 2.4199986750339144e-06, "epoch": 0.5724962630792227, "percentage": 11.45, "elapsed_time": "0:07:26", "remaining_time": "0:57:30", "throughput": 7031.79, "total_tokens": 3137536} {"current_steps": 384, "total_steps": 3345, "loss": 1.2187, "lr": 2.4195849118934013e-06, "epoch": 0.5739910313901345, "percentage": 11.48, "elapsed_time": "0:07:27", "remaining_time": "0:57:29", "throughput": 7031.85, "total_tokens": 3145728} {"current_steps": 385, "total_steps": 3345, "loss": 1.4294, "lr": 2.4191701170866303e-06, "epoch": 0.5754857997010463, "percentage": 11.51, "elapsed_time": "0:07:28", "remaining_time": "0:57:28", "throughput": 7031.79, "total_tokens": 3153920} {"current_steps": 386, "total_steps": 3345, "loss": 0.918, "lr": 2.4187542909794835e-06, "epoch": 0.5769805680119582, "percentage": 11.54, "elapsed_time": "0:07:29", "remaining_time": "0:57:27", "throughput": 7031.87, "total_tokens": 3162112} {"current_steps": 387, "total_steps": 3345, "loss": 1.3533, "lr": 2.4183374339387534e-06, "epoch": 0.57847533632287, "percentage": 11.57, "elapsed_time": "0:07:30", "remaining_time": "0:57:25", "throughput": 7031.98, "total_tokens": 3170304} {"current_steps": 388, "total_steps": 3345, "loss": 1.3455, "lr": 2.4179195463321395e-06, "epoch": 0.5799701046337817, "percentage": 11.6, "elapsed_time": "0:07:31", "remaining_time": "0:57:24", "throughput": 7032.1, "total_tokens": 3178496} {"current_steps": 389, "total_steps": 3345, "loss": 1.4657, "lr": 2.417500628528252e-06, "epoch": 0.5814648729446936, "percentage": 11.63, "elapsed_time": "0:07:33", "remaining_time": "0:57:23", "throughput": 7032.18, "total_tokens": 3186688} {"current_steps": 390, "total_steps": 3345, "loss": 1.3079, "lr": 2.41708068089661e-06, "epoch": 0.5829596412556054, "percentage": 11.66, "elapsed_time": "0:07:34", "remaining_time": "0:57:22", "throughput": 7032.22, "total_tokens": 3194880} {"current_steps": 391, "total_steps": 3345, "loss": 1.463, "lr": 2.41665970380764e-06, "epoch": 0.5844544095665172, "percentage": 11.69, "elapsed_time": "0:07:35", "remaining_time": "0:57:21", "throughput": 7032.29, "total_tokens": 3203072} {"current_steps": 392, "total_steps": 3345, "loss": 1.2003, "lr": 2.4162376976326774e-06, "epoch": 0.585949177877429, "percentage": 11.72, "elapsed_time": "0:07:36", "remaining_time": "0:57:19", "throughput": 7032.36, "total_tokens": 3211264} {"current_steps": 393, "total_steps": 3345, "loss": 0.8038, "lr": 2.4158146627439646e-06, "epoch": 0.5874439461883408, "percentage": 11.75, "elapsed_time": "0:07:37", "remaining_time": "0:57:18", "throughput": 7032.42, "total_tokens": 3219456} {"current_steps": 394, "total_steps": 3345, "loss": 1.2562, "lr": 2.4153905995146522e-06, "epoch": 0.5889387144992526, "percentage": 11.78, "elapsed_time": "0:07:38", "remaining_time": "0:57:17", "throughput": 7032.54, "total_tokens": 3227648} {"current_steps": 395, "total_steps": 3345, "loss": 1.0577, "lr": 2.414965508318797e-06, "epoch": 0.5904334828101644, "percentage": 11.81, "elapsed_time": "0:07:40", "remaining_time": "0:57:16", "throughput": 7032.65, "total_tokens": 3235840} {"current_steps": 396, "total_steps": 3345, "loss": 1.3035, "lr": 2.414539389531363e-06, "epoch": 0.5919282511210763, "percentage": 11.84, "elapsed_time": "0:07:41", "remaining_time": "0:57:15", "throughput": 7032.72, "total_tokens": 3244032} {"current_steps": 397, "total_steps": 3345, "loss": 1.5563, "lr": 2.4141122435282207e-06, "epoch": 0.593423019431988, "percentage": 11.87, "elapsed_time": "0:07:42", "remaining_time": "0:57:13", "throughput": 7032.78, "total_tokens": 3252224} {"current_steps": 398, "total_steps": 3345, "loss": 1.3888, "lr": 2.4136840706861465e-06, "epoch": 0.5949177877428998, "percentage": 11.9, "elapsed_time": "0:07:43", "remaining_time": "0:57:12", "throughput": 7032.88, "total_tokens": 3260416} {"current_steps": 399, "total_steps": 3345, "loss": 0.9794, "lr": 2.4132548713828235e-06, "epoch": 0.5964125560538116, "percentage": 11.93, "elapsed_time": "0:07:44", "remaining_time": "0:57:11", "throughput": 7032.95, "total_tokens": 3268608} {"current_steps": 400, "total_steps": 3345, "loss": 1.1906, "lr": 2.4128246459968387e-06, "epoch": 0.5979073243647235, "percentage": 11.96, "elapsed_time": "0:07:45", "remaining_time": "0:57:10", "throughput": 7032.99, "total_tokens": 3276800} {"current_steps": 401, "total_steps": 3345, "loss": 1.4865, "lr": 2.4123933949076847e-06, "epoch": 0.5994020926756353, "percentage": 11.99, "elapsed_time": "0:07:47", "remaining_time": "0:57:09", "throughput": 7033.09, "total_tokens": 3284992} {"current_steps": 402, "total_steps": 3345, "loss": 1.5206, "lr": 2.411961118495759e-06, "epoch": 0.600896860986547, "percentage": 12.02, "elapsed_time": "0:07:48", "remaining_time": "0:57:07", "throughput": 7033.14, "total_tokens": 3293184} {"current_steps": 403, "total_steps": 3345, "loss": 1.2845, "lr": 2.4115278171423643e-06, "epoch": 0.6023916292974589, "percentage": 12.05, "elapsed_time": "0:07:49", "remaining_time": "0:57:06", "throughput": 7033.04, "total_tokens": 3301376} {"current_steps": 404, "total_steps": 3345, "loss": 1.1723, "lr": 2.411093491229706e-06, "epoch": 0.6038863976083707, "percentage": 12.08, "elapsed_time": "0:07:50", "remaining_time": "0:57:05", "throughput": 7033.14, "total_tokens": 3309568} {"current_steps": 405, "total_steps": 3345, "loss": 1.4888, "lr": 2.410658141140894e-06, "epoch": 0.6053811659192825, "percentage": 12.11, "elapsed_time": "0:07:51", "remaining_time": "0:57:04", "throughput": 7033.27, "total_tokens": 3317760} {"current_steps": 406, "total_steps": 3345, "loss": 1.5311, "lr": 2.410221767259941e-06, "epoch": 0.6068759342301944, "percentage": 12.14, "elapsed_time": "0:07:52", "remaining_time": "0:57:03", "throughput": 7033.39, "total_tokens": 3325952} {"current_steps": 407, "total_steps": 3345, "loss": 1.2216, "lr": 2.4097843699717638e-06, "epoch": 0.6083707025411061, "percentage": 12.17, "elapsed_time": "0:07:54", "remaining_time": "0:57:01", "throughput": 7033.51, "total_tokens": 3334144} {"current_steps": 408, "total_steps": 3345, "loss": 1.4159, "lr": 2.4093459496621812e-06, "epoch": 0.6098654708520179, "percentage": 12.2, "elapsed_time": "0:07:55", "remaining_time": "0:57:00", "throughput": 7033.59, "total_tokens": 3342336} {"current_steps": 409, "total_steps": 3345, "loss": 1.6163, "lr": 2.4089065067179147e-06, "epoch": 0.6113602391629297, "percentage": 12.23, "elapsed_time": "0:07:56", "remaining_time": "0:56:59", "throughput": 7033.74, "total_tokens": 3350528} {"current_steps": 410, "total_steps": 3345, "loss": 1.2793, "lr": 2.4084660415265875e-06, "epoch": 0.6128550074738416, "percentage": 12.26, "elapsed_time": "0:07:57", "remaining_time": "0:56:58", "throughput": 7033.82, "total_tokens": 3358720} {"current_steps": 411, "total_steps": 3345, "loss": 1.0496, "lr": 2.4080245544767245e-06, "epoch": 0.6143497757847534, "percentage": 12.29, "elapsed_time": "0:07:58", "remaining_time": "0:56:57", "throughput": 7033.93, "total_tokens": 3366912} {"current_steps": 412, "total_steps": 3345, "loss": 1.3184, "lr": 2.4075820459577525e-06, "epoch": 0.6158445440956651, "percentage": 12.32, "elapsed_time": "0:07:59", "remaining_time": "0:56:55", "throughput": 7034.03, "total_tokens": 3375104} {"current_steps": 413, "total_steps": 3345, "loss": 1.2051, "lr": 2.4071385163599985e-06, "epoch": 0.617339312406577, "percentage": 12.35, "elapsed_time": "0:08:00", "remaining_time": "0:56:54", "throughput": 7034.19, "total_tokens": 3383296} {"current_steps": 414, "total_steps": 3345, "loss": 1.3398, "lr": 2.406693966074691e-06, "epoch": 0.6188340807174888, "percentage": 12.38, "elapsed_time": "0:08:02", "remaining_time": "0:56:53", "throughput": 7034.29, "total_tokens": 3391488} {"current_steps": 415, "total_steps": 3345, "loss": 1.2478, "lr": 2.4062483954939585e-06, "epoch": 0.6203288490284006, "percentage": 12.41, "elapsed_time": "0:08:03", "remaining_time": "0:56:52", "throughput": 7034.47, "total_tokens": 3399680} {"current_steps": 416, "total_steps": 3345, "loss": 1.1588, "lr": 2.4058018050108293e-06, "epoch": 0.6218236173393124, "percentage": 12.44, "elapsed_time": "0:08:04", "remaining_time": "0:56:50", "throughput": 7034.66, "total_tokens": 3407872} {"current_steps": 417, "total_steps": 3345, "loss": 1.4203, "lr": 2.4053541950192313e-06, "epoch": 0.6233183856502242, "percentage": 12.47, "elapsed_time": "0:08:05", "remaining_time": "0:56:49", "throughput": 7034.82, "total_tokens": 3416064} {"current_steps": 418, "total_steps": 3345, "loss": 1.4368, "lr": 2.4049055659139924e-06, "epoch": 0.624813153961136, "percentage": 12.5, "elapsed_time": "0:08:06", "remaining_time": "0:56:48", "throughput": 7034.98, "total_tokens": 3424256} {"current_steps": 419, "total_steps": 3345, "loss": 1.0747, "lr": 2.404455918090838e-06, "epoch": 0.6263079222720478, "percentage": 12.53, "elapsed_time": "0:08:07", "remaining_time": "0:56:47", "throughput": 7035.05, "total_tokens": 3432448} {"current_steps": 420, "total_steps": 3345, "loss": 1.3157, "lr": 2.404005251946394e-06, "epoch": 0.6278026905829597, "percentage": 12.56, "elapsed_time": "0:08:09", "remaining_time": "0:56:46", "throughput": 7035.06, "total_tokens": 3440640} {"current_steps": 421, "total_steps": 3345, "loss": 1.2423, "lr": 2.403553567878183e-06, "epoch": 0.6292974588938715, "percentage": 12.59, "elapsed_time": "0:08:10", "remaining_time": "0:56:44", "throughput": 7035.14, "total_tokens": 3448832} {"current_steps": 422, "total_steps": 3345, "loss": 1.3683, "lr": 2.4031008662846262e-06, "epoch": 0.6307922272047832, "percentage": 12.62, "elapsed_time": "0:08:11", "remaining_time": "0:56:43", "throughput": 7035.18, "total_tokens": 3457024} {"current_steps": 423, "total_steps": 3345, "loss": 1.4928, "lr": 2.4026471475650414e-06, "epoch": 0.6322869955156951, "percentage": 12.65, "elapsed_time": "0:08:12", "remaining_time": "0:56:42", "throughput": 7035.28, "total_tokens": 3465216} {"current_steps": 424, "total_steps": 3345, "loss": 1.4355, "lr": 2.4021924121196456e-06, "epoch": 0.6337817638266069, "percentage": 12.68, "elapsed_time": "0:08:13", "remaining_time": "0:56:41", "throughput": 7035.38, "total_tokens": 3473408} {"current_steps": 425, "total_steps": 3345, "loss": 1.4816, "lr": 2.401736660349551e-06, "epoch": 0.6352765321375187, "percentage": 12.71, "elapsed_time": "0:08:14", "remaining_time": "0:56:39", "throughput": 7035.5, "total_tokens": 3481600} {"current_steps": 426, "total_steps": 3345, "loss": 1.3948, "lr": 2.401279892656766e-06, "epoch": 0.6367713004484304, "percentage": 12.74, "elapsed_time": "0:08:16", "remaining_time": "0:56:38", "throughput": 7035.53, "total_tokens": 3489792} {"current_steps": 427, "total_steps": 3345, "loss": 1.2937, "lr": 2.400822109444196e-06, "epoch": 0.6382660687593423, "percentage": 12.77, "elapsed_time": "0:08:17", "remaining_time": "0:56:37", "throughput": 7035.6, "total_tokens": 3497984} {"current_steps": 428, "total_steps": 3345, "loss": 1.3156, "lr": 2.4003633111156424e-06, "epoch": 0.6397608370702541, "percentage": 12.8, "elapsed_time": "0:08:18", "remaining_time": "0:56:36", "throughput": 7035.69, "total_tokens": 3506176} {"current_steps": 429, "total_steps": 3345, "loss": 1.0507, "lr": 2.3999034980758013e-06, "epoch": 0.6412556053811659, "percentage": 12.83, "elapsed_time": "0:08:19", "remaining_time": "0:56:35", "throughput": 7035.74, "total_tokens": 3514368} {"current_steps": 430, "total_steps": 3345, "loss": 1.3475, "lr": 2.3994426707302638e-06, "epoch": 0.6427503736920778, "percentage": 12.86, "elapsed_time": "0:08:20", "remaining_time": "0:56:34", "throughput": 7035.82, "total_tokens": 3522560} {"current_steps": 431, "total_steps": 3345, "loss": 1.2136, "lr": 2.398980829485517e-06, "epoch": 0.6442451420029895, "percentage": 12.88, "elapsed_time": "0:08:21", "remaining_time": "0:56:32", "throughput": 7035.9, "total_tokens": 3530752} {"current_steps": 432, "total_steps": 3345, "loss": 1.1022, "lr": 2.39851797474894e-06, "epoch": 0.6457399103139013, "percentage": 12.91, "elapsed_time": "0:08:22", "remaining_time": "0:56:31", "throughput": 7035.98, "total_tokens": 3538944} {"current_steps": 433, "total_steps": 3345, "loss": 1.4567, "lr": 2.398054106928808e-06, "epoch": 0.6472346786248132, "percentage": 12.94, "elapsed_time": "0:08:24", "remaining_time": "0:56:30", "throughput": 7036.05, "total_tokens": 3547136} {"current_steps": 434, "total_steps": 3345, "loss": 1.0199, "lr": 2.3975892264342893e-06, "epoch": 0.648729446935725, "percentage": 12.97, "elapsed_time": "0:08:25", "remaining_time": "0:56:29", "throughput": 7036.16, "total_tokens": 3555328} {"current_steps": 435, "total_steps": 3345, "loss": 1.1723, "lr": 2.3971233336754445e-06, "epoch": 0.6502242152466368, "percentage": 13.0, "elapsed_time": "0:08:26", "remaining_time": "0:56:28", "throughput": 7036.21, "total_tokens": 3563520} {"current_steps": 436, "total_steps": 3345, "loss": 1.1808, "lr": 2.3966564290632286e-06, "epoch": 0.6517189835575485, "percentage": 13.03, "elapsed_time": "0:08:27", "remaining_time": "0:56:26", "throughput": 7036.32, "total_tokens": 3571712} {"current_steps": 437, "total_steps": 3345, "loss": 1.3823, "lr": 2.3961885130094874e-06, "epoch": 0.6532137518684604, "percentage": 13.06, "elapsed_time": "0:08:28", "remaining_time": "0:56:25", "throughput": 7036.37, "total_tokens": 3579904} {"current_steps": 438, "total_steps": 3345, "loss": 1.177, "lr": 2.3957195859269607e-06, "epoch": 0.6547085201793722, "percentage": 13.09, "elapsed_time": "0:08:29", "remaining_time": "0:56:24", "throughput": 7036.46, "total_tokens": 3588096} {"current_steps": 439, "total_steps": 3345, "loss": 1.4336, "lr": 2.3952496482292787e-06, "epoch": 0.656203288490284, "percentage": 13.12, "elapsed_time": "0:08:31", "remaining_time": "0:56:23", "throughput": 7036.52, "total_tokens": 3596288} {"current_steps": 440, "total_steps": 3345, "loss": 1.1787, "lr": 2.3947787003309635e-06, "epoch": 0.6576980568011959, "percentage": 13.15, "elapsed_time": "0:08:32", "remaining_time": "0:56:22", "throughput": 7036.58, "total_tokens": 3604480} {"current_steps": 441, "total_steps": 3345, "loss": 1.2015, "lr": 2.394306742647429e-06, "epoch": 0.6591928251121076, "percentage": 13.18, "elapsed_time": "0:08:33", "remaining_time": "0:56:20", "throughput": 7036.65, "total_tokens": 3612672} {"current_steps": 442, "total_steps": 3345, "loss": 1.3135, "lr": 2.3938337755949785e-06, "epoch": 0.6606875934230194, "percentage": 13.21, "elapsed_time": "0:08:34", "remaining_time": "0:56:19", "throughput": 7036.75, "total_tokens": 3620864} {"current_steps": 443, "total_steps": 3345, "loss": 1.3809, "lr": 2.3933597995908065e-06, "epoch": 0.6621823617339312, "percentage": 13.24, "elapsed_time": "0:08:35", "remaining_time": "0:56:18", "throughput": 7036.86, "total_tokens": 3629056} {"current_steps": 444, "total_steps": 3345, "loss": 1.3309, "lr": 2.3928848150529972e-06, "epoch": 0.6636771300448431, "percentage": 13.27, "elapsed_time": "0:08:36", "remaining_time": "0:56:17", "throughput": 7036.97, "total_tokens": 3637248} {"current_steps": 445, "total_steps": 3345, "loss": 1.189, "lr": 2.3924088224005244e-06, "epoch": 0.6651718983557549, "percentage": 13.3, "elapsed_time": "0:08:38", "remaining_time": "0:56:15", "throughput": 7037.04, "total_tokens": 3645440} {"current_steps": 446, "total_steps": 3345, "loss": 1.1884, "lr": 2.391931822053251e-06, "epoch": 0.6666666666666666, "percentage": 13.33, "elapsed_time": "0:08:39", "remaining_time": "0:56:14", "throughput": 7037.15, "total_tokens": 3653632} {"current_steps": 447, "total_steps": 3345, "loss": 1.3532, "lr": 2.39145381443193e-06, "epoch": 0.6681614349775785, "percentage": 13.36, "elapsed_time": "0:08:40", "remaining_time": "0:56:13", "throughput": 7037.27, "total_tokens": 3661824} {"current_steps": 448, "total_steps": 3345, "loss": 1.2681, "lr": 2.3909747999582007e-06, "epoch": 0.6696562032884903, "percentage": 13.39, "elapsed_time": "0:08:41", "remaining_time": "0:56:12", "throughput": 7037.25, "total_tokens": 3670016} {"current_steps": 449, "total_steps": 3345, "loss": 1.0705, "lr": 2.3904947790545926e-06, "epoch": 0.6711509715994021, "percentage": 13.42, "elapsed_time": "0:08:42", "remaining_time": "0:56:11", "throughput": 7037.3, "total_tokens": 3678208} {"current_steps": 450, "total_steps": 3345, "loss": 1.2476, "lr": 2.3900137521445215e-06, "epoch": 0.672645739910314, "percentage": 13.45, "elapsed_time": "0:08:43", "remaining_time": "0:56:09", "throughput": 7037.36, "total_tokens": 3686400} {"current_steps": 451, "total_steps": 3345, "loss": 1.1608, "lr": 2.389531719652291e-06, "epoch": 0.6741405082212257, "percentage": 13.48, "elapsed_time": "0:08:44", "remaining_time": "0:56:08", "throughput": 7037.44, "total_tokens": 3694592} {"current_steps": 452, "total_steps": 3345, "loss": 1.1485, "lr": 2.389048682003092e-06, "epoch": 0.6756352765321375, "percentage": 13.51, "elapsed_time": "0:08:46", "remaining_time": "0:56:07", "throughput": 7037.53, "total_tokens": 3702784} {"current_steps": 453, "total_steps": 3345, "loss": 1.1073, "lr": 2.388564639623002e-06, "epoch": 0.6771300448430493, "percentage": 13.54, "elapsed_time": "0:08:47", "remaining_time": "0:56:06", "throughput": 7037.61, "total_tokens": 3710976} {"current_steps": 454, "total_steps": 3345, "loss": 1.3056, "lr": 2.388079592938985e-06, "epoch": 0.6786248131539612, "percentage": 13.57, "elapsed_time": "0:08:48", "remaining_time": "0:56:05", "throughput": 7037.66, "total_tokens": 3719168} {"current_steps": 455, "total_steps": 3345, "loss": 1.3437, "lr": 2.387593542378889e-06, "epoch": 0.680119581464873, "percentage": 13.6, "elapsed_time": "0:08:49", "remaining_time": "0:56:03", "throughput": 7037.79, "total_tokens": 3727360} {"current_steps": 456, "total_steps": 3345, "loss": 1.2043, "lr": 2.3871064883714513e-06, "epoch": 0.6816143497757847, "percentage": 13.63, "elapsed_time": "0:08:50", "remaining_time": "0:56:02", "throughput": 7037.84, "total_tokens": 3735552} {"current_steps": 457, "total_steps": 3345, "loss": 1.3478, "lr": 2.3866184313462897e-06, "epoch": 0.6831091180866966, "percentage": 13.66, "elapsed_time": "0:08:51", "remaining_time": "0:56:01", "throughput": 7037.91, "total_tokens": 3743744} {"current_steps": 458, "total_steps": 3345, "loss": 1.4065, "lr": 2.3861293717339103e-06, "epoch": 0.6846038863976084, "percentage": 13.69, "elapsed_time": "0:08:53", "remaining_time": "0:56:00", "throughput": 7037.99, "total_tokens": 3751936} {"current_steps": 459, "total_steps": 3345, "loss": 1.4844, "lr": 2.385639309965702e-06, "epoch": 0.6860986547085202, "percentage": 13.72, "elapsed_time": "0:08:54", "remaining_time": "0:55:59", "throughput": 7038.05, "total_tokens": 3760128} {"current_steps": 460, "total_steps": 3345, "loss": 1.5495, "lr": 2.385148246473938e-06, "epoch": 0.6875934230194319, "percentage": 13.75, "elapsed_time": "0:08:55", "remaining_time": "0:55:57", "throughput": 7038.13, "total_tokens": 3768320} {"current_steps": 461, "total_steps": 3345, "loss": 1.2571, "lr": 2.384656181691775e-06, "epoch": 0.6890881913303438, "percentage": 13.78, "elapsed_time": "0:08:56", "remaining_time": "0:55:56", "throughput": 7038.21, "total_tokens": 3776512} {"current_steps": 462, "total_steps": 3345, "loss": 1.3456, "lr": 2.3841631160532534e-06, "epoch": 0.6905829596412556, "percentage": 13.81, "elapsed_time": "0:08:57", "remaining_time": "0:55:55", "throughput": 7038.3, "total_tokens": 3784704} {"current_steps": 463, "total_steps": 3345, "loss": 1.571, "lr": 2.3836690499932956e-06, "epoch": 0.6920777279521674, "percentage": 13.84, "elapsed_time": "0:08:58", "remaining_time": "0:55:54", "throughput": 7038.37, "total_tokens": 3792896} {"current_steps": 464, "total_steps": 3345, "loss": 1.4055, "lr": 2.383173983947707e-06, "epoch": 0.6935724962630793, "percentage": 13.87, "elapsed_time": "0:09:00", "remaining_time": "0:55:53", "throughput": 7038.43, "total_tokens": 3801088} {"current_steps": 465, "total_steps": 3345, "loss": 1.2513, "lr": 2.3826779183531744e-06, "epoch": 0.695067264573991, "percentage": 13.9, "elapsed_time": "0:09:01", "remaining_time": "0:55:52", "throughput": 7038.41, "total_tokens": 3809280} {"current_steps": 466, "total_steps": 3345, "loss": 1.1249, "lr": 2.382180853647268e-06, "epoch": 0.6965620328849028, "percentage": 13.93, "elapsed_time": "0:09:02", "remaining_time": "0:55:50", "throughput": 7038.45, "total_tokens": 3817472} {"current_steps": 467, "total_steps": 3345, "loss": 0.9903, "lr": 2.381682790268437e-06, "epoch": 0.6980568011958147, "percentage": 13.96, "elapsed_time": "0:09:03", "remaining_time": "0:55:49", "throughput": 7038.53, "total_tokens": 3825664} {"current_steps": 468, "total_steps": 3345, "loss": 1.3147, "lr": 2.3811837286560135e-06, "epoch": 0.6995515695067265, "percentage": 13.99, "elapsed_time": "0:09:04", "remaining_time": "0:55:48", "throughput": 7038.6, "total_tokens": 3833856} {"current_steps": 469, "total_steps": 3345, "loss": 1.4715, "lr": 2.3806836692502087e-06, "epoch": 0.7010463378176383, "percentage": 14.02, "elapsed_time": "0:09:05", "remaining_time": "0:55:47", "throughput": 7038.6, "total_tokens": 3842048} {"current_steps": 470, "total_steps": 3345, "loss": 1.1261, "lr": 2.3801826124921153e-06, "epoch": 0.70254110612855, "percentage": 14.05, "elapsed_time": "0:09:07", "remaining_time": "0:55:46", "throughput": 7038.66, "total_tokens": 3850240} {"current_steps": 471, "total_steps": 3345, "loss": 1.4026, "lr": 2.379680558823704e-06, "epoch": 0.7040358744394619, "percentage": 14.08, "elapsed_time": "0:09:08", "remaining_time": "0:55:44", "throughput": 7038.71, "total_tokens": 3858432} {"current_steps": 472, "total_steps": 3345, "loss": 1.381, "lr": 2.3791775086878257e-06, "epoch": 0.7055306427503737, "percentage": 14.11, "elapsed_time": "0:09:09", "remaining_time": "0:55:43", "throughput": 7038.67, "total_tokens": 3866624} {"current_steps": 473, "total_steps": 3345, "loss": 1.1492, "lr": 2.378673462528211e-06, "epoch": 0.7070254110612855, "percentage": 14.14, "elapsed_time": "0:09:10", "remaining_time": "0:55:42", "throughput": 7038.64, "total_tokens": 3874816} {"current_steps": 474, "total_steps": 3345, "loss": 1.4113, "lr": 2.378168420789468e-06, "epoch": 0.7085201793721974, "percentage": 14.17, "elapsed_time": "0:09:11", "remaining_time": "0:55:41", "throughput": 7038.69, "total_tokens": 3883008} {"current_steps": 475, "total_steps": 3345, "loss": 1.1761, "lr": 2.377662383917083e-06, "epoch": 0.7100149476831091, "percentage": 14.2, "elapsed_time": "0:09:12", "remaining_time": "0:55:40", "throughput": 7038.74, "total_tokens": 3891200} {"current_steps": 476, "total_steps": 3345, "loss": 1.4833, "lr": 2.377155352357422e-06, "epoch": 0.7115097159940209, "percentage": 14.23, "elapsed_time": "0:09:13", "remaining_time": "0:55:39", "throughput": 7038.77, "total_tokens": 3899392} {"current_steps": 477, "total_steps": 3345, "loss": 1.748, "lr": 2.3766473265577256e-06, "epoch": 0.7130044843049327, "percentage": 14.26, "elapsed_time": "0:09:15", "remaining_time": "0:55:37", "throughput": 7038.64, "total_tokens": 3907584} {"current_steps": 478, "total_steps": 3345, "loss": 1.202, "lr": 2.3761383069661125e-06, "epoch": 0.7144992526158446, "percentage": 14.29, "elapsed_time": "0:09:16", "remaining_time": "0:55:36", "throughput": 7038.67, "total_tokens": 3915776} {"current_steps": 479, "total_steps": 3345, "loss": 1.2793, "lr": 2.3756282940315796e-06, "epoch": 0.7159940209267563, "percentage": 14.32, "elapsed_time": "0:09:17", "remaining_time": "0:55:35", "throughput": 7038.68, "total_tokens": 3923968} {"current_steps": 480, "total_steps": 3345, "loss": 1.4118, "lr": 2.375117288203997e-06, "epoch": 0.7174887892376681, "percentage": 14.35, "elapsed_time": "0:09:18", "remaining_time": "0:55:34", "throughput": 7038.71, "total_tokens": 3932160} {"current_steps": 481, "total_steps": 3345, "loss": 1.2965, "lr": 2.374605289934113e-06, "epoch": 0.71898355754858, "percentage": 14.38, "elapsed_time": "0:09:19", "remaining_time": "0:55:33", "throughput": 7038.76, "total_tokens": 3940352} {"current_steps": 482, "total_steps": 3345, "loss": 1.4401, "lr": 2.3740922996735504e-06, "epoch": 0.7204783258594918, "percentage": 14.41, "elapsed_time": "0:09:20", "remaining_time": "0:55:32", "throughput": 7038.83, "total_tokens": 3948544} {"current_steps": 483, "total_steps": 3345, "loss": 0.9722, "lr": 2.3735783178748068e-06, "epoch": 0.7219730941704036, "percentage": 14.44, "elapsed_time": "0:09:22", "remaining_time": "0:55:30", "throughput": 7038.89, "total_tokens": 3956736} {"current_steps": 484, "total_steps": 3345, "loss": 1.2976, "lr": 2.3730633449912553e-06, "epoch": 0.7234678624813154, "percentage": 14.47, "elapsed_time": "0:09:23", "remaining_time": "0:55:29", "throughput": 7038.98, "total_tokens": 3964928} {"current_steps": 485, "total_steps": 3345, "loss": 1.5269, "lr": 2.3725473814771425e-06, "epoch": 0.7249626307922272, "percentage": 14.5, "elapsed_time": "0:09:24", "remaining_time": "0:55:28", "throughput": 7039.05, "total_tokens": 3973120} {"current_steps": 486, "total_steps": 3345, "loss": 1.1434, "lr": 2.3720304277875884e-06, "epoch": 0.726457399103139, "percentage": 14.53, "elapsed_time": "0:09:25", "remaining_time": "0:55:27", "throughput": 7039.04, "total_tokens": 3981312} {"current_steps": 487, "total_steps": 3345, "loss": 1.5355, "lr": 2.3715124843785878e-06, "epoch": 0.7279521674140508, "percentage": 14.56, "elapsed_time": "0:09:26", "remaining_time": "0:55:26", "throughput": 7039.08, "total_tokens": 3989504} {"current_steps": 488, "total_steps": 3345, "loss": 1.4146, "lr": 2.3709935517070072e-06, "epoch": 0.7294469357249627, "percentage": 14.59, "elapsed_time": "0:09:27", "remaining_time": "0:55:24", "throughput": 7039.12, "total_tokens": 3997696} {"current_steps": 489, "total_steps": 3345, "loss": 1.448, "lr": 2.370473630230586e-06, "epoch": 0.7309417040358744, "percentage": 14.62, "elapsed_time": "0:09:29", "remaining_time": "0:55:23", "throughput": 7039.18, "total_tokens": 4005888} {"current_steps": 490, "total_steps": 3345, "loss": 1.616, "lr": 2.3699527204079368e-06, "epoch": 0.7324364723467862, "percentage": 14.65, "elapsed_time": "0:09:30", "remaining_time": "0:55:22", "throughput": 7039.19, "total_tokens": 4014080} {"current_steps": 491, "total_steps": 3345, "loss": 1.2975, "lr": 2.3694308226985425e-06, "epoch": 0.7339312406576981, "percentage": 14.68, "elapsed_time": "0:09:31", "remaining_time": "0:55:21", "throughput": 7039.19, "total_tokens": 4022272} {"current_steps": 492, "total_steps": 3345, "loss": 1.2189, "lr": 2.3689079375627583e-06, "epoch": 0.7354260089686099, "percentage": 14.71, "elapsed_time": "0:09:32", "remaining_time": "0:55:20", "throughput": 7039.26, "total_tokens": 4030464} {"current_steps": 493, "total_steps": 3345, "loss": 1.0615, "lr": 2.36838406546181e-06, "epoch": 0.7369207772795217, "percentage": 14.74, "elapsed_time": "0:09:33", "remaining_time": "0:55:19", "throughput": 7039.31, "total_tokens": 4038656} {"current_steps": 494, "total_steps": 3345, "loss": 1.0425, "lr": 2.3678592068577943e-06, "epoch": 0.7384155455904334, "percentage": 14.77, "elapsed_time": "0:09:34", "remaining_time": "0:55:17", "throughput": 7039.34, "total_tokens": 4046848} {"current_steps": 495, "total_steps": 3345, "loss": 1.3126, "lr": 2.3673333622136783e-06, "epoch": 0.7399103139013453, "percentage": 14.8, "elapsed_time": "0:09:36", "remaining_time": "0:55:16", "throughput": 7039.41, "total_tokens": 4055040} {"current_steps": 496, "total_steps": 3345, "loss": 1.2551, "lr": 2.366806531993298e-06, "epoch": 0.7414050822122571, "percentage": 14.83, "elapsed_time": "0:09:37", "remaining_time": "0:55:15", "throughput": 7039.46, "total_tokens": 4063232} {"current_steps": 497, "total_steps": 3345, "loss": 1.2574, "lr": 2.3662787166613595e-06, "epoch": 0.7428998505231689, "percentage": 14.86, "elapsed_time": "0:09:38", "remaining_time": "0:55:14", "throughput": 7039.49, "total_tokens": 4071424} {"current_steps": 498, "total_steps": 3345, "loss": 1.06, "lr": 2.3657499166834373e-06, "epoch": 0.7443946188340808, "percentage": 14.89, "elapsed_time": "0:09:39", "remaining_time": "0:55:13", "throughput": 7039.56, "total_tokens": 4079616} {"current_steps": 499, "total_steps": 3345, "loss": 1.1019, "lr": 2.3652201325259757e-06, "epoch": 0.7458893871449925, "percentage": 14.92, "elapsed_time": "0:09:40", "remaining_time": "0:55:11", "throughput": 7039.6, "total_tokens": 4087808} {"current_steps": 500, "total_steps": 3345, "loss": 1.1465, "lr": 2.3646893646562845e-06, "epoch": 0.7473841554559043, "percentage": 14.95, "elapsed_time": "0:09:41", "remaining_time": "0:55:10", "throughput": 7039.64, "total_tokens": 4096000} {"current_steps": 501, "total_steps": 3345, "loss": 1.214, "lr": 2.3641576135425445e-06, "epoch": 0.7488789237668162, "percentage": 14.98, "elapsed_time": "0:09:43", "remaining_time": "0:55:09", "throughput": 7039.69, "total_tokens": 4104192} {"current_steps": 502, "total_steps": 3345, "loss": 1.2581, "lr": 2.3636248796538013e-06, "epoch": 0.750373692077728, "percentage": 15.01, "elapsed_time": "0:09:44", "remaining_time": "0:55:08", "throughput": 7039.72, "total_tokens": 4112384} {"current_steps": 503, "total_steps": 3345, "loss": 1.1821, "lr": 2.3630911634599686e-06, "epoch": 0.7518684603886397, "percentage": 15.04, "elapsed_time": "0:09:45", "remaining_time": "0:55:07", "throughput": 7039.68, "total_tokens": 4120576} {"current_steps": 504, "total_steps": 3345, "loss": 1.0926, "lr": 2.362556465431826e-06, "epoch": 0.7533632286995515, "percentage": 15.07, "elapsed_time": "0:09:46", "remaining_time": "0:55:06", "throughput": 7039.75, "total_tokens": 4128768} {"current_steps": 505, "total_steps": 3345, "loss": 1.2311, "lr": 2.3620207860410195e-06, "epoch": 0.7548579970104634, "percentage": 15.1, "elapsed_time": "0:09:47", "remaining_time": "0:55:04", "throughput": 7039.8, "total_tokens": 4136960} {"current_steps": 506, "total_steps": 3345, "loss": 1.1783, "lr": 2.3614841257600605e-06, "epoch": 0.7563527653213752, "percentage": 15.13, "elapsed_time": "0:09:48", "remaining_time": "0:55:03", "throughput": 7039.88, "total_tokens": 4145152} {"current_steps": 507, "total_steps": 3345, "loss": 1.2937, "lr": 2.360946485062326e-06, "epoch": 0.757847533632287, "percentage": 15.16, "elapsed_time": "0:09:49", "remaining_time": "0:55:02", "throughput": 7039.91, "total_tokens": 4153344} {"current_steps": 508, "total_steps": 3345, "loss": 1.3468, "lr": 2.3604078644220575e-06, "epoch": 0.7593423019431988, "percentage": 15.19, "elapsed_time": "0:09:51", "remaining_time": "0:55:01", "throughput": 7039.95, "total_tokens": 4161536} {"current_steps": 509, "total_steps": 3345, "loss": 1.4457, "lr": 2.3598682643143607e-06, "epoch": 0.7608370702541106, "percentage": 15.22, "elapsed_time": "0:09:52", "remaining_time": "0:55:00", "throughput": 7040.04, "total_tokens": 4169728} {"current_steps": 510, "total_steps": 3345, "loss": 1.2439, "lr": 2.3593276852152056e-06, "epoch": 0.7623318385650224, "percentage": 15.25, "elapsed_time": "0:09:53", "remaining_time": "0:54:58", "throughput": 7040.09, "total_tokens": 4177920} {"current_steps": 511, "total_steps": 3345, "loss": 1.1751, "lr": 2.3587861276014255e-06, "epoch": 0.7638266068759342, "percentage": 15.28, "elapsed_time": "0:09:54", "remaining_time": "0:54:57", "throughput": 7040.17, "total_tokens": 4186112} {"current_steps": 512, "total_steps": 3345, "loss": 1.2012, "lr": 2.358243591950718e-06, "epoch": 0.7653213751868461, "percentage": 15.31, "elapsed_time": "0:09:55", "remaining_time": "0:54:56", "throughput": 7040.22, "total_tokens": 4194304} {"current_steps": 513, "total_steps": 3345, "loss": 1.3113, "lr": 2.357700078741641e-06, "epoch": 0.7668161434977578, "percentage": 15.34, "elapsed_time": "0:09:56", "remaining_time": "0:54:55", "throughput": 7040.28, "total_tokens": 4202496} {"current_steps": 514, "total_steps": 3345, "loss": 1.3102, "lr": 2.357155588453617e-06, "epoch": 0.7683109118086696, "percentage": 15.37, "elapsed_time": "0:09:58", "remaining_time": "0:54:54", "throughput": 7040.36, "total_tokens": 4210688} {"current_steps": 515, "total_steps": 3345, "loss": 1.3936, "lr": 2.356610121566929e-06, "epoch": 0.7698056801195815, "percentage": 15.4, "elapsed_time": "0:09:59", "remaining_time": "0:54:52", "throughput": 7040.45, "total_tokens": 4218880} {"current_steps": 516, "total_steps": 3345, "loss": 1.4053, "lr": 2.3560636785627216e-06, "epoch": 0.7713004484304933, "percentage": 15.43, "elapsed_time": "0:10:00", "remaining_time": "0:54:51", "throughput": 7040.56, "total_tokens": 4227072} {"current_steps": 517, "total_steps": 3345, "loss": 1.1896, "lr": 2.3555162599230016e-06, "epoch": 0.772795216741405, "percentage": 15.46, "elapsed_time": "0:10:01", "remaining_time": "0:54:50", "throughput": 7040.6, "total_tokens": 4235264} {"current_steps": 518, "total_steps": 3345, "loss": 0.9216, "lr": 2.3549678661306345e-06, "epoch": 0.7742899850523169, "percentage": 15.49, "elapsed_time": "0:10:02", "remaining_time": "0:54:49", "throughput": 7040.7, "total_tokens": 4243456} {"current_steps": 519, "total_steps": 3345, "loss": 1.332, "lr": 2.354418497669348e-06, "epoch": 0.7757847533632287, "percentage": 15.52, "elapsed_time": "0:10:03", "remaining_time": "0:54:48", "throughput": 7040.74, "total_tokens": 4251648} {"current_steps": 520, "total_steps": 3345, "loss": 1.0605, "lr": 2.3538681550237273e-06, "epoch": 0.7772795216741405, "percentage": 15.55, "elapsed_time": "0:10:05", "remaining_time": "0:54:46", "throughput": 7040.8, "total_tokens": 4259840} {"current_steps": 521, "total_steps": 3345, "loss": 1.2962, "lr": 2.3533168386792186e-06, "epoch": 0.7787742899850523, "percentage": 15.58, "elapsed_time": "0:10:06", "remaining_time": "0:54:45", "throughput": 7040.86, "total_tokens": 4268032} {"current_steps": 522, "total_steps": 3345, "loss": 1.1768, "lr": 2.3527645491221267e-06, "epoch": 0.7802690582959642, "percentage": 15.61, "elapsed_time": "0:10:07", "remaining_time": "0:54:44", "throughput": 7040.92, "total_tokens": 4276224} {"current_steps": 523, "total_steps": 3345, "loss": 1.3555, "lr": 2.352211286839614e-06, "epoch": 0.7817638266068759, "percentage": 15.64, "elapsed_time": "0:10:08", "remaining_time": "0:54:43", "throughput": 7041.0, "total_tokens": 4284416} {"current_steps": 524, "total_steps": 3345, "loss": 1.1821, "lr": 2.3516570523197023e-06, "epoch": 0.7832585949177877, "percentage": 15.67, "elapsed_time": "0:10:09", "remaining_time": "0:54:42", "throughput": 7041.08, "total_tokens": 4292608} {"current_steps": 525, "total_steps": 3345, "loss": 1.4139, "lr": 2.3511018460512696e-06, "epoch": 0.7847533632286996, "percentage": 15.7, "elapsed_time": "0:10:10", "remaining_time": "0:54:40", "throughput": 7041.13, "total_tokens": 4300800} {"current_steps": 526, "total_steps": 3345, "loss": 1.2344, "lr": 2.350545668524052e-06, "epoch": 0.7862481315396114, "percentage": 15.72, "elapsed_time": "0:10:11", "remaining_time": "0:54:39", "throughput": 7041.2, "total_tokens": 4308992} {"current_steps": 527, "total_steps": 3345, "loss": 1.1616, "lr": 2.3499885202286415e-06, "epoch": 0.7877428998505231, "percentage": 15.75, "elapsed_time": "0:10:13", "remaining_time": "0:54:38", "throughput": 7041.21, "total_tokens": 4317184} {"current_steps": 528, "total_steps": 3345, "loss": 1.3172, "lr": 2.3494304016564878e-06, "epoch": 0.7892376681614349, "percentage": 15.78, "elapsed_time": "0:10:14", "remaining_time": "0:54:37", "throughput": 7041.25, "total_tokens": 4325376} {"current_steps": 529, "total_steps": 3345, "loss": 1.3006, "lr": 2.3488713132998946e-06, "epoch": 0.7907324364723468, "percentage": 15.81, "elapsed_time": "0:10:15", "remaining_time": "0:54:36", "throughput": 7041.3, "total_tokens": 4333568} {"current_steps": 530, "total_steps": 3345, "loss": 1.0379, "lr": 2.348311255652023e-06, "epoch": 0.7922272047832586, "percentage": 15.84, "elapsed_time": "0:10:16", "remaining_time": "0:54:35", "throughput": 7041.31, "total_tokens": 4341760} {"current_steps": 531, "total_steps": 3345, "loss": 1.4969, "lr": 2.347750229206887e-06, "epoch": 0.7937219730941704, "percentage": 15.87, "elapsed_time": "0:10:17", "remaining_time": "0:54:33", "throughput": 7041.37, "total_tokens": 4349952} {"current_steps": 532, "total_steps": 3345, "loss": 1.4313, "lr": 2.347188234459357e-06, "epoch": 0.7952167414050823, "percentage": 15.9, "elapsed_time": "0:10:18", "remaining_time": "0:54:32", "throughput": 7041.41, "total_tokens": 4358144} {"current_steps": 533, "total_steps": 3345, "loss": 1.2672, "lr": 2.3466252719051563e-06, "epoch": 0.796711509715994, "percentage": 15.93, "elapsed_time": "0:10:20", "remaining_time": "0:54:31", "throughput": 7041.46, "total_tokens": 4366336} {"current_steps": 534, "total_steps": 3345, "loss": 1.3077, "lr": 2.3460613420408626e-06, "epoch": 0.7982062780269058, "percentage": 15.96, "elapsed_time": "0:10:21", "remaining_time": "0:54:30", "throughput": 7041.5, "total_tokens": 4374528} {"current_steps": 535, "total_steps": 3345, "loss": 1.0849, "lr": 2.3454964453639065e-06, "epoch": 0.7997010463378177, "percentage": 15.99, "elapsed_time": "0:10:22", "remaining_time": "0:54:29", "throughput": 7041.54, "total_tokens": 4382720} {"current_steps": 536, "total_steps": 3345, "loss": 1.4678, "lr": 2.3449305823725716e-06, "epoch": 0.8011958146487295, "percentage": 16.02, "elapsed_time": "0:10:23", "remaining_time": "0:54:27", "throughput": 7041.56, "total_tokens": 4390912} {"current_steps": 537, "total_steps": 3345, "loss": 1.4439, "lr": 2.344363753565993e-06, "epoch": 0.8026905829596412, "percentage": 16.05, "elapsed_time": "0:10:24", "remaining_time": "0:54:26", "throughput": 7041.55, "total_tokens": 4399104} {"current_steps": 538, "total_steps": 3345, "loss": 0.8849, "lr": 2.3437959594441597e-06, "epoch": 0.804185351270553, "percentage": 16.08, "elapsed_time": "0:10:25", "remaining_time": "0:54:25", "throughput": 7041.44, "total_tokens": 4407296} {"current_steps": 539, "total_steps": 3345, "loss": 0.9841, "lr": 2.34322720050791e-06, "epoch": 0.8056801195814649, "percentage": 16.11, "elapsed_time": "0:10:27", "remaining_time": "0:54:24", "throughput": 7041.47, "total_tokens": 4415488} {"current_steps": 540, "total_steps": 3345, "loss": 1.2415, "lr": 2.342657477258935e-06, "epoch": 0.8071748878923767, "percentage": 16.14, "elapsed_time": "0:10:28", "remaining_time": "0:54:23", "throughput": 7041.56, "total_tokens": 4423680} {"current_steps": 541, "total_steps": 3345, "loss": 1.3047, "lr": 2.3420867901997746e-06, "epoch": 0.8086696562032885, "percentage": 16.17, "elapsed_time": "0:10:29", "remaining_time": "0:54:22", "throughput": 7041.64, "total_tokens": 4431872} {"current_steps": 542, "total_steps": 3345, "loss": 0.8676, "lr": 2.341515139833821e-06, "epoch": 0.8101644245142003, "percentage": 16.2, "elapsed_time": "0:10:30", "remaining_time": "0:54:20", "throughput": 7041.71, "total_tokens": 4440064} {"current_steps": 543, "total_steps": 3345, "loss": 1.2453, "lr": 2.3409425266653137e-06, "epoch": 0.8116591928251121, "percentage": 16.23, "elapsed_time": "0:10:31", "remaining_time": "0:54:19", "throughput": 7041.74, "total_tokens": 4448256} {"current_steps": 544, "total_steps": 3345, "loss": 1.3653, "lr": 2.3403689511993435e-06, "epoch": 0.8131539611360239, "percentage": 16.26, "elapsed_time": "0:10:32", "remaining_time": "0:54:18", "throughput": 7041.81, "total_tokens": 4456448} {"current_steps": 545, "total_steps": 3345, "loss": 1.2241, "lr": 2.3397944139418494e-06, "epoch": 0.8146487294469357, "percentage": 16.29, "elapsed_time": "0:10:34", "remaining_time": "0:54:17", "throughput": 7041.85, "total_tokens": 4464640} {"current_steps": 546, "total_steps": 3345, "loss": 1.3134, "lr": 2.339218915399618e-06, "epoch": 0.8161434977578476, "percentage": 16.32, "elapsed_time": "0:10:35", "remaining_time": "0:54:16", "throughput": 7041.9, "total_tokens": 4472832} {"current_steps": 547, "total_steps": 3345, "loss": 1.4142, "lr": 2.3386424560802854e-06, "epoch": 0.8176382660687593, "percentage": 16.35, "elapsed_time": "0:10:36", "remaining_time": "0:54:14", "throughput": 7041.95, "total_tokens": 4481024} {"current_steps": 548, "total_steps": 3345, "loss": 1.1869, "lr": 2.3380650364923336e-06, "epoch": 0.8191330343796711, "percentage": 16.38, "elapsed_time": "0:10:37", "remaining_time": "0:54:13", "throughput": 7041.98, "total_tokens": 4489216} {"current_steps": 549, "total_steps": 3345, "loss": 0.9564, "lr": 2.3374866571450923e-06, "epoch": 0.820627802690583, "percentage": 16.41, "elapsed_time": "0:10:38", "remaining_time": "0:54:12", "throughput": 7041.98, "total_tokens": 4497408} {"current_steps": 550, "total_steps": 3345, "loss": 1.1339, "lr": 2.3369073185487373e-06, "epoch": 0.8221225710014948, "percentage": 16.44, "elapsed_time": "0:10:39", "remaining_time": "0:54:11", "throughput": 7042.0, "total_tokens": 4505600} {"current_steps": 551, "total_steps": 3345, "loss": 1.1341, "lr": 2.3363270212142918e-06, "epoch": 0.8236173393124065, "percentage": 16.47, "elapsed_time": "0:10:40", "remaining_time": "0:54:10", "throughput": 7042.01, "total_tokens": 4513792} {"current_steps": 552, "total_steps": 3345, "loss": 1.3129, "lr": 2.335745765653624e-06, "epoch": 0.8251121076233184, "percentage": 16.5, "elapsed_time": "0:10:42", "remaining_time": "0:54:09", "throughput": 7042.01, "total_tokens": 4521984} {"current_steps": 553, "total_steps": 3345, "loss": 1.3722, "lr": 2.3351635523794462e-06, "epoch": 0.8266068759342302, "percentage": 16.53, "elapsed_time": "0:10:43", "remaining_time": "0:54:07", "throughput": 7042.04, "total_tokens": 4530176} {"current_steps": 554, "total_steps": 3345, "loss": 1.3828, "lr": 2.3345803819053176e-06, "epoch": 0.828101644245142, "percentage": 16.56, "elapsed_time": "0:10:44", "remaining_time": "0:54:06", "throughput": 7042.07, "total_tokens": 4538368} {"current_steps": 555, "total_steps": 3345, "loss": 1.1897, "lr": 2.33399625474564e-06, "epoch": 0.8295964125560538, "percentage": 16.59, "elapsed_time": "0:10:45", "remaining_time": "0:54:05", "throughput": 7042.1, "total_tokens": 4546560} {"current_steps": 556, "total_steps": 3345, "loss": 1.373, "lr": 2.3334111714156598e-06, "epoch": 0.8310911808669657, "percentage": 16.62, "elapsed_time": "0:10:46", "remaining_time": "0:54:04", "throughput": 7042.1, "total_tokens": 4554752} {"current_steps": 557, "total_steps": 3345, "loss": 1.0569, "lr": 2.3328251324314668e-06, "epoch": 0.8325859491778774, "percentage": 16.65, "elapsed_time": "0:10:47", "remaining_time": "0:54:03", "throughput": 7042.12, "total_tokens": 4562944} {"current_steps": 558, "total_steps": 3345, "loss": 1.0018, "lr": 2.332238138309993e-06, "epoch": 0.8340807174887892, "percentage": 16.68, "elapsed_time": "0:10:49", "remaining_time": "0:54:02", "throughput": 7042.18, "total_tokens": 4571136} {"current_steps": 559, "total_steps": 3345, "loss": 1.3899, "lr": 2.3316501895690144e-06, "epoch": 0.8355754857997011, "percentage": 16.71, "elapsed_time": "0:10:50", "remaining_time": "0:54:00", "throughput": 7042.25, "total_tokens": 4579328} {"current_steps": 560, "total_steps": 3345, "loss": 1.2138, "lr": 2.331061286727148e-06, "epoch": 0.8370702541106129, "percentage": 16.74, "elapsed_time": "0:10:51", "remaining_time": "0:53:59", "throughput": 7042.32, "total_tokens": 4587520} {"current_steps": 561, "total_steps": 3345, "loss": 1.2264, "lr": 2.3304714303038526e-06, "epoch": 0.8385650224215246, "percentage": 16.77, "elapsed_time": "0:10:52", "remaining_time": "0:53:58", "throughput": 7042.43, "total_tokens": 4595712} {"current_steps": 562, "total_steps": 3345, "loss": 1.2892, "lr": 2.329880620819428e-06, "epoch": 0.8400597907324364, "percentage": 16.8, "elapsed_time": "0:10:53", "remaining_time": "0:53:57", "throughput": 7042.49, "total_tokens": 4603904} {"current_steps": 563, "total_steps": 3345, "loss": 1.184, "lr": 2.3292888587950153e-06, "epoch": 0.8415545590433483, "percentage": 16.83, "elapsed_time": "0:10:54", "remaining_time": "0:53:56", "throughput": 7042.55, "total_tokens": 4612096} {"current_steps": 564, "total_steps": 3345, "loss": 1.1039, "lr": 2.3286961447525945e-06, "epoch": 0.8430493273542601, "percentage": 16.86, "elapsed_time": "0:10:56", "remaining_time": "0:53:54", "throughput": 7042.51, "total_tokens": 4620288} {"current_steps": 565, "total_steps": 3345, "loss": 1.2192, "lr": 2.328102479214987e-06, "epoch": 0.8445440956651719, "percentage": 16.89, "elapsed_time": "0:10:57", "remaining_time": "0:53:53", "throughput": 7042.49, "total_tokens": 4628480} {"current_steps": 566, "total_steps": 3345, "loss": 1.4948, "lr": 2.327507862705852e-06, "epoch": 0.8460388639760837, "percentage": 16.92, "elapsed_time": "0:10:58", "remaining_time": "0:53:52", "throughput": 7042.53, "total_tokens": 4636672} {"current_steps": 567, "total_steps": 3345, "loss": 1.3092, "lr": 2.326912295749689e-06, "epoch": 0.8475336322869955, "percentage": 16.95, "elapsed_time": "0:10:59", "remaining_time": "0:53:51", "throughput": 7042.56, "total_tokens": 4644864} {"current_steps": 568, "total_steps": 3345, "loss": 1.1143, "lr": 2.3263157788718344e-06, "epoch": 0.8490284005979073, "percentage": 16.98, "elapsed_time": "0:11:00", "remaining_time": "0:53:50", "throughput": 7042.61, "total_tokens": 4653056} {"current_steps": 569, "total_steps": 3345, "loss": 1.0223, "lr": 2.3257183125984635e-06, "epoch": 0.8505231689088192, "percentage": 17.01, "elapsed_time": "0:11:01", "remaining_time": "0:53:49", "throughput": 7042.66, "total_tokens": 4661248} {"current_steps": 570, "total_steps": 3345, "loss": 1.1962, "lr": 2.3251198974565885e-06, "epoch": 0.852017937219731, "percentage": 17.04, "elapsed_time": "0:11:03", "remaining_time": "0:53:47", "throughput": 7042.71, "total_tokens": 4669440} {"current_steps": 571, "total_steps": 3345, "loss": 1.1066, "lr": 2.3245205339740597e-06, "epoch": 0.8535127055306427, "percentage": 17.07, "elapsed_time": "0:11:04", "remaining_time": "0:53:46", "throughput": 7042.77, "total_tokens": 4677632} {"current_steps": 572, "total_steps": 3345, "loss": 1.13, "lr": 2.3239202226795616e-06, "epoch": 0.8550074738415545, "percentage": 17.1, "elapsed_time": "0:11:05", "remaining_time": "0:53:45", "throughput": 7042.82, "total_tokens": 4685824} {"current_steps": 573, "total_steps": 3345, "loss": 1.4793, "lr": 2.3233189641026172e-06, "epoch": 0.8565022421524664, "percentage": 17.13, "elapsed_time": "0:11:06", "remaining_time": "0:53:44", "throughput": 7042.87, "total_tokens": 4694016} {"current_steps": 574, "total_steps": 3345, "loss": 1.1945, "lr": 2.3227167587735836e-06, "epoch": 0.8579970104633782, "percentage": 17.16, "elapsed_time": "0:11:07", "remaining_time": "0:53:43", "throughput": 7042.94, "total_tokens": 4702208} {"current_steps": 575, "total_steps": 3345, "loss": 1.3955, "lr": 2.322113607223654e-06, "epoch": 0.85949177877429, "percentage": 17.19, "elapsed_time": "0:11:08", "remaining_time": "0:53:41", "throughput": 7042.97, "total_tokens": 4710400} {"current_steps": 576, "total_steps": 3345, "loss": 1.1938, "lr": 2.3215095099848543e-06, "epoch": 0.8609865470852018, "percentage": 17.22, "elapsed_time": "0:11:09", "remaining_time": "0:53:40", "throughput": 7043.02, "total_tokens": 4718592} {"current_steps": 577, "total_steps": 3345, "loss": 1.3646, "lr": 2.320904467590048e-06, "epoch": 0.8624813153961136, "percentage": 17.25, "elapsed_time": "0:11:11", "remaining_time": "0:53:39", "throughput": 7043.03, "total_tokens": 4726784} {"current_steps": 578, "total_steps": 3345, "loss": 1.1402, "lr": 2.320298480572929e-06, "epoch": 0.8639760837070254, "percentage": 17.28, "elapsed_time": "0:11:12", "remaining_time": "0:53:38", "throughput": 7043.07, "total_tokens": 4734976} {"current_steps": 579, "total_steps": 3345, "loss": 1.2572, "lr": 2.3196915494680257e-06, "epoch": 0.8654708520179372, "percentage": 17.31, "elapsed_time": "0:11:13", "remaining_time": "0:53:37", "throughput": 7043.1, "total_tokens": 4743168} {"current_steps": 580, "total_steps": 3345, "loss": 1.1902, "lr": 2.3190836748106997e-06, "epoch": 0.866965620328849, "percentage": 17.34, "elapsed_time": "0:11:14", "remaining_time": "0:53:36", "throughput": 7043.13, "total_tokens": 4751360} {"current_steps": 581, "total_steps": 3345, "loss": 1.4262, "lr": 2.3184748571371445e-06, "epoch": 0.8684603886397608, "percentage": 17.37, "elapsed_time": "0:11:15", "remaining_time": "0:53:34", "throughput": 7043.2, "total_tokens": 4759552} {"current_steps": 582, "total_steps": 3345, "loss": 0.9969, "lr": 2.3178650969843847e-06, "epoch": 0.8699551569506726, "percentage": 17.4, "elapsed_time": "0:11:16", "remaining_time": "0:53:33", "throughput": 7043.27, "total_tokens": 4767744} {"current_steps": 583, "total_steps": 3345, "loss": 1.2527, "lr": 2.3172543948902776e-06, "epoch": 0.8714499252615845, "percentage": 17.43, "elapsed_time": "0:11:18", "remaining_time": "0:53:32", "throughput": 7043.33, "total_tokens": 4775936} {"current_steps": 584, "total_steps": 3345, "loss": 1.3916, "lr": 2.31664275139351e-06, "epoch": 0.8729446935724963, "percentage": 17.46, "elapsed_time": "0:11:19", "remaining_time": "0:53:31", "throughput": 7043.35, "total_tokens": 4784128} {"current_steps": 585, "total_steps": 3345, "loss": 0.9973, "lr": 2.316030167033601e-06, "epoch": 0.874439461883408, "percentage": 17.49, "elapsed_time": "0:11:20", "remaining_time": "0:53:30", "throughput": 7043.41, "total_tokens": 4792320} {"current_steps": 586, "total_steps": 3345, "loss": 1.3755, "lr": 2.3154166423508973e-06, "epoch": 0.8759342301943199, "percentage": 17.52, "elapsed_time": "0:11:21", "remaining_time": "0:53:28", "throughput": 7043.47, "total_tokens": 4800512} {"current_steps": 587, "total_steps": 3345, "loss": 1.3422, "lr": 2.3148021778865763e-06, "epoch": 0.8774289985052317, "percentage": 17.55, "elapsed_time": "0:11:22", "remaining_time": "0:53:27", "throughput": 7043.55, "total_tokens": 4808704} {"current_steps": 588, "total_steps": 3345, "loss": 1.2586, "lr": 2.314186774182644e-06, "epoch": 0.8789237668161435, "percentage": 17.58, "elapsed_time": "0:11:23", "remaining_time": "0:53:26", "throughput": 7043.62, "total_tokens": 4816896} {"current_steps": 589, "total_steps": 3345, "loss": 1.3784, "lr": 2.3135704317819357e-06, "epoch": 0.8804185351270553, "percentage": 17.61, "elapsed_time": "0:11:25", "remaining_time": "0:53:25", "throughput": 7043.63, "total_tokens": 4825088} {"current_steps": 590, "total_steps": 3345, "loss": 1.2548, "lr": 2.3129531512281133e-06, "epoch": 0.8819133034379671, "percentage": 17.64, "elapsed_time": "0:11:26", "remaining_time": "0:53:24", "throughput": 7043.69, "total_tokens": 4833280} {"current_steps": 591, "total_steps": 3345, "loss": 1.4933, "lr": 2.312334933065668e-06, "epoch": 0.8834080717488789, "percentage": 17.67, "elapsed_time": "0:11:27", "remaining_time": "0:53:22", "throughput": 7043.69, "total_tokens": 4841472} {"current_steps": 592, "total_steps": 3345, "loss": 1.2206, "lr": 2.3117157778399164e-06, "epoch": 0.8849028400597907, "percentage": 17.7, "elapsed_time": "0:11:28", "remaining_time": "0:53:21", "throughput": 7043.65, "total_tokens": 4849664} {"current_steps": 593, "total_steps": 3345, "loss": 1.3925, "lr": 2.311095686097002e-06, "epoch": 0.8863976083707026, "percentage": 17.73, "elapsed_time": "0:11:29", "remaining_time": "0:53:20", "throughput": 7043.71, "total_tokens": 4857856} {"current_steps": 594, "total_steps": 3345, "loss": 1.4215, "lr": 2.310474658383895e-06, "epoch": 0.8878923766816144, "percentage": 17.76, "elapsed_time": "0:11:30", "remaining_time": "0:53:19", "throughput": 7043.78, "total_tokens": 4866048} {"current_steps": 595, "total_steps": 3345, "loss": 1.2385, "lr": 2.3098526952483913e-06, "epoch": 0.8893871449925261, "percentage": 17.79, "elapsed_time": "0:11:31", "remaining_time": "0:53:18", "throughput": 7043.86, "total_tokens": 4874240} {"current_steps": 596, "total_steps": 3345, "loss": 1.1668, "lr": 2.309229797239111e-06, "epoch": 0.890881913303438, "percentage": 17.82, "elapsed_time": "0:11:33", "remaining_time": "0:53:17", "throughput": 7043.95, "total_tokens": 4882432} {"current_steps": 597, "total_steps": 3345, "loss": 1.0915, "lr": 2.3086059649054992e-06, "epoch": 0.8923766816143498, "percentage": 17.85, "elapsed_time": "0:11:34", "remaining_time": "0:53:15", "throughput": 7044.02, "total_tokens": 4890624} {"current_steps": 598, "total_steps": 3345, "loss": 1.0639, "lr": 2.3079811987978262e-06, "epoch": 0.8938714499252616, "percentage": 17.88, "elapsed_time": "0:11:35", "remaining_time": "0:53:14", "throughput": 7044.04, "total_tokens": 4898816} {"current_steps": 599, "total_steps": 3345, "loss": 1.2192, "lr": 2.307355499467184e-06, "epoch": 0.8953662182361734, "percentage": 17.91, "elapsed_time": "0:11:36", "remaining_time": "0:53:13", "throughput": 7044.11, "total_tokens": 4907008} {"current_steps": 600, "total_steps": 3345, "loss": 1.3426, "lr": 2.306728867465489e-06, "epoch": 0.8968609865470852, "percentage": 17.94, "elapsed_time": "0:11:37", "remaining_time": "0:53:12", "throughput": 7044.17, "total_tokens": 4915200} {"current_steps": 601, "total_steps": 3345, "loss": 1.4156, "lr": 2.306101303345481e-06, "epoch": 0.898355754857997, "percentage": 17.97, "elapsed_time": "0:11:38", "remaining_time": "0:53:11", "throughput": 7044.19, "total_tokens": 4923392} {"current_steps": 602, "total_steps": 3345, "loss": 1.0583, "lr": 2.30547280766072e-06, "epoch": 0.8998505231689088, "percentage": 18.0, "elapsed_time": "0:11:40", "remaining_time": "0:53:09", "throughput": 7044.19, "total_tokens": 4931584} {"current_steps": 603, "total_steps": 3345, "loss": 1.2057, "lr": 2.3048433809655894e-06, "epoch": 0.9013452914798207, "percentage": 18.03, "elapsed_time": "0:11:41", "remaining_time": "0:53:08", "throughput": 7044.22, "total_tokens": 4939776} {"current_steps": 604, "total_steps": 3345, "loss": 1.0048, "lr": 2.304213023815293e-06, "epoch": 0.9028400597907325, "percentage": 18.06, "elapsed_time": "0:11:42", "remaining_time": "0:53:07", "throughput": 7044.3, "total_tokens": 4947968} {"current_steps": 605, "total_steps": 3345, "loss": 1.2543, "lr": 2.303581736765856e-06, "epoch": 0.9043348281016442, "percentage": 18.09, "elapsed_time": "0:11:43", "remaining_time": "0:53:06", "throughput": 7044.34, "total_tokens": 4956160} {"current_steps": 606, "total_steps": 3345, "loss": 1.1515, "lr": 2.3029495203741227e-06, "epoch": 0.905829596412556, "percentage": 18.12, "elapsed_time": "0:11:44", "remaining_time": "0:53:05", "throughput": 7044.36, "total_tokens": 4964352} {"current_steps": 607, "total_steps": 3345, "loss": 1.3401, "lr": 2.3023163751977587e-06, "epoch": 0.9073243647234679, "percentage": 18.15, "elapsed_time": "0:11:45", "remaining_time": "0:53:04", "throughput": 7044.31, "total_tokens": 4972544} {"current_steps": 608, "total_steps": 3345, "loss": 1.306, "lr": 2.301682301795248e-06, "epoch": 0.9088191330343797, "percentage": 18.18, "elapsed_time": "0:11:47", "remaining_time": "0:53:02", "throughput": 7044.21, "total_tokens": 4980736} {"current_steps": 609, "total_steps": 3345, "loss": 1.3959, "lr": 2.3010473007258925e-06, "epoch": 0.9103139013452914, "percentage": 18.21, "elapsed_time": "0:11:48", "remaining_time": "0:53:01", "throughput": 7044.19, "total_tokens": 4988928} {"current_steps": 610, "total_steps": 3345, "loss": 1.2087, "lr": 2.300411372549814e-06, "epoch": 0.9118086696562033, "percentage": 18.24, "elapsed_time": "0:11:49", "remaining_time": "0:53:01", "throughput": 7042.14, "total_tokens": 4997120} {"current_steps": 611, "total_steps": 3345, "loss": 1.164, "lr": 2.299774517827951e-06, "epoch": 0.9133034379671151, "percentage": 18.27, "elapsed_time": "0:11:50", "remaining_time": "0:53:00", "throughput": 7042.19, "total_tokens": 5005312} {"current_steps": 612, "total_steps": 3345, "loss": 1.1986, "lr": 2.2991367371220607e-06, "epoch": 0.9147982062780269, "percentage": 18.3, "elapsed_time": "0:11:51", "remaining_time": "0:52:59", "throughput": 7042.24, "total_tokens": 5013504} {"current_steps": 613, "total_steps": 3345, "loss": 1.2583, "lr": 2.2984980309947148e-06, "epoch": 0.9162929745889388, "percentage": 18.33, "elapsed_time": "0:11:53", "remaining_time": "0:52:58", "throughput": 7042.28, "total_tokens": 5021696} {"current_steps": 614, "total_steps": 3345, "loss": 1.175, "lr": 2.297858400009303e-06, "epoch": 0.9177877428998505, "percentage": 18.36, "elapsed_time": "0:11:54", "remaining_time": "0:52:56", "throughput": 7042.27, "total_tokens": 5029888} {"current_steps": 615, "total_steps": 3345, "loss": 1.2416, "lr": 2.2972178447300307e-06, "epoch": 0.9192825112107623, "percentage": 18.39, "elapsed_time": "0:11:55", "remaining_time": "0:52:55", "throughput": 7042.31, "total_tokens": 5038080} {"current_steps": 616, "total_steps": 3345, "loss": 1.3263, "lr": 2.2965763657219176e-06, "epoch": 0.9207772795216741, "percentage": 18.42, "elapsed_time": "0:11:56", "remaining_time": "0:52:54", "throughput": 7042.36, "total_tokens": 5046272} {"current_steps": 617, "total_steps": 3345, "loss": 1.1564, "lr": 2.2959339635507992e-06, "epoch": 0.922272047832586, "percentage": 18.45, "elapsed_time": "0:11:57", "remaining_time": "0:52:53", "throughput": 7042.39, "total_tokens": 5054464} {"current_steps": 618, "total_steps": 3345, "loss": 1.1459, "lr": 2.295290638783325e-06, "epoch": 0.9237668161434978, "percentage": 18.48, "elapsed_time": "0:11:58", "remaining_time": "0:52:52", "throughput": 7042.39, "total_tokens": 5062656} {"current_steps": 619, "total_steps": 3345, "loss": 1.1657, "lr": 2.294646391986958e-06, "epoch": 0.9252615844544095, "percentage": 18.51, "elapsed_time": "0:12:00", "remaining_time": "0:52:51", "throughput": 7042.33, "total_tokens": 5070848} {"current_steps": 620, "total_steps": 3345, "loss": 1.3175, "lr": 2.294001223729975e-06, "epoch": 0.9267563527653214, "percentage": 18.54, "elapsed_time": "0:12:01", "remaining_time": "0:52:49", "throughput": 7042.2, "total_tokens": 5079040} {"current_steps": 621, "total_steps": 3345, "loss": 1.3441, "lr": 2.2933551345814653e-06, "epoch": 0.9282511210762332, "percentage": 18.57, "elapsed_time": "0:12:02", "remaining_time": "0:52:48", "throughput": 7042.14, "total_tokens": 5087232} {"current_steps": 622, "total_steps": 3345, "loss": 0.9893, "lr": 2.2927081251113304e-06, "epoch": 0.929745889387145, "percentage": 18.59, "elapsed_time": "0:12:03", "remaining_time": "0:52:47", "throughput": 7041.97, "total_tokens": 5095424} {"current_steps": 623, "total_steps": 3345, "loss": 1.3339, "lr": 2.292060195890284e-06, "epoch": 0.9312406576980568, "percentage": 18.62, "elapsed_time": "0:12:04", "remaining_time": "0:52:46", "throughput": 7041.97, "total_tokens": 5103616} {"current_steps": 624, "total_steps": 3345, "loss": 1.4305, "lr": 2.29141134748985e-06, "epoch": 0.9327354260089686, "percentage": 18.65, "elapsed_time": "0:12:05", "remaining_time": "0:52:45", "throughput": 7041.98, "total_tokens": 5111808} {"current_steps": 625, "total_steps": 3345, "loss": 1.0558, "lr": 2.2907615804823655e-06, "epoch": 0.9342301943198804, "percentage": 18.68, "elapsed_time": "0:12:07", "remaining_time": "0:52:44", "throughput": 7041.95, "total_tokens": 5120000} {"current_steps": 626, "total_steps": 3345, "loss": 1.2774, "lr": 2.2901108954409752e-06, "epoch": 0.9357249626307922, "percentage": 18.71, "elapsed_time": "0:12:08", "remaining_time": "0:52:43", "throughput": 7041.97, "total_tokens": 5128192} {"current_steps": 627, "total_steps": 3345, "loss": 1.3545, "lr": 2.289459292939635e-06, "epoch": 0.9372197309417041, "percentage": 18.74, "elapsed_time": "0:12:09", "remaining_time": "0:52:41", "throughput": 7041.82, "total_tokens": 5136384} {"current_steps": 628, "total_steps": 3345, "loss": 1.2568, "lr": 2.2888067735531095e-06, "epoch": 0.9387144992526159, "percentage": 18.77, "elapsed_time": "0:12:10", "remaining_time": "0:52:40", "throughput": 7041.81, "total_tokens": 5144576} {"current_steps": 629, "total_steps": 3345, "loss": 1.1388, "lr": 2.2881533378569724e-06, "epoch": 0.9402092675635276, "percentage": 18.8, "elapsed_time": "0:12:11", "remaining_time": "0:52:39", "throughput": 7041.83, "total_tokens": 5152768} {"current_steps": 630, "total_steps": 3345, "loss": 0.9463, "lr": 2.287498986427606e-06, "epoch": 0.9417040358744395, "percentage": 18.83, "elapsed_time": "0:12:12", "remaining_time": "0:52:38", "throughput": 7041.84, "total_tokens": 5160960} {"current_steps": 631, "total_steps": 3345, "loss": 1.4185, "lr": 2.2868437198421995e-06, "epoch": 0.9431988041853513, "percentage": 18.86, "elapsed_time": "0:12:14", "remaining_time": "0:52:37", "throughput": 7041.85, "total_tokens": 5169152} {"current_steps": 632, "total_steps": 3345, "loss": 1.0967, "lr": 2.28618753867875e-06, "epoch": 0.9446935724962631, "percentage": 18.89, "elapsed_time": "0:12:15", "remaining_time": "0:52:36", "throughput": 7041.83, "total_tokens": 5177344} {"current_steps": 633, "total_steps": 3345, "loss": 0.9837, "lr": 2.285530443516061e-06, "epoch": 0.9461883408071748, "percentage": 18.92, "elapsed_time": "0:12:16", "remaining_time": "0:52:34", "throughput": 7041.82, "total_tokens": 5185536} {"current_steps": 634, "total_steps": 3345, "loss": 1.0993, "lr": 2.2848724349337425e-06, "epoch": 0.9476831091180867, "percentage": 18.95, "elapsed_time": "0:12:17", "remaining_time": "0:52:33", "throughput": 7041.85, "total_tokens": 5193728} {"current_steps": 635, "total_steps": 3345, "loss": 1.4117, "lr": 2.2842135135122096e-06, "epoch": 0.9491778774289985, "percentage": 18.98, "elapsed_time": "0:12:18", "remaining_time": "0:52:32", "throughput": 7041.77, "total_tokens": 5201920} {"current_steps": 636, "total_steps": 3345, "loss": 1.3149, "lr": 2.2835536798326836e-06, "epoch": 0.9506726457399103, "percentage": 19.01, "elapsed_time": "0:12:19", "remaining_time": "0:52:31", "throughput": 7041.78, "total_tokens": 5210112} {"current_steps": 637, "total_steps": 3345, "loss": 1.482, "lr": 2.2828929344771893e-06, "epoch": 0.9521674140508222, "percentage": 19.04, "elapsed_time": "0:12:21", "remaining_time": "0:52:30", "throughput": 7041.8, "total_tokens": 5218304} {"current_steps": 638, "total_steps": 3345, "loss": 1.1257, "lr": 2.282231278028557e-06, "epoch": 0.953662182361734, "percentage": 19.07, "elapsed_time": "0:12:22", "remaining_time": "0:52:29", "throughput": 7041.78, "total_tokens": 5226496} {"current_steps": 639, "total_steps": 3345, "loss": 1.4944, "lr": 2.2815687110704198e-06, "epoch": 0.9551569506726457, "percentage": 19.1, "elapsed_time": "0:12:23", "remaining_time": "0:52:27", "throughput": 7041.81, "total_tokens": 5234688} {"current_steps": 640, "total_steps": 3345, "loss": 1.0257, "lr": 2.2809052341872135e-06, "epoch": 0.9566517189835575, "percentage": 19.13, "elapsed_time": "0:12:24", "remaining_time": "0:52:26", "throughput": 7041.82, "total_tokens": 5242880} {"current_steps": 641, "total_steps": 3345, "loss": 1.4925, "lr": 2.280240847964177e-06, "epoch": 0.9581464872944694, "percentage": 19.16, "elapsed_time": "0:12:25", "remaining_time": "0:52:25", "throughput": 7041.86, "total_tokens": 5251072} {"current_steps": 642, "total_steps": 3345, "loss": 1.2469, "lr": 2.2795755529873524e-06, "epoch": 0.9596412556053812, "percentage": 19.19, "elapsed_time": "0:12:26", "remaining_time": "0:52:24", "throughput": 7041.87, "total_tokens": 5259264} {"current_steps": 643, "total_steps": 3345, "loss": 1.3478, "lr": 2.278909349843582e-06, "epoch": 0.9611360239162929, "percentage": 19.22, "elapsed_time": "0:12:28", "remaining_time": "0:52:23", "throughput": 7041.91, "total_tokens": 5267456} {"current_steps": 644, "total_steps": 3345, "loss": 1.2591, "lr": 2.278242239120509e-06, "epoch": 0.9626307922272048, "percentage": 19.25, "elapsed_time": "0:12:29", "remaining_time": "0:52:22", "throughput": 7041.98, "total_tokens": 5275648} {"current_steps": 645, "total_steps": 3345, "loss": 1.198, "lr": 2.2775742214065788e-06, "epoch": 0.9641255605381166, "percentage": 19.28, "elapsed_time": "0:12:30", "remaining_time": "0:52:20", "throughput": 7041.98, "total_tokens": 5283840} {"current_steps": 646, "total_steps": 3345, "loss": 1.0562, "lr": 2.276905297291035e-06, "epoch": 0.9656203288490284, "percentage": 19.31, "elapsed_time": "0:12:31", "remaining_time": "0:52:19", "throughput": 7042.0, "total_tokens": 5292032} {"current_steps": 647, "total_steps": 3345, "loss": 1.0703, "lr": 2.2762354673639213e-06, "epoch": 0.9671150971599403, "percentage": 19.34, "elapsed_time": "0:12:32", "remaining_time": "0:52:18", "throughput": 7042.02, "total_tokens": 5300224} {"current_steps": 648, "total_steps": 3345, "loss": 1.4556, "lr": 2.275564732216081e-06, "epoch": 0.968609865470852, "percentage": 19.37, "elapsed_time": "0:12:33", "remaining_time": "0:52:17", "throughput": 7042.03, "total_tokens": 5308416} {"current_steps": 649, "total_steps": 3345, "loss": 1.2362, "lr": 2.2748930924391556e-06, "epoch": 0.9701046337817638, "percentage": 19.4, "elapsed_time": "0:12:34", "remaining_time": "0:52:16", "throughput": 7042.07, "total_tokens": 5316608} {"current_steps": 650, "total_steps": 3345, "loss": 1.0507, "lr": 2.274220548625584e-06, "epoch": 0.9715994020926756, "percentage": 19.43, "elapsed_time": "0:12:36", "remaining_time": "0:52:15", "throughput": 7042.09, "total_tokens": 5324800} {"current_steps": 651, "total_steps": 3345, "loss": 1.4144, "lr": 2.2735471013686037e-06, "epoch": 0.9730941704035875, "percentage": 19.46, "elapsed_time": "0:12:37", "remaining_time": "0:52:13", "throughput": 7042.09, "total_tokens": 5332992} {"current_steps": 652, "total_steps": 3345, "loss": 1.2807, "lr": 2.272872751262248e-06, "epoch": 0.9745889387144993, "percentage": 19.49, "elapsed_time": "0:12:38", "remaining_time": "0:52:12", "throughput": 7042.11, "total_tokens": 5341184} {"current_steps": 653, "total_steps": 3345, "loss": 1.3781, "lr": 2.272197498901346e-06, "epoch": 0.976083707025411, "percentage": 19.52, "elapsed_time": "0:12:39", "remaining_time": "0:52:11", "throughput": 7042.14, "total_tokens": 5349376} {"current_steps": 654, "total_steps": 3345, "loss": 1.1453, "lr": 2.2715213448815255e-06, "epoch": 0.9775784753363229, "percentage": 19.55, "elapsed_time": "0:12:40", "remaining_time": "0:52:10", "throughput": 7042.26, "total_tokens": 5357568} {"current_steps": 655, "total_steps": 3345, "loss": 1.4255, "lr": 2.270844289799206e-06, "epoch": 0.9790732436472347, "percentage": 19.58, "elapsed_time": "0:12:41", "remaining_time": "0:52:09", "throughput": 7042.3, "total_tokens": 5365760} {"current_steps": 656, "total_steps": 3345, "loss": 1.3419, "lr": 2.2701663342516043e-06, "epoch": 0.9805680119581465, "percentage": 19.61, "elapsed_time": "0:12:43", "remaining_time": "0:52:07", "throughput": 7042.3, "total_tokens": 5373952} {"current_steps": 657, "total_steps": 3345, "loss": 1.447, "lr": 2.269487478836731e-06, "epoch": 0.9820627802690582, "percentage": 19.64, "elapsed_time": "0:12:44", "remaining_time": "0:52:06", "throughput": 7042.32, "total_tokens": 5382144} {"current_steps": 658, "total_steps": 3345, "loss": 1.2545, "lr": 2.2688077241533895e-06, "epoch": 0.9835575485799701, "percentage": 19.67, "elapsed_time": "0:12:45", "remaining_time": "0:52:05", "throughput": 7042.3, "total_tokens": 5390336} {"current_steps": 659, "total_steps": 3345, "loss": 1.2755, "lr": 2.2681270708011776e-06, "epoch": 0.9850523168908819, "percentage": 19.7, "elapsed_time": "0:12:46", "remaining_time": "0:52:04", "throughput": 7042.33, "total_tokens": 5398528} {"current_steps": 660, "total_steps": 3345, "loss": 1.1254, "lr": 2.2674455193804857e-06, "epoch": 0.9865470852017937, "percentage": 19.73, "elapsed_time": "0:12:47", "remaining_time": "0:52:03", "throughput": 7042.35, "total_tokens": 5406720} {"current_steps": 661, "total_steps": 3345, "loss": 0.9801, "lr": 2.2667630704924947e-06, "epoch": 0.9880418535127056, "percentage": 19.76, "elapsed_time": "0:12:48", "remaining_time": "0:52:02", "throughput": 7042.38, "total_tokens": 5414912} {"current_steps": 662, "total_steps": 3345, "loss": 1.242, "lr": 2.2660797247391793e-06, "epoch": 0.9895366218236173, "percentage": 19.79, "elapsed_time": "0:12:50", "remaining_time": "0:52:00", "throughput": 7042.42, "total_tokens": 5423104} {"current_steps": 663, "total_steps": 3345, "loss": 1.1746, "lr": 2.2653954827233046e-06, "epoch": 0.9910313901345291, "percentage": 19.82, "elapsed_time": "0:12:51", "remaining_time": "0:51:59", "throughput": 7042.5, "total_tokens": 5431296} {"current_steps": 664, "total_steps": 3345, "loss": 1.3818, "lr": 2.2647103450484256e-06, "epoch": 0.992526158445441, "percentage": 19.85, "elapsed_time": "0:12:52", "remaining_time": "0:51:58", "throughput": 7042.57, "total_tokens": 5439488} {"current_steps": 665, "total_steps": 3345, "loss": 1.3323, "lr": 2.2640243123188884e-06, "epoch": 0.9940209267563528, "percentage": 19.88, "elapsed_time": "0:12:53", "remaining_time": "0:51:57", "throughput": 7042.64, "total_tokens": 5447680} {"current_steps": 666, "total_steps": 3345, "loss": 1.2564, "lr": 2.2633373851398273e-06, "epoch": 0.9955156950672646, "percentage": 19.91, "elapsed_time": "0:12:54", "remaining_time": "0:51:56", "throughput": 7042.71, "total_tokens": 5455872} {"current_steps": 667, "total_steps": 3345, "loss": 1.2066, "lr": 2.262649564117166e-06, "epoch": 0.9970104633781763, "percentage": 19.94, "elapsed_time": "0:12:55", "remaining_time": "0:51:55", "throughput": 7042.74, "total_tokens": 5464064} {"current_steps": 668, "total_steps": 3345, "loss": 1.1303, "lr": 2.261960849857619e-06, "epoch": 0.9985052316890882, "percentage": 19.97, "elapsed_time": "0:12:57", "remaining_time": "0:51:53", "throughput": 7042.79, "total_tokens": 5472256} {"current_steps": 669, "total_steps": 3345, "loss": 1.1075, "lr": 2.2612712429686846e-06, "epoch": 1.0, "percentage": 20.0, "elapsed_time": "0:12:58", "remaining_time": "0:51:52", "throughput": 7043.01, "total_tokens": 5480448} {"current_steps": 670, "total_steps": 3345, "loss": 0.8495, "lr": 2.2605807440586516e-06, "epoch": 1.0014947683109119, "percentage": 20.03, "elapsed_time": "0:12:59", "remaining_time": "0:51:51", "throughput": 7042.89, "total_tokens": 5488640} {"current_steps": 671, "total_steps": 3345, "loss": 0.8293, "lr": 2.2598893537365934e-06, "epoch": 1.0029895366218236, "percentage": 20.06, "elapsed_time": "0:13:00", "remaining_time": "0:51:50", "throughput": 7042.9, "total_tokens": 5496832} {"current_steps": 672, "total_steps": 3345, "loss": 0.4843, "lr": 2.2591970726123725e-06, "epoch": 1.0044843049327354, "percentage": 20.09, "elapsed_time": "0:13:01", "remaining_time": "0:51:49", "throughput": 7042.95, "total_tokens": 5505024} {"current_steps": 673, "total_steps": 3345, "loss": 0.888, "lr": 2.258503901296634e-06, "epoch": 1.0059790732436473, "percentage": 20.12, "elapsed_time": "0:13:02", "remaining_time": "0:51:48", "throughput": 7042.79, "total_tokens": 5513216} {"current_steps": 674, "total_steps": 3345, "loss": 0.9518, "lr": 2.2578098404008112e-06, "epoch": 1.007473841554559, "percentage": 20.15, "elapsed_time": "0:13:03", "remaining_time": "0:51:46", "throughput": 7042.83, "total_tokens": 5521408} {"current_steps": 675, "total_steps": 3345, "loss": 0.7609, "lr": 2.2571148905371197e-06, "epoch": 1.0089686098654709, "percentage": 20.18, "elapsed_time": "0:13:05", "remaining_time": "0:51:45", "throughput": 7042.86, "total_tokens": 5529600} {"current_steps": 676, "total_steps": 3345, "loss": 0.7529, "lr": 2.2564190523185604e-06, "epoch": 1.0104633781763828, "percentage": 20.21, "elapsed_time": "0:13:06", "remaining_time": "0:51:44", "throughput": 7042.9, "total_tokens": 5537792} {"current_steps": 677, "total_steps": 3345, "loss": 0.9406, "lr": 2.2557223263589172e-06, "epoch": 1.0119581464872944, "percentage": 20.24, "elapsed_time": "0:13:07", "remaining_time": "0:51:43", "throughput": 7042.95, "total_tokens": 5545984} {"current_steps": 678, "total_steps": 3345, "loss": 0.7754, "lr": 2.2550247132727575e-06, "epoch": 1.0134529147982063, "percentage": 20.27, "elapsed_time": "0:13:08", "remaining_time": "0:51:42", "throughput": 7042.97, "total_tokens": 5554176} {"current_steps": 679, "total_steps": 3345, "loss": 1.2127, "lr": 2.254326213675432e-06, "epoch": 1.014947683109118, "percentage": 20.3, "elapsed_time": "0:13:09", "remaining_time": "0:51:40", "throughput": 7042.98, "total_tokens": 5562368} {"current_steps": 680, "total_steps": 3345, "loss": 1.1422, "lr": 2.2536268281830716e-06, "epoch": 1.0164424514200299, "percentage": 20.33, "elapsed_time": "0:13:10", "remaining_time": "0:51:39", "throughput": 7042.95, "total_tokens": 5570560} {"current_steps": 681, "total_steps": 3345, "loss": 0.6858, "lr": 2.25292655741259e-06, "epoch": 1.0179372197309418, "percentage": 20.36, "elapsed_time": "0:13:12", "remaining_time": "0:51:38", "throughput": 7043.01, "total_tokens": 5578752} {"current_steps": 682, "total_steps": 3345, "loss": 0.9548, "lr": 2.25222540198168e-06, "epoch": 1.0194319880418534, "percentage": 20.39, "elapsed_time": "0:13:13", "remaining_time": "0:51:37", "throughput": 7043.02, "total_tokens": 5586944} {"current_steps": 683, "total_steps": 3345, "loss": 0.8213, "lr": 2.2515233625088184e-06, "epoch": 1.0209267563527653, "percentage": 20.42, "elapsed_time": "0:13:14", "remaining_time": "0:51:36", "throughput": 7043.07, "total_tokens": 5595136} {"current_steps": 684, "total_steps": 3345, "loss": 0.8316, "lr": 2.250820439613258e-06, "epoch": 1.0224215246636772, "percentage": 20.45, "elapsed_time": "0:13:15", "remaining_time": "0:51:35", "throughput": 7043.1, "total_tokens": 5603328} {"current_steps": 685, "total_steps": 3345, "loss": 0.9309, "lr": 2.2501166339150323e-06, "epoch": 1.0239162929745889, "percentage": 20.48, "elapsed_time": "0:13:16", "remaining_time": "0:51:33", "throughput": 7043.14, "total_tokens": 5611520} {"current_steps": 686, "total_steps": 3345, "loss": 0.7165, "lr": 2.249411946034954e-06, "epoch": 1.0254110612855007, "percentage": 20.51, "elapsed_time": "0:13:17", "remaining_time": "0:51:32", "throughput": 7043.17, "total_tokens": 5619712} {"current_steps": 687, "total_steps": 3345, "loss": 0.6427, "lr": 2.248706376594613e-06, "epoch": 1.0269058295964126, "percentage": 20.54, "elapsed_time": "0:13:19", "remaining_time": "0:51:31", "throughput": 7043.2, "total_tokens": 5627904} {"current_steps": 688, "total_steps": 3345, "loss": 0.9046, "lr": 2.247999926216378e-06, "epoch": 1.0284005979073243, "percentage": 20.57, "elapsed_time": "0:13:20", "remaining_time": "0:51:30", "throughput": 7043.22, "total_tokens": 5636096} {"current_steps": 689, "total_steps": 3345, "loss": 0.5317, "lr": 2.2472925955233927e-06, "epoch": 1.0298953662182362, "percentage": 20.6, "elapsed_time": "0:13:21", "remaining_time": "0:51:29", "throughput": 7043.25, "total_tokens": 5644288} {"current_steps": 690, "total_steps": 3345, "loss": 0.8307, "lr": 2.24658438513958e-06, "epoch": 1.031390134529148, "percentage": 20.63, "elapsed_time": "0:13:22", "remaining_time": "0:51:28", "throughput": 7043.21, "total_tokens": 5652480} {"current_steps": 691, "total_steps": 3345, "loss": 0.9358, "lr": 2.2458752956896362e-06, "epoch": 1.0328849028400597, "percentage": 20.66, "elapsed_time": "0:13:23", "remaining_time": "0:51:26", "throughput": 7043.26, "total_tokens": 5660672} {"current_steps": 692, "total_steps": 3345, "loss": 0.935, "lr": 2.2451653277990352e-06, "epoch": 1.0343796711509716, "percentage": 20.69, "elapsed_time": "0:13:24", "remaining_time": "0:51:25", "throughput": 7043.27, "total_tokens": 5668864} {"current_steps": 693, "total_steps": 3345, "loss": 0.7766, "lr": 2.244454482094024e-06, "epoch": 1.0358744394618835, "percentage": 20.72, "elapsed_time": "0:13:26", "remaining_time": "0:51:24", "throughput": 7043.28, "total_tokens": 5677056} {"current_steps": 694, "total_steps": 3345, "loss": 0.9246, "lr": 2.2437427592016256e-06, "epoch": 1.0373692077727952, "percentage": 20.75, "elapsed_time": "0:13:27", "remaining_time": "0:51:23", "throughput": 7043.29, "total_tokens": 5685248} {"current_steps": 695, "total_steps": 3345, "loss": 0.9061, "lr": 2.243030159749635e-06, "epoch": 1.038863976083707, "percentage": 20.78, "elapsed_time": "0:13:28", "remaining_time": "0:51:22", "throughput": 7043.33, "total_tokens": 5693440} {"current_steps": 696, "total_steps": 3345, "loss": 0.8714, "lr": 2.242316684366621e-06, "epoch": 1.0403587443946187, "percentage": 20.81, "elapsed_time": "0:13:29", "remaining_time": "0:51:21", "throughput": 7043.35, "total_tokens": 5701632} {"current_steps": 697, "total_steps": 3345, "loss": 0.8871, "lr": 2.2416023336819265e-06, "epoch": 1.0418535127055306, "percentage": 20.84, "elapsed_time": "0:13:30", "remaining_time": "0:51:19", "throughput": 7043.4, "total_tokens": 5709824} {"current_steps": 698, "total_steps": 3345, "loss": 1.0013, "lr": 2.2408871083256637e-06, "epoch": 1.0433482810164425, "percentage": 20.87, "elapsed_time": "0:13:31", "remaining_time": "0:51:18", "throughput": 7043.43, "total_tokens": 5718016} {"current_steps": 699, "total_steps": 3345, "loss": 0.9816, "lr": 2.2401710089287183e-06, "epoch": 1.0448430493273542, "percentage": 20.9, "elapsed_time": "0:13:32", "remaining_time": "0:51:17", "throughput": 7043.46, "total_tokens": 5726208} {"current_steps": 700, "total_steps": 3345, "loss": 0.8737, "lr": 2.2394540361227474e-06, "epoch": 1.046337817638266, "percentage": 20.93, "elapsed_time": "0:13:34", "remaining_time": "0:51:16", "throughput": 7043.47, "total_tokens": 5734400} {"current_steps": 701, "total_steps": 3345, "loss": 0.5322, "lr": 2.2387361905401767e-06, "epoch": 1.047832585949178, "percentage": 20.96, "elapsed_time": "0:13:35", "remaining_time": "0:51:15", "throughput": 7043.51, "total_tokens": 5742592} {"current_steps": 702, "total_steps": 3345, "loss": 0.9539, "lr": 2.2380174728142022e-06, "epoch": 1.0493273542600896, "percentage": 20.99, "elapsed_time": "0:13:36", "remaining_time": "0:51:13", "throughput": 7043.53, "total_tokens": 5750784} {"current_steps": 703, "total_steps": 3345, "loss": 1.1064, "lr": 2.2372978835787914e-06, "epoch": 1.0508221225710015, "percentage": 21.02, "elapsed_time": "0:13:37", "remaining_time": "0:51:12", "throughput": 7043.56, "total_tokens": 5758976} {"current_steps": 704, "total_steps": 3345, "loss": 0.9372, "lr": 2.2365774234686776e-06, "epoch": 1.0523168908819134, "percentage": 21.05, "elapsed_time": "0:13:38", "remaining_time": "0:51:11", "throughput": 7043.54, "total_tokens": 5767168} {"current_steps": 705, "total_steps": 3345, "loss": 0.9915, "lr": 2.235856093119364e-06, "epoch": 1.053811659192825, "percentage": 21.08, "elapsed_time": "0:13:39", "remaining_time": "0:51:10", "throughput": 7043.59, "total_tokens": 5775360} {"current_steps": 706, "total_steps": 3345, "loss": 0.6327, "lr": 2.23513389316712e-06, "epoch": 1.055306427503737, "percentage": 21.11, "elapsed_time": "0:13:41", "remaining_time": "0:51:09", "throughput": 7043.64, "total_tokens": 5783552} {"current_steps": 707, "total_steps": 3345, "loss": 0.7063, "lr": 2.234410824248984e-06, "epoch": 1.0568011958146488, "percentage": 21.14, "elapsed_time": "0:13:42", "remaining_time": "0:51:08", "throughput": 7043.66, "total_tokens": 5791744} {"current_steps": 708, "total_steps": 3345, "loss": 0.9481, "lr": 2.23368688700276e-06, "epoch": 1.0582959641255605, "percentage": 21.17, "elapsed_time": "0:13:43", "remaining_time": "0:51:06", "throughput": 7043.7, "total_tokens": 5799936} {"current_steps": 709, "total_steps": 3345, "loss": 0.8246, "lr": 2.232962082067017e-06, "epoch": 1.0597907324364724, "percentage": 21.2, "elapsed_time": "0:13:44", "remaining_time": "0:51:05", "throughput": 7043.74, "total_tokens": 5808128} {"current_steps": 710, "total_steps": 3345, "loss": 0.7131, "lr": 2.2322364100810913e-06, "epoch": 1.0612855007473843, "percentage": 21.23, "elapsed_time": "0:13:45", "remaining_time": "0:51:04", "throughput": 7043.78, "total_tokens": 5816320} {"current_steps": 711, "total_steps": 3345, "loss": 0.9662, "lr": 2.2315098716850816e-06, "epoch": 1.062780269058296, "percentage": 21.26, "elapsed_time": "0:13:46", "remaining_time": "0:51:03", "throughput": 7043.8, "total_tokens": 5824512} {"current_steps": 712, "total_steps": 3345, "loss": 0.7708, "lr": 2.2307824675198524e-06, "epoch": 1.0642750373692078, "percentage": 21.29, "elapsed_time": "0:13:48", "remaining_time": "0:51:02", "throughput": 7043.83, "total_tokens": 5832704} {"current_steps": 713, "total_steps": 3345, "loss": 0.5539, "lr": 2.230054198227033e-06, "epoch": 1.0657698056801195, "percentage": 21.32, "elapsed_time": "0:13:49", "remaining_time": "0:51:01", "throughput": 7043.86, "total_tokens": 5840896} {"current_steps": 714, "total_steps": 3345, "loss": 0.9789, "lr": 2.229325064449013e-06, "epoch": 1.0672645739910314, "percentage": 21.35, "elapsed_time": "0:13:50", "remaining_time": "0:50:59", "throughput": 7043.88, "total_tokens": 5849088} {"current_steps": 715, "total_steps": 3345, "loss": 1.2027, "lr": 2.2285950668289457e-06, "epoch": 1.0687593423019432, "percentage": 21.38, "elapsed_time": "0:13:51", "remaining_time": "0:50:58", "throughput": 7043.88, "total_tokens": 5857280} {"current_steps": 716, "total_steps": 3345, "loss": 0.896, "lr": 2.227864206010748e-06, "epoch": 1.070254110612855, "percentage": 21.41, "elapsed_time": "0:13:52", "remaining_time": "0:50:57", "throughput": 7043.91, "total_tokens": 5865472} {"current_steps": 717, "total_steps": 3345, "loss": 1.0622, "lr": 2.2271324826390962e-06, "epoch": 1.0717488789237668, "percentage": 21.43, "elapsed_time": "0:13:53", "remaining_time": "0:50:56", "throughput": 7043.94, "total_tokens": 5873664} {"current_steps": 718, "total_steps": 3345, "loss": 0.9864, "lr": 2.2263998973594278e-06, "epoch": 1.0732436472346787, "percentage": 21.46, "elapsed_time": "0:13:55", "remaining_time": "0:50:55", "throughput": 7043.97, "total_tokens": 5881856} {"current_steps": 719, "total_steps": 3345, "loss": 1.0859, "lr": 2.2256664508179414e-06, "epoch": 1.0747384155455904, "percentage": 21.49, "elapsed_time": "0:13:56", "remaining_time": "0:50:53", "throughput": 7043.98, "total_tokens": 5890048} {"current_steps": 720, "total_steps": 3345, "loss": 0.9028, "lr": 2.224932143661594e-06, "epoch": 1.0762331838565022, "percentage": 21.52, "elapsed_time": "0:13:57", "remaining_time": "0:50:52", "throughput": 7044.03, "total_tokens": 5898240} {"current_steps": 721, "total_steps": 3345, "loss": 1.1393, "lr": 2.224196976538104e-06, "epoch": 1.0777279521674141, "percentage": 21.55, "elapsed_time": "0:13:58", "remaining_time": "0:50:51", "throughput": 7044.07, "total_tokens": 5906432} {"current_steps": 722, "total_steps": 3345, "loss": 0.8207, "lr": 2.2234609500959455e-06, "epoch": 1.0792227204783258, "percentage": 21.58, "elapsed_time": "0:13:59", "remaining_time": "0:50:50", "throughput": 7044.07, "total_tokens": 5914624} {"current_steps": 723, "total_steps": 3345, "loss": 0.9732, "lr": 2.2227240649843518e-06, "epoch": 1.0807174887892377, "percentage": 21.61, "elapsed_time": "0:14:00", "remaining_time": "0:50:49", "throughput": 7044.11, "total_tokens": 5922816} {"current_steps": 724, "total_steps": 3345, "loss": 0.7859, "lr": 2.2219863218533144e-06, "epoch": 1.0822122571001496, "percentage": 21.64, "elapsed_time": "0:14:01", "remaining_time": "0:50:48", "throughput": 7044.14, "total_tokens": 5931008} {"current_steps": 725, "total_steps": 3345, "loss": 1.07, "lr": 2.2212477213535814e-06, "epoch": 1.0837070254110612, "percentage": 21.67, "elapsed_time": "0:14:03", "remaining_time": "0:50:46", "throughput": 7044.17, "total_tokens": 5939200} {"current_steps": 726, "total_steps": 3345, "loss": 1.0105, "lr": 2.220508264136656e-06, "epoch": 1.0852017937219731, "percentage": 21.7, "elapsed_time": "0:14:04", "remaining_time": "0:50:45", "throughput": 7044.19, "total_tokens": 5947392} {"current_steps": 727, "total_steps": 3345, "loss": 0.8576, "lr": 2.219767950854798e-06, "epoch": 1.086696562032885, "percentage": 21.73, "elapsed_time": "0:14:05", "remaining_time": "0:50:44", "throughput": 7044.2, "total_tokens": 5955584} {"current_steps": 728, "total_steps": 3345, "loss": 1.2595, "lr": 2.219026782161023e-06, "epoch": 1.0881913303437967, "percentage": 21.76, "elapsed_time": "0:14:06", "remaining_time": "0:50:43", "throughput": 7044.19, "total_tokens": 5963776} {"current_steps": 729, "total_steps": 3345, "loss": 1.0334, "lr": 2.2182847587090987e-06, "epoch": 1.0896860986547086, "percentage": 21.79, "elapsed_time": "0:14:07", "remaining_time": "0:50:42", "throughput": 7044.2, "total_tokens": 5971968} {"current_steps": 730, "total_steps": 3345, "loss": 0.5847, "lr": 2.2175418811535503e-06, "epoch": 1.0911808669656202, "percentage": 21.82, "elapsed_time": "0:14:08", "remaining_time": "0:50:41", "throughput": 7044.22, "total_tokens": 5980160} {"current_steps": 731, "total_steps": 3345, "loss": 0.6871, "lr": 2.216798150149653e-06, "epoch": 1.092675635276532, "percentage": 21.85, "elapsed_time": "0:14:10", "remaining_time": "0:50:39", "throughput": 7044.23, "total_tokens": 5988352} {"current_steps": 732, "total_steps": 3345, "loss": 0.9976, "lr": 2.2160535663534365e-06, "epoch": 1.094170403587444, "percentage": 21.88, "elapsed_time": "0:14:11", "remaining_time": "0:50:38", "throughput": 7044.2, "total_tokens": 5996544} {"current_steps": 733, "total_steps": 3345, "loss": 0.9371, "lr": 2.215308130421683e-06, "epoch": 1.0956651718983557, "percentage": 21.91, "elapsed_time": "0:14:12", "remaining_time": "0:50:37", "throughput": 7044.2, "total_tokens": 6004736} {"current_steps": 734, "total_steps": 3345, "loss": 0.877, "lr": 2.214561843011926e-06, "epoch": 1.0971599402092675, "percentage": 21.94, "elapsed_time": "0:14:13", "remaining_time": "0:50:36", "throughput": 7044.16, "total_tokens": 6012928} {"current_steps": 735, "total_steps": 3345, "loss": 0.7017, "lr": 2.213814704782449e-06, "epoch": 1.0986547085201794, "percentage": 21.97, "elapsed_time": "0:14:14", "remaining_time": "0:50:35", "throughput": 7044.18, "total_tokens": 6021120} {"current_steps": 736, "total_steps": 3345, "loss": 0.9847, "lr": 2.2130667163922876e-06, "epoch": 1.100149476831091, "percentage": 22.0, "elapsed_time": "0:14:15", "remaining_time": "0:50:34", "throughput": 7044.14, "total_tokens": 6029312} {"current_steps": 737, "total_steps": 3345, "loss": 0.9027, "lr": 2.212317878501227e-06, "epoch": 1.101644245142003, "percentage": 22.03, "elapsed_time": "0:14:17", "remaining_time": "0:50:33", "throughput": 7044.02, "total_tokens": 6037504} {"current_steps": 738, "total_steps": 3345, "loss": 1.0074, "lr": 2.2115681917698005e-06, "epoch": 1.1031390134529149, "percentage": 22.06, "elapsed_time": "0:14:18", "remaining_time": "0:50:31", "throughput": 7044.06, "total_tokens": 6045696} {"current_steps": 739, "total_steps": 3345, "loss": 0.8864, "lr": 2.2108176568592914e-06, "epoch": 1.1046337817638265, "percentage": 22.09, "elapsed_time": "0:14:19", "remaining_time": "0:50:30", "throughput": 7044.1, "total_tokens": 6053888} {"current_steps": 740, "total_steps": 3345, "loss": 0.7563, "lr": 2.2100662744317307e-06, "epoch": 1.1061285500747384, "percentage": 22.12, "elapsed_time": "0:14:20", "remaining_time": "0:50:29", "throughput": 7044.13, "total_tokens": 6062080} {"current_steps": 741, "total_steps": 3345, "loss": 1.0246, "lr": 2.2093140451498975e-06, "epoch": 1.1076233183856503, "percentage": 22.15, "elapsed_time": "0:14:21", "remaining_time": "0:50:28", "throughput": 7044.13, "total_tokens": 6070272} {"current_steps": 742, "total_steps": 3345, "loss": 0.701, "lr": 2.2085609696773164e-06, "epoch": 1.109118086696562, "percentage": 22.18, "elapsed_time": "0:14:22", "remaining_time": "0:50:27", "throughput": 7044.16, "total_tokens": 6078464} {"current_steps": 743, "total_steps": 3345, "loss": 0.8307, "lr": 2.2078070486782604e-06, "epoch": 1.1106128550074739, "percentage": 22.21, "elapsed_time": "0:14:24", "remaining_time": "0:50:25", "throughput": 7044.23, "total_tokens": 6086656} {"current_steps": 744, "total_steps": 3345, "loss": 0.7166, "lr": 2.207052282817747e-06, "epoch": 1.1121076233183858, "percentage": 22.24, "elapsed_time": "0:14:25", "remaining_time": "0:50:24", "throughput": 7044.26, "total_tokens": 6094848} {"current_steps": 745, "total_steps": 3345, "loss": 0.8589, "lr": 2.206296672761539e-06, "epoch": 1.1136023916292974, "percentage": 22.27, "elapsed_time": "0:14:26", "remaining_time": "0:50:23", "throughput": 7044.28, "total_tokens": 6103040} {"current_steps": 746, "total_steps": 3345, "loss": 0.9241, "lr": 2.2055402191761454e-06, "epoch": 1.1150971599402093, "percentage": 22.3, "elapsed_time": "0:14:27", "remaining_time": "0:50:22", "throughput": 7044.28, "total_tokens": 6111232} {"current_steps": 747, "total_steps": 3345, "loss": 1.0461, "lr": 2.204782922728816e-06, "epoch": 1.116591928251121, "percentage": 22.33, "elapsed_time": "0:14:28", "remaining_time": "0:50:21", "throughput": 7044.24, "total_tokens": 6119424} {"current_steps": 748, "total_steps": 3345, "loss": 0.8095, "lr": 2.2040247840875477e-06, "epoch": 1.1180866965620329, "percentage": 22.36, "elapsed_time": "0:14:29", "remaining_time": "0:50:20", "throughput": 7044.26, "total_tokens": 6127616} {"current_steps": 749, "total_steps": 3345, "loss": 0.8445, "lr": 2.203265803921078e-06, "epoch": 1.1195814648729447, "percentage": 22.39, "elapsed_time": "0:14:31", "remaining_time": "0:50:19", "throughput": 7044.18, "total_tokens": 6135808} {"current_steps": 750, "total_steps": 3345, "loss": 1.0588, "lr": 2.2025059828988874e-06, "epoch": 1.1210762331838564, "percentage": 22.42, "elapsed_time": "0:14:32", "remaining_time": "0:50:17", "throughput": 7044.13, "total_tokens": 6144000} {"current_steps": 751, "total_steps": 3345, "loss": 0.8745, "lr": 2.201745321691198e-06, "epoch": 1.1225710014947683, "percentage": 22.45, "elapsed_time": "0:14:33", "remaining_time": "0:50:16", "throughput": 7044.18, "total_tokens": 6152192} {"current_steps": 752, "total_steps": 3345, "loss": 0.8061, "lr": 2.200983820968973e-06, "epoch": 1.1240657698056802, "percentage": 22.48, "elapsed_time": "0:14:34", "remaining_time": "0:50:15", "throughput": 7044.13, "total_tokens": 6160384} {"current_steps": 753, "total_steps": 3345, "loss": 1.0602, "lr": 2.2002214814039166e-06, "epoch": 1.1255605381165918, "percentage": 22.51, "elapsed_time": "0:14:35", "remaining_time": "0:50:14", "throughput": 7044.13, "total_tokens": 6168576} {"current_steps": 754, "total_steps": 3345, "loss": 0.8653, "lr": 2.199458303668472e-06, "epoch": 1.1270553064275037, "percentage": 22.54, "elapsed_time": "0:14:36", "remaining_time": "0:50:13", "throughput": 7044.16, "total_tokens": 6176768} {"current_steps": 755, "total_steps": 3345, "loss": 0.9817, "lr": 2.1986942884358224e-06, "epoch": 1.1285500747384156, "percentage": 22.57, "elapsed_time": "0:14:38", "remaining_time": "0:50:12", "throughput": 7044.16, "total_tokens": 6184960} {"current_steps": 756, "total_steps": 3345, "loss": 1.0963, "lr": 2.19792943637989e-06, "epoch": 1.1300448430493273, "percentage": 22.6, "elapsed_time": "0:14:39", "remaining_time": "0:50:10", "throughput": 7044.18, "total_tokens": 6193152} {"current_steps": 757, "total_steps": 3345, "loss": 0.7665, "lr": 2.1971637481753342e-06, "epoch": 1.1315396113602392, "percentage": 22.63, "elapsed_time": "0:14:40", "remaining_time": "0:50:09", "throughput": 7044.13, "total_tokens": 6201344} {"current_steps": 758, "total_steps": 3345, "loss": 0.7927, "lr": 2.196397224497552e-06, "epoch": 1.133034379671151, "percentage": 22.66, "elapsed_time": "0:14:41", "remaining_time": "0:50:08", "throughput": 7044.15, "total_tokens": 6209536} {"current_steps": 759, "total_steps": 3345, "loss": 1.1593, "lr": 2.1956298660226792e-06, "epoch": 1.1345291479820627, "percentage": 22.69, "elapsed_time": "0:14:42", "remaining_time": "0:50:07", "throughput": 7044.17, "total_tokens": 6217728} {"current_steps": 760, "total_steps": 3345, "loss": 0.848, "lr": 2.1948616734275853e-06, "epoch": 1.1360239162929746, "percentage": 22.72, "elapsed_time": "0:14:43", "remaining_time": "0:50:06", "throughput": 7044.19, "total_tokens": 6225920} {"current_steps": 761, "total_steps": 3345, "loss": 0.9107, "lr": 2.194092647389878e-06, "epoch": 1.1375186846038865, "percentage": 22.75, "elapsed_time": "0:14:44", "remaining_time": "0:50:05", "throughput": 7044.23, "total_tokens": 6234112} {"current_steps": 762, "total_steps": 3345, "loss": 1.1238, "lr": 2.1933227885878975e-06, "epoch": 1.1390134529147982, "percentage": 22.78, "elapsed_time": "0:14:46", "remaining_time": "0:50:03", "throughput": 7044.26, "total_tokens": 6242304} {"current_steps": 763, "total_steps": 3345, "loss": 0.883, "lr": 2.1925520977007213e-06, "epoch": 1.14050822122571, "percentage": 22.81, "elapsed_time": "0:14:47", "remaining_time": "0:50:02", "throughput": 7044.26, "total_tokens": 6250496} {"current_steps": 764, "total_steps": 3345, "loss": 0.9244, "lr": 2.1917805754081588e-06, "epoch": 1.1420029895366217, "percentage": 22.84, "elapsed_time": "0:14:48", "remaining_time": "0:50:01", "throughput": 7044.27, "total_tokens": 6258688} {"current_steps": 765, "total_steps": 3345, "loss": 1.0988, "lr": 2.1910082223907543e-06, "epoch": 1.1434977578475336, "percentage": 22.87, "elapsed_time": "0:14:49", "remaining_time": "0:50:00", "throughput": 7044.3, "total_tokens": 6266880} {"current_steps": 766, "total_steps": 3345, "loss": 1.1902, "lr": 2.1902350393297838e-06, "epoch": 1.1449925261584455, "percentage": 22.9, "elapsed_time": "0:14:50", "remaining_time": "0:49:59", "throughput": 7044.3, "total_tokens": 6275072} {"current_steps": 767, "total_steps": 3345, "loss": 0.7715, "lr": 2.189461026907256e-06, "epoch": 1.1464872944693572, "percentage": 22.93, "elapsed_time": "0:14:51", "remaining_time": "0:49:58", "throughput": 7044.31, "total_tokens": 6283264} {"current_steps": 768, "total_steps": 3345, "loss": 0.8523, "lr": 2.1886861858059104e-06, "epoch": 1.147982062780269, "percentage": 22.96, "elapsed_time": "0:14:53", "remaining_time": "0:49:56", "throughput": 7044.35, "total_tokens": 6291456} {"current_steps": 769, "total_steps": 3345, "loss": 0.8858, "lr": 2.187910516709219e-06, "epoch": 1.149476831091181, "percentage": 22.99, "elapsed_time": "0:14:54", "remaining_time": "0:49:55", "throughput": 7044.38, "total_tokens": 6299648} {"current_steps": 770, "total_steps": 3345, "loss": 0.9112, "lr": 2.1871340203013827e-06, "epoch": 1.1509715994020926, "percentage": 23.02, "elapsed_time": "0:14:55", "remaining_time": "0:49:54", "throughput": 7044.38, "total_tokens": 6307840} {"current_steps": 771, "total_steps": 3345, "loss": 0.8237, "lr": 2.1863566972673324e-06, "epoch": 1.1524663677130045, "percentage": 23.05, "elapsed_time": "0:14:56", "remaining_time": "0:49:53", "throughput": 7044.42, "total_tokens": 6316032} {"current_steps": 772, "total_steps": 3345, "loss": 0.838, "lr": 2.185578548292729e-06, "epoch": 1.1539611360239164, "percentage": 23.08, "elapsed_time": "0:14:57", "remaining_time": "0:49:52", "throughput": 7044.48, "total_tokens": 6324224} {"current_steps": 773, "total_steps": 3345, "loss": 0.6564, "lr": 2.1847995740639605e-06, "epoch": 1.155455904334828, "percentage": 23.11, "elapsed_time": "0:14:58", "remaining_time": "0:49:50", "throughput": 7044.5, "total_tokens": 6332416} {"current_steps": 774, "total_steps": 3345, "loss": 0.892, "lr": 2.184019775268145e-06, "epoch": 1.15695067264574, "percentage": 23.14, "elapsed_time": "0:15:00", "remaining_time": "0:49:49", "throughput": 7044.54, "total_tokens": 6340608} {"current_steps": 775, "total_steps": 3345, "loss": 0.8165, "lr": 2.183239152593125e-06, "epoch": 1.1584454409566518, "percentage": 23.17, "elapsed_time": "0:15:01", "remaining_time": "0:49:48", "throughput": 7044.57, "total_tokens": 6348800} {"current_steps": 776, "total_steps": 3345, "loss": 0.7876, "lr": 2.182457706727472e-06, "epoch": 1.1599402092675635, "percentage": 23.2, "elapsed_time": "0:15:02", "remaining_time": "0:49:47", "throughput": 7044.57, "total_tokens": 6356992} {"current_steps": 777, "total_steps": 3345, "loss": 0.7526, "lr": 2.181675438360484e-06, "epoch": 1.1614349775784754, "percentage": 23.23, "elapsed_time": "0:15:03", "remaining_time": "0:49:46", "throughput": 7044.6, "total_tokens": 6365184} {"current_steps": 778, "total_steps": 3345, "loss": 1.0234, "lr": 2.180892348182182e-06, "epoch": 1.1629297458893872, "percentage": 23.26, "elapsed_time": "0:15:04", "remaining_time": "0:49:45", "throughput": 7044.62, "total_tokens": 6373376} {"current_steps": 779, "total_steps": 3345, "loss": 0.5844, "lr": 2.180108436883314e-06, "epoch": 1.164424514200299, "percentage": 23.29, "elapsed_time": "0:15:05", "remaining_time": "0:49:43", "throughput": 7044.64, "total_tokens": 6381568} {"current_steps": 780, "total_steps": 3345, "loss": 0.9119, "lr": 2.1793237051553517e-06, "epoch": 1.1659192825112108, "percentage": 23.32, "elapsed_time": "0:15:07", "remaining_time": "0:49:42", "throughput": 7044.62, "total_tokens": 6389760} {"current_steps": 781, "total_steps": 3345, "loss": 0.8476, "lr": 2.1785381536904905e-06, "epoch": 1.1674140508221225, "percentage": 23.35, "elapsed_time": "0:15:08", "remaining_time": "0:49:41", "throughput": 7044.66, "total_tokens": 6397952} {"current_steps": 782, "total_steps": 3345, "loss": 0.7794, "lr": 2.1777517831816486e-06, "epoch": 1.1689088191330343, "percentage": 23.38, "elapsed_time": "0:15:09", "remaining_time": "0:49:40", "throughput": 7044.67, "total_tokens": 6406144} {"current_steps": 783, "total_steps": 3345, "loss": 0.9305, "lr": 2.176964594322467e-06, "epoch": 1.1704035874439462, "percentage": 23.41, "elapsed_time": "0:15:10", "remaining_time": "0:49:39", "throughput": 7044.69, "total_tokens": 6414336} {"current_steps": 784, "total_steps": 3345, "loss": 0.6844, "lr": 2.1761765878073087e-06, "epoch": 1.171898355754858, "percentage": 23.44, "elapsed_time": "0:15:11", "remaining_time": "0:49:38", "throughput": 7044.69, "total_tokens": 6422528} {"current_steps": 785, "total_steps": 3345, "loss": 1.0833, "lr": 2.1753877643312577e-06, "epoch": 1.1733931240657698, "percentage": 23.47, "elapsed_time": "0:15:12", "remaining_time": "0:49:36", "throughput": 7044.65, "total_tokens": 6430720} {"current_steps": 786, "total_steps": 3345, "loss": 0.8449, "lr": 2.1745981245901176e-06, "epoch": 1.1748878923766817, "percentage": 23.5, "elapsed_time": "0:15:14", "remaining_time": "0:49:35", "throughput": 7044.68, "total_tokens": 6438912} {"current_steps": 787, "total_steps": 3345, "loss": 1.0192, "lr": 2.1738076692804145e-06, "epoch": 1.1763826606875933, "percentage": 23.53, "elapsed_time": "0:15:15", "remaining_time": "0:49:34", "throughput": 7044.7, "total_tokens": 6447104} {"current_steps": 788, "total_steps": 3345, "loss": 0.9555, "lr": 2.173016399099391e-06, "epoch": 1.1778774289985052, "percentage": 23.56, "elapsed_time": "0:15:16", "remaining_time": "0:49:33", "throughput": 7044.72, "total_tokens": 6455296} {"current_steps": 789, "total_steps": 3345, "loss": 0.9043, "lr": 2.1722243147450113e-06, "epoch": 1.1793721973094171, "percentage": 23.59, "elapsed_time": "0:15:17", "remaining_time": "0:49:32", "throughput": 7044.74, "total_tokens": 6463488} {"current_steps": 790, "total_steps": 3345, "loss": 0.7436, "lr": 2.171431416915955e-06, "epoch": 1.1808669656203288, "percentage": 23.62, "elapsed_time": "0:15:18", "remaining_time": "0:49:31", "throughput": 7044.77, "total_tokens": 6471680} {"current_steps": 791, "total_steps": 3345, "loss": 0.9603, "lr": 2.170637706311621e-06, "epoch": 1.1823617339312407, "percentage": 23.65, "elapsed_time": "0:15:19", "remaining_time": "0:49:29", "throughput": 7044.8, "total_tokens": 6479872} {"current_steps": 792, "total_steps": 3345, "loss": 1.0046, "lr": 2.1698431836321255e-06, "epoch": 1.1838565022421526, "percentage": 23.68, "elapsed_time": "0:15:20", "remaining_time": "0:49:28", "throughput": 7044.84, "total_tokens": 6488064} {"current_steps": 793, "total_steps": 3345, "loss": 1.014, "lr": 2.1690478495782996e-06, "epoch": 1.1853512705530642, "percentage": 23.71, "elapsed_time": "0:15:22", "remaining_time": "0:49:27", "throughput": 7044.88, "total_tokens": 6496256} {"current_steps": 794, "total_steps": 3345, "loss": 0.8789, "lr": 2.168251704851691e-06, "epoch": 1.186846038863976, "percentage": 23.74, "elapsed_time": "0:15:23", "remaining_time": "0:49:26", "throughput": 7044.84, "total_tokens": 6504448} {"current_steps": 795, "total_steps": 3345, "loss": 0.9675, "lr": 2.167454750154562e-06, "epoch": 1.188340807174888, "percentage": 23.77, "elapsed_time": "0:15:24", "remaining_time": "0:49:25", "throughput": 7044.87, "total_tokens": 6512640} {"current_steps": 796, "total_steps": 3345, "loss": 1.2538, "lr": 2.166656986189889e-06, "epoch": 1.1898355754857997, "percentage": 23.8, "elapsed_time": "0:15:25", "remaining_time": "0:49:24", "throughput": 7044.92, "total_tokens": 6520832} {"current_steps": 797, "total_steps": 3345, "loss": 0.9065, "lr": 2.1658584136613643e-06, "epoch": 1.1913303437967115, "percentage": 23.83, "elapsed_time": "0:15:26", "remaining_time": "0:49:22", "throughput": 7044.97, "total_tokens": 6529024} {"current_steps": 798, "total_steps": 3345, "loss": 0.985, "lr": 2.1650590332733907e-06, "epoch": 1.1928251121076232, "percentage": 23.86, "elapsed_time": "0:15:27", "remaining_time": "0:49:21", "throughput": 7044.98, "total_tokens": 6537216} {"current_steps": 799, "total_steps": 3345, "loss": 0.9108, "lr": 2.164258845731085e-06, "epoch": 1.194319880418535, "percentage": 23.89, "elapsed_time": "0:15:29", "remaining_time": "0:49:20", "throughput": 7045.0, "total_tokens": 6545408} {"current_steps": 800, "total_steps": 3345, "loss": 0.8731, "lr": 2.163457851740276e-06, "epoch": 1.195814648729447, "percentage": 23.92, "elapsed_time": "0:15:30", "remaining_time": "0:49:19", "throughput": 7045.02, "total_tokens": 6553600} {"current_steps": 801, "total_steps": 3345, "loss": 1.0263, "lr": 2.162656052007504e-06, "epoch": 1.1973094170403586, "percentage": 23.95, "elapsed_time": "0:15:31", "remaining_time": "0:49:18", "throughput": 7045.01, "total_tokens": 6561792} {"current_steps": 802, "total_steps": 3345, "loss": 0.8214, "lr": 2.1618534472400197e-06, "epoch": 1.1988041853512705, "percentage": 23.98, "elapsed_time": "0:15:32", "remaining_time": "0:49:17", "throughput": 7045.02, "total_tokens": 6569984} {"current_steps": 803, "total_steps": 3345, "loss": 0.6386, "lr": 2.1610500381457834e-06, "epoch": 1.2002989536621824, "percentage": 24.01, "elapsed_time": "0:15:33", "remaining_time": "0:49:15", "throughput": 7045.04, "total_tokens": 6578176} {"current_steps": 804, "total_steps": 3345, "loss": 0.9945, "lr": 2.160245825433465e-06, "epoch": 1.201793721973094, "percentage": 24.04, "elapsed_time": "0:15:34", "remaining_time": "0:49:14", "throughput": 7045.07, "total_tokens": 6586368} {"current_steps": 805, "total_steps": 3345, "loss": 1.0806, "lr": 2.1594408098124445e-06, "epoch": 1.203288490284006, "percentage": 24.07, "elapsed_time": "0:15:36", "remaining_time": "0:49:13", "throughput": 7045.05, "total_tokens": 6594560} {"current_steps": 806, "total_steps": 3345, "loss": 0.7377, "lr": 2.158634991992809e-06, "epoch": 1.2047832585949179, "percentage": 24.1, "elapsed_time": "0:15:37", "remaining_time": "0:49:12", "throughput": 7045.09, "total_tokens": 6602752} {"current_steps": 807, "total_steps": 3345, "loss": 1.0696, "lr": 2.1578283726853533e-06, "epoch": 1.2062780269058295, "percentage": 24.13, "elapsed_time": "0:15:38", "remaining_time": "0:49:11", "throughput": 7045.11, "total_tokens": 6610944} {"current_steps": 808, "total_steps": 3345, "loss": 0.7352, "lr": 2.1570209526015794e-06, "epoch": 1.2077727952167414, "percentage": 24.16, "elapsed_time": "0:15:39", "remaining_time": "0:49:09", "throughput": 7045.15, "total_tokens": 6619136} {"current_steps": 809, "total_steps": 3345, "loss": 1.0742, "lr": 2.1562127324536952e-06, "epoch": 1.2092675635276533, "percentage": 24.19, "elapsed_time": "0:15:40", "remaining_time": "0:49:08", "throughput": 7045.08, "total_tokens": 6627328} {"current_steps": 810, "total_steps": 3345, "loss": 1.0762, "lr": 2.1554037129546155e-06, "epoch": 1.210762331838565, "percentage": 24.22, "elapsed_time": "0:15:41", "remaining_time": "0:49:07", "throughput": 7045.13, "total_tokens": 6635520} {"current_steps": 811, "total_steps": 3345, "loss": 0.7626, "lr": 2.154593894817959e-06, "epoch": 1.2122571001494769, "percentage": 24.25, "elapsed_time": "0:15:43", "remaining_time": "0:49:06", "throughput": 7045.19, "total_tokens": 6643712} {"current_steps": 812, "total_steps": 3345, "loss": 1.1006, "lr": 2.153783278758049e-06, "epoch": 1.2137518684603887, "percentage": 24.28, "elapsed_time": "0:15:44", "remaining_time": "0:49:05", "throughput": 7045.25, "total_tokens": 6651904} {"current_steps": 813, "total_steps": 3345, "loss": 0.884, "lr": 2.1529718654899127e-06, "epoch": 1.2152466367713004, "percentage": 24.3, "elapsed_time": "0:15:45", "remaining_time": "0:49:04", "throughput": 7045.32, "total_tokens": 6660096} {"current_steps": 814, "total_steps": 3345, "loss": 1.0928, "lr": 2.1521596557292816e-06, "epoch": 1.2167414050822123, "percentage": 24.33, "elapsed_time": "0:15:46", "remaining_time": "0:49:02", "throughput": 7045.34, "total_tokens": 6668288} {"current_steps": 815, "total_steps": 3345, "loss": 1.1909, "lr": 2.1513466501925883e-06, "epoch": 1.218236173393124, "percentage": 24.36, "elapsed_time": "0:15:47", "remaining_time": "0:49:01", "throughput": 7045.35, "total_tokens": 6676480} {"current_steps": 816, "total_steps": 3345, "loss": 0.6835, "lr": 2.150532849596968e-06, "epoch": 1.2197309417040358, "percentage": 24.39, "elapsed_time": "0:15:48", "remaining_time": "0:49:00", "throughput": 7045.39, "total_tokens": 6684672} {"current_steps": 817, "total_steps": 3345, "loss": 0.932, "lr": 2.1497182546602565e-06, "epoch": 1.2212257100149477, "percentage": 24.42, "elapsed_time": "0:15:49", "remaining_time": "0:48:59", "throughput": 7045.41, "total_tokens": 6692864} {"current_steps": 818, "total_steps": 3345, "loss": 1.0113, "lr": 2.1489028661009916e-06, "epoch": 1.2227204783258596, "percentage": 24.45, "elapsed_time": "0:15:51", "remaining_time": "0:48:58", "throughput": 7045.44, "total_tokens": 6701056} {"current_steps": 819, "total_steps": 3345, "loss": 0.8469, "lr": 2.1480866846384102e-06, "epoch": 1.2242152466367713, "percentage": 24.48, "elapsed_time": "0:15:52", "remaining_time": "0:48:57", "throughput": 7045.46, "total_tokens": 6709248} {"current_steps": 820, "total_steps": 3345, "loss": 0.9339, "lr": 2.147269710992449e-06, "epoch": 1.2257100149476832, "percentage": 24.51, "elapsed_time": "0:15:53", "remaining_time": "0:48:55", "throughput": 7045.49, "total_tokens": 6717440} {"current_steps": 821, "total_steps": 3345, "loss": 0.8995, "lr": 2.146451945883743e-06, "epoch": 1.2272047832585948, "percentage": 24.54, "elapsed_time": "0:15:54", "remaining_time": "0:48:54", "throughput": 7045.49, "total_tokens": 6725632} {"current_steps": 822, "total_steps": 3345, "loss": 0.8767, "lr": 2.145633390033625e-06, "epoch": 1.2286995515695067, "percentage": 24.57, "elapsed_time": "0:15:55", "remaining_time": "0:48:53", "throughput": 7045.51, "total_tokens": 6733824} {"current_steps": 823, "total_steps": 3345, "loss": 0.874, "lr": 2.1448140441641274e-06, "epoch": 1.2301943198804186, "percentage": 24.6, "elapsed_time": "0:15:56", "remaining_time": "0:48:52", "throughput": 7045.52, "total_tokens": 6742016} {"current_steps": 824, "total_steps": 3345, "loss": 1.1185, "lr": 2.143993908997977e-06, "epoch": 1.2316890881913303, "percentage": 24.63, "elapsed_time": "0:15:58", "remaining_time": "0:48:51", "throughput": 7045.52, "total_tokens": 6750208} {"current_steps": 825, "total_steps": 3345, "loss": 1.2735, "lr": 2.1431729852585977e-06, "epoch": 1.2331838565022422, "percentage": 24.66, "elapsed_time": "0:15:59", "remaining_time": "0:48:50", "throughput": 7045.54, "total_tokens": 6758400} {"current_steps": 826, "total_steps": 3345, "loss": 1.0645, "lr": 2.1423512736701087e-06, "epoch": 1.234678624813154, "percentage": 24.69, "elapsed_time": "0:16:00", "remaining_time": "0:48:48", "throughput": 7045.55, "total_tokens": 6766592} {"current_steps": 827, "total_steps": 3345, "loss": 0.9357, "lr": 2.1415287749573257e-06, "epoch": 1.2361733931240657, "percentage": 24.72, "elapsed_time": "0:16:01", "remaining_time": "0:48:47", "throughput": 7045.56, "total_tokens": 6774784} {"current_steps": 828, "total_steps": 3345, "loss": 0.9033, "lr": 2.140705489845757e-06, "epoch": 1.2376681614349776, "percentage": 24.75, "elapsed_time": "0:16:02", "remaining_time": "0:48:46", "throughput": 7045.55, "total_tokens": 6782976} {"current_steps": 829, "total_steps": 3345, "loss": 0.9474, "lr": 2.139881419061605e-06, "epoch": 1.2391629297458895, "percentage": 24.78, "elapsed_time": "0:16:03", "remaining_time": "0:48:45", "throughput": 7045.54, "total_tokens": 6791168} {"current_steps": 830, "total_steps": 3345, "loss": 0.8628, "lr": 2.1390565633317647e-06, "epoch": 1.2406576980568012, "percentage": 24.81, "elapsed_time": "0:16:05", "remaining_time": "0:48:44", "throughput": 7045.56, "total_tokens": 6799360} {"current_steps": 831, "total_steps": 3345, "loss": 1.0098, "lr": 2.138230923383825e-06, "epoch": 1.242152466367713, "percentage": 24.84, "elapsed_time": "0:16:06", "remaining_time": "0:48:43", "throughput": 7045.56, "total_tokens": 6807552} {"current_steps": 832, "total_steps": 3345, "loss": 0.8756, "lr": 2.1374044999460646e-06, "epoch": 1.2436472346786247, "percentage": 24.87, "elapsed_time": "0:16:07", "remaining_time": "0:48:41", "throughput": 7045.57, "total_tokens": 6815744} {"current_steps": 833, "total_steps": 3345, "loss": 0.9093, "lr": 2.136577293747455e-06, "epoch": 1.2451420029895366, "percentage": 24.9, "elapsed_time": "0:16:08", "remaining_time": "0:48:40", "throughput": 7045.59, "total_tokens": 6823936} {"current_steps": 834, "total_steps": 3345, "loss": 0.8864, "lr": 2.135749305517657e-06, "epoch": 1.2466367713004485, "percentage": 24.93, "elapsed_time": "0:16:09", "remaining_time": "0:48:39", "throughput": 7045.61, "total_tokens": 6832128} {"current_steps": 835, "total_steps": 3345, "loss": 0.7884, "lr": 2.134920535987022e-06, "epoch": 1.2481315396113604, "percentage": 24.96, "elapsed_time": "0:16:10", "remaining_time": "0:48:38", "throughput": 7045.61, "total_tokens": 6840320} {"current_steps": 836, "total_steps": 3345, "loss": 0.8046, "lr": 2.1340909858865892e-06, "epoch": 1.249626307922272, "percentage": 24.99, "elapsed_time": "0:16:12", "remaining_time": "0:48:37", "throughput": 7045.62, "total_tokens": 6848512} {"current_steps": 837, "total_steps": 3345, "loss": 0.944, "lr": 2.1332606559480883e-06, "epoch": 1.251121076233184, "percentage": 25.02, "elapsed_time": "0:16:13", "remaining_time": "0:48:36", "throughput": 7045.59, "total_tokens": 6856704} {"current_steps": 838, "total_steps": 3345, "loss": 0.9118, "lr": 2.1324295469039353e-06, "epoch": 1.2526158445440956, "percentage": 25.05, "elapsed_time": "0:16:14", "remaining_time": "0:48:34", "throughput": 7045.55, "total_tokens": 6864896} {"current_steps": 839, "total_steps": 3345, "loss": 0.8194, "lr": 2.1315976594872347e-06, "epoch": 1.2541106128550075, "percentage": 25.08, "elapsed_time": "0:16:15", "remaining_time": "0:48:33", "throughput": 7045.33, "total_tokens": 6873088} {"current_steps": 840, "total_steps": 3345, "loss": 0.904, "lr": 2.130764994431776e-06, "epoch": 1.2556053811659194, "percentage": 25.11, "elapsed_time": "0:16:16", "remaining_time": "0:48:32", "throughput": 7045.37, "total_tokens": 6881280} {"current_steps": 841, "total_steps": 3345, "loss": 0.8557, "lr": 2.129931552472036e-06, "epoch": 1.257100149476831, "percentage": 25.14, "elapsed_time": "0:16:17", "remaining_time": "0:48:31", "throughput": 7045.39, "total_tokens": 6889472} {"current_steps": 842, "total_steps": 3345, "loss": 0.9875, "lr": 2.1290973343431766e-06, "epoch": 1.258594917787743, "percentage": 25.17, "elapsed_time": "0:16:19", "remaining_time": "0:48:30", "throughput": 7045.39, "total_tokens": 6897664} {"current_steps": 843, "total_steps": 3345, "loss": 0.7632, "lr": 2.1282623407810434e-06, "epoch": 1.2600896860986546, "percentage": 25.2, "elapsed_time": "0:16:20", "remaining_time": "0:48:29", "throughput": 7045.43, "total_tokens": 6905856} {"current_steps": 844, "total_steps": 3345, "loss": 0.772, "lr": 2.127426572522167e-06, "epoch": 1.2615844544095665, "percentage": 25.23, "elapsed_time": "0:16:21", "remaining_time": "0:48:28", "throughput": 7045.4, "total_tokens": 6914048} {"current_steps": 845, "total_steps": 3345, "loss": 0.8869, "lr": 2.1265900303037614e-06, "epoch": 1.2630792227204783, "percentage": 25.26, "elapsed_time": "0:16:22", "remaining_time": "0:48:26", "throughput": 7045.39, "total_tokens": 6922240} {"current_steps": 846, "total_steps": 3345, "loss": 0.7646, "lr": 2.1257527148637223e-06, "epoch": 1.2645739910313902, "percentage": 25.29, "elapsed_time": "0:16:23", "remaining_time": "0:48:25", "throughput": 7045.29, "total_tokens": 6930432} {"current_steps": 847, "total_steps": 3345, "loss": 0.7522, "lr": 2.1249146269406285e-06, "epoch": 1.266068759342302, "percentage": 25.32, "elapsed_time": "0:16:24", "remaining_time": "0:48:24", "throughput": 7045.3, "total_tokens": 6938624} {"current_steps": 848, "total_steps": 3345, "loss": 0.7609, "lr": 2.1240757672737394e-06, "epoch": 1.2675635276532138, "percentage": 25.35, "elapsed_time": "0:16:26", "remaining_time": "0:48:23", "throughput": 7045.25, "total_tokens": 6946816} {"current_steps": 849, "total_steps": 3345, "loss": 0.7955, "lr": 2.1232361366029956e-06, "epoch": 1.2690582959641254, "percentage": 25.38, "elapsed_time": "0:16:27", "remaining_time": "0:48:22", "throughput": 7045.21, "total_tokens": 6955008} {"current_steps": 850, "total_steps": 3345, "loss": 1.0406, "lr": 2.1223957356690176e-06, "epoch": 1.2705530642750373, "percentage": 25.41, "elapsed_time": "0:16:28", "remaining_time": "0:48:21", "throughput": 7045.08, "total_tokens": 6963200} {"current_steps": 851, "total_steps": 3345, "loss": 0.9267, "lr": 2.1215545652131054e-06, "epoch": 1.2720478325859492, "percentage": 25.44, "elapsed_time": "0:16:29", "remaining_time": "0:48:20", "throughput": 7045.1, "total_tokens": 6971392} {"current_steps": 852, "total_steps": 3345, "loss": 1.0772, "lr": 2.1207126259772383e-06, "epoch": 1.273542600896861, "percentage": 25.47, "elapsed_time": "0:16:30", "remaining_time": "0:48:18", "throughput": 7045.14, "total_tokens": 6979584} {"current_steps": 853, "total_steps": 3345, "loss": 0.7631, "lr": 2.119869918704072e-06, "epoch": 1.2750373692077728, "percentage": 25.5, "elapsed_time": "0:16:31", "remaining_time": "0:48:17", "throughput": 7045.14, "total_tokens": 6987776} {"current_steps": 854, "total_steps": 3345, "loss": 0.9288, "lr": 2.1190264441369417e-06, "epoch": 1.2765321375186847, "percentage": 25.53, "elapsed_time": "0:16:33", "remaining_time": "0:48:16", "throughput": 7045.17, "total_tokens": 6995968} {"current_steps": 855, "total_steps": 3345, "loss": 0.8539, "lr": 2.118182203019859e-06, "epoch": 1.2780269058295963, "percentage": 25.56, "elapsed_time": "0:16:34", "remaining_time": "0:48:15", "throughput": 7045.13, "total_tokens": 7004160} {"current_steps": 856, "total_steps": 3345, "loss": 1.1166, "lr": 2.1173371960975103e-06, "epoch": 1.2795216741405082, "percentage": 25.59, "elapsed_time": "0:16:35", "remaining_time": "0:48:14", "throughput": 7045.16, "total_tokens": 7012352} {"current_steps": 857, "total_steps": 3345, "loss": 1.0568, "lr": 2.1164914241152585e-06, "epoch": 1.28101644245142, "percentage": 25.62, "elapsed_time": "0:16:36", "remaining_time": "0:48:13", "throughput": 7045.17, "total_tokens": 7020544} {"current_steps": 858, "total_steps": 3345, "loss": 0.9269, "lr": 2.1156448878191423e-06, "epoch": 1.2825112107623318, "percentage": 25.65, "elapsed_time": "0:16:37", "remaining_time": "0:48:11", "throughput": 7045.17, "total_tokens": 7028736} {"current_steps": 859, "total_steps": 3345, "loss": 0.611, "lr": 2.1147975879558723e-06, "epoch": 1.2840059790732437, "percentage": 25.68, "elapsed_time": "0:16:38", "remaining_time": "0:48:10", "throughput": 7045.18, "total_tokens": 7036928} {"current_steps": 860, "total_steps": 3345, "loss": 0.6321, "lr": 2.113949525272835e-06, "epoch": 1.2855007473841553, "percentage": 25.71, "elapsed_time": "0:16:39", "remaining_time": "0:48:09", "throughput": 7045.21, "total_tokens": 7045120} {"current_steps": 861, "total_steps": 3345, "loss": 0.8805, "lr": 2.1131007005180874e-06, "epoch": 1.2869955156950672, "percentage": 25.74, "elapsed_time": "0:16:41", "remaining_time": "0:48:08", "throughput": 7045.24, "total_tokens": 7053312} {"current_steps": 862, "total_steps": 3345, "loss": 0.8499, "lr": 2.1122511144403614e-06, "epoch": 1.288490284005979, "percentage": 25.77, "elapsed_time": "0:16:42", "remaining_time": "0:48:07", "throughput": 7045.27, "total_tokens": 7061504} {"current_steps": 863, "total_steps": 3345, "loss": 0.9426, "lr": 2.111400767789058e-06, "epoch": 1.289985052316891, "percentage": 25.8, "elapsed_time": "0:16:43", "remaining_time": "0:48:05", "throughput": 7045.29, "total_tokens": 7069696} {"current_steps": 864, "total_steps": 3345, "loss": 0.8339, "lr": 2.1105496613142505e-06, "epoch": 1.2914798206278026, "percentage": 25.83, "elapsed_time": "0:16:44", "remaining_time": "0:48:04", "throughput": 7045.29, "total_tokens": 7077888} {"current_steps": 865, "total_steps": 3345, "loss": 0.9632, "lr": 2.109697795766682e-06, "epoch": 1.2929745889387145, "percentage": 25.86, "elapsed_time": "0:16:45", "remaining_time": "0:48:03", "throughput": 7045.24, "total_tokens": 7086080} {"current_steps": 866, "total_steps": 3345, "loss": 1.0313, "lr": 2.108845171897765e-06, "epoch": 1.2944693572496262, "percentage": 25.89, "elapsed_time": "0:16:47", "remaining_time": "0:48:02", "throughput": 7044.91, "total_tokens": 7094272} {"current_steps": 867, "total_steps": 3345, "loss": 0.8767, "lr": 2.107991790459581e-06, "epoch": 1.295964125560538, "percentage": 25.92, "elapsed_time": "0:16:48", "remaining_time": "0:48:01", "throughput": 7044.92, "total_tokens": 7102464} {"current_steps": 868, "total_steps": 3345, "loss": 1.0628, "lr": 2.1071376522048802e-06, "epoch": 1.29745889387145, "percentage": 25.95, "elapsed_time": "0:16:49", "remaining_time": "0:48:00", "throughput": 7044.95, "total_tokens": 7110656} {"current_steps": 869, "total_steps": 3345, "loss": 0.8196, "lr": 2.10628275788708e-06, "epoch": 1.2989536621823619, "percentage": 25.98, "elapsed_time": "0:16:50", "remaining_time": "0:47:59", "throughput": 7044.87, "total_tokens": 7118848} {"current_steps": 870, "total_steps": 3345, "loss": 1.0013, "lr": 2.1054271082602647e-06, "epoch": 1.3004484304932735, "percentage": 26.01, "elapsed_time": "0:16:51", "remaining_time": "0:47:58", "throughput": 7044.71, "total_tokens": 7127040} {"current_steps": 871, "total_steps": 3345, "loss": 0.7538, "lr": 2.104570704079184e-06, "epoch": 1.3019431988041854, "percentage": 26.04, "elapsed_time": "0:16:52", "remaining_time": "0:47:56", "throughput": 7044.73, "total_tokens": 7135232} {"current_steps": 872, "total_steps": 3345, "loss": 0.8695, "lr": 2.1037135460992554e-06, "epoch": 1.303437967115097, "percentage": 26.07, "elapsed_time": "0:16:54", "remaining_time": "0:47:55", "throughput": 7044.75, "total_tokens": 7143424} {"current_steps": 873, "total_steps": 3345, "loss": 0.8103, "lr": 2.102855635076559e-06, "epoch": 1.304932735426009, "percentage": 26.1, "elapsed_time": "0:16:55", "remaining_time": "0:47:54", "throughput": 7044.78, "total_tokens": 7151616} {"current_steps": 874, "total_steps": 3345, "loss": 0.9914, "lr": 2.10199697176784e-06, "epoch": 1.3064275037369208, "percentage": 26.13, "elapsed_time": "0:16:56", "remaining_time": "0:47:53", "throughput": 7044.8, "total_tokens": 7159808} {"current_steps": 875, "total_steps": 3345, "loss": 0.7215, "lr": 2.1011375569305076e-06, "epoch": 1.3079222720478325, "percentage": 26.16, "elapsed_time": "0:16:57", "remaining_time": "0:47:52", "throughput": 7044.85, "total_tokens": 7168000} {"current_steps": 876, "total_steps": 3345, "loss": 0.8321, "lr": 2.100277391322634e-06, "epoch": 1.3094170403587444, "percentage": 26.19, "elapsed_time": "0:16:58", "remaining_time": "0:47:51", "throughput": 7044.82, "total_tokens": 7176192} {"current_steps": 877, "total_steps": 3345, "loss": 0.9232, "lr": 2.099416475702952e-06, "epoch": 1.310911808669656, "percentage": 26.22, "elapsed_time": "0:16:59", "remaining_time": "0:47:49", "throughput": 7044.84, "total_tokens": 7184384} {"current_steps": 878, "total_steps": 3345, "loss": 1.1586, "lr": 2.0985548108308583e-06, "epoch": 1.312406576980568, "percentage": 26.25, "elapsed_time": "0:17:00", "remaining_time": "0:47:48", "throughput": 7044.85, "total_tokens": 7192576} {"current_steps": 879, "total_steps": 3345, "loss": 1.2156, "lr": 2.0976923974664086e-06, "epoch": 1.3139013452914798, "percentage": 26.28, "elapsed_time": "0:17:02", "remaining_time": "0:47:47", "throughput": 7044.87, "total_tokens": 7200768} {"current_steps": 880, "total_steps": 3345, "loss": 0.8236, "lr": 2.0968292363703204e-06, "epoch": 1.3153961136023917, "percentage": 26.31, "elapsed_time": "0:17:03", "remaining_time": "0:47:46", "throughput": 7044.87, "total_tokens": 7208960} {"current_steps": 881, "total_steps": 3345, "loss": 1.0598, "lr": 2.0959653283039696e-06, "epoch": 1.3168908819133034, "percentage": 26.34, "elapsed_time": "0:17:04", "remaining_time": "0:47:45", "throughput": 7044.88, "total_tokens": 7217152} {"current_steps": 882, "total_steps": 3345, "loss": 0.89, "lr": 2.0951006740293905e-06, "epoch": 1.3183856502242153, "percentage": 26.37, "elapsed_time": "0:17:05", "remaining_time": "0:47:44", "throughput": 7044.88, "total_tokens": 7225344} {"current_steps": 883, "total_steps": 3345, "loss": 0.7036, "lr": 2.0942352743092776e-06, "epoch": 1.319880418535127, "percentage": 26.4, "elapsed_time": "0:17:06", "remaining_time": "0:47:42", "throughput": 7044.9, "total_tokens": 7233536} {"current_steps": 884, "total_steps": 3345, "loss": 0.6017, "lr": 2.0933691299069816e-06, "epoch": 1.3213751868460388, "percentage": 26.43, "elapsed_time": "0:17:07", "remaining_time": "0:47:41", "throughput": 7044.93, "total_tokens": 7241728} {"current_steps": 885, "total_steps": 3345, "loss": 0.8703, "lr": 2.092502241586509e-06, "epoch": 1.3228699551569507, "percentage": 26.46, "elapsed_time": "0:17:09", "remaining_time": "0:47:40", "throughput": 7044.96, "total_tokens": 7249920} {"current_steps": 886, "total_steps": 3345, "loss": 0.8602, "lr": 2.0916346101125258e-06, "epoch": 1.3243647234678626, "percentage": 26.49, "elapsed_time": "0:17:10", "remaining_time": "0:47:39", "throughput": 7044.99, "total_tokens": 7258112} {"current_steps": 887, "total_steps": 3345, "loss": 0.823, "lr": 2.09076623625035e-06, "epoch": 1.3258594917787743, "percentage": 26.52, "elapsed_time": "0:17:11", "remaining_time": "0:47:38", "throughput": 7045.03, "total_tokens": 7266304} {"current_steps": 888, "total_steps": 3345, "loss": 0.7899, "lr": 2.0898971207659565e-06, "epoch": 1.3273542600896862, "percentage": 26.55, "elapsed_time": "0:17:12", "remaining_time": "0:47:37", "throughput": 7045.06, "total_tokens": 7274496} {"current_steps": 889, "total_steps": 3345, "loss": 0.7512, "lr": 2.089027264425974e-06, "epoch": 1.3288490284005978, "percentage": 26.58, "elapsed_time": "0:17:13", "remaining_time": "0:47:35", "throughput": 7045.07, "total_tokens": 7282688} {"current_steps": 890, "total_steps": 3345, "loss": 0.7364, "lr": 2.088156667997684e-06, "epoch": 1.3303437967115097, "percentage": 26.61, "elapsed_time": "0:17:14", "remaining_time": "0:47:34", "throughput": 7045.08, "total_tokens": 7290880} {"current_steps": 891, "total_steps": 3345, "loss": 1.0623, "lr": 2.087285332249021e-06, "epoch": 1.3318385650224216, "percentage": 26.64, "elapsed_time": "0:17:16", "remaining_time": "0:47:33", "throughput": 7045.09, "total_tokens": 7299072} {"current_steps": 892, "total_steps": 3345, "loss": 0.8629, "lr": 2.086413257948573e-06, "epoch": 1.3333333333333333, "percentage": 26.67, "elapsed_time": "0:17:17", "remaining_time": "0:47:32", "throughput": 7045.12, "total_tokens": 7307264} {"current_steps": 893, "total_steps": 3345, "loss": 0.8763, "lr": 2.0855404458655777e-06, "epoch": 1.3348281016442451, "percentage": 26.7, "elapsed_time": "0:17:18", "remaining_time": "0:47:31", "throughput": 7045.14, "total_tokens": 7315456} {"current_steps": 894, "total_steps": 3345, "loss": 0.7508, "lr": 2.084666896769924e-06, "epoch": 1.336322869955157, "percentage": 26.73, "elapsed_time": "0:17:19", "remaining_time": "0:47:29", "throughput": 7045.15, "total_tokens": 7323648} {"current_steps": 895, "total_steps": 3345, "loss": 0.6737, "lr": 2.0837926114321522e-06, "epoch": 1.3378176382660687, "percentage": 26.76, "elapsed_time": "0:17:20", "remaining_time": "0:47:28", "throughput": 7045.14, "total_tokens": 7331840} {"current_steps": 896, "total_steps": 3345, "loss": 0.9336, "lr": 2.08291759062345e-06, "epoch": 1.3393124065769806, "percentage": 26.79, "elapsed_time": "0:17:21", "remaining_time": "0:47:27", "throughput": 7045.16, "total_tokens": 7340032} {"current_steps": 897, "total_steps": 3345, "loss": 0.5708, "lr": 2.082041835115655e-06, "epoch": 1.3408071748878925, "percentage": 26.82, "elapsed_time": "0:17:23", "remaining_time": "0:47:26", "throughput": 7045.21, "total_tokens": 7348224} {"current_steps": 898, "total_steps": 3345, "loss": 1.0242, "lr": 2.0811653456812534e-06, "epoch": 1.3423019431988041, "percentage": 26.85, "elapsed_time": "0:17:24", "remaining_time": "0:47:25", "throughput": 7045.24, "total_tokens": 7356416} {"current_steps": 899, "total_steps": 3345, "loss": 0.9897, "lr": 2.080288123093378e-06, "epoch": 1.343796711509716, "percentage": 26.88, "elapsed_time": "0:17:25", "remaining_time": "0:47:24", "throughput": 7045.24, "total_tokens": 7364608} {"current_steps": 900, "total_steps": 3345, "loss": 0.8969, "lr": 2.0794101681258077e-06, "epoch": 1.3452914798206277, "percentage": 26.91, "elapsed_time": "0:17:26", "remaining_time": "0:47:22", "throughput": 7045.27, "total_tokens": 7372800} {"current_steps": 901, "total_steps": 3345, "loss": 1.0002, "lr": 2.0785314815529684e-06, "epoch": 1.3467862481315396, "percentage": 26.94, "elapsed_time": "0:17:27", "remaining_time": "0:47:21", "throughput": 7045.3, "total_tokens": 7380992} {"current_steps": 902, "total_steps": 3345, "loss": 0.8648, "lr": 2.0776520641499314e-06, "epoch": 1.3482810164424515, "percentage": 26.97, "elapsed_time": "0:17:28", "remaining_time": "0:47:20", "throughput": 7045.29, "total_tokens": 7389184} {"current_steps": 903, "total_steps": 3345, "loss": 0.9056, "lr": 2.076771916692412e-06, "epoch": 1.3497757847533634, "percentage": 27.0, "elapsed_time": "0:17:29", "remaining_time": "0:47:19", "throughput": 7045.34, "total_tokens": 7397376} {"current_steps": 904, "total_steps": 3345, "loss": 0.999, "lr": 2.0758910399567696e-06, "epoch": 1.351270553064275, "percentage": 27.03, "elapsed_time": "0:17:31", "remaining_time": "0:47:18", "throughput": 7045.36, "total_tokens": 7405568} {"current_steps": 905, "total_steps": 3345, "loss": 0.8712, "lr": 2.0750094347200074e-06, "epoch": 1.352765321375187, "percentage": 27.06, "elapsed_time": "0:17:32", "remaining_time": "0:47:17", "throughput": 7045.39, "total_tokens": 7413760} {"current_steps": 906, "total_steps": 3345, "loss": 0.7284, "lr": 2.0741271017597705e-06, "epoch": 1.3542600896860986, "percentage": 27.09, "elapsed_time": "0:17:33", "remaining_time": "0:47:15", "throughput": 7045.39, "total_tokens": 7421952} {"current_steps": 907, "total_steps": 3345, "loss": 0.951, "lr": 2.0732440418543465e-06, "epoch": 1.3557548579970105, "percentage": 27.12, "elapsed_time": "0:17:34", "remaining_time": "0:47:14", "throughput": 7045.39, "total_tokens": 7430144} {"current_steps": 908, "total_steps": 3345, "loss": 0.9831, "lr": 2.072360255782664e-06, "epoch": 1.3572496263079223, "percentage": 27.14, "elapsed_time": "0:17:35", "remaining_time": "0:47:13", "throughput": 7045.4, "total_tokens": 7438336} {"current_steps": 909, "total_steps": 3345, "loss": 0.738, "lr": 2.071475744324292e-06, "epoch": 1.358744394618834, "percentage": 27.17, "elapsed_time": "0:17:36", "remaining_time": "0:47:12", "throughput": 7045.43, "total_tokens": 7446528} {"current_steps": 910, "total_steps": 3345, "loss": 0.9908, "lr": 2.07059050825944e-06, "epoch": 1.360239162929746, "percentage": 27.2, "elapsed_time": "0:17:38", "remaining_time": "0:47:11", "throughput": 7045.43, "total_tokens": 7454720} {"current_steps": 911, "total_steps": 3345, "loss": 1.0451, "lr": 2.0697045483689547e-06, "epoch": 1.3617339312406578, "percentage": 27.23, "elapsed_time": "0:17:39", "remaining_time": "0:47:10", "throughput": 7045.46, "total_tokens": 7462912} {"current_steps": 912, "total_steps": 3345, "loss": 0.9855, "lr": 2.0688178654343245e-06, "epoch": 1.3632286995515694, "percentage": 27.26, "elapsed_time": "0:17:40", "remaining_time": "0:47:08", "throughput": 7045.46, "total_tokens": 7471104} {"current_steps": 913, "total_steps": 3345, "loss": 1.0105, "lr": 2.067930460237672e-06, "epoch": 1.3647234678624813, "percentage": 27.29, "elapsed_time": "0:17:41", "remaining_time": "0:47:07", "throughput": 7045.45, "total_tokens": 7479296} {"current_steps": 914, "total_steps": 3345, "loss": 0.8559, "lr": 2.0670423335617603e-06, "epoch": 1.3662182361733932, "percentage": 27.32, "elapsed_time": "0:17:42", "remaining_time": "0:47:06", "throughput": 7045.45, "total_tokens": 7487488} {"current_steps": 915, "total_steps": 3345, "loss": 0.758, "lr": 2.0661534861899855e-06, "epoch": 1.3677130044843049, "percentage": 27.35, "elapsed_time": "0:17:43", "remaining_time": "0:47:05", "throughput": 7045.47, "total_tokens": 7495680} {"current_steps": 916, "total_steps": 3345, "loss": 1.0122, "lr": 2.065263918906383e-06, "epoch": 1.3692077727952168, "percentage": 27.38, "elapsed_time": "0:17:45", "remaining_time": "0:47:04", "throughput": 7045.47, "total_tokens": 7503872} {"current_steps": 917, "total_steps": 3345, "loss": 0.6519, "lr": 2.0643736324956203e-06, "epoch": 1.3707025411061284, "percentage": 27.41, "elapsed_time": "0:17:46", "remaining_time": "0:47:03", "throughput": 7045.47, "total_tokens": 7512064} {"current_steps": 918, "total_steps": 3345, "loss": 0.7683, "lr": 2.0634826277430008e-06, "epoch": 1.3721973094170403, "percentage": 27.44, "elapsed_time": "0:17:47", "remaining_time": "0:47:01", "throughput": 7045.49, "total_tokens": 7520256} {"current_steps": 919, "total_steps": 3345, "loss": 0.9492, "lr": 2.0625909054344605e-06, "epoch": 1.3736920777279522, "percentage": 27.47, "elapsed_time": "0:17:48", "remaining_time": "0:47:00", "throughput": 7045.51, "total_tokens": 7528448} {"current_steps": 920, "total_steps": 3345, "loss": 0.7372, "lr": 2.0616984663565698e-06, "epoch": 1.375186846038864, "percentage": 27.5, "elapsed_time": "0:17:49", "remaining_time": "0:46:59", "throughput": 7045.49, "total_tokens": 7536640} {"current_steps": 921, "total_steps": 3345, "loss": 0.8241, "lr": 2.0608053112965294e-06, "epoch": 1.3766816143497758, "percentage": 27.53, "elapsed_time": "0:17:50", "remaining_time": "0:46:58", "throughput": 7045.54, "total_tokens": 7544832} {"current_steps": 922, "total_steps": 3345, "loss": 0.9226, "lr": 2.059911441042173e-06, "epoch": 1.3781763826606876, "percentage": 27.56, "elapsed_time": "0:17:52", "remaining_time": "0:46:57", "throughput": 7045.57, "total_tokens": 7553024} {"current_steps": 923, "total_steps": 3345, "loss": 0.8888, "lr": 2.0590168563819655e-06, "epoch": 1.3796711509715993, "percentage": 27.59, "elapsed_time": "0:17:53", "remaining_time": "0:46:56", "throughput": 7045.58, "total_tokens": 7561216} {"current_steps": 924, "total_steps": 3345, "loss": 0.9524, "lr": 2.0581215581050002e-06, "epoch": 1.3811659192825112, "percentage": 27.62, "elapsed_time": "0:17:54", "remaining_time": "0:46:54", "throughput": 7045.61, "total_tokens": 7569408} {"current_steps": 925, "total_steps": 3345, "loss": 0.7608, "lr": 2.057225547001001e-06, "epoch": 1.382660687593423, "percentage": 27.65, "elapsed_time": "0:17:55", "remaining_time": "0:46:53", "throughput": 7045.62, "total_tokens": 7577600} {"current_steps": 926, "total_steps": 3345, "loss": 0.821, "lr": 2.056328823860321e-06, "epoch": 1.3841554559043348, "percentage": 27.68, "elapsed_time": "0:17:56", "remaining_time": "0:46:52", "throughput": 7045.61, "total_tokens": 7585792} {"current_steps": 927, "total_steps": 3345, "loss": 0.7995, "lr": 2.0554313894739404e-06, "epoch": 1.3856502242152466, "percentage": 27.71, "elapsed_time": "0:17:57", "remaining_time": "0:46:51", "throughput": 7045.62, "total_tokens": 7593984} {"current_steps": 928, "total_steps": 3345, "loss": 0.7627, "lr": 2.0545332446334674e-06, "epoch": 1.3871449925261585, "percentage": 27.74, "elapsed_time": "0:17:58", "remaining_time": "0:46:50", "throughput": 7045.64, "total_tokens": 7602176} {"current_steps": 929, "total_steps": 3345, "loss": 0.9411, "lr": 2.053634390131137e-06, "epoch": 1.3886397608370702, "percentage": 27.77, "elapsed_time": "0:18:00", "remaining_time": "0:46:49", "throughput": 7045.66, "total_tokens": 7610368} {"current_steps": 930, "total_steps": 3345, "loss": 0.9108, "lr": 2.0527348267598086e-06, "epoch": 1.390134529147982, "percentage": 27.8, "elapsed_time": "0:18:01", "remaining_time": "0:46:47", "throughput": 7045.65, "total_tokens": 7618560} {"current_steps": 931, "total_steps": 3345, "loss": 0.8375, "lr": 2.0518345553129694e-06, "epoch": 1.391629297458894, "percentage": 27.83, "elapsed_time": "0:18:02", "remaining_time": "0:46:46", "throughput": 7045.66, "total_tokens": 7626752} {"current_steps": 932, "total_steps": 3345, "loss": 0.6322, "lr": 2.0509335765847297e-06, "epoch": 1.3931240657698056, "percentage": 27.86, "elapsed_time": "0:18:03", "remaining_time": "0:46:45", "throughput": 7045.67, "total_tokens": 7634944} {"current_steps": 933, "total_steps": 3345, "loss": 0.7917, "lr": 2.0500318913698235e-06, "epoch": 1.3946188340807175, "percentage": 27.89, "elapsed_time": "0:18:04", "remaining_time": "0:46:44", "throughput": 7045.67, "total_tokens": 7643136} {"current_steps": 934, "total_steps": 3345, "loss": 0.9094, "lr": 2.0491295004636085e-06, "epoch": 1.3961136023916292, "percentage": 27.92, "elapsed_time": "0:18:05", "remaining_time": "0:46:43", "throughput": 7045.69, "total_tokens": 7651328} {"current_steps": 935, "total_steps": 3345, "loss": 0.8805, "lr": 2.048226404662065e-06, "epoch": 1.397608370702541, "percentage": 27.95, "elapsed_time": "0:18:07", "remaining_time": "0:46:42", "throughput": 7045.69, "total_tokens": 7659520} {"current_steps": 936, "total_steps": 3345, "loss": 0.8473, "lr": 2.0473226047617944e-06, "epoch": 1.399103139013453, "percentage": 27.98, "elapsed_time": "0:18:08", "remaining_time": "0:46:40", "throughput": 7045.64, "total_tokens": 7667712} {"current_steps": 937, "total_steps": 3345, "loss": 0.8, "lr": 2.0464181015600204e-06, "epoch": 1.4005979073243648, "percentage": 28.01, "elapsed_time": "0:18:09", "remaining_time": "0:46:39", "throughput": 7045.64, "total_tokens": 7675904} {"current_steps": 938, "total_steps": 3345, "loss": 0.8495, "lr": 2.045512895854585e-06, "epoch": 1.4020926756352765, "percentage": 28.04, "elapsed_time": "0:18:10", "remaining_time": "0:46:38", "throughput": 7045.65, "total_tokens": 7684096} {"current_steps": 939, "total_steps": 3345, "loss": 1.1349, "lr": 2.044606988443952e-06, "epoch": 1.4035874439461884, "percentage": 28.07, "elapsed_time": "0:18:11", "remaining_time": "0:46:37", "throughput": 7045.61, "total_tokens": 7692288} {"current_steps": 940, "total_steps": 3345, "loss": 0.9137, "lr": 2.0437003801272033e-06, "epoch": 1.4050822122571, "percentage": 28.1, "elapsed_time": "0:18:13", "remaining_time": "0:46:36", "throughput": 7045.12, "total_tokens": 7700480} {"current_steps": 941, "total_steps": 3345, "loss": 0.7452, "lr": 2.0427930717040382e-06, "epoch": 1.406576980568012, "percentage": 28.13, "elapsed_time": "0:18:14", "remaining_time": "0:46:35", "throughput": 7045.17, "total_tokens": 7708672} {"current_steps": 942, "total_steps": 3345, "loss": 1.0008, "lr": 2.0418850639747757e-06, "epoch": 1.4080717488789238, "percentage": 28.16, "elapsed_time": "0:18:15", "remaining_time": "0:46:34", "throughput": 7045.21, "total_tokens": 7716864} {"current_steps": 943, "total_steps": 3345, "loss": 0.9923, "lr": 2.0409763577403493e-06, "epoch": 1.4095665171898355, "percentage": 28.19, "elapsed_time": "0:18:16", "remaining_time": "0:46:32", "throughput": 7045.2, "total_tokens": 7725056} {"current_steps": 944, "total_steps": 3345, "loss": 0.7709, "lr": 2.04006695380231e-06, "epoch": 1.4110612855007474, "percentage": 28.22, "elapsed_time": "0:18:17", "remaining_time": "0:46:31", "throughput": 7045.12, "total_tokens": 7733248} {"current_steps": 945, "total_steps": 3345, "loss": 1.0267, "lr": 2.0391568529628237e-06, "epoch": 1.4125560538116593, "percentage": 28.25, "elapsed_time": "0:18:18", "remaining_time": "0:46:30", "throughput": 7045.15, "total_tokens": 7741440} {"current_steps": 946, "total_steps": 3345, "loss": 1.0515, "lr": 2.0382460560246715e-06, "epoch": 1.414050822122571, "percentage": 28.28, "elapsed_time": "0:18:19", "remaining_time": "0:46:29", "throughput": 7045.15, "total_tokens": 7749632} {"current_steps": 947, "total_steps": 3345, "loss": 0.7944, "lr": 2.0373345637912483e-06, "epoch": 1.4155455904334828, "percentage": 28.31, "elapsed_time": "0:18:21", "remaining_time": "0:46:28", "throughput": 7045.16, "total_tokens": 7757824} {"current_steps": 948, "total_steps": 3345, "loss": 1.0083, "lr": 2.036422377066562e-06, "epoch": 1.4170403587443947, "percentage": 28.34, "elapsed_time": "0:18:22", "remaining_time": "0:46:27", "throughput": 7045.15, "total_tokens": 7766016} {"current_steps": 949, "total_steps": 3345, "loss": 0.7178, "lr": 2.035509496655233e-06, "epoch": 1.4185351270553064, "percentage": 28.37, "elapsed_time": "0:18:23", "remaining_time": "0:46:26", "throughput": 7045.17, "total_tokens": 7774208} {"current_steps": 950, "total_steps": 3345, "loss": 0.9695, "lr": 2.0345959233624946e-06, "epoch": 1.4200298953662183, "percentage": 28.4, "elapsed_time": "0:18:24", "remaining_time": "0:46:24", "throughput": 7045.17, "total_tokens": 7782400} {"current_steps": 951, "total_steps": 3345, "loss": 0.6867, "lr": 2.0336816579941896e-06, "epoch": 1.42152466367713, "percentage": 28.43, "elapsed_time": "0:18:25", "remaining_time": "0:46:23", "throughput": 7045.16, "total_tokens": 7790592} {"current_steps": 952, "total_steps": 3345, "loss": 0.8887, "lr": 2.0327667013567737e-06, "epoch": 1.4230194319880418, "percentage": 28.46, "elapsed_time": "0:18:26", "remaining_time": "0:46:22", "throughput": 7045.18, "total_tokens": 7798784} {"current_steps": 953, "total_steps": 3345, "loss": 0.7886, "lr": 2.03185105425731e-06, "epoch": 1.4245142002989537, "percentage": 28.49, "elapsed_time": "0:18:28", "remaining_time": "0:46:21", "throughput": 7045.17, "total_tokens": 7806976} {"current_steps": 954, "total_steps": 3345, "loss": 0.5225, "lr": 2.0309347175034717e-06, "epoch": 1.4260089686098656, "percentage": 28.52, "elapsed_time": "0:18:29", "remaining_time": "0:46:20", "throughput": 7045.2, "total_tokens": 7815168} {"current_steps": 955, "total_steps": 3345, "loss": 0.8341, "lr": 2.03001769190354e-06, "epoch": 1.4275037369207773, "percentage": 28.55, "elapsed_time": "0:18:30", "remaining_time": "0:46:19", "throughput": 7045.22, "total_tokens": 7823360} {"current_steps": 956, "total_steps": 3345, "loss": 0.8225, "lr": 2.029099978266404e-06, "epoch": 1.4289985052316891, "percentage": 28.58, "elapsed_time": "0:18:31", "remaining_time": "0:46:17", "throughput": 7045.24, "total_tokens": 7831552} {"current_steps": 957, "total_steps": 3345, "loss": 0.8322, "lr": 2.02818157740156e-06, "epoch": 1.4304932735426008, "percentage": 28.61, "elapsed_time": "0:18:32", "remaining_time": "0:46:16", "throughput": 7045.25, "total_tokens": 7839744} {"current_steps": 958, "total_steps": 3345, "loss": 0.8964, "lr": 2.0272624901191095e-06, "epoch": 1.4319880418535127, "percentage": 28.64, "elapsed_time": "0:18:33", "remaining_time": "0:46:15", "throughput": 7045.26, "total_tokens": 7847936} {"current_steps": 959, "total_steps": 3345, "loss": 1.1001, "lr": 2.0263427172297605e-06, "epoch": 1.4334828101644246, "percentage": 28.67, "elapsed_time": "0:18:35", "remaining_time": "0:46:14", "throughput": 7045.29, "total_tokens": 7856128} {"current_steps": 960, "total_steps": 3345, "loss": 1.1461, "lr": 2.0254222595448252e-06, "epoch": 1.4349775784753362, "percentage": 28.7, "elapsed_time": "0:18:36", "remaining_time": "0:46:13", "throughput": 7045.29, "total_tokens": 7864320} {"current_steps": 961, "total_steps": 3345, "loss": 0.7043, "lr": 2.0245011178762196e-06, "epoch": 1.4364723467862481, "percentage": 28.73, "elapsed_time": "0:18:37", "remaining_time": "0:46:12", "throughput": 7045.3, "total_tokens": 7872512} {"current_steps": 962, "total_steps": 3345, "loss": 0.7942, "lr": 2.023579293036464e-06, "epoch": 1.43796711509716, "percentage": 28.76, "elapsed_time": "0:18:38", "remaining_time": "0:46:10", "throughput": 7045.32, "total_tokens": 7880704} {"current_steps": 963, "total_steps": 3345, "loss": 0.8796, "lr": 2.0226567858386803e-06, "epoch": 1.4394618834080717, "percentage": 28.79, "elapsed_time": "0:18:39", "remaining_time": "0:46:09", "throughput": 7045.36, "total_tokens": 7888896} {"current_steps": 964, "total_steps": 3345, "loss": 0.7446, "lr": 2.021733597096593e-06, "epoch": 1.4409566517189836, "percentage": 28.82, "elapsed_time": "0:18:40", "remaining_time": "0:46:08", "throughput": 7045.4, "total_tokens": 7897088} {"current_steps": 965, "total_steps": 3345, "loss": 0.724, "lr": 2.020809727624527e-06, "epoch": 1.4424514200298955, "percentage": 28.85, "elapsed_time": "0:18:42", "remaining_time": "0:46:07", "throughput": 7045.42, "total_tokens": 7905280} {"current_steps": 966, "total_steps": 3345, "loss": 0.9702, "lr": 2.0198851782374087e-06, "epoch": 1.4439461883408071, "percentage": 28.88, "elapsed_time": "0:18:43", "remaining_time": "0:46:06", "throughput": 7045.43, "total_tokens": 7913472} {"current_steps": 967, "total_steps": 3345, "loss": 1.0202, "lr": 2.0189599497507634e-06, "epoch": 1.445440956651719, "percentage": 28.91, "elapsed_time": "0:18:44", "remaining_time": "0:46:05", "throughput": 7045.41, "total_tokens": 7921664} {"current_steps": 968, "total_steps": 3345, "loss": 0.9357, "lr": 2.0180340429807155e-06, "epoch": 1.4469357249626307, "percentage": 28.94, "elapsed_time": "0:18:45", "remaining_time": "0:46:03", "throughput": 7045.36, "total_tokens": 7929856} {"current_steps": 969, "total_steps": 3345, "loss": 0.7002, "lr": 2.0171074587439883e-06, "epoch": 1.4484304932735426, "percentage": 28.97, "elapsed_time": "0:18:46", "remaining_time": "0:46:02", "throughput": 7045.36, "total_tokens": 7938048} {"current_steps": 970, "total_steps": 3345, "loss": 0.9179, "lr": 2.016180197857902e-06, "epoch": 1.4499252615844545, "percentage": 29.0, "elapsed_time": "0:18:47", "remaining_time": "0:46:01", "throughput": 7045.31, "total_tokens": 7946240} {"current_steps": 971, "total_steps": 3345, "loss": 1.1201, "lr": 2.015252261140374e-06, "epoch": 1.4514200298953663, "percentage": 29.03, "elapsed_time": "0:18:49", "remaining_time": "0:46:00", "throughput": 7045.3, "total_tokens": 7954432} {"current_steps": 972, "total_steps": 3345, "loss": 1.1085, "lr": 2.014323649409918e-06, "epoch": 1.452914798206278, "percentage": 29.06, "elapsed_time": "0:18:50", "remaining_time": "0:45:59", "throughput": 7045.29, "total_tokens": 7962624} {"current_steps": 973, "total_steps": 3345, "loss": 0.7087, "lr": 2.013394363485642e-06, "epoch": 1.45440956651719, "percentage": 29.09, "elapsed_time": "0:18:51", "remaining_time": "0:45:58", "throughput": 7045.29, "total_tokens": 7970816} {"current_steps": 974, "total_steps": 3345, "loss": 0.7044, "lr": 2.012464404187251e-06, "epoch": 1.4559043348281016, "percentage": 29.12, "elapsed_time": "0:18:52", "remaining_time": "0:45:56", "throughput": 7045.31, "total_tokens": 7979008} {"current_steps": 975, "total_steps": 3345, "loss": 0.8056, "lr": 2.011533772335041e-06, "epoch": 1.4573991031390134, "percentage": 29.15, "elapsed_time": "0:18:53", "remaining_time": "0:45:55", "throughput": 7045.3, "total_tokens": 7987200} {"current_steps": 976, "total_steps": 3345, "loss": 0.7154, "lr": 2.0106024687499044e-06, "epoch": 1.4588938714499253, "percentage": 29.18, "elapsed_time": "0:18:54", "remaining_time": "0:45:54", "throughput": 7045.3, "total_tokens": 7995392} {"current_steps": 977, "total_steps": 3345, "loss": 0.9838, "lr": 2.009670494253323e-06, "epoch": 1.460388639760837, "percentage": 29.21, "elapsed_time": "0:18:56", "remaining_time": "0:45:53", "throughput": 7045.3, "total_tokens": 8003584} {"current_steps": 978, "total_steps": 3345, "loss": 0.8935, "lr": 2.008737849667373e-06, "epoch": 1.4618834080717489, "percentage": 29.24, "elapsed_time": "0:18:57", "remaining_time": "0:45:52", "throughput": 7045.31, "total_tokens": 8011776} {"current_steps": 979, "total_steps": 3345, "loss": 0.8945, "lr": 2.0078045358147196e-06, "epoch": 1.4633781763826608, "percentage": 29.27, "elapsed_time": "0:18:58", "remaining_time": "0:45:51", "throughput": 7045.3, "total_tokens": 8019968} {"current_steps": 980, "total_steps": 3345, "loss": 0.7892, "lr": 2.0068705535186205e-06, "epoch": 1.4648729446935724, "percentage": 29.3, "elapsed_time": "0:18:59", "remaining_time": "0:45:49", "throughput": 7045.32, "total_tokens": 8028160} {"current_steps": 981, "total_steps": 3345, "loss": 0.9208, "lr": 2.0059359036029206e-06, "epoch": 1.4663677130044843, "percentage": 29.33, "elapsed_time": "0:19:00", "remaining_time": "0:45:48", "throughput": 7045.35, "total_tokens": 8036352} {"current_steps": 982, "total_steps": 3345, "loss": 0.7731, "lr": 2.0050005868920562e-06, "epoch": 1.4678624813153962, "percentage": 29.36, "elapsed_time": "0:19:01", "remaining_time": "0:45:47", "throughput": 7045.31, "total_tokens": 8044544} {"current_steps": 983, "total_steps": 3345, "loss": 0.9565, "lr": 2.0040646042110496e-06, "epoch": 1.4693572496263079, "percentage": 29.39, "elapsed_time": "0:19:02", "remaining_time": "0:45:46", "throughput": 7045.35, "total_tokens": 8052736} {"current_steps": 984, "total_steps": 3345, "loss": 0.8407, "lr": 2.0031279563855115e-06, "epoch": 1.4708520179372198, "percentage": 29.42, "elapsed_time": "0:19:04", "remaining_time": "0:45:45", "throughput": 7045.38, "total_tokens": 8060928} {"current_steps": 985, "total_steps": 3345, "loss": 0.6125, "lr": 2.0021906442416395e-06, "epoch": 1.4723467862481314, "percentage": 29.45, "elapsed_time": "0:19:05", "remaining_time": "0:45:44", "throughput": 7045.4, "total_tokens": 8069120} {"current_steps": 986, "total_steps": 3345, "loss": 0.88, "lr": 2.001252668606217e-06, "epoch": 1.4738415545590433, "percentage": 29.48, "elapsed_time": "0:19:06", "remaining_time": "0:45:42", "throughput": 7045.41, "total_tokens": 8077312} {"current_steps": 987, "total_steps": 3345, "loss": 0.8495, "lr": 2.0003140303066124e-06, "epoch": 1.4753363228699552, "percentage": 29.51, "elapsed_time": "0:19:07", "remaining_time": "0:45:41", "throughput": 7045.42, "total_tokens": 8085504} {"current_steps": 988, "total_steps": 3345, "loss": 0.7603, "lr": 1.9993747301707787e-06, "epoch": 1.476831091180867, "percentage": 29.54, "elapsed_time": "0:19:08", "remaining_time": "0:45:40", "throughput": 7045.43, "total_tokens": 8093696} {"current_steps": 989, "total_steps": 3345, "loss": 0.9196, "lr": 1.9984347690272533e-06, "epoch": 1.4783258594917787, "percentage": 29.57, "elapsed_time": "0:19:09", "remaining_time": "0:45:39", "throughput": 7045.44, "total_tokens": 8101888} {"current_steps": 990, "total_steps": 3345, "loss": 0.8452, "lr": 1.9974941477051558e-06, "epoch": 1.4798206278026906, "percentage": 29.6, "elapsed_time": "0:19:11", "remaining_time": "0:45:38", "throughput": 7045.46, "total_tokens": 8110080} {"current_steps": 991, "total_steps": 3345, "loss": 1.06, "lr": 1.9965528670341883e-06, "epoch": 1.4813153961136023, "percentage": 29.63, "elapsed_time": "0:19:12", "remaining_time": "0:45:37", "throughput": 7045.49, "total_tokens": 8118272} {"current_steps": 992, "total_steps": 3345, "loss": 0.8055, "lr": 1.995610927844635e-06, "epoch": 1.4828101644245142, "percentage": 29.66, "elapsed_time": "0:19:13", "remaining_time": "0:45:35", "throughput": 7045.54, "total_tokens": 8126464} {"current_steps": 993, "total_steps": 3345, "loss": 0.5399, "lr": 1.9946683309673606e-06, "epoch": 1.484304932735426, "percentage": 29.69, "elapsed_time": "0:19:14", "remaining_time": "0:45:34", "throughput": 7045.6, "total_tokens": 8134656} {"current_steps": 994, "total_steps": 3345, "loss": 1.0101, "lr": 1.99372507723381e-06, "epoch": 1.4857997010463377, "percentage": 29.72, "elapsed_time": "0:19:15", "remaining_time": "0:45:33", "throughput": 7045.63, "total_tokens": 8142848} {"current_steps": 995, "total_steps": 3345, "loss": 0.7383, "lr": 1.9927811674760073e-06, "epoch": 1.4872944693572496, "percentage": 29.75, "elapsed_time": "0:19:16", "remaining_time": "0:45:32", "throughput": 7045.59, "total_tokens": 8151040} {"current_steps": 996, "total_steps": 3345, "loss": 1.1104, "lr": 1.9918366025265556e-06, "epoch": 1.4887892376681615, "percentage": 29.78, "elapsed_time": "0:19:18", "remaining_time": "0:45:31", "throughput": 7045.61, "total_tokens": 8159232} {"current_steps": 997, "total_steps": 3345, "loss": 0.669, "lr": 1.990891383218636e-06, "epoch": 1.4902840059790732, "percentage": 29.81, "elapsed_time": "0:19:19", "remaining_time": "0:45:30", "throughput": 7045.6, "total_tokens": 8167424} {"current_steps": 998, "total_steps": 3345, "loss": 0.7041, "lr": 1.989945510386006e-06, "epoch": 1.491778774289985, "percentage": 29.84, "elapsed_time": "0:19:20", "remaining_time": "0:45:28", "throughput": 7045.6, "total_tokens": 8175616} {"current_steps": 999, "total_steps": 3345, "loss": 1.1275, "lr": 1.988998984863001e-06, "epoch": 1.493273542600897, "percentage": 29.87, "elapsed_time": "0:19:21", "remaining_time": "0:45:27", "throughput": 7045.59, "total_tokens": 8183808} {"current_steps": 1000, "total_steps": 3345, "loss": 1.0901, "lr": 1.98805180748453e-06, "epoch": 1.4947683109118086, "percentage": 29.9, "elapsed_time": "0:19:22", "remaining_time": "0:45:26", "throughput": 7045.56, "total_tokens": 8192000} {"current_steps": 1001, "total_steps": 3345, "loss": 0.8426, "lr": 1.987103979086079e-06, "epoch": 1.4962630792227205, "percentage": 29.93, "elapsed_time": "0:19:23", "remaining_time": "0:45:25", "throughput": 7045.52, "total_tokens": 8200192} {"current_steps": 1002, "total_steps": 3345, "loss": 0.9653, "lr": 1.986155500503708e-06, "epoch": 1.4977578475336322, "percentage": 29.96, "elapsed_time": "0:19:25", "remaining_time": "0:45:24", "throughput": 7045.51, "total_tokens": 8208384} {"current_steps": 1003, "total_steps": 3345, "loss": 0.9704, "lr": 1.9852063725740494e-06, "epoch": 1.499252615844544, "percentage": 29.99, "elapsed_time": "0:19:26", "remaining_time": "0:45:23", "throughput": 7045.48, "total_tokens": 8216576} {"current_steps": 1004, "total_steps": 3345, "loss": 0.6976, "lr": 1.9842565961343092e-06, "epoch": 1.500747384155456, "percentage": 30.01, "elapsed_time": "0:19:27", "remaining_time": "0:45:21", "throughput": 7045.48, "total_tokens": 8224768} {"current_steps": 1005, "total_steps": 3345, "loss": 0.8219, "lr": 1.9833061720222648e-06, "epoch": 1.5022421524663678, "percentage": 30.04, "elapsed_time": "0:19:28", "remaining_time": "0:45:20", "throughput": 7045.48, "total_tokens": 8232960} {"current_steps": 1006, "total_steps": 3345, "loss": 0.6393, "lr": 1.9823551010762655e-06, "epoch": 1.5037369207772795, "percentage": 30.07, "elapsed_time": "0:19:29", "remaining_time": "0:45:19", "throughput": 7045.5, "total_tokens": 8241152} {"current_steps": 1007, "total_steps": 3345, "loss": 1.0197, "lr": 1.9814033841352316e-06, "epoch": 1.5052316890881914, "percentage": 30.1, "elapsed_time": "0:19:30", "remaining_time": "0:45:18", "throughput": 7045.5, "total_tokens": 8249344} {"current_steps": 1008, "total_steps": 3345, "loss": 0.7188, "lr": 1.9804510220386513e-06, "epoch": 1.506726457399103, "percentage": 30.13, "elapsed_time": "0:19:32", "remaining_time": "0:45:17", "throughput": 7045.48, "total_tokens": 8257536} {"current_steps": 1009, "total_steps": 3345, "loss": 0.7904, "lr": 1.9794980156265845e-06, "epoch": 1.508221225710015, "percentage": 30.16, "elapsed_time": "0:19:33", "remaining_time": "0:45:16", "throughput": 7045.5, "total_tokens": 8265728} {"current_steps": 1010, "total_steps": 3345, "loss": 1.1518, "lr": 1.978544365739658e-06, "epoch": 1.5097159940209268, "percentage": 30.19, "elapsed_time": "0:19:34", "remaining_time": "0:45:14", "throughput": 7045.51, "total_tokens": 8273920} {"current_steps": 1011, "total_steps": 3345, "loss": 0.7212, "lr": 1.9775900732190654e-06, "epoch": 1.5112107623318387, "percentage": 30.22, "elapsed_time": "0:19:35", "remaining_time": "0:45:13", "throughput": 7045.54, "total_tokens": 8282112} {"current_steps": 1012, "total_steps": 3345, "loss": 1.0875, "lr": 1.9766351389065692e-06, "epoch": 1.5127055306427504, "percentage": 30.25, "elapsed_time": "0:19:36", "remaining_time": "0:45:12", "throughput": 7045.49, "total_tokens": 8290304} {"current_steps": 1013, "total_steps": 3345, "loss": 0.9076, "lr": 1.9756795636444956e-06, "epoch": 1.514200298953662, "percentage": 30.28, "elapsed_time": "0:19:37", "remaining_time": "0:45:11", "throughput": 7045.49, "total_tokens": 8298496} {"current_steps": 1014, "total_steps": 3345, "loss": 1.0755, "lr": 1.9747233482757384e-06, "epoch": 1.515695067264574, "percentage": 30.31, "elapsed_time": "0:19:39", "remaining_time": "0:45:10", "throughput": 7045.46, "total_tokens": 8306688} {"current_steps": 1015, "total_steps": 3345, "loss": 0.4617, "lr": 1.9737664936437543e-06, "epoch": 1.5171898355754858, "percentage": 30.34, "elapsed_time": "0:19:40", "remaining_time": "0:45:09", "throughput": 7045.47, "total_tokens": 8314880} {"current_steps": 1016, "total_steps": 3345, "loss": 0.8685, "lr": 1.972809000592566e-06, "epoch": 1.5186846038863977, "percentage": 30.37, "elapsed_time": "0:19:41", "remaining_time": "0:45:08", "throughput": 7045.46, "total_tokens": 8323072} {"current_steps": 1017, "total_steps": 3345, "loss": 0.6354, "lr": 1.9718508699667565e-06, "epoch": 1.5201793721973094, "percentage": 30.4, "elapsed_time": "0:19:42", "remaining_time": "0:45:06", "throughput": 7045.48, "total_tokens": 8331264} {"current_steps": 1018, "total_steps": 3345, "loss": 0.5987, "lr": 1.9708921026114735e-06, "epoch": 1.5216741405082213, "percentage": 30.43, "elapsed_time": "0:19:43", "remaining_time": "0:45:05", "throughput": 7045.5, "total_tokens": 8339456} {"current_steps": 1019, "total_steps": 3345, "loss": 1.1048, "lr": 1.9699326993724257e-06, "epoch": 1.523168908819133, "percentage": 30.46, "elapsed_time": "0:19:44", "remaining_time": "0:45:04", "throughput": 7045.5, "total_tokens": 8347648} {"current_steps": 1020, "total_steps": 3345, "loss": 0.7691, "lr": 1.9689726610958815e-06, "epoch": 1.5246636771300448, "percentage": 30.49, "elapsed_time": "0:19:45", "remaining_time": "0:45:03", "throughput": 7045.55, "total_tokens": 8355840} {"current_steps": 1021, "total_steps": 3345, "loss": 0.9826, "lr": 1.9680119886286716e-06, "epoch": 1.5261584454409567, "percentage": 30.52, "elapsed_time": "0:19:47", "remaining_time": "0:45:02", "throughput": 7045.6, "total_tokens": 8364032} {"current_steps": 1022, "total_steps": 3345, "loss": 0.9144, "lr": 1.967050682818184e-06, "epoch": 1.5276532137518686, "percentage": 30.55, "elapsed_time": "0:19:48", "remaining_time": "0:45:00", "throughput": 7045.62, "total_tokens": 8372224} {"current_steps": 1023, "total_steps": 3345, "loss": 0.7882, "lr": 1.966088744512367e-06, "epoch": 1.5291479820627802, "percentage": 30.58, "elapsed_time": "0:19:49", "remaining_time": "0:44:59", "throughput": 7045.63, "total_tokens": 8380416} {"current_steps": 1024, "total_steps": 3345, "loss": 0.7745, "lr": 1.9651261745597265e-06, "epoch": 1.5306427503736921, "percentage": 30.61, "elapsed_time": "0:19:50", "remaining_time": "0:44:58", "throughput": 7045.61, "total_tokens": 8388608} {"current_steps": 1025, "total_steps": 3345, "loss": 0.9478, "lr": 1.9641629738093243e-06, "epoch": 1.5321375186846038, "percentage": 30.64, "elapsed_time": "0:19:51", "remaining_time": "0:44:57", "throughput": 7045.63, "total_tokens": 8396800} {"current_steps": 1026, "total_steps": 3345, "loss": 0.7511, "lr": 1.96319914311078e-06, "epoch": 1.5336322869955157, "percentage": 30.67, "elapsed_time": "0:19:52", "remaining_time": "0:44:56", "throughput": 7045.64, "total_tokens": 8404992} {"current_steps": 1027, "total_steps": 3345, "loss": 0.7526, "lr": 1.9622346833142684e-06, "epoch": 1.5351270553064276, "percentage": 30.7, "elapsed_time": "0:19:54", "remaining_time": "0:44:55", "throughput": 7045.64, "total_tokens": 8413184} {"current_steps": 1028, "total_steps": 3345, "loss": 1.0662, "lr": 1.961269595270519e-06, "epoch": 1.5366218236173395, "percentage": 30.73, "elapsed_time": "0:19:55", "remaining_time": "0:44:53", "throughput": 7045.64, "total_tokens": 8421376} {"current_steps": 1029, "total_steps": 3345, "loss": 1.0373, "lr": 1.960303879830816e-06, "epoch": 1.5381165919282511, "percentage": 30.76, "elapsed_time": "0:19:56", "remaining_time": "0:44:52", "throughput": 7045.66, "total_tokens": 8429568} {"current_steps": 1030, "total_steps": 3345, "loss": 0.8047, "lr": 1.9593375378469962e-06, "epoch": 1.5396113602391628, "percentage": 30.79, "elapsed_time": "0:19:57", "remaining_time": "0:44:51", "throughput": 7045.67, "total_tokens": 8437760} {"current_steps": 1031, "total_steps": 3345, "loss": 0.7684, "lr": 1.95837057017145e-06, "epoch": 1.5411061285500747, "percentage": 30.82, "elapsed_time": "0:19:58", "remaining_time": "0:44:50", "throughput": 7045.7, "total_tokens": 8445952} {"current_steps": 1032, "total_steps": 3345, "loss": 0.8552, "lr": 1.957402977657119e-06, "epoch": 1.5426008968609866, "percentage": 30.85, "elapsed_time": "0:19:59", "remaining_time": "0:44:49", "throughput": 7045.69, "total_tokens": 8454144} {"current_steps": 1033, "total_steps": 3345, "loss": 0.7103, "lr": 1.9564347611574967e-06, "epoch": 1.5440956651718984, "percentage": 30.88, "elapsed_time": "0:20:01", "remaining_time": "0:44:48", "throughput": 7045.63, "total_tokens": 8462336} {"current_steps": 1034, "total_steps": 3345, "loss": 0.9889, "lr": 1.955465921526626e-06, "epoch": 1.54559043348281, "percentage": 30.91, "elapsed_time": "0:20:02", "remaining_time": "0:44:47", "throughput": 7045.66, "total_tokens": 8470528} {"current_steps": 1035, "total_steps": 3345, "loss": 0.7703, "lr": 1.9544964596191e-06, "epoch": 1.547085201793722, "percentage": 30.94, "elapsed_time": "0:20:03", "remaining_time": "0:44:45", "throughput": 7045.67, "total_tokens": 8478720} {"current_steps": 1036, "total_steps": 3345, "loss": 0.9549, "lr": 1.95352637629006e-06, "epoch": 1.5485799701046337, "percentage": 30.97, "elapsed_time": "0:20:04", "remaining_time": "0:44:44", "throughput": 7045.69, "total_tokens": 8486912} {"current_steps": 1037, "total_steps": 3345, "loss": 0.7643, "lr": 1.952555672395198e-06, "epoch": 1.5500747384155455, "percentage": 31.0, "elapsed_time": "0:20:05", "remaining_time": "0:44:43", "throughput": 7045.7, "total_tokens": 8495104} {"current_steps": 1038, "total_steps": 3345, "loss": 1.0563, "lr": 1.9515843487907498e-06, "epoch": 1.5515695067264574, "percentage": 31.03, "elapsed_time": "0:20:06", "remaining_time": "0:44:42", "throughput": 7045.71, "total_tokens": 8503296} {"current_steps": 1039, "total_steps": 3345, "loss": 0.8424, "lr": 1.9506124063335e-06, "epoch": 1.5530642750373693, "percentage": 31.06, "elapsed_time": "0:20:08", "remaining_time": "0:44:41", "throughput": 7045.71, "total_tokens": 8511488} {"current_steps": 1040, "total_steps": 3345, "loss": 0.9968, "lr": 1.949639845880779e-06, "epoch": 1.554559043348281, "percentage": 31.09, "elapsed_time": "0:20:09", "remaining_time": "0:44:40", "throughput": 7045.73, "total_tokens": 8519680} {"current_steps": 1041, "total_steps": 3345, "loss": 1.0288, "lr": 1.9486666682904614e-06, "epoch": 1.5560538116591929, "percentage": 31.12, "elapsed_time": "0:20:10", "remaining_time": "0:44:38", "throughput": 7045.73, "total_tokens": 8527872} {"current_steps": 1042, "total_steps": 3345, "loss": 0.8755, "lr": 1.947692874420967e-06, "epoch": 1.5575485799701045, "percentage": 31.15, "elapsed_time": "0:20:11", "remaining_time": "0:44:37", "throughput": 7045.75, "total_tokens": 8536064} {"current_steps": 1043, "total_steps": 3345, "loss": 1.0206, "lr": 1.9467184651312587e-06, "epoch": 1.5590433482810164, "percentage": 31.18, "elapsed_time": "0:20:12", "remaining_time": "0:44:36", "throughput": 7045.78, "total_tokens": 8544256} {"current_steps": 1044, "total_steps": 3345, "loss": 0.8231, "lr": 1.9457434412808424e-06, "epoch": 1.5605381165919283, "percentage": 31.21, "elapsed_time": "0:20:13", "remaining_time": "0:44:35", "throughput": 7045.81, "total_tokens": 8552448} {"current_steps": 1045, "total_steps": 3345, "loss": 1.093, "lr": 1.944767803729767e-06, "epoch": 1.5620328849028402, "percentage": 31.24, "elapsed_time": "0:20:14", "remaining_time": "0:44:34", "throughput": 7045.8, "total_tokens": 8560640} {"current_steps": 1046, "total_steps": 3345, "loss": 0.8563, "lr": 1.94379155333862e-06, "epoch": 1.5635276532137519, "percentage": 31.27, "elapsed_time": "0:20:16", "remaining_time": "0:44:32", "throughput": 7045.82, "total_tokens": 8568832} {"current_steps": 1047, "total_steps": 3345, "loss": 0.9461, "lr": 1.9428146909685335e-06, "epoch": 1.5650224215246635, "percentage": 31.3, "elapsed_time": "0:20:17", "remaining_time": "0:44:31", "throughput": 7045.81, "total_tokens": 8577024} {"current_steps": 1048, "total_steps": 3345, "loss": 0.9313, "lr": 1.9418372174811757e-06, "epoch": 1.5665171898355754, "percentage": 31.33, "elapsed_time": "0:20:18", "remaining_time": "0:44:30", "throughput": 7045.83, "total_tokens": 8585216} {"current_steps": 1049, "total_steps": 3345, "loss": 0.6967, "lr": 1.9408591337387557e-06, "epoch": 1.5680119581464873, "percentage": 31.36, "elapsed_time": "0:20:19", "remaining_time": "0:44:29", "throughput": 7045.84, "total_tokens": 8593408} {"current_steps": 1050, "total_steps": 3345, "loss": 1.0637, "lr": 1.9398804406040214e-06, "epoch": 1.5695067264573992, "percentage": 31.39, "elapsed_time": "0:20:20", "remaining_time": "0:44:28", "throughput": 7045.83, "total_tokens": 8601600} {"current_steps": 1051, "total_steps": 3345, "loss": 0.7161, "lr": 1.938901138940257e-06, "epoch": 1.5710014947683109, "percentage": 31.42, "elapsed_time": "0:20:21", "remaining_time": "0:44:27", "throughput": 7045.85, "total_tokens": 8609792} {"current_steps": 1052, "total_steps": 3345, "loss": 0.7405, "lr": 1.9379212296112833e-06, "epoch": 1.5724962630792227, "percentage": 31.45, "elapsed_time": "0:20:23", "remaining_time": "0:44:26", "throughput": 7045.82, "total_tokens": 8617984} {"current_steps": 1053, "total_steps": 3345, "loss": 0.9971, "lr": 1.9369407134814584e-06, "epoch": 1.5739910313901344, "percentage": 31.48, "elapsed_time": "0:20:24", "remaining_time": "0:44:24", "throughput": 7045.81, "total_tokens": 8626176} {"current_steps": 1054, "total_steps": 3345, "loss": 0.6717, "lr": 1.9359595914156745e-06, "epoch": 1.5754857997010463, "percentage": 31.51, "elapsed_time": "0:20:25", "remaining_time": "0:44:23", "throughput": 7045.84, "total_tokens": 8634368} {"current_steps": 1055, "total_steps": 3345, "loss": 1.0462, "lr": 1.9349778642793594e-06, "epoch": 1.5769805680119582, "percentage": 31.54, "elapsed_time": "0:20:26", "remaining_time": "0:44:22", "throughput": 7045.85, "total_tokens": 8642560} {"current_steps": 1056, "total_steps": 3345, "loss": 0.8282, "lr": 1.9339955329384735e-06, "epoch": 1.57847533632287, "percentage": 31.57, "elapsed_time": "0:20:27", "remaining_time": "0:44:21", "throughput": 7045.86, "total_tokens": 8650752} {"current_steps": 1057, "total_steps": 3345, "loss": 1.0103, "lr": 1.9330125982595103e-06, "epoch": 1.5799701046337817, "percentage": 31.6, "elapsed_time": "0:20:28", "remaining_time": "0:44:20", "throughput": 7045.88, "total_tokens": 8658944} {"current_steps": 1058, "total_steps": 3345, "loss": 0.8463, "lr": 1.9320290611094965e-06, "epoch": 1.5814648729446936, "percentage": 31.63, "elapsed_time": "0:20:30", "remaining_time": "0:44:19", "throughput": 7045.89, "total_tokens": 8667136} {"current_steps": 1059, "total_steps": 3345, "loss": 0.9292, "lr": 1.9310449223559892e-06, "epoch": 1.5829596412556053, "percentage": 31.66, "elapsed_time": "0:20:31", "remaining_time": "0:44:17", "throughput": 7045.92, "total_tokens": 8675328} {"current_steps": 1060, "total_steps": 3345, "loss": 1.0962, "lr": 1.930060182867077e-06, "epoch": 1.5844544095665172, "percentage": 31.69, "elapsed_time": "0:20:32", "remaining_time": "0:44:16", "throughput": 7045.94, "total_tokens": 8683520} {"current_steps": 1061, "total_steps": 3345, "loss": 1.125, "lr": 1.9290748435113764e-06, "epoch": 1.585949177877429, "percentage": 31.72, "elapsed_time": "0:20:33", "remaining_time": "0:44:15", "throughput": 7045.97, "total_tokens": 8691712} {"current_steps": 1062, "total_steps": 3345, "loss": 1.0214, "lr": 1.9280889051580365e-06, "epoch": 1.587443946188341, "percentage": 31.75, "elapsed_time": "0:20:34", "remaining_time": "0:44:14", "throughput": 7046.0, "total_tokens": 8699904} {"current_steps": 1063, "total_steps": 3345, "loss": 0.7301, "lr": 1.9271023686767313e-06, "epoch": 1.5889387144992526, "percentage": 31.78, "elapsed_time": "0:20:35", "remaining_time": "0:44:13", "throughput": 7046.03, "total_tokens": 8708096} {"current_steps": 1064, "total_steps": 3345, "loss": 0.8926, "lr": 1.926115234937665e-06, "epoch": 1.5904334828101643, "percentage": 31.81, "elapsed_time": "0:20:37", "remaining_time": "0:44:11", "throughput": 7046.04, "total_tokens": 8716288} {"current_steps": 1065, "total_steps": 3345, "loss": 0.8636, "lr": 1.9251275048115662e-06, "epoch": 1.5919282511210762, "percentage": 31.84, "elapsed_time": "0:20:38", "remaining_time": "0:44:10", "throughput": 7046.05, "total_tokens": 8724480} {"current_steps": 1066, "total_steps": 3345, "loss": 1.0291, "lr": 1.9241391791696923e-06, "epoch": 1.593423019431988, "percentage": 31.87, "elapsed_time": "0:20:39", "remaining_time": "0:44:09", "throughput": 7046.06, "total_tokens": 8732672} {"current_steps": 1067, "total_steps": 3345, "loss": 0.7917, "lr": 1.9231502588838237e-06, "epoch": 1.5949177877429, "percentage": 31.9, "elapsed_time": "0:20:40", "remaining_time": "0:44:08", "throughput": 7046.08, "total_tokens": 8740864} {"current_steps": 1068, "total_steps": 3345, "loss": 0.9978, "lr": 1.9221607448262666e-06, "epoch": 1.5964125560538116, "percentage": 31.93, "elapsed_time": "0:20:41", "remaining_time": "0:44:07", "throughput": 7046.12, "total_tokens": 8749056} {"current_steps": 1069, "total_steps": 3345, "loss": 0.7909, "lr": 1.92117063786985e-06, "epoch": 1.5979073243647235, "percentage": 31.96, "elapsed_time": "0:20:42", "remaining_time": "0:44:06", "throughput": 7046.15, "total_tokens": 8757248} {"current_steps": 1070, "total_steps": 3345, "loss": 0.7575, "lr": 1.9201799388879266e-06, "epoch": 1.5994020926756352, "percentage": 31.99, "elapsed_time": "0:20:44", "remaining_time": "0:44:04", "throughput": 7046.13, "total_tokens": 8765440} {"current_steps": 1071, "total_steps": 3345, "loss": 0.9317, "lr": 1.9191886487543714e-06, "epoch": 1.600896860986547, "percentage": 32.02, "elapsed_time": "0:20:45", "remaining_time": "0:44:03", "throughput": 7046.12, "total_tokens": 8773632} {"current_steps": 1072, "total_steps": 3345, "loss": 0.7145, "lr": 1.918196768343581e-06, "epoch": 1.602391629297459, "percentage": 32.05, "elapsed_time": "0:20:46", "remaining_time": "0:44:02", "throughput": 7046.14, "total_tokens": 8781824} {"current_steps": 1073, "total_steps": 3345, "loss": 1.0068, "lr": 1.917204298530471e-06, "epoch": 1.6038863976083708, "percentage": 32.08, "elapsed_time": "0:20:47", "remaining_time": "0:44:01", "throughput": 7046.17, "total_tokens": 8790016} {"current_steps": 1074, "total_steps": 3345, "loss": 0.6294, "lr": 1.916211240190479e-06, "epoch": 1.6053811659192825, "percentage": 32.11, "elapsed_time": "0:20:48", "remaining_time": "0:44:00", "throughput": 7046.19, "total_tokens": 8798208} {"current_steps": 1075, "total_steps": 3345, "loss": 0.9168, "lr": 1.9152175941995614e-06, "epoch": 1.6068759342301944, "percentage": 32.14, "elapsed_time": "0:20:49", "remaining_time": "0:43:59", "throughput": 7046.22, "total_tokens": 8806400} {"current_steps": 1076, "total_steps": 3345, "loss": 0.9799, "lr": 1.9142233614341914e-06, "epoch": 1.608370702541106, "percentage": 32.17, "elapsed_time": "0:20:50", "remaining_time": "0:43:57", "throughput": 7046.24, "total_tokens": 8814592} {"current_steps": 1077, "total_steps": 3345, "loss": 0.7283, "lr": 1.9132285427713613e-06, "epoch": 1.609865470852018, "percentage": 32.2, "elapsed_time": "0:20:52", "remaining_time": "0:43:56", "throughput": 7046.25, "total_tokens": 8822784} {"current_steps": 1078, "total_steps": 3345, "loss": 0.8832, "lr": 1.9122331390885794e-06, "epoch": 1.6113602391629298, "percentage": 32.23, "elapsed_time": "0:20:53", "remaining_time": "0:43:55", "throughput": 7046.26, "total_tokens": 8830976} {"current_steps": 1079, "total_steps": 3345, "loss": 0.6093, "lr": 1.9112371512638705e-06, "epoch": 1.6128550074738417, "percentage": 32.26, "elapsed_time": "0:20:54", "remaining_time": "0:43:54", "throughput": 7046.26, "total_tokens": 8839168} {"current_steps": 1080, "total_steps": 3345, "loss": 0.9198, "lr": 1.910240580175775e-06, "epoch": 1.6143497757847534, "percentage": 32.29, "elapsed_time": "0:20:55", "remaining_time": "0:43:53", "throughput": 7046.21, "total_tokens": 8847360} {"current_steps": 1081, "total_steps": 3345, "loss": 0.7761, "lr": 1.909243426703347e-06, "epoch": 1.615844544095665, "percentage": 32.32, "elapsed_time": "0:20:56", "remaining_time": "0:43:52", "throughput": 7046.24, "total_tokens": 8855552} {"current_steps": 1082, "total_steps": 3345, "loss": 0.8384, "lr": 1.908245691726154e-06, "epoch": 1.617339312406577, "percentage": 32.35, "elapsed_time": "0:20:57", "remaining_time": "0:43:50", "throughput": 7046.26, "total_tokens": 8863744} {"current_steps": 1083, "total_steps": 3345, "loss": 0.7026, "lr": 1.907247376124278e-06, "epoch": 1.6188340807174888, "percentage": 32.38, "elapsed_time": "0:20:59", "remaining_time": "0:43:49", "throughput": 7046.3, "total_tokens": 8871936} {"current_steps": 1084, "total_steps": 3345, "loss": 1.2489, "lr": 1.9062484807783116e-06, "epoch": 1.6203288490284007, "percentage": 32.41, "elapsed_time": "0:21:00", "remaining_time": "0:43:48", "throughput": 7046.35, "total_tokens": 8880128} {"current_steps": 1085, "total_steps": 3345, "loss": 0.6427, "lr": 1.9052490065693595e-06, "epoch": 1.6218236173393124, "percentage": 32.44, "elapsed_time": "0:21:01", "remaining_time": "0:43:47", "throughput": 7046.38, "total_tokens": 8888320} {"current_steps": 1086, "total_steps": 3345, "loss": 0.7576, "lr": 1.9042489543790371e-06, "epoch": 1.6233183856502242, "percentage": 32.47, "elapsed_time": "0:21:02", "remaining_time": "0:43:46", "throughput": 7046.4, "total_tokens": 8896512} {"current_steps": 1087, "total_steps": 3345, "loss": 1.0106, "lr": 1.903248325089469e-06, "epoch": 1.624813153961136, "percentage": 32.5, "elapsed_time": "0:21:03", "remaining_time": "0:43:45", "throughput": 7046.41, "total_tokens": 8904704} {"current_steps": 1088, "total_steps": 3345, "loss": 0.7489, "lr": 1.9022471195832899e-06, "epoch": 1.6263079222720478, "percentage": 32.53, "elapsed_time": "0:21:04", "remaining_time": "0:43:43", "throughput": 7046.43, "total_tokens": 8912896} {"current_steps": 1089, "total_steps": 3345, "loss": 0.8193, "lr": 1.9012453387436414e-06, "epoch": 1.6278026905829597, "percentage": 32.56, "elapsed_time": "0:21:06", "remaining_time": "0:43:42", "throughput": 7046.46, "total_tokens": 8921088} {"current_steps": 1090, "total_steps": 3345, "loss": 0.8844, "lr": 1.9002429834541738e-06, "epoch": 1.6292974588938716, "percentage": 32.59, "elapsed_time": "0:21:07", "remaining_time": "0:43:41", "throughput": 7046.48, "total_tokens": 8929280} {"current_steps": 1091, "total_steps": 3345, "loss": 0.7795, "lr": 1.899240054599043e-06, "epoch": 1.6307922272047832, "percentage": 32.62, "elapsed_time": "0:21:08", "remaining_time": "0:43:40", "throughput": 7046.51, "total_tokens": 8937472} {"current_steps": 1092, "total_steps": 3345, "loss": 0.7198, "lr": 1.8982365530629128e-06, "epoch": 1.6322869955156951, "percentage": 32.65, "elapsed_time": "0:21:09", "remaining_time": "0:43:39", "throughput": 7046.51, "total_tokens": 8945664} {"current_steps": 1093, "total_steps": 3345, "loss": 0.8681, "lr": 1.8972324797309494e-06, "epoch": 1.6337817638266068, "percentage": 32.68, "elapsed_time": "0:21:10", "remaining_time": "0:43:38", "throughput": 7046.54, "total_tokens": 8953856} {"current_steps": 1094, "total_steps": 3345, "loss": 0.8103, "lr": 1.8962278354888253e-06, "epoch": 1.6352765321375187, "percentage": 32.71, "elapsed_time": "0:21:11", "remaining_time": "0:43:36", "throughput": 7046.56, "total_tokens": 8962048} {"current_steps": 1095, "total_steps": 3345, "loss": 1.1215, "lr": 1.895222621222716e-06, "epoch": 1.6367713004484306, "percentage": 32.74, "elapsed_time": "0:21:12", "remaining_time": "0:43:35", "throughput": 7046.57, "total_tokens": 8970240} {"current_steps": 1096, "total_steps": 3345, "loss": 1.0053, "lr": 1.8942168378192998e-06, "epoch": 1.6382660687593424, "percentage": 32.77, "elapsed_time": "0:21:14", "remaining_time": "0:43:34", "throughput": 7046.59, "total_tokens": 8978432} {"current_steps": 1097, "total_steps": 3345, "loss": 0.9005, "lr": 1.8932104861657574e-06, "epoch": 1.639760837070254, "percentage": 32.8, "elapsed_time": "0:21:15", "remaining_time": "0:43:33", "throughput": 7046.6, "total_tokens": 8986624} {"current_steps": 1098, "total_steps": 3345, "loss": 0.7988, "lr": 1.8922035671497702e-06, "epoch": 1.6412556053811658, "percentage": 32.83, "elapsed_time": "0:21:16", "remaining_time": "0:43:32", "throughput": 7046.66, "total_tokens": 8994816} {"current_steps": 1099, "total_steps": 3345, "loss": 0.752, "lr": 1.8911960816595205e-06, "epoch": 1.6427503736920777, "percentage": 32.86, "elapsed_time": "0:21:17", "remaining_time": "0:43:31", "throughput": 7046.7, "total_tokens": 9003008} {"current_steps": 1100, "total_steps": 3345, "loss": 0.7636, "lr": 1.8901880305836895e-06, "epoch": 1.6442451420029895, "percentage": 32.88, "elapsed_time": "0:21:18", "remaining_time": "0:43:29", "throughput": 7046.73, "total_tokens": 9011200} {"current_steps": 1101, "total_steps": 3345, "loss": 0.4462, "lr": 1.8891794148114588e-06, "epoch": 1.6457399103139014, "percentage": 32.91, "elapsed_time": "0:21:19", "remaining_time": "0:43:28", "throughput": 7046.74, "total_tokens": 9019392} {"current_steps": 1102, "total_steps": 3345, "loss": 0.8737, "lr": 1.8881702352325066e-06, "epoch": 1.6472346786248133, "percentage": 32.94, "elapsed_time": "0:21:21", "remaining_time": "0:43:27", "throughput": 7046.77, "total_tokens": 9027584} {"current_steps": 1103, "total_steps": 3345, "loss": 0.8417, "lr": 1.8871604927370082e-06, "epoch": 1.648729446935725, "percentage": 32.97, "elapsed_time": "0:21:22", "remaining_time": "0:43:26", "throughput": 7046.79, "total_tokens": 9035776} {"current_steps": 1104, "total_steps": 3345, "loss": 0.9589, "lr": 1.8861501882156376e-06, "epoch": 1.6502242152466366, "percentage": 33.0, "elapsed_time": "0:21:23", "remaining_time": "0:43:25", "throughput": 7046.79, "total_tokens": 9043968} {"current_steps": 1105, "total_steps": 3345, "loss": 0.932, "lr": 1.8851393225595628e-06, "epoch": 1.6517189835575485, "percentage": 33.03, "elapsed_time": "0:21:24", "remaining_time": "0:43:24", "throughput": 7046.78, "total_tokens": 9052160} {"current_steps": 1106, "total_steps": 3345, "loss": 1.0544, "lr": 1.8841278966604467e-06, "epoch": 1.6532137518684604, "percentage": 33.06, "elapsed_time": "0:21:25", "remaining_time": "0:43:22", "throughput": 7046.79, "total_tokens": 9060352} {"current_steps": 1107, "total_steps": 3345, "loss": 0.7463, "lr": 1.8831159114104472e-06, "epoch": 1.6547085201793723, "percentage": 33.09, "elapsed_time": "0:21:26", "remaining_time": "0:43:21", "throughput": 7046.82, "total_tokens": 9068544} {"current_steps": 1108, "total_steps": 3345, "loss": 1.177, "lr": 1.8821033677022149e-06, "epoch": 1.656203288490284, "percentage": 33.12, "elapsed_time": "0:21:28", "remaining_time": "0:43:20", "throughput": 7046.84, "total_tokens": 9076736} {"current_steps": 1109, "total_steps": 3345, "loss": 0.6477, "lr": 1.8810902664288932e-06, "epoch": 1.6576980568011959, "percentage": 33.15, "elapsed_time": "0:21:29", "remaining_time": "0:43:19", "throughput": 7046.83, "total_tokens": 9084928} {"current_steps": 1110, "total_steps": 3345, "loss": 0.9408, "lr": 1.8800766084841181e-06, "epoch": 1.6591928251121075, "percentage": 33.18, "elapsed_time": "0:21:30", "remaining_time": "0:43:18", "throughput": 7046.84, "total_tokens": 9093120} {"current_steps": 1111, "total_steps": 3345, "loss": 0.6805, "lr": 1.8790623947620157e-06, "epoch": 1.6606875934230194, "percentage": 33.21, "elapsed_time": "0:21:31", "remaining_time": "0:43:17", "throughput": 7046.86, "total_tokens": 9101312} {"current_steps": 1112, "total_steps": 3345, "loss": 0.9766, "lr": 1.8780476261572024e-06, "epoch": 1.6621823617339313, "percentage": 33.24, "elapsed_time": "0:21:32", "remaining_time": "0:43:15", "throughput": 7046.88, "total_tokens": 9109504} {"current_steps": 1113, "total_steps": 3345, "loss": 0.9245, "lr": 1.8770323035647842e-06, "epoch": 1.6636771300448432, "percentage": 33.27, "elapsed_time": "0:21:33", "remaining_time": "0:43:14", "throughput": 7046.89, "total_tokens": 9117696} {"current_steps": 1114, "total_steps": 3345, "loss": 1.0339, "lr": 1.8760164278803562e-06, "epoch": 1.6651718983557549, "percentage": 33.3, "elapsed_time": "0:21:35", "remaining_time": "0:43:13", "throughput": 7046.91, "total_tokens": 9125888} {"current_steps": 1115, "total_steps": 3345, "loss": 1.0622, "lr": 1.8750000000000003e-06, "epoch": 1.6666666666666665, "percentage": 33.33, "elapsed_time": "0:21:36", "remaining_time": "0:43:12", "throughput": 7046.91, "total_tokens": 9134080} {"current_steps": 1116, "total_steps": 3345, "loss": 1.0599, "lr": 1.8739830208202866e-06, "epoch": 1.6681614349775784, "percentage": 33.36, "elapsed_time": "0:21:37", "remaining_time": "0:43:11", "throughput": 7046.93, "total_tokens": 9142272} {"current_steps": 1117, "total_steps": 3345, "loss": 0.8241, "lr": 1.8729654912382712e-06, "epoch": 1.6696562032884903, "percentage": 33.39, "elapsed_time": "0:21:38", "remaining_time": "0:43:10", "throughput": 7046.94, "total_tokens": 9150464} {"current_steps": 1118, "total_steps": 3345, "loss": 0.8551, "lr": 1.8719474121514953e-06, "epoch": 1.6711509715994022, "percentage": 33.42, "elapsed_time": "0:21:39", "remaining_time": "0:43:08", "throughput": 7046.93, "total_tokens": 9158656} {"current_steps": 1119, "total_steps": 3345, "loss": 0.9046, "lr": 1.8709287844579852e-06, "epoch": 1.672645739910314, "percentage": 33.45, "elapsed_time": "0:21:40", "remaining_time": "0:43:07", "throughput": 7046.94, "total_tokens": 9166848} {"current_steps": 1120, "total_steps": 3345, "loss": 1.0722, "lr": 1.8699096090562507e-06, "epoch": 1.6741405082212257, "percentage": 33.48, "elapsed_time": "0:21:41", "remaining_time": "0:43:06", "throughput": 7046.98, "total_tokens": 9175040} {"current_steps": 1121, "total_steps": 3345, "loss": 1.1095, "lr": 1.8688898868452855e-06, "epoch": 1.6756352765321374, "percentage": 33.51, "elapsed_time": "0:21:43", "remaining_time": "0:43:05", "throughput": 7047.0, "total_tokens": 9183232} {"current_steps": 1122, "total_steps": 3345, "loss": 0.8375, "lr": 1.8678696187245643e-06, "epoch": 1.6771300448430493, "percentage": 33.54, "elapsed_time": "0:21:44", "remaining_time": "0:43:04", "throughput": 7047.02, "total_tokens": 9191424} {"current_steps": 1123, "total_steps": 3345, "loss": 0.9692, "lr": 1.8668488055940454e-06, "epoch": 1.6786248131539612, "percentage": 33.57, "elapsed_time": "0:21:45", "remaining_time": "0:43:03", "throughput": 7047.05, "total_tokens": 9199616} {"current_steps": 1124, "total_steps": 3345, "loss": 0.7297, "lr": 1.8658274483541653e-06, "epoch": 1.680119581464873, "percentage": 33.6, "elapsed_time": "0:21:46", "remaining_time": "0:43:01", "throughput": 7047.1, "total_tokens": 9207808} {"current_steps": 1125, "total_steps": 3345, "loss": 0.7464, "lr": 1.8648055479058423e-06, "epoch": 1.6816143497757847, "percentage": 33.63, "elapsed_time": "0:21:47", "remaining_time": "0:43:00", "throughput": 7047.13, "total_tokens": 9216000} {"current_steps": 1126, "total_steps": 3345, "loss": 0.7434, "lr": 1.8637831051504734e-06, "epoch": 1.6831091180866966, "percentage": 33.66, "elapsed_time": "0:21:48", "remaining_time": "0:42:59", "throughput": 7047.13, "total_tokens": 9224192} {"current_steps": 1127, "total_steps": 3345, "loss": 0.7044, "lr": 1.8627601209899337e-06, "epoch": 1.6846038863976083, "percentage": 33.69, "elapsed_time": "0:21:50", "remaining_time": "0:42:58", "throughput": 7047.14, "total_tokens": 9232384} {"current_steps": 1128, "total_steps": 3345, "loss": 0.7935, "lr": 1.861736596326576e-06, "epoch": 1.6860986547085202, "percentage": 33.72, "elapsed_time": "0:21:51", "remaining_time": "0:42:57", "throughput": 7047.15, "total_tokens": 9240576} {"current_steps": 1129, "total_steps": 3345, "loss": 0.9189, "lr": 1.8607125320632301e-06, "epoch": 1.687593423019432, "percentage": 33.75, "elapsed_time": "0:21:52", "remaining_time": "0:42:55", "throughput": 7047.18, "total_tokens": 9248768} {"current_steps": 1130, "total_steps": 3345, "loss": 0.8729, "lr": 1.8596879291032015e-06, "epoch": 1.689088191330344, "percentage": 33.78, "elapsed_time": "0:21:53", "remaining_time": "0:42:54", "throughput": 7047.19, "total_tokens": 9256960} {"current_steps": 1131, "total_steps": 3345, "loss": 0.6905, "lr": 1.8586627883502708e-06, "epoch": 1.6905829596412556, "percentage": 33.81, "elapsed_time": "0:21:54", "remaining_time": "0:42:53", "throughput": 7047.23, "total_tokens": 9265152} {"current_steps": 1132, "total_steps": 3345, "loss": 0.9088, "lr": 1.8576371107086931e-06, "epoch": 1.6920777279521673, "percentage": 33.84, "elapsed_time": "0:21:55", "remaining_time": "0:42:52", "throughput": 7047.28, "total_tokens": 9273344} {"current_steps": 1133, "total_steps": 3345, "loss": 0.687, "lr": 1.8566108970831972e-06, "epoch": 1.6935724962630792, "percentage": 33.87, "elapsed_time": "0:21:57", "remaining_time": "0:42:51", "throughput": 7047.32, "total_tokens": 9281536} {"current_steps": 1134, "total_steps": 3345, "loss": 0.8834, "lr": 1.8555841483789843e-06, "epoch": 1.695067264573991, "percentage": 33.9, "elapsed_time": "0:21:58", "remaining_time": "0:42:50", "throughput": 7047.36, "total_tokens": 9289728} {"current_steps": 1135, "total_steps": 3345, "loss": 0.8831, "lr": 1.8545568655017282e-06, "epoch": 1.696562032884903, "percentage": 33.93, "elapsed_time": "0:21:59", "remaining_time": "0:42:48", "throughput": 7047.4, "total_tokens": 9297920} {"current_steps": 1136, "total_steps": 3345, "loss": 0.6699, "lr": 1.853529049357573e-06, "epoch": 1.6980568011958148, "percentage": 33.96, "elapsed_time": "0:22:00", "remaining_time": "0:42:47", "throughput": 7047.43, "total_tokens": 9306112} {"current_steps": 1137, "total_steps": 3345, "loss": 0.7568, "lr": 1.8525007008531342e-06, "epoch": 1.6995515695067265, "percentage": 33.99, "elapsed_time": "0:22:01", "remaining_time": "0:42:46", "throughput": 7047.44, "total_tokens": 9314304} {"current_steps": 1138, "total_steps": 3345, "loss": 0.89, "lr": 1.8514718208954966e-06, "epoch": 1.7010463378176381, "percentage": 34.02, "elapsed_time": "0:22:02", "remaining_time": "0:42:45", "throughput": 7047.45, "total_tokens": 9322496} {"current_steps": 1139, "total_steps": 3345, "loss": 0.6759, "lr": 1.8504424103922129e-06, "epoch": 1.70254110612855, "percentage": 34.05, "elapsed_time": "0:22:03", "remaining_time": "0:42:44", "throughput": 7047.46, "total_tokens": 9330688} {"current_steps": 1140, "total_steps": 3345, "loss": 0.8024, "lr": 1.849412470251305e-06, "epoch": 1.704035874439462, "percentage": 34.08, "elapsed_time": "0:22:05", "remaining_time": "0:42:43", "throughput": 7047.45, "total_tokens": 9338880} {"current_steps": 1141, "total_steps": 3345, "loss": 0.9901, "lr": 1.848382001381261e-06, "epoch": 1.7055306427503738, "percentage": 34.11, "elapsed_time": "0:22:06", "remaining_time": "0:42:41", "throughput": 7047.47, "total_tokens": 9347072} {"current_steps": 1142, "total_steps": 3345, "loss": 0.6605, "lr": 1.847351004691036e-06, "epoch": 1.7070254110612855, "percentage": 34.14, "elapsed_time": "0:22:07", "remaining_time": "0:42:40", "throughput": 7047.47, "total_tokens": 9355264} {"current_steps": 1143, "total_steps": 3345, "loss": 0.6703, "lr": 1.8463194810900502e-06, "epoch": 1.7085201793721974, "percentage": 34.17, "elapsed_time": "0:22:08", "remaining_time": "0:42:39", "throughput": 7047.48, "total_tokens": 9363456} {"current_steps": 1144, "total_steps": 3345, "loss": 1.0689, "lr": 1.8452874314881897e-06, "epoch": 1.710014947683109, "percentage": 34.2, "elapsed_time": "0:22:09", "remaining_time": "0:42:38", "throughput": 7047.47, "total_tokens": 9371648} {"current_steps": 1145, "total_steps": 3345, "loss": 0.8552, "lr": 1.8442548567958033e-06, "epoch": 1.711509715994021, "percentage": 34.23, "elapsed_time": "0:22:10", "remaining_time": "0:42:37", "throughput": 7047.47, "total_tokens": 9379840} {"current_steps": 1146, "total_steps": 3345, "loss": 0.9705, "lr": 1.8432217579237032e-06, "epoch": 1.7130044843049328, "percentage": 34.26, "elapsed_time": "0:22:12", "remaining_time": "0:42:36", "throughput": 7047.48, "total_tokens": 9388032} {"current_steps": 1147, "total_steps": 3345, "loss": 0.6831, "lr": 1.8421881357831647e-06, "epoch": 1.7144992526158447, "percentage": 34.29, "elapsed_time": "0:22:13", "remaining_time": "0:42:34", "throughput": 7047.45, "total_tokens": 9396224} {"current_steps": 1148, "total_steps": 3345, "loss": 0.9478, "lr": 1.841153991285924e-06, "epoch": 1.7159940209267563, "percentage": 34.32, "elapsed_time": "0:22:14", "remaining_time": "0:42:33", "throughput": 7047.44, "total_tokens": 9404416} {"current_steps": 1149, "total_steps": 3345, "loss": 0.8535, "lr": 1.8401193253441773e-06, "epoch": 1.717488789237668, "percentage": 34.35, "elapsed_time": "0:22:15", "remaining_time": "0:42:32", "throughput": 7047.41, "total_tokens": 9412608} {"current_steps": 1150, "total_steps": 3345, "loss": 1.0491, "lr": 1.8390841388705832e-06, "epoch": 1.71898355754858, "percentage": 34.38, "elapsed_time": "0:22:16", "remaining_time": "0:42:31", "throughput": 7047.43, "total_tokens": 9420800} {"current_steps": 1151, "total_steps": 3345, "loss": 0.8554, "lr": 1.8380484327782566e-06, "epoch": 1.7204783258594918, "percentage": 34.41, "elapsed_time": "0:22:17", "remaining_time": "0:42:30", "throughput": 7047.42, "total_tokens": 9428992} {"current_steps": 1152, "total_steps": 3345, "loss": 0.9547, "lr": 1.8370122079807727e-06, "epoch": 1.7219730941704037, "percentage": 34.44, "elapsed_time": "0:22:19", "remaining_time": "0:42:29", "throughput": 7047.44, "total_tokens": 9437184} {"current_steps": 1153, "total_steps": 3345, "loss": 0.9568, "lr": 1.8359754653921635e-06, "epoch": 1.7234678624813156, "percentage": 34.47, "elapsed_time": "0:22:20", "remaining_time": "0:42:27", "throughput": 7047.46, "total_tokens": 9445376} {"current_steps": 1154, "total_steps": 3345, "loss": 0.7253, "lr": 1.834938205926918e-06, "epoch": 1.7249626307922272, "percentage": 34.5, "elapsed_time": "0:22:21", "remaining_time": "0:42:26", "throughput": 7047.49, "total_tokens": 9453568} {"current_steps": 1155, "total_steps": 3345, "loss": 0.5915, "lr": 1.8339004304999809e-06, "epoch": 1.726457399103139, "percentage": 34.53, "elapsed_time": "0:22:22", "remaining_time": "0:42:25", "throughput": 7047.52, "total_tokens": 9461760} {"current_steps": 1156, "total_steps": 3345, "loss": 0.8704, "lr": 1.8328621400267522e-06, "epoch": 1.7279521674140508, "percentage": 34.56, "elapsed_time": "0:22:23", "remaining_time": "0:42:24", "throughput": 7047.52, "total_tokens": 9469952} {"current_steps": 1157, "total_steps": 3345, "loss": 0.9091, "lr": 1.8318233354230856e-06, "epoch": 1.7294469357249627, "percentage": 34.59, "elapsed_time": "0:22:24", "remaining_time": "0:42:23", "throughput": 7047.51, "total_tokens": 9478144} {"current_steps": 1158, "total_steps": 3345, "loss": 0.9603, "lr": 1.8307840176052892e-06, "epoch": 1.7309417040358746, "percentage": 34.62, "elapsed_time": "0:22:26", "remaining_time": "0:42:22", "throughput": 7047.5, "total_tokens": 9486336} {"current_steps": 1159, "total_steps": 3345, "loss": 0.8854, "lr": 1.8297441874901228e-06, "epoch": 1.7324364723467862, "percentage": 34.65, "elapsed_time": "0:22:27", "remaining_time": "0:42:20", "throughput": 7047.53, "total_tokens": 9494528} {"current_steps": 1160, "total_steps": 3345, "loss": 0.6919, "lr": 1.8287038459947996e-06, "epoch": 1.733931240657698, "percentage": 34.68, "elapsed_time": "0:22:28", "remaining_time": "0:42:19", "throughput": 7047.52, "total_tokens": 9502720} {"current_steps": 1161, "total_steps": 3345, "loss": 0.9909, "lr": 1.8276629940369822e-06, "epoch": 1.7354260089686098, "percentage": 34.71, "elapsed_time": "0:22:29", "remaining_time": "0:42:18", "throughput": 7047.54, "total_tokens": 9510912} {"current_steps": 1162, "total_steps": 3345, "loss": 1.106, "lr": 1.826621632534785e-06, "epoch": 1.7369207772795217, "percentage": 34.74, "elapsed_time": "0:22:30", "remaining_time": "0:42:17", "throughput": 7047.56, "total_tokens": 9519104} {"current_steps": 1163, "total_steps": 3345, "loss": 0.7569, "lr": 1.8255797624067706e-06, "epoch": 1.7384155455904335, "percentage": 34.77, "elapsed_time": "0:22:31", "remaining_time": "0:42:16", "throughput": 7047.58, "total_tokens": 9527296} {"current_steps": 1164, "total_steps": 3345, "loss": 1.0772, "lr": 1.8245373845719505e-06, "epoch": 1.7399103139013454, "percentage": 34.8, "elapsed_time": "0:22:33", "remaining_time": "0:42:15", "throughput": 7047.61, "total_tokens": 9535488} {"current_steps": 1165, "total_steps": 3345, "loss": 1.0787, "lr": 1.823494499949785e-06, "epoch": 1.741405082212257, "percentage": 34.83, "elapsed_time": "0:22:34", "remaining_time": "0:42:13", "throughput": 7047.63, "total_tokens": 9543680} {"current_steps": 1166, "total_steps": 3345, "loss": 0.8483, "lr": 1.82245110946018e-06, "epoch": 1.7428998505231688, "percentage": 34.86, "elapsed_time": "0:22:35", "remaining_time": "0:42:12", "throughput": 7047.61, "total_tokens": 9551872} {"current_steps": 1167, "total_steps": 3345, "loss": 1.1009, "lr": 1.8214072140234884e-06, "epoch": 1.7443946188340806, "percentage": 34.89, "elapsed_time": "0:22:36", "remaining_time": "0:42:11", "throughput": 7047.64, "total_tokens": 9560064} {"current_steps": 1168, "total_steps": 3345, "loss": 0.7891, "lr": 1.8203628145605083e-06, "epoch": 1.7458893871449925, "percentage": 34.92, "elapsed_time": "0:22:37", "remaining_time": "0:42:10", "throughput": 7047.62, "total_tokens": 9568256} {"current_steps": 1169, "total_steps": 3345, "loss": 1.1094, "lr": 1.819317911992483e-06, "epoch": 1.7473841554559044, "percentage": 34.95, "elapsed_time": "0:22:38", "remaining_time": "0:42:09", "throughput": 7047.64, "total_tokens": 9576448} {"current_steps": 1170, "total_steps": 3345, "loss": 0.9259, "lr": 1.818272507241099e-06, "epoch": 1.7488789237668163, "percentage": 34.98, "elapsed_time": "0:22:39", "remaining_time": "0:42:08", "throughput": 7047.64, "total_tokens": 9584640} {"current_steps": 1171, "total_steps": 3345, "loss": 0.9041, "lr": 1.8172266012284856e-06, "epoch": 1.750373692077728, "percentage": 35.01, "elapsed_time": "0:22:41", "remaining_time": "0:42:06", "throughput": 7047.66, "total_tokens": 9592832} {"current_steps": 1172, "total_steps": 3345, "loss": 0.9622, "lr": 1.8161801948772149e-06, "epoch": 1.7518684603886396, "percentage": 35.04, "elapsed_time": "0:22:42", "remaining_time": "0:42:05", "throughput": 7047.53, "total_tokens": 9601024} {"current_steps": 1173, "total_steps": 3345, "loss": 0.9113, "lr": 1.815133289110299e-06, "epoch": 1.7533632286995515, "percentage": 35.07, "elapsed_time": "0:22:43", "remaining_time": "0:42:04", "throughput": 7047.5, "total_tokens": 9609216} {"current_steps": 1174, "total_steps": 3345, "loss": 0.9546, "lr": 1.8140858848511927e-06, "epoch": 1.7548579970104634, "percentage": 35.1, "elapsed_time": "0:22:44", "remaining_time": "0:42:03", "throughput": 7047.52, "total_tokens": 9617408} {"current_steps": 1175, "total_steps": 3345, "loss": 0.8225, "lr": 1.8130379830237884e-06, "epoch": 1.7563527653213753, "percentage": 35.13, "elapsed_time": "0:22:45", "remaining_time": "0:42:02", "throughput": 7047.54, "total_tokens": 9625600} {"current_steps": 1176, "total_steps": 3345, "loss": 0.7508, "lr": 1.8119895845524185e-06, "epoch": 1.757847533632287, "percentage": 35.16, "elapsed_time": "0:22:46", "remaining_time": "0:42:01", "throughput": 7047.56, "total_tokens": 9633792} {"current_steps": 1177, "total_steps": 3345, "loss": 0.8397, "lr": 1.8109406903618532e-06, "epoch": 1.7593423019431988, "percentage": 35.19, "elapsed_time": "0:22:48", "remaining_time": "0:42:00", "throughput": 7047.59, "total_tokens": 9641984} {"current_steps": 1178, "total_steps": 3345, "loss": 0.6013, "lr": 1.8098913013773004e-06, "epoch": 1.7608370702541105, "percentage": 35.22, "elapsed_time": "0:22:49", "remaining_time": "0:41:58", "throughput": 7047.59, "total_tokens": 9650176} {"current_steps": 1179, "total_steps": 3345, "loss": 0.9233, "lr": 1.8088414185244034e-06, "epoch": 1.7623318385650224, "percentage": 35.25, "elapsed_time": "0:22:50", "remaining_time": "0:41:57", "throughput": 7047.6, "total_tokens": 9658368} {"current_steps": 1180, "total_steps": 3345, "loss": 1.0989, "lr": 1.8077910427292424e-06, "epoch": 1.7638266068759343, "percentage": 35.28, "elapsed_time": "0:22:51", "remaining_time": "0:41:56", "throughput": 7047.62, "total_tokens": 9666560} {"current_steps": 1181, "total_steps": 3345, "loss": 0.9456, "lr": 1.8067401749183316e-06, "epoch": 1.7653213751868462, "percentage": 35.31, "elapsed_time": "0:22:52", "remaining_time": "0:41:55", "throughput": 7047.63, "total_tokens": 9674752} {"current_steps": 1182, "total_steps": 3345, "loss": 0.7974, "lr": 1.8056888160186193e-06, "epoch": 1.7668161434977578, "percentage": 35.34, "elapsed_time": "0:22:53", "remaining_time": "0:41:54", "throughput": 7047.65, "total_tokens": 9682944} {"current_steps": 1183, "total_steps": 3345, "loss": 0.6949, "lr": 1.804636966957487e-06, "epoch": 1.7683109118086695, "percentage": 35.37, "elapsed_time": "0:22:55", "remaining_time": "0:41:53", "throughput": 7047.67, "total_tokens": 9691136} {"current_steps": 1184, "total_steps": 3345, "loss": 0.9265, "lr": 1.8035846286627488e-06, "epoch": 1.7698056801195814, "percentage": 35.4, "elapsed_time": "0:22:56", "remaining_time": "0:41:51", "throughput": 7047.67, "total_tokens": 9699328} {"current_steps": 1185, "total_steps": 3345, "loss": 0.9055, "lr": 1.8025318020626498e-06, "epoch": 1.7713004484304933, "percentage": 35.43, "elapsed_time": "0:22:57", "remaining_time": "0:41:50", "throughput": 7047.67, "total_tokens": 9707520} {"current_steps": 1186, "total_steps": 3345, "loss": 0.7479, "lr": 1.801478488085867e-06, "epoch": 1.7727952167414052, "percentage": 35.46, "elapsed_time": "0:22:58", "remaining_time": "0:41:49", "throughput": 7047.69, "total_tokens": 9715712} {"current_steps": 1187, "total_steps": 3345, "loss": 0.6241, "lr": 1.800424687661506e-06, "epoch": 1.774289985052317, "percentage": 35.49, "elapsed_time": "0:22:59", "remaining_time": "0:41:48", "throughput": 7047.68, "total_tokens": 9723904} {"current_steps": 1188, "total_steps": 3345, "loss": 0.6206, "lr": 1.7993704017191021e-06, "epoch": 1.7757847533632287, "percentage": 35.52, "elapsed_time": "0:23:00", "remaining_time": "0:41:47", "throughput": 7047.67, "total_tokens": 9732096} {"current_steps": 1189, "total_steps": 3345, "loss": 0.579, "lr": 1.7983156311886188e-06, "epoch": 1.7772795216741404, "percentage": 35.55, "elapsed_time": "0:23:02", "remaining_time": "0:41:46", "throughput": 7047.64, "total_tokens": 9740288} {"current_steps": 1190, "total_steps": 3345, "loss": 0.911, "lr": 1.7972603770004465e-06, "epoch": 1.7787742899850523, "percentage": 35.58, "elapsed_time": "0:23:03", "remaining_time": "0:41:44", "throughput": 7047.61, "total_tokens": 9748480} {"current_steps": 1191, "total_steps": 3345, "loss": 0.8916, "lr": 1.7962046400854035e-06, "epoch": 1.7802690582959642, "percentage": 35.61, "elapsed_time": "0:23:04", "remaining_time": "0:41:43", "throughput": 7047.6, "total_tokens": 9756672} {"current_steps": 1192, "total_steps": 3345, "loss": 1.032, "lr": 1.7951484213747328e-06, "epoch": 1.781763826606876, "percentage": 35.64, "elapsed_time": "0:23:05", "remaining_time": "0:41:42", "throughput": 7047.62, "total_tokens": 9764864} {"current_steps": 1193, "total_steps": 3345, "loss": 0.6609, "lr": 1.7940917218001025e-06, "epoch": 1.7832585949177877, "percentage": 35.67, "elapsed_time": "0:23:06", "remaining_time": "0:41:41", "throughput": 7047.64, "total_tokens": 9773056} {"current_steps": 1194, "total_steps": 3345, "loss": 0.8271, "lr": 1.793034542293605e-06, "epoch": 1.7847533632286996, "percentage": 35.7, "elapsed_time": "0:23:07", "remaining_time": "0:41:40", "throughput": 7047.64, "total_tokens": 9781248} {"current_steps": 1195, "total_steps": 3345, "loss": 0.9614, "lr": 1.7919768837877568e-06, "epoch": 1.7862481315396113, "percentage": 35.72, "elapsed_time": "0:23:09", "remaining_time": "0:41:39", "throughput": 7047.65, "total_tokens": 9789440} {"current_steps": 1196, "total_steps": 3345, "loss": 0.9831, "lr": 1.790918747215496e-06, "epoch": 1.7877428998505231, "percentage": 35.75, "elapsed_time": "0:23:10", "remaining_time": "0:41:37", "throughput": 7047.66, "total_tokens": 9797632} {"current_steps": 1197, "total_steps": 3345, "loss": 0.7491, "lr": 1.789860133510182e-06, "epoch": 1.789237668161435, "percentage": 35.78, "elapsed_time": "0:23:11", "remaining_time": "0:41:36", "throughput": 7047.65, "total_tokens": 9805824} {"current_steps": 1198, "total_steps": 3345, "loss": 0.6215, "lr": 1.7888010436055964e-06, "epoch": 1.790732436472347, "percentage": 35.81, "elapsed_time": "0:23:12", "remaining_time": "0:41:35", "throughput": 7047.67, "total_tokens": 9814016} {"current_steps": 1199, "total_steps": 3345, "loss": 0.9444, "lr": 1.7877414784359399e-06, "epoch": 1.7922272047832586, "percentage": 35.84, "elapsed_time": "0:23:13", "remaining_time": "0:41:34", "throughput": 7047.67, "total_tokens": 9822208} {"current_steps": 1200, "total_steps": 3345, "loss": 0.7009, "lr": 1.7866814389358323e-06, "epoch": 1.7937219730941703, "percentage": 35.87, "elapsed_time": "0:23:14", "remaining_time": "0:41:33", "throughput": 7047.67, "total_tokens": 9830400} {"current_steps": 1201, "total_steps": 3345, "loss": 0.7895, "lr": 1.7856209260403126e-06, "epoch": 1.7952167414050821, "percentage": 35.9, "elapsed_time": "0:23:16", "remaining_time": "0:41:32", "throughput": 7047.68, "total_tokens": 9838592} {"current_steps": 1202, "total_steps": 3345, "loss": 0.8112, "lr": 1.7845599406848365e-06, "epoch": 1.796711509715994, "percentage": 35.93, "elapsed_time": "0:23:17", "remaining_time": "0:41:30", "throughput": 7047.7, "total_tokens": 9846784} {"current_steps": 1203, "total_steps": 3345, "loss": 0.8209, "lr": 1.7834984838052777e-06, "epoch": 1.798206278026906, "percentage": 35.96, "elapsed_time": "0:23:18", "remaining_time": "0:41:29", "throughput": 7047.66, "total_tokens": 9854976} {"current_steps": 1204, "total_steps": 3345, "loss": 0.9124, "lr": 1.7824365563379241e-06, "epoch": 1.7997010463378178, "percentage": 35.99, "elapsed_time": "0:23:19", "remaining_time": "0:41:28", "throughput": 7047.59, "total_tokens": 9863168} {"current_steps": 1205, "total_steps": 3345, "loss": 0.8698, "lr": 1.7813741592194806e-06, "epoch": 1.8011958146487295, "percentage": 36.02, "elapsed_time": "0:23:20", "remaining_time": "0:41:27", "throughput": 7047.6, "total_tokens": 9871360} {"current_steps": 1206, "total_steps": 3345, "loss": 1.0273, "lr": 1.7803112933870641e-06, "epoch": 1.8026905829596411, "percentage": 36.05, "elapsed_time": "0:23:21", "remaining_time": "0:41:26", "throughput": 7047.61, "total_tokens": 9879552} {"current_steps": 1207, "total_steps": 3345, "loss": 0.8047, "lr": 1.779247959778207e-06, "epoch": 1.804185351270553, "percentage": 36.08, "elapsed_time": "0:23:22", "remaining_time": "0:41:25", "throughput": 7047.6, "total_tokens": 9887744} {"current_steps": 1208, "total_steps": 3345, "loss": 1.1327, "lr": 1.7781841593308532e-06, "epoch": 1.805680119581465, "percentage": 36.11, "elapsed_time": "0:23:24", "remaining_time": "0:41:24", "throughput": 7047.6, "total_tokens": 9895936} {"current_steps": 1209, "total_steps": 3345, "loss": 0.9154, "lr": 1.777119892983359e-06, "epoch": 1.8071748878923768, "percentage": 36.14, "elapsed_time": "0:23:25", "remaining_time": "0:41:22", "throughput": 7047.6, "total_tokens": 9904128} {"current_steps": 1210, "total_steps": 3345, "loss": 0.5924, "lr": 1.7760551616744905e-06, "epoch": 1.8086696562032885, "percentage": 36.17, "elapsed_time": "0:23:26", "remaining_time": "0:41:21", "throughput": 7047.59, "total_tokens": 9912320} {"current_steps": 1211, "total_steps": 3345, "loss": 0.8654, "lr": 1.774989966343426e-06, "epoch": 1.8101644245142003, "percentage": 36.2, "elapsed_time": "0:23:27", "remaining_time": "0:41:20", "throughput": 7047.6, "total_tokens": 9920512} {"current_steps": 1212, "total_steps": 3345, "loss": 0.9056, "lr": 1.7739243079297517e-06, "epoch": 1.811659192825112, "percentage": 36.23, "elapsed_time": "0:23:28", "remaining_time": "0:41:19", "throughput": 7047.6, "total_tokens": 9928704} {"current_steps": 1213, "total_steps": 3345, "loss": 0.8381, "lr": 1.7728581873734622e-06, "epoch": 1.813153961136024, "percentage": 36.26, "elapsed_time": "0:23:29", "remaining_time": "0:41:18", "throughput": 7047.53, "total_tokens": 9936896} {"current_steps": 1214, "total_steps": 3345, "loss": 0.8906, "lr": 1.7717916056149597e-06, "epoch": 1.8146487294469358, "percentage": 36.29, "elapsed_time": "0:23:31", "remaining_time": "0:41:17", "throughput": 7047.51, "total_tokens": 9945088} {"current_steps": 1215, "total_steps": 3345, "loss": 0.7499, "lr": 1.7707245635950537e-06, "epoch": 1.8161434977578477, "percentage": 36.32, "elapsed_time": "0:23:32", "remaining_time": "0:41:15", "throughput": 7047.44, "total_tokens": 9953280} {"current_steps": 1216, "total_steps": 3345, "loss": 0.8841, "lr": 1.7696570622549602e-06, "epoch": 1.8176382660687593, "percentage": 36.35, "elapsed_time": "0:23:33", "remaining_time": "0:41:14", "throughput": 7047.43, "total_tokens": 9961472} {"current_steps": 1217, "total_steps": 3345, "loss": 0.9248, "lr": 1.7685891025362987e-06, "epoch": 1.819133034379671, "percentage": 36.38, "elapsed_time": "0:23:34", "remaining_time": "0:41:13", "throughput": 7047.43, "total_tokens": 9969664} {"current_steps": 1218, "total_steps": 3345, "loss": 1.0521, "lr": 1.7675206853810945e-06, "epoch": 1.8206278026905829, "percentage": 36.41, "elapsed_time": "0:23:35", "remaining_time": "0:41:12", "throughput": 7047.43, "total_tokens": 9977856} {"current_steps": 1219, "total_steps": 3345, "loss": 1.0231, "lr": 1.7664518117317758e-06, "epoch": 1.8221225710014948, "percentage": 36.44, "elapsed_time": "0:23:36", "remaining_time": "0:41:11", "throughput": 7047.42, "total_tokens": 9986048} {"current_steps": 1220, "total_steps": 3345, "loss": 0.7707, "lr": 1.7653824825311738e-06, "epoch": 1.8236173393124067, "percentage": 36.47, "elapsed_time": "0:23:38", "remaining_time": "0:41:10", "throughput": 7047.44, "total_tokens": 9994240} {"current_steps": 1221, "total_steps": 3345, "loss": 0.7372, "lr": 1.7643126987225211e-06, "epoch": 1.8251121076233185, "percentage": 36.5, "elapsed_time": "0:23:39", "remaining_time": "0:41:08", "throughput": 7047.44, "total_tokens": 10002432} {"current_steps": 1222, "total_steps": 3345, "loss": 0.8823, "lr": 1.763242461249452e-06, "epoch": 1.8266068759342302, "percentage": 36.53, "elapsed_time": "0:23:40", "remaining_time": "0:41:07", "throughput": 7047.42, "total_tokens": 10010624} {"current_steps": 1223, "total_steps": 3345, "loss": 0.871, "lr": 1.7621717710559993e-06, "epoch": 1.8281016442451419, "percentage": 36.56, "elapsed_time": "0:23:41", "remaining_time": "0:41:06", "throughput": 7047.42, "total_tokens": 10018816} {"current_steps": 1224, "total_steps": 3345, "loss": 0.8596, "lr": 1.7611006290865975e-06, "epoch": 1.8295964125560538, "percentage": 36.59, "elapsed_time": "0:23:42", "remaining_time": "0:41:05", "throughput": 7047.42, "total_tokens": 10027008} {"current_steps": 1225, "total_steps": 3345, "loss": 0.6245, "lr": 1.7600290362860777e-06, "epoch": 1.8310911808669657, "percentage": 36.62, "elapsed_time": "0:23:43", "remaining_time": "0:41:04", "throughput": 7047.42, "total_tokens": 10035200} {"current_steps": 1226, "total_steps": 3345, "loss": 0.5992, "lr": 1.7589569935996699e-06, "epoch": 1.8325859491778775, "percentage": 36.65, "elapsed_time": "0:23:45", "remaining_time": "0:41:03", "throughput": 7047.42, "total_tokens": 10043392} {"current_steps": 1227, "total_steps": 3345, "loss": 0.9822, "lr": 1.7578845019729996e-06, "epoch": 1.8340807174887892, "percentage": 36.68, "elapsed_time": "0:23:46", "remaining_time": "0:41:01", "throughput": 7047.44, "total_tokens": 10051584} {"current_steps": 1228, "total_steps": 3345, "loss": 0.6609, "lr": 1.75681156235209e-06, "epoch": 1.835575485799701, "percentage": 36.71, "elapsed_time": "0:23:47", "remaining_time": "0:41:00", "throughput": 7047.44, "total_tokens": 10059776} {"current_steps": 1229, "total_steps": 3345, "loss": 0.948, "lr": 1.7557381756833583e-06, "epoch": 1.8370702541106128, "percentage": 36.74, "elapsed_time": "0:23:48", "remaining_time": "0:40:59", "throughput": 7047.44, "total_tokens": 10067968} {"current_steps": 1230, "total_steps": 3345, "loss": 0.7239, "lr": 1.7546643429136162e-06, "epoch": 1.8385650224215246, "percentage": 36.77, "elapsed_time": "0:23:49", "remaining_time": "0:40:58", "throughput": 7047.44, "total_tokens": 10076160} {"current_steps": 1231, "total_steps": 3345, "loss": 0.9666, "lr": 1.7535900649900688e-06, "epoch": 1.8400597907324365, "percentage": 36.8, "elapsed_time": "0:23:50", "remaining_time": "0:40:57", "throughput": 7047.44, "total_tokens": 10084352} {"current_steps": 1232, "total_steps": 3345, "loss": 0.7627, "lr": 1.7525153428603148e-06, "epoch": 1.8415545590433484, "percentage": 36.83, "elapsed_time": "0:23:52", "remaining_time": "0:40:56", "throughput": 7047.45, "total_tokens": 10092544} {"current_steps": 1233, "total_steps": 3345, "loss": 0.7271, "lr": 1.7514401774723427e-06, "epoch": 1.84304932735426, "percentage": 36.86, "elapsed_time": "0:23:53", "remaining_time": "0:40:54", "throughput": 7047.46, "total_tokens": 10100736} {"current_steps": 1234, "total_steps": 3345, "loss": 0.6308, "lr": 1.7503645697745347e-06, "epoch": 1.8445440956651717, "percentage": 36.89, "elapsed_time": "0:23:54", "remaining_time": "0:40:53", "throughput": 7047.46, "total_tokens": 10108928} {"current_steps": 1235, "total_steps": 3345, "loss": 1.1538, "lr": 1.7492885207156609e-06, "epoch": 1.8460388639760836, "percentage": 36.92, "elapsed_time": "0:23:55", "remaining_time": "0:40:52", "throughput": 7047.41, "total_tokens": 10117120} {"current_steps": 1236, "total_steps": 3345, "loss": 0.9121, "lr": 1.7482120312448816e-06, "epoch": 1.8475336322869955, "percentage": 36.95, "elapsed_time": "0:23:56", "remaining_time": "0:40:51", "throughput": 7047.39, "total_tokens": 10125312} {"current_steps": 1237, "total_steps": 3345, "loss": 0.6205, "lr": 1.747135102311746e-06, "epoch": 1.8490284005979074, "percentage": 36.98, "elapsed_time": "0:23:57", "remaining_time": "0:40:50", "throughput": 7047.38, "total_tokens": 10133504} {"current_steps": 1238, "total_steps": 3345, "loss": 0.9325, "lr": 1.74605773486619e-06, "epoch": 1.8505231689088193, "percentage": 37.01, "elapsed_time": "0:23:59", "remaining_time": "0:40:49", "throughput": 7047.39, "total_tokens": 10141696} {"current_steps": 1239, "total_steps": 3345, "loss": 0.6812, "lr": 1.7449799298585369e-06, "epoch": 1.852017937219731, "percentage": 37.04, "elapsed_time": "0:24:00", "remaining_time": "0:40:48", "throughput": 7047.39, "total_tokens": 10149888} {"current_steps": 1240, "total_steps": 3345, "loss": 0.818, "lr": 1.743901688239496e-06, "epoch": 1.8535127055306426, "percentage": 37.07, "elapsed_time": "0:24:01", "remaining_time": "0:40:46", "throughput": 7047.39, "total_tokens": 10158080} {"current_steps": 1241, "total_steps": 3345, "loss": 0.6232, "lr": 1.742823010960161e-06, "epoch": 1.8550074738415545, "percentage": 37.1, "elapsed_time": "0:24:02", "remaining_time": "0:40:45", "throughput": 7047.37, "total_tokens": 10166272} {"current_steps": 1242, "total_steps": 3345, "loss": 0.8292, "lr": 1.7417438989720112e-06, "epoch": 1.8565022421524664, "percentage": 37.13, "elapsed_time": "0:24:03", "remaining_time": "0:40:44", "throughput": 7047.37, "total_tokens": 10174464} {"current_steps": 1243, "total_steps": 3345, "loss": 0.8645, "lr": 1.740664353226908e-06, "epoch": 1.8579970104633783, "percentage": 37.16, "elapsed_time": "0:24:04", "remaining_time": "0:40:43", "throughput": 7047.35, "total_tokens": 10182656} {"current_steps": 1244, "total_steps": 3345, "loss": 0.7881, "lr": 1.7395843746770962e-06, "epoch": 1.85949177877429, "percentage": 37.19, "elapsed_time": "0:24:06", "remaining_time": "0:40:42", "throughput": 7047.35, "total_tokens": 10190848} {"current_steps": 1245, "total_steps": 3345, "loss": 0.9513, "lr": 1.7385039642752026e-06, "epoch": 1.8609865470852018, "percentage": 37.22, "elapsed_time": "0:24:07", "remaining_time": "0:40:41", "throughput": 7047.38, "total_tokens": 10199040} {"current_steps": 1246, "total_steps": 3345, "loss": 0.8329, "lr": 1.737423122974234e-06, "epoch": 1.8624813153961135, "percentage": 37.25, "elapsed_time": "0:24:08", "remaining_time": "0:40:39", "throughput": 7047.42, "total_tokens": 10207232} {"current_steps": 1247, "total_steps": 3345, "loss": 0.9661, "lr": 1.7363418517275779e-06, "epoch": 1.8639760837070254, "percentage": 37.28, "elapsed_time": "0:24:09", "remaining_time": "0:40:38", "throughput": 7047.43, "total_tokens": 10215424} {"current_steps": 1248, "total_steps": 3345, "loss": 0.9769, "lr": 1.7352601514890007e-06, "epoch": 1.8654708520179373, "percentage": 37.31, "elapsed_time": "0:24:10", "remaining_time": "0:40:37", "throughput": 7047.44, "total_tokens": 10223616} {"current_steps": 1249, "total_steps": 3345, "loss": 0.8374, "lr": 1.7341780232126481e-06, "epoch": 1.8669656203288492, "percentage": 37.34, "elapsed_time": "0:24:11", "remaining_time": "0:40:36", "throughput": 7047.45, "total_tokens": 10231808} {"current_steps": 1250, "total_steps": 3345, "loss": 0.8093, "lr": 1.7330954678530417e-06, "epoch": 1.8684603886397608, "percentage": 37.37, "elapsed_time": "0:24:13", "remaining_time": "0:40:35", "throughput": 7047.46, "total_tokens": 10240000} {"current_steps": 1251, "total_steps": 3345, "loss": 0.8934, "lr": 1.7320124863650817e-06, "epoch": 1.8699551569506725, "percentage": 37.4, "elapsed_time": "0:24:14", "remaining_time": "0:40:34", "throughput": 7047.39, "total_tokens": 10248192} {"current_steps": 1252, "total_steps": 3345, "loss": 0.6877, "lr": 1.7309290797040431e-06, "epoch": 1.8714499252615844, "percentage": 37.43, "elapsed_time": "0:24:15", "remaining_time": "0:40:32", "throughput": 7047.4, "total_tokens": 10256384} {"current_steps": 1253, "total_steps": 3345, "loss": 0.679, "lr": 1.7298452488255757e-06, "epoch": 1.8729446935724963, "percentage": 37.46, "elapsed_time": "0:24:16", "remaining_time": "0:40:31", "throughput": 7047.43, "total_tokens": 10264576} {"current_steps": 1254, "total_steps": 3345, "loss": 0.8141, "lr": 1.7287609946857045e-06, "epoch": 1.8744394618834082, "percentage": 37.49, "elapsed_time": "0:24:17", "remaining_time": "0:40:30", "throughput": 7047.44, "total_tokens": 10272768} {"current_steps": 1255, "total_steps": 3345, "loss": 0.8872, "lr": 1.7276763182408268e-06, "epoch": 1.87593423019432, "percentage": 37.52, "elapsed_time": "0:24:18", "remaining_time": "0:40:29", "throughput": 7047.44, "total_tokens": 10280960} {"current_steps": 1256, "total_steps": 3345, "loss": 0.8949, "lr": 1.7265912204477133e-06, "epoch": 1.8774289985052317, "percentage": 37.55, "elapsed_time": "0:24:19", "remaining_time": "0:40:28", "throughput": 7047.44, "total_tokens": 10289152} {"current_steps": 1257, "total_steps": 3345, "loss": 0.7936, "lr": 1.7255057022635058e-06, "epoch": 1.8789237668161434, "percentage": 37.58, "elapsed_time": "0:24:21", "remaining_time": "0:40:27", "throughput": 7047.46, "total_tokens": 10297344} {"current_steps": 1258, "total_steps": 3345, "loss": 0.6669, "lr": 1.7244197646457168e-06, "epoch": 1.8804185351270553, "percentage": 37.61, "elapsed_time": "0:24:22", "remaining_time": "0:40:25", "throughput": 7047.46, "total_tokens": 10305536} {"current_steps": 1259, "total_steps": 3345, "loss": 0.7592, "lr": 1.7233334085522294e-06, "epoch": 1.8819133034379671, "percentage": 37.64, "elapsed_time": "0:24:23", "remaining_time": "0:40:24", "throughput": 7047.48, "total_tokens": 10313728} {"current_steps": 1260, "total_steps": 3345, "loss": 0.7905, "lr": 1.7222466349412952e-06, "epoch": 1.883408071748879, "percentage": 37.67, "elapsed_time": "0:24:24", "remaining_time": "0:40:23", "throughput": 7047.5, "total_tokens": 10321920} {"current_steps": 1261, "total_steps": 3345, "loss": 0.7379, "lr": 1.7211594447715343e-06, "epoch": 1.8849028400597907, "percentage": 37.7, "elapsed_time": "0:24:25", "remaining_time": "0:40:22", "throughput": 7047.51, "total_tokens": 10330112} {"current_steps": 1262, "total_steps": 3345, "loss": 0.7061, "lr": 1.720071839001935e-06, "epoch": 1.8863976083707026, "percentage": 37.73, "elapsed_time": "0:24:26", "remaining_time": "0:40:21", "throughput": 7047.36, "total_tokens": 10338304} {"current_steps": 1263, "total_steps": 3345, "loss": 0.8693, "lr": 1.7189838185918507e-06, "epoch": 1.8878923766816142, "percentage": 37.76, "elapsed_time": "0:24:28", "remaining_time": "0:40:20", "throughput": 7047.36, "total_tokens": 10346496} {"current_steps": 1264, "total_steps": 3345, "loss": 0.8009, "lr": 1.7178953845010017e-06, "epoch": 1.8893871449925261, "percentage": 37.79, "elapsed_time": "0:24:29", "remaining_time": "0:40:19", "throughput": 7047.34, "total_tokens": 10354688} {"current_steps": 1265, "total_steps": 3345, "loss": 0.6739, "lr": 1.7168065376894722e-06, "epoch": 1.890881913303438, "percentage": 37.82, "elapsed_time": "0:24:30", "remaining_time": "0:40:17", "throughput": 7047.34, "total_tokens": 10362880} {"current_steps": 1266, "total_steps": 3345, "loss": 0.6366, "lr": 1.7157172791177118e-06, "epoch": 1.89237668161435, "percentage": 37.85, "elapsed_time": "0:24:31", "remaining_time": "0:40:16", "throughput": 7047.38, "total_tokens": 10371072} {"current_steps": 1267, "total_steps": 3345, "loss": 0.923, "lr": 1.7146276097465324e-06, "epoch": 1.8938714499252616, "percentage": 37.88, "elapsed_time": "0:24:32", "remaining_time": "0:40:15", "throughput": 7047.41, "total_tokens": 10379264} {"current_steps": 1268, "total_steps": 3345, "loss": 0.8624, "lr": 1.7135375305371084e-06, "epoch": 1.8953662182361732, "percentage": 37.91, "elapsed_time": "0:24:33", "remaining_time": "0:40:14", "throughput": 7047.43, "total_tokens": 10387456} {"current_steps": 1269, "total_steps": 3345, "loss": 0.9791, "lr": 1.7124470424509759e-06, "epoch": 1.8968609865470851, "percentage": 37.94, "elapsed_time": "0:24:35", "remaining_time": "0:40:13", "throughput": 7047.45, "total_tokens": 10395648} {"current_steps": 1270, "total_steps": 3345, "loss": 0.9766, "lr": 1.711356146450031e-06, "epoch": 1.898355754857997, "percentage": 37.97, "elapsed_time": "0:24:36", "remaining_time": "0:40:11", "throughput": 7047.46, "total_tokens": 10403840} {"current_steps": 1271, "total_steps": 3345, "loss": 0.7408, "lr": 1.7102648434965307e-06, "epoch": 1.899850523168909, "percentage": 38.0, "elapsed_time": "0:24:37", "remaining_time": "0:40:10", "throughput": 7047.47, "total_tokens": 10412032} {"current_steps": 1272, "total_steps": 3345, "loss": 0.8001, "lr": 1.70917313455309e-06, "epoch": 1.9013452914798208, "percentage": 38.03, "elapsed_time": "0:24:38", "remaining_time": "0:40:09", "throughput": 7047.45, "total_tokens": 10420224} {"current_steps": 1273, "total_steps": 3345, "loss": 0.9968, "lr": 1.7080810205826828e-06, "epoch": 1.9028400597907325, "percentage": 38.06, "elapsed_time": "0:24:39", "remaining_time": "0:40:08", "throughput": 7047.45, "total_tokens": 10428416} {"current_steps": 1274, "total_steps": 3345, "loss": 0.9772, "lr": 1.7069885025486393e-06, "epoch": 1.9043348281016441, "percentage": 38.09, "elapsed_time": "0:24:40", "remaining_time": "0:40:07", "throughput": 7047.46, "total_tokens": 10436608} {"current_steps": 1275, "total_steps": 3345, "loss": 0.9559, "lr": 1.7058955814146472e-06, "epoch": 1.905829596412556, "percentage": 38.12, "elapsed_time": "0:24:42", "remaining_time": "0:40:06", "throughput": 7047.47, "total_tokens": 10444800} {"current_steps": 1276, "total_steps": 3345, "loss": 0.8995, "lr": 1.7048022581447494e-06, "epoch": 1.907324364723468, "percentage": 38.15, "elapsed_time": "0:24:43", "remaining_time": "0:40:05", "throughput": 7047.48, "total_tokens": 10452992} {"current_steps": 1277, "total_steps": 3345, "loss": 0.7396, "lr": 1.7037085337033427e-06, "epoch": 1.9088191330343798, "percentage": 38.18, "elapsed_time": "0:24:44", "remaining_time": "0:40:03", "throughput": 7047.48, "total_tokens": 10461184} {"current_steps": 1278, "total_steps": 3345, "loss": 0.7628, "lr": 1.7026144090551783e-06, "epoch": 1.9103139013452914, "percentage": 38.21, "elapsed_time": "0:24:45", "remaining_time": "0:40:02", "throughput": 7047.5, "total_tokens": 10469376} {"current_steps": 1279, "total_steps": 3345, "loss": 0.8049, "lr": 1.7015198851653618e-06, "epoch": 1.9118086696562033, "percentage": 38.24, "elapsed_time": "0:24:46", "remaining_time": "0:40:01", "throughput": 7047.51, "total_tokens": 10477568} {"current_steps": 1280, "total_steps": 3345, "loss": 0.7813, "lr": 1.7004249629993485e-06, "epoch": 1.913303437967115, "percentage": 38.27, "elapsed_time": "0:24:47", "remaining_time": "0:40:00", "throughput": 7047.49, "total_tokens": 10485760} {"current_steps": 1281, "total_steps": 3345, "loss": 0.6279, "lr": 1.6993296435229467e-06, "epoch": 1.9147982062780269, "percentage": 38.3, "elapsed_time": "0:24:49", "remaining_time": "0:39:59", "throughput": 7047.51, "total_tokens": 10493952} {"current_steps": 1282, "total_steps": 3345, "loss": 0.9077, "lr": 1.6982339277023144e-06, "epoch": 1.9162929745889388, "percentage": 38.33, "elapsed_time": "0:24:50", "remaining_time": "0:39:58", "throughput": 7047.52, "total_tokens": 10502144} {"current_steps": 1283, "total_steps": 3345, "loss": 0.9154, "lr": 1.69713781650396e-06, "epoch": 1.9177877428998507, "percentage": 38.36, "elapsed_time": "0:24:51", "remaining_time": "0:39:56", "throughput": 7047.52, "total_tokens": 10510336} {"current_steps": 1284, "total_steps": 3345, "loss": 0.6979, "lr": 1.6960413108947398e-06, "epoch": 1.9192825112107623, "percentage": 38.39, "elapsed_time": "0:24:52", "remaining_time": "0:39:55", "throughput": 7047.55, "total_tokens": 10518528} {"current_steps": 1285, "total_steps": 3345, "loss": 0.7473, "lr": 1.6949444118418583e-06, "epoch": 1.920777279521674, "percentage": 38.42, "elapsed_time": "0:24:53", "remaining_time": "0:39:54", "throughput": 7047.57, "total_tokens": 10526720} {"current_steps": 1286, "total_steps": 3345, "loss": 0.7321, "lr": 1.6938471203128675e-06, "epoch": 1.9222720478325859, "percentage": 38.45, "elapsed_time": "0:24:54", "remaining_time": "0:39:53", "throughput": 7047.59, "total_tokens": 10534912} {"current_steps": 1287, "total_steps": 3345, "loss": 0.8871, "lr": 1.6927494372756643e-06, "epoch": 1.9237668161434978, "percentage": 38.48, "elapsed_time": "0:24:55", "remaining_time": "0:39:52", "throughput": 7047.61, "total_tokens": 10543104} {"current_steps": 1288, "total_steps": 3345, "loss": 0.6133, "lr": 1.6916513636984927e-06, "epoch": 1.9252615844544096, "percentage": 38.51, "elapsed_time": "0:24:57", "remaining_time": "0:39:51", "throughput": 7047.61, "total_tokens": 10551296} {"current_steps": 1289, "total_steps": 3345, "loss": 0.7988, "lr": 1.69055290054994e-06, "epoch": 1.9267563527653215, "percentage": 38.54, "elapsed_time": "0:24:58", "remaining_time": "0:39:49", "throughput": 7047.62, "total_tokens": 10559488} {"current_steps": 1290, "total_steps": 3345, "loss": 0.8642, "lr": 1.6894540487989374e-06, "epoch": 1.9282511210762332, "percentage": 38.57, "elapsed_time": "0:24:59", "remaining_time": "0:39:48", "throughput": 7047.62, "total_tokens": 10567680} {"current_steps": 1291, "total_steps": 3345, "loss": 1.0204, "lr": 1.6883548094147589e-06, "epoch": 1.9297458893871449, "percentage": 38.59, "elapsed_time": "0:25:00", "remaining_time": "0:39:47", "throughput": 7047.63, "total_tokens": 10575872} {"current_steps": 1292, "total_steps": 3345, "loss": 0.6737, "lr": 1.6872551833670205e-06, "epoch": 1.9312406576980568, "percentage": 38.62, "elapsed_time": "0:25:01", "remaining_time": "0:39:46", "throughput": 7047.63, "total_tokens": 10584064} {"current_steps": 1293, "total_steps": 3345, "loss": 0.6673, "lr": 1.6861551716256795e-06, "epoch": 1.9327354260089686, "percentage": 38.65, "elapsed_time": "0:25:02", "remaining_time": "0:39:45", "throughput": 7047.64, "total_tokens": 10592256} {"current_steps": 1294, "total_steps": 3345, "loss": 0.9487, "lr": 1.6850547751610325e-06, "epoch": 1.9342301943198805, "percentage": 38.68, "elapsed_time": "0:25:04", "remaining_time": "0:39:44", "throughput": 7047.66, "total_tokens": 10600448} {"current_steps": 1295, "total_steps": 3345, "loss": 0.9979, "lr": 1.6839539949437163e-06, "epoch": 1.9357249626307922, "percentage": 38.71, "elapsed_time": "0:25:05", "remaining_time": "0:39:42", "throughput": 7047.66, "total_tokens": 10608640} {"current_steps": 1296, "total_steps": 3345, "loss": 1.004, "lr": 1.6828528319447066e-06, "epoch": 1.937219730941704, "percentage": 38.74, "elapsed_time": "0:25:06", "remaining_time": "0:39:41", "throughput": 7047.67, "total_tokens": 10616832} {"current_steps": 1297, "total_steps": 3345, "loss": 0.8876, "lr": 1.6817512871353154e-06, "epoch": 1.9387144992526157, "percentage": 38.77, "elapsed_time": "0:25:07", "remaining_time": "0:39:40", "throughput": 7047.6, "total_tokens": 10625024} {"current_steps": 1298, "total_steps": 3345, "loss": 0.6975, "lr": 1.6806493614871927e-06, "epoch": 1.9402092675635276, "percentage": 38.8, "elapsed_time": "0:25:08", "remaining_time": "0:39:39", "throughput": 7047.61, "total_tokens": 10633216} {"current_steps": 1299, "total_steps": 3345, "loss": 1.0375, "lr": 1.6795470559723232e-06, "epoch": 1.9417040358744395, "percentage": 38.83, "elapsed_time": "0:25:09", "remaining_time": "0:39:38", "throughput": 7047.61, "total_tokens": 10641408} {"current_steps": 1300, "total_steps": 3345, "loss": 1.0152, "lr": 1.6784443715630283e-06, "epoch": 1.9431988041853514, "percentage": 38.86, "elapsed_time": "0:25:11", "remaining_time": "0:39:37", "throughput": 7047.59, "total_tokens": 10649600} {"current_steps": 1301, "total_steps": 3345, "loss": 0.935, "lr": 1.6773413092319621e-06, "epoch": 1.944693572496263, "percentage": 38.89, "elapsed_time": "0:25:12", "remaining_time": "0:39:35", "throughput": 7047.6, "total_tokens": 10657792} {"current_steps": 1302, "total_steps": 3345, "loss": 0.8549, "lr": 1.676237869952113e-06, "epoch": 1.9461883408071747, "percentage": 38.92, "elapsed_time": "0:25:13", "remaining_time": "0:39:34", "throughput": 7047.55, "total_tokens": 10665984} {"current_steps": 1303, "total_steps": 3345, "loss": 0.8674, "lr": 1.6751340546968018e-06, "epoch": 1.9476831091180866, "percentage": 38.95, "elapsed_time": "0:25:14", "remaining_time": "0:39:33", "throughput": 7047.55, "total_tokens": 10674176} {"current_steps": 1304, "total_steps": 3345, "loss": 0.7374, "lr": 1.67402986443968e-06, "epoch": 1.9491778774289985, "percentage": 38.98, "elapsed_time": "0:25:15", "remaining_time": "0:39:32", "throughput": 7047.53, "total_tokens": 10682368} {"current_steps": 1305, "total_steps": 3345, "loss": 0.8623, "lr": 1.6729253001547313e-06, "epoch": 1.9506726457399104, "percentage": 39.01, "elapsed_time": "0:25:16", "remaining_time": "0:39:31", "throughput": 7047.54, "total_tokens": 10690560} {"current_steps": 1306, "total_steps": 3345, "loss": 1.0372, "lr": 1.6718203628162685e-06, "epoch": 1.9521674140508223, "percentage": 39.04, "elapsed_time": "0:25:18", "remaining_time": "0:39:30", "throughput": 7047.54, "total_tokens": 10698752} {"current_steps": 1307, "total_steps": 3345, "loss": 0.9064, "lr": 1.670715053398933e-06, "epoch": 1.953662182361734, "percentage": 39.07, "elapsed_time": "0:25:19", "remaining_time": "0:39:28", "throughput": 7047.54, "total_tokens": 10706944} {"current_steps": 1308, "total_steps": 3345, "loss": 0.9447, "lr": 1.669609372877696e-06, "epoch": 1.9551569506726456, "percentage": 39.1, "elapsed_time": "0:25:20", "remaining_time": "0:39:27", "throughput": 7047.54, "total_tokens": 10715136} {"current_steps": 1309, "total_steps": 3345, "loss": 0.851, "lr": 1.6685033222278544e-06, "epoch": 1.9566517189835575, "percentage": 39.13, "elapsed_time": "0:25:21", "remaining_time": "0:39:26", "throughput": 7047.5, "total_tokens": 10723328} {"current_steps": 1310, "total_steps": 3345, "loss": 0.7602, "lr": 1.6673969024250321e-06, "epoch": 1.9581464872944694, "percentage": 39.16, "elapsed_time": "0:25:22", "remaining_time": "0:39:25", "throughput": 7047.5, "total_tokens": 10731520} {"current_steps": 1311, "total_steps": 3345, "loss": 0.8149, "lr": 1.6662901144451793e-06, "epoch": 1.9596412556053813, "percentage": 39.19, "elapsed_time": "0:25:23", "remaining_time": "0:39:24", "throughput": 7047.52, "total_tokens": 10739712} {"current_steps": 1312, "total_steps": 3345, "loss": 1.1078, "lr": 1.6651829592645695e-06, "epoch": 1.961136023916293, "percentage": 39.22, "elapsed_time": "0:25:25", "remaining_time": "0:39:23", "throughput": 7047.5, "total_tokens": 10747904} {"current_steps": 1313, "total_steps": 3345, "loss": 1.0081, "lr": 1.6640754378598022e-06, "epoch": 1.9626307922272048, "percentage": 39.25, "elapsed_time": "0:25:26", "remaining_time": "0:39:21", "throughput": 7047.52, "total_tokens": 10756096} {"current_steps": 1314, "total_steps": 3345, "loss": 0.7214, "lr": 1.662967551207798e-06, "epoch": 1.9641255605381165, "percentage": 39.28, "elapsed_time": "0:25:27", "remaining_time": "0:39:20", "throughput": 7047.52, "total_tokens": 10764288} {"current_steps": 1315, "total_steps": 3345, "loss": 1.0068, "lr": 1.6618593002858002e-06, "epoch": 1.9656203288490284, "percentage": 39.31, "elapsed_time": "0:25:28", "remaining_time": "0:39:19", "throughput": 7047.48, "total_tokens": 10772480} {"current_steps": 1316, "total_steps": 3345, "loss": 0.8237, "lr": 1.6607506860713743e-06, "epoch": 1.9671150971599403, "percentage": 39.34, "elapsed_time": "0:25:29", "remaining_time": "0:39:18", "throughput": 7047.49, "total_tokens": 10780672} {"current_steps": 1317, "total_steps": 3345, "loss": 0.8372, "lr": 1.6596417095424053e-06, "epoch": 1.9686098654708521, "percentage": 39.37, "elapsed_time": "0:25:30", "remaining_time": "0:39:17", "throughput": 7047.5, "total_tokens": 10788864} {"current_steps": 1318, "total_steps": 3345, "loss": 0.7471, "lr": 1.658532371677098e-06, "epoch": 1.9701046337817638, "percentage": 39.4, "elapsed_time": "0:25:32", "remaining_time": "0:39:16", "throughput": 7047.5, "total_tokens": 10797056} {"current_steps": 1319, "total_steps": 3345, "loss": 0.9476, "lr": 1.6574226734539762e-06, "epoch": 1.9715994020926755, "percentage": 39.43, "elapsed_time": "0:25:33", "remaining_time": "0:39:15", "throughput": 7047.51, "total_tokens": 10805248} {"current_steps": 1320, "total_steps": 3345, "loss": 0.6111, "lr": 1.6563126158518808e-06, "epoch": 1.9730941704035874, "percentage": 39.46, "elapsed_time": "0:25:34", "remaining_time": "0:39:13", "throughput": 7047.52, "total_tokens": 10813440} {"current_steps": 1321, "total_steps": 3345, "loss": 1.0113, "lr": 1.6552021998499708e-06, "epoch": 1.9745889387144993, "percentage": 39.49, "elapsed_time": "0:25:35", "remaining_time": "0:39:12", "throughput": 7047.56, "total_tokens": 10821632} {"current_steps": 1322, "total_steps": 3345, "loss": 0.7544, "lr": 1.6540914264277207e-06, "epoch": 1.9760837070254111, "percentage": 39.52, "elapsed_time": "0:25:36", "remaining_time": "0:39:11", "throughput": 7047.57, "total_tokens": 10829824} {"current_steps": 1323, "total_steps": 3345, "loss": 0.7342, "lr": 1.6529802965649203e-06, "epoch": 1.977578475336323, "percentage": 39.55, "elapsed_time": "0:25:37", "remaining_time": "0:39:10", "throughput": 7047.6, "total_tokens": 10838016} {"current_steps": 1324, "total_steps": 3345, "loss": 0.6334, "lr": 1.6518688112416742e-06, "epoch": 1.9790732436472347, "percentage": 39.58, "elapsed_time": "0:25:38", "remaining_time": "0:39:09", "throughput": 7047.62, "total_tokens": 10846208} {"current_steps": 1325, "total_steps": 3345, "loss": 0.8767, "lr": 1.6507569714383997e-06, "epoch": 1.9805680119581464, "percentage": 39.61, "elapsed_time": "0:25:40", "remaining_time": "0:39:08", "throughput": 7047.63, "total_tokens": 10854400} {"current_steps": 1326, "total_steps": 3345, "loss": 0.809, "lr": 1.649644778135828e-06, "epoch": 1.9820627802690582, "percentage": 39.64, "elapsed_time": "0:25:41", "remaining_time": "0:39:06", "throughput": 7047.65, "total_tokens": 10862592} {"current_steps": 1327, "total_steps": 3345, "loss": 0.8516, "lr": 1.6485322323150008e-06, "epoch": 1.9835575485799701, "percentage": 39.67, "elapsed_time": "0:25:42", "remaining_time": "0:39:05", "throughput": 7047.64, "total_tokens": 10870784} {"current_steps": 1328, "total_steps": 3345, "loss": 1.024, "lr": 1.6474193349572717e-06, "epoch": 1.985052316890882, "percentage": 39.7, "elapsed_time": "0:25:43", "remaining_time": "0:39:04", "throughput": 7047.64, "total_tokens": 10878976} {"current_steps": 1329, "total_steps": 3345, "loss": 0.9305, "lr": 1.6463060870443038e-06, "epoch": 1.9865470852017937, "percentage": 39.73, "elapsed_time": "0:25:44", "remaining_time": "0:39:03", "throughput": 7047.64, "total_tokens": 10887168} {"current_steps": 1330, "total_steps": 3345, "loss": 0.8352, "lr": 1.6451924895580699e-06, "epoch": 1.9880418535127056, "percentage": 39.76, "elapsed_time": "0:25:45", "remaining_time": "0:39:02", "throughput": 7047.68, "total_tokens": 10895360} {"current_steps": 1331, "total_steps": 3345, "loss": 0.801, "lr": 1.6440785434808507e-06, "epoch": 1.9895366218236172, "percentage": 39.79, "elapsed_time": "0:25:47", "remaining_time": "0:39:00", "throughput": 7047.72, "total_tokens": 10903552} {"current_steps": 1332, "total_steps": 3345, "loss": 1.1098, "lr": 1.6429642497952348e-06, "epoch": 1.9910313901345291, "percentage": 39.82, "elapsed_time": "0:25:48", "remaining_time": "0:38:59", "throughput": 7047.76, "total_tokens": 10911744} {"current_steps": 1333, "total_steps": 3345, "loss": 0.7659, "lr": 1.6418496094841174e-06, "epoch": 1.992526158445441, "percentage": 39.85, "elapsed_time": "0:25:49", "remaining_time": "0:38:58", "throughput": 7047.79, "total_tokens": 10919936} {"current_steps": 1334, "total_steps": 3345, "loss": 0.9814, "lr": 1.640734623530699e-06, "epoch": 1.994020926756353, "percentage": 39.88, "elapsed_time": "0:25:50", "remaining_time": "0:38:57", "throughput": 7047.79, "total_tokens": 10928128} {"current_steps": 1335, "total_steps": 3345, "loss": 0.9384, "lr": 1.6396192929184853e-06, "epoch": 1.9955156950672646, "percentage": 39.91, "elapsed_time": "0:25:51", "remaining_time": "0:38:56", "throughput": 7047.81, "total_tokens": 10936320} {"current_steps": 1336, "total_steps": 3345, "loss": 0.8278, "lr": 1.6385036186312863e-06, "epoch": 1.9970104633781762, "percentage": 39.94, "elapsed_time": "0:25:52", "remaining_time": "0:38:55", "throughput": 7047.84, "total_tokens": 10944512} {"current_steps": 1337, "total_steps": 3345, "loss": 0.8444, "lr": 1.6373876016532142e-06, "epoch": 1.9985052316890881, "percentage": 39.97, "elapsed_time": "0:25:54", "remaining_time": "0:38:53", "throughput": 7047.86, "total_tokens": 10952704} {"current_steps": 1338, "total_steps": 3345, "loss": 0.4987, "lr": 1.6362712429686844e-06, "epoch": 2.0, "percentage": 40.0, "elapsed_time": "0:25:55", "remaining_time": "0:38:52", "throughput": 7047.98, "total_tokens": 10960896} {"current_steps": 1339, "total_steps": 3345, "loss": 0.4477, "lr": 1.6351545435624138e-06, "epoch": 2.001494768310912, "percentage": 40.03, "elapsed_time": "0:25:56", "remaining_time": "0:38:51", "throughput": 7047.93, "total_tokens": 10969088} {"current_steps": 1340, "total_steps": 3345, "loss": 0.6945, "lr": 1.6340375044194188e-06, "epoch": 2.0029895366218238, "percentage": 40.06, "elapsed_time": "0:25:57", "remaining_time": "0:38:50", "throughput": 7047.95, "total_tokens": 10977280} {"current_steps": 1341, "total_steps": 3345, "loss": 0.6251, "lr": 1.6329201265250167e-06, "epoch": 2.004484304932735, "percentage": 40.09, "elapsed_time": "0:25:58", "remaining_time": "0:38:49", "throughput": 7047.97, "total_tokens": 10985472} {"current_steps": 1342, "total_steps": 3345, "loss": 0.4558, "lr": 1.6318024108648228e-06, "epoch": 2.005979073243647, "percentage": 40.12, "elapsed_time": "0:25:59", "remaining_time": "0:38:48", "throughput": 7047.97, "total_tokens": 10993664} {"current_steps": 1343, "total_steps": 3345, "loss": 0.53, "lr": 1.630684358424751e-06, "epoch": 2.007473841554559, "percentage": 40.15, "elapsed_time": "0:26:00", "remaining_time": "0:38:46", "throughput": 7047.99, "total_tokens": 11001856} {"current_steps": 1344, "total_steps": 3345, "loss": 0.4297, "lr": 1.629565970191011e-06, "epoch": 2.008968609865471, "percentage": 40.18, "elapsed_time": "0:26:02", "remaining_time": "0:38:45", "throughput": 7048.01, "total_tokens": 11010048} {"current_steps": 1345, "total_steps": 3345, "loss": 0.6703, "lr": 1.6284472471501102e-06, "epoch": 2.0104633781763828, "percentage": 40.21, "elapsed_time": "0:26:03", "remaining_time": "0:38:44", "throughput": 7048.03, "total_tokens": 11018240} {"current_steps": 1346, "total_steps": 3345, "loss": 0.6328, "lr": 1.6273281902888501e-06, "epoch": 2.0119581464872947, "percentage": 40.24, "elapsed_time": "0:26:04", "remaining_time": "0:38:43", "throughput": 7048.04, "total_tokens": 11026432} {"current_steps": 1347, "total_steps": 3345, "loss": 0.2746, "lr": 1.626208800594328e-06, "epoch": 2.013452914798206, "percentage": 40.27, "elapsed_time": "0:26:05", "remaining_time": "0:38:42", "throughput": 7048.06, "total_tokens": 11034624} {"current_steps": 1348, "total_steps": 3345, "loss": 0.5257, "lr": 1.6250890790539333e-06, "epoch": 2.014947683109118, "percentage": 40.3, "elapsed_time": "0:26:06", "remaining_time": "0:38:41", "throughput": 7048.09, "total_tokens": 11042816} {"current_steps": 1349, "total_steps": 3345, "loss": 0.4903, "lr": 1.6239690266553495e-06, "epoch": 2.01644245142003, "percentage": 40.33, "elapsed_time": "0:26:07", "remaining_time": "0:38:39", "throughput": 7048.11, "total_tokens": 11051008} {"current_steps": 1350, "total_steps": 3345, "loss": 0.4829, "lr": 1.622848644386551e-06, "epoch": 2.0179372197309418, "percentage": 40.36, "elapsed_time": "0:26:09", "remaining_time": "0:38:38", "throughput": 7048.05, "total_tokens": 11059200} {"current_steps": 1351, "total_steps": 3345, "loss": 0.3061, "lr": 1.621727933235803e-06, "epoch": 2.0194319880418536, "percentage": 40.39, "elapsed_time": "0:26:10", "remaining_time": "0:38:37", "throughput": 7048.07, "total_tokens": 11067392} {"current_steps": 1352, "total_steps": 3345, "loss": 0.5382, "lr": 1.6206068941916618e-06, "epoch": 2.0209267563527655, "percentage": 40.42, "elapsed_time": "0:26:11", "remaining_time": "0:38:36", "throughput": 7048.1, "total_tokens": 11075584} {"current_steps": 1353, "total_steps": 3345, "loss": 0.3616, "lr": 1.6194855282429722e-06, "epoch": 2.022421524663677, "percentage": 40.45, "elapsed_time": "0:26:12", "remaining_time": "0:38:35", "throughput": 7048.14, "total_tokens": 11083776} {"current_steps": 1354, "total_steps": 3345, "loss": 0.5561, "lr": 1.6183638363788674e-06, "epoch": 2.023916292974589, "percentage": 40.48, "elapsed_time": "0:26:13", "remaining_time": "0:38:34", "throughput": 7048.14, "total_tokens": 11091968} {"current_steps": 1355, "total_steps": 3345, "loss": 0.5609, "lr": 1.6172418195887679e-06, "epoch": 2.0254110612855007, "percentage": 40.51, "elapsed_time": "0:26:14", "remaining_time": "0:38:32", "throughput": 7048.17, "total_tokens": 11100160} {"current_steps": 1356, "total_steps": 3345, "loss": 0.5554, "lr": 1.6161194788623818e-06, "epoch": 2.0269058295964126, "percentage": 40.54, "elapsed_time": "0:26:16", "remaining_time": "0:38:31", "throughput": 7048.2, "total_tokens": 11108352} {"current_steps": 1357, "total_steps": 3345, "loss": 0.2907, "lr": 1.614996815189702e-06, "epoch": 2.0284005979073245, "percentage": 40.57, "elapsed_time": "0:26:17", "remaining_time": "0:38:30", "throughput": 7048.21, "total_tokens": 11116544} {"current_steps": 1358, "total_steps": 3345, "loss": 0.35, "lr": 1.6138738295610066e-06, "epoch": 2.029895366218236, "percentage": 40.6, "elapsed_time": "0:26:18", "remaining_time": "0:38:29", "throughput": 7048.22, "total_tokens": 11124736} {"current_steps": 1359, "total_steps": 3345, "loss": 0.6675, "lr": 1.6127505229668571e-06, "epoch": 2.031390134529148, "percentage": 40.63, "elapsed_time": "0:26:19", "remaining_time": "0:38:28", "throughput": 7048.24, "total_tokens": 11132928} {"current_steps": 1360, "total_steps": 3345, "loss": 0.4826, "lr": 1.6116268963980997e-06, "epoch": 2.0328849028400597, "percentage": 40.66, "elapsed_time": "0:26:20", "remaining_time": "0:38:27", "throughput": 7048.26, "total_tokens": 11141120} {"current_steps": 1361, "total_steps": 3345, "loss": 0.4312, "lr": 1.6105029508458606e-06, "epoch": 2.0343796711509716, "percentage": 40.69, "elapsed_time": "0:26:21", "remaining_time": "0:38:25", "throughput": 7048.29, "total_tokens": 11149312} {"current_steps": 1362, "total_steps": 3345, "loss": 0.4357, "lr": 1.6093786873015493e-06, "epoch": 2.0358744394618835, "percentage": 40.72, "elapsed_time": "0:26:23", "remaining_time": "0:38:24", "throughput": 7048.32, "total_tokens": 11157504} {"current_steps": 1363, "total_steps": 3345, "loss": 0.735, "lr": 1.608254106756854e-06, "epoch": 2.0373692077727954, "percentage": 40.75, "elapsed_time": "0:26:24", "remaining_time": "0:38:23", "throughput": 7048.35, "total_tokens": 11165696} {"current_steps": 1364, "total_steps": 3345, "loss": 0.6572, "lr": 1.607129210203745e-06, "epoch": 2.038863976083707, "percentage": 40.78, "elapsed_time": "0:26:25", "remaining_time": "0:38:22", "throughput": 7048.37, "total_tokens": 11173888} {"current_steps": 1365, "total_steps": 3345, "loss": 0.6061, "lr": 1.6060039986344692e-06, "epoch": 2.0403587443946187, "percentage": 40.81, "elapsed_time": "0:26:26", "remaining_time": "0:38:21", "throughput": 7048.4, "total_tokens": 11182080} {"current_steps": 1366, "total_steps": 3345, "loss": 0.2365, "lr": 1.6048784730415517e-06, "epoch": 2.0418535127055306, "percentage": 40.84, "elapsed_time": "0:26:27", "remaining_time": "0:38:20", "throughput": 7048.41, "total_tokens": 11190272} {"current_steps": 1367, "total_steps": 3345, "loss": 0.5912, "lr": 1.603752634417796e-06, "epoch": 2.0433482810164425, "percentage": 40.87, "elapsed_time": "0:26:28", "remaining_time": "0:38:18", "throughput": 7048.45, "total_tokens": 11198464} {"current_steps": 1368, "total_steps": 3345, "loss": 0.5028, "lr": 1.6026264837562795e-06, "epoch": 2.0448430493273544, "percentage": 40.9, "elapsed_time": "0:26:29", "remaining_time": "0:38:17", "throughput": 7048.48, "total_tokens": 11206656} {"current_steps": 1369, "total_steps": 3345, "loss": 0.6157, "lr": 1.6015000220503564e-06, "epoch": 2.0463378176382663, "percentage": 40.93, "elapsed_time": "0:26:31", "remaining_time": "0:38:16", "throughput": 7048.5, "total_tokens": 11214848} {"current_steps": 1370, "total_steps": 3345, "loss": 0.877, "lr": 1.6003732502936552e-06, "epoch": 2.0478325859491777, "percentage": 40.96, "elapsed_time": "0:26:32", "remaining_time": "0:38:15", "throughput": 7048.52, "total_tokens": 11223040} {"current_steps": 1371, "total_steps": 3345, "loss": 0.4721, "lr": 1.5992461694800773e-06, "epoch": 2.0493273542600896, "percentage": 40.99, "elapsed_time": "0:26:33", "remaining_time": "0:38:14", "throughput": 7048.54, "total_tokens": 11231232} {"current_steps": 1372, "total_steps": 3345, "loss": 0.5777, "lr": 1.5981187806037974e-06, "epoch": 2.0508221225710015, "percentage": 41.02, "elapsed_time": "0:26:34", "remaining_time": "0:38:13", "throughput": 7048.54, "total_tokens": 11239424} {"current_steps": 1373, "total_steps": 3345, "loss": 0.5537, "lr": 1.5969910846592607e-06, "epoch": 2.0523168908819134, "percentage": 41.05, "elapsed_time": "0:26:35", "remaining_time": "0:38:11", "throughput": 7048.56, "total_tokens": 11247616} {"current_steps": 1374, "total_steps": 3345, "loss": 0.4358, "lr": 1.5958630826411846e-06, "epoch": 2.0538116591928253, "percentage": 41.08, "elapsed_time": "0:26:36", "remaining_time": "0:38:10", "throughput": 7048.58, "total_tokens": 11255808} {"current_steps": 1375, "total_steps": 3345, "loss": 0.4037, "lr": 1.5947347755445564e-06, "epoch": 2.0553064275037367, "percentage": 41.11, "elapsed_time": "0:26:38", "remaining_time": "0:38:09", "throughput": 7048.61, "total_tokens": 11264000} {"current_steps": 1376, "total_steps": 3345, "loss": 0.5311, "lr": 1.5936061643646314e-06, "epoch": 2.0568011958146486, "percentage": 41.14, "elapsed_time": "0:26:39", "remaining_time": "0:38:08", "throughput": 7048.62, "total_tokens": 11272192} {"current_steps": 1377, "total_steps": 3345, "loss": 0.5821, "lr": 1.5924772500969337e-06, "epoch": 2.0582959641255605, "percentage": 41.17, "elapsed_time": "0:26:40", "remaining_time": "0:38:07", "throughput": 7048.64, "total_tokens": 11280384} {"current_steps": 1378, "total_steps": 3345, "loss": 0.6339, "lr": 1.5913480337372555e-06, "epoch": 2.0597907324364724, "percentage": 41.2, "elapsed_time": "0:26:41", "remaining_time": "0:38:06", "throughput": 7048.66, "total_tokens": 11288576} {"current_steps": 1379, "total_steps": 3345, "loss": 0.3979, "lr": 1.5902185162816542e-06, "epoch": 2.0612855007473843, "percentage": 41.23, "elapsed_time": "0:26:42", "remaining_time": "0:38:04", "throughput": 7048.7, "total_tokens": 11296768} {"current_steps": 1380, "total_steps": 3345, "loss": 0.5518, "lr": 1.5890886987264536e-06, "epoch": 2.062780269058296, "percentage": 41.26, "elapsed_time": "0:26:43", "remaining_time": "0:38:03", "throughput": 7048.69, "total_tokens": 11304960} {"current_steps": 1381, "total_steps": 3345, "loss": 0.7097, "lr": 1.587958582068242e-06, "epoch": 2.0642750373692076, "percentage": 41.29, "elapsed_time": "0:26:44", "remaining_time": "0:38:02", "throughput": 7048.7, "total_tokens": 11313152} {"current_steps": 1382, "total_steps": 3345, "loss": 0.3947, "lr": 1.5868281673038716e-06, "epoch": 2.0657698056801195, "percentage": 41.32, "elapsed_time": "0:26:46", "remaining_time": "0:38:01", "throughput": 7048.71, "total_tokens": 11321344} {"current_steps": 1383, "total_steps": 3345, "loss": 0.44, "lr": 1.5856974554304578e-06, "epoch": 2.0672645739910314, "percentage": 41.35, "elapsed_time": "0:26:47", "remaining_time": "0:38:00", "throughput": 7048.73, "total_tokens": 11329536} {"current_steps": 1384, "total_steps": 3345, "loss": 0.5374, "lr": 1.5845664474453771e-06, "epoch": 2.0687593423019432, "percentage": 41.38, "elapsed_time": "0:26:48", "remaining_time": "0:37:59", "throughput": 7048.72, "total_tokens": 11337728} {"current_steps": 1385, "total_steps": 3345, "loss": 0.4937, "lr": 1.5834351443462683e-06, "epoch": 2.070254110612855, "percentage": 41.41, "elapsed_time": "0:26:49", "remaining_time": "0:37:57", "throughput": 7048.74, "total_tokens": 11345920} {"current_steps": 1386, "total_steps": 3345, "loss": 0.4275, "lr": 1.58230354713103e-06, "epoch": 2.071748878923767, "percentage": 41.43, "elapsed_time": "0:26:50", "remaining_time": "0:37:56", "throughput": 7048.75, "total_tokens": 11354112} {"current_steps": 1387, "total_steps": 3345, "loss": 0.3564, "lr": 1.58117165679782e-06, "epoch": 2.0732436472346785, "percentage": 41.46, "elapsed_time": "0:26:51", "remaining_time": "0:37:55", "throughput": 7048.77, "total_tokens": 11362304} {"current_steps": 1388, "total_steps": 3345, "loss": 0.3026, "lr": 1.5800394743450556e-06, "epoch": 2.0747384155455904, "percentage": 41.49, "elapsed_time": "0:26:53", "remaining_time": "0:37:54", "throughput": 7048.78, "total_tokens": 11370496} {"current_steps": 1389, "total_steps": 3345, "loss": 0.6821, "lr": 1.5789070007714103e-06, "epoch": 2.0762331838565022, "percentage": 41.52, "elapsed_time": "0:26:54", "remaining_time": "0:37:53", "throughput": 7048.78, "total_tokens": 11378688} {"current_steps": 1390, "total_steps": 3345, "loss": 0.4336, "lr": 1.5777742370758162e-06, "epoch": 2.077727952167414, "percentage": 41.55, "elapsed_time": "0:26:55", "remaining_time": "0:37:52", "throughput": 7048.81, "total_tokens": 11386880} {"current_steps": 1391, "total_steps": 3345, "loss": 0.4662, "lr": 1.5766411842574597e-06, "epoch": 2.079222720478326, "percentage": 41.58, "elapsed_time": "0:26:56", "remaining_time": "0:37:50", "throughput": 7048.83, "total_tokens": 11395072} {"current_steps": 1392, "total_steps": 3345, "loss": 0.4076, "lr": 1.575507843315783e-06, "epoch": 2.0807174887892375, "percentage": 41.61, "elapsed_time": "0:26:57", "remaining_time": "0:37:49", "throughput": 7048.88, "total_tokens": 11403264} {"current_steps": 1393, "total_steps": 3345, "loss": 0.5879, "lr": 1.5743742152504823e-06, "epoch": 2.0822122571001493, "percentage": 41.64, "elapsed_time": "0:26:58", "remaining_time": "0:37:48", "throughput": 7048.91, "total_tokens": 11411456} {"current_steps": 1394, "total_steps": 3345, "loss": 0.8093, "lr": 1.573240301061507e-06, "epoch": 2.0837070254110612, "percentage": 41.67, "elapsed_time": "0:27:00", "remaining_time": "0:37:47", "throughput": 7048.92, "total_tokens": 11419648} {"current_steps": 1395, "total_steps": 3345, "loss": 0.5262, "lr": 1.5721061017490594e-06, "epoch": 2.085201793721973, "percentage": 41.7, "elapsed_time": "0:27:01", "remaining_time": "0:37:46", "throughput": 7048.93, "total_tokens": 11427840} {"current_steps": 1396, "total_steps": 3345, "loss": 0.4989, "lr": 1.570971618313592e-06, "epoch": 2.086696562032885, "percentage": 41.73, "elapsed_time": "0:27:02", "remaining_time": "0:37:45", "throughput": 7048.95, "total_tokens": 11436032} {"current_steps": 1397, "total_steps": 3345, "loss": 0.7668, "lr": 1.5698368517558093e-06, "epoch": 2.088191330343797, "percentage": 41.76, "elapsed_time": "0:27:03", "remaining_time": "0:37:43", "throughput": 7048.97, "total_tokens": 11444224} {"current_steps": 1398, "total_steps": 3345, "loss": 0.5889, "lr": 1.5687018030766654e-06, "epoch": 2.0896860986547083, "percentage": 41.79, "elapsed_time": "0:27:04", "remaining_time": "0:37:42", "throughput": 7049.0, "total_tokens": 11452416} {"current_steps": 1399, "total_steps": 3345, "loss": 0.658, "lr": 1.5675664732773627e-06, "epoch": 2.09118086696562, "percentage": 41.82, "elapsed_time": "0:27:05", "remaining_time": "0:37:41", "throughput": 7049.03, "total_tokens": 11460608} {"current_steps": 1400, "total_steps": 3345, "loss": 0.4852, "lr": 1.5664308633593512e-06, "epoch": 2.092675635276532, "percentage": 41.85, "elapsed_time": "0:27:06", "remaining_time": "0:37:40", "throughput": 7049.06, "total_tokens": 11468800} {"current_steps": 1401, "total_steps": 3345, "loss": 0.6371, "lr": 1.565294974324329e-06, "epoch": 2.094170403587444, "percentage": 41.88, "elapsed_time": "0:27:08", "remaining_time": "0:37:39", "throughput": 7049.09, "total_tokens": 11476992} {"current_steps": 1402, "total_steps": 3345, "loss": 0.6255, "lr": 1.5641588071742397e-06, "epoch": 2.095665171898356, "percentage": 41.91, "elapsed_time": "0:27:09", "remaining_time": "0:37:38", "throughput": 7049.12, "total_tokens": 11485184} {"current_steps": 1403, "total_steps": 3345, "loss": 0.5771, "lr": 1.563022362911273e-06, "epoch": 2.0971599402092678, "percentage": 41.94, "elapsed_time": "0:27:10", "remaining_time": "0:37:36", "throughput": 7049.13, "total_tokens": 11493376} {"current_steps": 1404, "total_steps": 3345, "loss": 0.7178, "lr": 1.561885642537861e-06, "epoch": 2.098654708520179, "percentage": 41.97, "elapsed_time": "0:27:11", "remaining_time": "0:37:35", "throughput": 7049.12, "total_tokens": 11501568} {"current_steps": 1405, "total_steps": 3345, "loss": 0.766, "lr": 1.5607486470566827e-06, "epoch": 2.100149476831091, "percentage": 42.0, "elapsed_time": "0:27:12", "remaining_time": "0:37:34", "throughput": 7049.14, "total_tokens": 11509760} {"current_steps": 1406, "total_steps": 3345, "loss": 0.6431, "lr": 1.5596113774706568e-06, "epoch": 2.101644245142003, "percentage": 42.03, "elapsed_time": "0:27:13", "remaining_time": "0:37:33", "throughput": 7049.14, "total_tokens": 11517952} {"current_steps": 1407, "total_steps": 3345, "loss": 0.6082, "lr": 1.558473834782945e-06, "epoch": 2.103139013452915, "percentage": 42.06, "elapsed_time": "0:27:15", "remaining_time": "0:37:32", "throughput": 7049.15, "total_tokens": 11526144} {"current_steps": 1408, "total_steps": 3345, "loss": 0.6299, "lr": 1.5573360199969506e-06, "epoch": 2.1046337817638268, "percentage": 42.09, "elapsed_time": "0:27:16", "remaining_time": "0:37:31", "throughput": 7049.15, "total_tokens": 11534336} {"current_steps": 1409, "total_steps": 3345, "loss": 0.6062, "lr": 1.556197934116315e-06, "epoch": 2.106128550074738, "percentage": 42.12, "elapsed_time": "0:27:17", "remaining_time": "0:37:29", "throughput": 7049.14, "total_tokens": 11542528} {"current_steps": 1410, "total_steps": 3345, "loss": 0.3432, "lr": 1.5550595781449204e-06, "epoch": 2.10762331838565, "percentage": 42.15, "elapsed_time": "0:27:18", "remaining_time": "0:37:28", "throughput": 7049.14, "total_tokens": 11550720} {"current_steps": 1411, "total_steps": 3345, "loss": 0.4182, "lr": 1.5539209530868865e-06, "epoch": 2.109118086696562, "percentage": 42.18, "elapsed_time": "0:27:19", "remaining_time": "0:37:27", "throughput": 7049.16, "total_tokens": 11558912} {"current_steps": 1412, "total_steps": 3345, "loss": 0.6214, "lr": 1.5527820599465703e-06, "epoch": 2.110612855007474, "percentage": 42.21, "elapsed_time": "0:27:20", "remaining_time": "0:37:26", "throughput": 7049.18, "total_tokens": 11567104} {"current_steps": 1413, "total_steps": 3345, "loss": 0.4918, "lr": 1.5516428997285663e-06, "epoch": 2.1121076233183858, "percentage": 42.24, "elapsed_time": "0:27:22", "remaining_time": "0:37:25", "throughput": 7049.19, "total_tokens": 11575296} {"current_steps": 1414, "total_steps": 3345, "loss": 0.4517, "lr": 1.5505034734377028e-06, "epoch": 2.1136023916292976, "percentage": 42.27, "elapsed_time": "0:27:23", "remaining_time": "0:37:24", "throughput": 7049.18, "total_tokens": 11583488} {"current_steps": 1415, "total_steps": 3345, "loss": 0.7508, "lr": 1.5493637820790443e-06, "epoch": 2.115097159940209, "percentage": 42.3, "elapsed_time": "0:27:24", "remaining_time": "0:37:22", "throughput": 7049.18, "total_tokens": 11591680} {"current_steps": 1416, "total_steps": 3345, "loss": 0.8172, "lr": 1.5482238266578889e-06, "epoch": 2.116591928251121, "percentage": 42.33, "elapsed_time": "0:27:25", "remaining_time": "0:37:21", "throughput": 7049.16, "total_tokens": 11599872} {"current_steps": 1417, "total_steps": 3345, "loss": 0.4464, "lr": 1.5470836081797667e-06, "epoch": 2.118086696562033, "percentage": 42.36, "elapsed_time": "0:27:26", "remaining_time": "0:37:20", "throughput": 7049.15, "total_tokens": 11608064} {"current_steps": 1418, "total_steps": 3345, "loss": 0.6442, "lr": 1.5459431276504406e-06, "epoch": 2.1195814648729447, "percentage": 42.39, "elapsed_time": "0:27:27", "remaining_time": "0:37:19", "throughput": 7049.16, "total_tokens": 11616256} {"current_steps": 1419, "total_steps": 3345, "loss": 0.4616, "lr": 1.5448023860759045e-06, "epoch": 2.1210762331838566, "percentage": 42.42, "elapsed_time": "0:27:29", "remaining_time": "0:37:18", "throughput": 7049.17, "total_tokens": 11624448} {"current_steps": 1420, "total_steps": 3345, "loss": 0.5614, "lr": 1.5436613844623824e-06, "epoch": 2.1225710014947685, "percentage": 42.45, "elapsed_time": "0:27:30", "remaining_time": "0:37:17", "throughput": 7049.16, "total_tokens": 11632640} {"current_steps": 1421, "total_steps": 3345, "loss": 0.3914, "lr": 1.542520123816328e-06, "epoch": 2.12406576980568, "percentage": 42.48, "elapsed_time": "0:27:31", "remaining_time": "0:37:15", "throughput": 7049.17, "total_tokens": 11640832} {"current_steps": 1422, "total_steps": 3345, "loss": 0.6092, "lr": 1.5413786051444237e-06, "epoch": 2.125560538116592, "percentage": 42.51, "elapsed_time": "0:27:32", "remaining_time": "0:37:14", "throughput": 7049.19, "total_tokens": 11649024} {"current_steps": 1423, "total_steps": 3345, "loss": 0.3426, "lr": 1.5402368294535783e-06, "epoch": 2.1270553064275037, "percentage": 42.54, "elapsed_time": "0:27:33", "remaining_time": "0:37:13", "throughput": 7049.21, "total_tokens": 11657216} {"current_steps": 1424, "total_steps": 3345, "loss": 0.4565, "lr": 1.539094797750929e-06, "epoch": 2.1285500747384156, "percentage": 42.57, "elapsed_time": "0:27:34", "remaining_time": "0:37:12", "throughput": 7049.22, "total_tokens": 11665408} {"current_steps": 1425, "total_steps": 3345, "loss": 0.533, "lr": 1.5379525110438375e-06, "epoch": 2.1300448430493275, "percentage": 42.6, "elapsed_time": "0:27:36", "remaining_time": "0:37:11", "throughput": 7049.24, "total_tokens": 11673600} {"current_steps": 1426, "total_steps": 3345, "loss": 0.3503, "lr": 1.5368099703398908e-06, "epoch": 2.131539611360239, "percentage": 42.63, "elapsed_time": "0:27:37", "remaining_time": "0:37:10", "throughput": 7049.27, "total_tokens": 11681792} {"current_steps": 1427, "total_steps": 3345, "loss": 0.8597, "lr": 1.5356671766469004e-06, "epoch": 2.133034379671151, "percentage": 42.66, "elapsed_time": "0:27:38", "remaining_time": "0:37:08", "throughput": 7049.28, "total_tokens": 11689984} {"current_steps": 1428, "total_steps": 3345, "loss": 0.4401, "lr": 1.5345241309728997e-06, "epoch": 2.1345291479820627, "percentage": 42.69, "elapsed_time": "0:27:39", "remaining_time": "0:37:07", "throughput": 7049.27, "total_tokens": 11698176} {"current_steps": 1429, "total_steps": 3345, "loss": 0.6326, "lr": 1.5333808343261464e-06, "epoch": 2.1360239162929746, "percentage": 42.72, "elapsed_time": "0:27:40", "remaining_time": "0:37:06", "throughput": 7049.26, "total_tokens": 11706368} {"current_steps": 1430, "total_steps": 3345, "loss": 0.4255, "lr": 1.532237287715118e-06, "epoch": 2.1375186846038865, "percentage": 42.75, "elapsed_time": "0:27:41", "remaining_time": "0:37:05", "throughput": 7049.29, "total_tokens": 11714560} {"current_steps": 1431, "total_steps": 3345, "loss": 0.4855, "lr": 1.5310934921485123e-06, "epoch": 2.1390134529147984, "percentage": 42.78, "elapsed_time": "0:27:42", "remaining_time": "0:37:04", "throughput": 7049.3, "total_tokens": 11722752} {"current_steps": 1432, "total_steps": 3345, "loss": 0.2798, "lr": 1.5299494486352484e-06, "epoch": 2.14050822122571, "percentage": 42.81, "elapsed_time": "0:27:44", "remaining_time": "0:37:03", "throughput": 7049.32, "total_tokens": 11730944} {"current_steps": 1433, "total_steps": 3345, "loss": 0.7265, "lr": 1.5288051581844623e-06, "epoch": 2.1420029895366217, "percentage": 42.84, "elapsed_time": "0:27:45", "remaining_time": "0:37:01", "throughput": 7049.33, "total_tokens": 11739136} {"current_steps": 1434, "total_steps": 3345, "loss": 0.5774, "lr": 1.527660621805509e-06, "epoch": 2.1434977578475336, "percentage": 42.87, "elapsed_time": "0:27:46", "remaining_time": "0:37:00", "throughput": 7049.34, "total_tokens": 11747328} {"current_steps": 1435, "total_steps": 3345, "loss": 0.4781, "lr": 1.5265158405079595e-06, "epoch": 2.1449925261584455, "percentage": 42.9, "elapsed_time": "0:27:47", "remaining_time": "0:36:59", "throughput": 7049.33, "total_tokens": 11755520} {"current_steps": 1436, "total_steps": 3345, "loss": 0.7112, "lr": 1.5253708153016015e-06, "epoch": 2.1464872944693574, "percentage": 42.93, "elapsed_time": "0:27:48", "remaining_time": "0:36:58", "throughput": 7049.33, "total_tokens": 11763712} {"current_steps": 1437, "total_steps": 3345, "loss": 0.396, "lr": 1.5242255471964373e-06, "epoch": 2.1479820627802693, "percentage": 42.96, "elapsed_time": "0:27:49", "remaining_time": "0:36:57", "throughput": 7049.32, "total_tokens": 11771904} {"current_steps": 1438, "total_steps": 3345, "loss": 0.4212, "lr": 1.5230800372026846e-06, "epoch": 2.1494768310911807, "percentage": 42.99, "elapsed_time": "0:27:51", "remaining_time": "0:36:56", "throughput": 7049.34, "total_tokens": 11780096} {"current_steps": 1439, "total_steps": 3345, "loss": 0.3143, "lr": 1.5219342863307734e-06, "epoch": 2.1509715994020926, "percentage": 43.02, "elapsed_time": "0:27:52", "remaining_time": "0:36:54", "throughput": 7049.36, "total_tokens": 11788288} {"current_steps": 1440, "total_steps": 3345, "loss": 0.5259, "lr": 1.5207882955913458e-06, "epoch": 2.1524663677130045, "percentage": 43.05, "elapsed_time": "0:27:53", "remaining_time": "0:36:53", "throughput": 7049.37, "total_tokens": 11796480} {"current_steps": 1441, "total_steps": 3345, "loss": 0.5242, "lr": 1.5196420659952572e-06, "epoch": 2.1539611360239164, "percentage": 43.08, "elapsed_time": "0:27:54", "remaining_time": "0:36:52", "throughput": 7049.38, "total_tokens": 11804672} {"current_steps": 1442, "total_steps": 3345, "loss": 0.4032, "lr": 1.5184955985535719e-06, "epoch": 2.1554559043348283, "percentage": 43.11, "elapsed_time": "0:27:55", "remaining_time": "0:36:51", "throughput": 7049.4, "total_tokens": 11812864} {"current_steps": 1443, "total_steps": 3345, "loss": 0.5216, "lr": 1.5173488942775646e-06, "epoch": 2.15695067264574, "percentage": 43.14, "elapsed_time": "0:27:56", "remaining_time": "0:36:50", "throughput": 7049.41, "total_tokens": 11821056} {"current_steps": 1444, "total_steps": 3345, "loss": 0.5268, "lr": 1.5162019541787198e-06, "epoch": 2.1584454409566516, "percentage": 43.17, "elapsed_time": "0:27:58", "remaining_time": "0:36:49", "throughput": 7049.42, "total_tokens": 11829248} {"current_steps": 1445, "total_steps": 3345, "loss": 0.6692, "lr": 1.5150547792687285e-06, "epoch": 2.1599402092675635, "percentage": 43.2, "elapsed_time": "0:27:59", "remaining_time": "0:36:47", "throughput": 7049.43, "total_tokens": 11837440} {"current_steps": 1446, "total_steps": 3345, "loss": 0.4783, "lr": 1.5139073705594897e-06, "epoch": 2.1614349775784754, "percentage": 43.23, "elapsed_time": "0:28:00", "remaining_time": "0:36:46", "throughput": 7049.44, "total_tokens": 11845632} {"current_steps": 1447, "total_steps": 3345, "loss": 0.7423, "lr": 1.5127597290631091e-06, "epoch": 2.1629297458893872, "percentage": 43.26, "elapsed_time": "0:28:01", "remaining_time": "0:36:45", "throughput": 7049.43, "total_tokens": 11853824} {"current_steps": 1448, "total_steps": 3345, "loss": 0.4192, "lr": 1.511611855791896e-06, "epoch": 2.164424514200299, "percentage": 43.29, "elapsed_time": "0:28:02", "remaining_time": "0:36:44", "throughput": 7049.45, "total_tokens": 11862016} {"current_steps": 1449, "total_steps": 3345, "loss": 0.6174, "lr": 1.5104637517583665e-06, "epoch": 2.1659192825112106, "percentage": 43.32, "elapsed_time": "0:28:03", "remaining_time": "0:36:43", "throughput": 7049.47, "total_tokens": 11870208} {"current_steps": 1450, "total_steps": 3345, "loss": 0.5872, "lr": 1.5093154179752384e-06, "epoch": 2.1674140508221225, "percentage": 43.35, "elapsed_time": "0:28:05", "remaining_time": "0:36:42", "throughput": 7049.48, "total_tokens": 11878400} {"current_steps": 1451, "total_steps": 3345, "loss": 0.5858, "lr": 1.5081668554554326e-06, "epoch": 2.1689088191330343, "percentage": 43.38, "elapsed_time": "0:28:06", "remaining_time": "0:36:40", "throughput": 7049.47, "total_tokens": 11886592} {"current_steps": 1452, "total_steps": 3345, "loss": 0.6585, "lr": 1.5070180652120724e-06, "epoch": 2.1704035874439462, "percentage": 43.41, "elapsed_time": "0:28:07", "remaining_time": "0:36:39", "throughput": 7049.49, "total_tokens": 11894784} {"current_steps": 1453, "total_steps": 3345, "loss": 0.5783, "lr": 1.5058690482584812e-06, "epoch": 2.171898355754858, "percentage": 43.44, "elapsed_time": "0:28:08", "remaining_time": "0:36:38", "throughput": 7049.5, "total_tokens": 11902976} {"current_steps": 1454, "total_steps": 3345, "loss": 0.5524, "lr": 1.504719805608183e-06, "epoch": 2.17339312406577, "percentage": 43.47, "elapsed_time": "0:28:09", "remaining_time": "0:36:37", "throughput": 7049.51, "total_tokens": 11911168} {"current_steps": 1455, "total_steps": 3345, "loss": 0.3828, "lr": 1.5035703382749002e-06, "epoch": 2.1748878923766815, "percentage": 43.5, "elapsed_time": "0:28:10", "remaining_time": "0:36:36", "throughput": 7049.51, "total_tokens": 11919360} {"current_steps": 1456, "total_steps": 3345, "loss": 0.3728, "lr": 1.5024206472725539e-06, "epoch": 2.1763826606875933, "percentage": 43.53, "elapsed_time": "0:28:11", "remaining_time": "0:36:35", "throughput": 7049.52, "total_tokens": 11927552} {"current_steps": 1457, "total_steps": 3345, "loss": 0.5614, "lr": 1.5012707336152625e-06, "epoch": 2.1778774289985052, "percentage": 43.56, "elapsed_time": "0:28:13", "remaining_time": "0:36:33", "throughput": 7049.53, "total_tokens": 11935744} {"current_steps": 1458, "total_steps": 3345, "loss": 0.5268, "lr": 1.5001205983173405e-06, "epoch": 2.179372197309417, "percentage": 43.59, "elapsed_time": "0:28:14", "remaining_time": "0:36:32", "throughput": 7049.53, "total_tokens": 11943936} {"current_steps": 1459, "total_steps": 3345, "loss": 0.5335, "lr": 1.4989702423932984e-06, "epoch": 2.180866965620329, "percentage": 43.62, "elapsed_time": "0:28:15", "remaining_time": "0:36:31", "throughput": 7049.51, "total_tokens": 11952128} {"current_steps": 1460, "total_steps": 3345, "loss": 0.3017, "lr": 1.4978196668578405e-06, "epoch": 2.1823617339312404, "percentage": 43.65, "elapsed_time": "0:28:16", "remaining_time": "0:36:30", "throughput": 7049.53, "total_tokens": 11960320} {"current_steps": 1461, "total_steps": 3345, "loss": 0.2545, "lr": 1.4966688727258653e-06, "epoch": 2.1838565022421523, "percentage": 43.68, "elapsed_time": "0:28:17", "remaining_time": "0:36:29", "throughput": 7049.54, "total_tokens": 11968512} {"current_steps": 1462, "total_steps": 3345, "loss": 0.6871, "lr": 1.4955178610124645e-06, "epoch": 2.185351270553064, "percentage": 43.71, "elapsed_time": "0:28:18", "remaining_time": "0:36:28", "throughput": 7049.57, "total_tokens": 11976704} {"current_steps": 1463, "total_steps": 3345, "loss": 0.683, "lr": 1.4943666327329212e-06, "epoch": 2.186846038863976, "percentage": 43.74, "elapsed_time": "0:28:20", "remaining_time": "0:36:26", "throughput": 7049.59, "total_tokens": 11984896} {"current_steps": 1464, "total_steps": 3345, "loss": 0.3143, "lr": 1.4932151889027097e-06, "epoch": 2.188340807174888, "percentage": 43.77, "elapsed_time": "0:28:21", "remaining_time": "0:36:25", "throughput": 7049.6, "total_tokens": 11993088} {"current_steps": 1465, "total_steps": 3345, "loss": 0.6275, "lr": 1.4920635305374936e-06, "epoch": 2.1898355754858, "percentage": 43.8, "elapsed_time": "0:28:22", "remaining_time": "0:36:24", "throughput": 7049.61, "total_tokens": 12001280} {"current_steps": 1466, "total_steps": 3345, "loss": 0.5728, "lr": 1.4909116586531278e-06, "epoch": 2.1913303437967113, "percentage": 43.83, "elapsed_time": "0:28:23", "remaining_time": "0:36:23", "throughput": 7049.65, "total_tokens": 12009472} {"current_steps": 1467, "total_steps": 3345, "loss": 0.6697, "lr": 1.4897595742656535e-06, "epoch": 2.192825112107623, "percentage": 43.86, "elapsed_time": "0:28:24", "remaining_time": "0:36:22", "throughput": 7049.66, "total_tokens": 12017664} {"current_steps": 1468, "total_steps": 3345, "loss": 0.5096, "lr": 1.4886072783913002e-06, "epoch": 2.194319880418535, "percentage": 43.89, "elapsed_time": "0:28:25", "remaining_time": "0:36:21", "throughput": 7049.66, "total_tokens": 12025856} {"current_steps": 1469, "total_steps": 3345, "loss": 0.5512, "lr": 1.487454772046484e-06, "epoch": 2.195814648729447, "percentage": 43.92, "elapsed_time": "0:28:27", "remaining_time": "0:36:19", "throughput": 7049.67, "total_tokens": 12034048} {"current_steps": 1470, "total_steps": 3345, "loss": 0.7278, "lr": 1.4863020562478064e-06, "epoch": 2.197309417040359, "percentage": 43.95, "elapsed_time": "0:28:28", "remaining_time": "0:36:18", "throughput": 7049.67, "total_tokens": 12042240} {"current_steps": 1471, "total_steps": 3345, "loss": 0.6651, "lr": 1.4851491320120542e-06, "epoch": 2.1988041853512708, "percentage": 43.98, "elapsed_time": "0:28:29", "remaining_time": "0:36:17", "throughput": 7049.69, "total_tokens": 12050432} {"current_steps": 1472, "total_steps": 3345, "loss": 0.5141, "lr": 1.483996000356197e-06, "epoch": 2.200298953662182, "percentage": 44.01, "elapsed_time": "0:28:30", "remaining_time": "0:36:16", "throughput": 7049.7, "total_tokens": 12058624} {"current_steps": 1473, "total_steps": 3345, "loss": 0.4399, "lr": 1.482842662297388e-06, "epoch": 2.201793721973094, "percentage": 44.04, "elapsed_time": "0:28:31", "remaining_time": "0:36:15", "throughput": 7049.7, "total_tokens": 12066816} {"current_steps": 1474, "total_steps": 3345, "loss": 0.7068, "lr": 1.4816891188529629e-06, "epoch": 2.203288490284006, "percentage": 44.07, "elapsed_time": "0:28:32", "remaining_time": "0:36:14", "throughput": 7049.71, "total_tokens": 12075008} {"current_steps": 1475, "total_steps": 3345, "loss": 0.736, "lr": 1.4805353710404377e-06, "epoch": 2.204783258594918, "percentage": 44.1, "elapsed_time": "0:28:33", "remaining_time": "0:36:12", "throughput": 7049.72, "total_tokens": 12083200} {"current_steps": 1476, "total_steps": 3345, "loss": 0.4686, "lr": 1.4793814198775096e-06, "epoch": 2.2062780269058297, "percentage": 44.13, "elapsed_time": "0:28:35", "remaining_time": "0:36:11", "throughput": 7049.75, "total_tokens": 12091392} {"current_steps": 1477, "total_steps": 3345, "loss": 0.6044, "lr": 1.4782272663820543e-06, "epoch": 2.2077727952167416, "percentage": 44.16, "elapsed_time": "0:28:36", "remaining_time": "0:36:10", "throughput": 7049.78, "total_tokens": 12099584} {"current_steps": 1478, "total_steps": 3345, "loss": 0.2856, "lr": 1.477072911572126e-06, "epoch": 2.209267563527653, "percentage": 44.19, "elapsed_time": "0:28:37", "remaining_time": "0:36:09", "throughput": 7049.79, "total_tokens": 12107776} {"current_steps": 1479, "total_steps": 3345, "loss": 0.4746, "lr": 1.4759183564659573e-06, "epoch": 2.210762331838565, "percentage": 44.22, "elapsed_time": "0:28:38", "remaining_time": "0:36:08", "throughput": 7049.81, "total_tokens": 12115968} {"current_steps": 1480, "total_steps": 3345, "loss": 0.4585, "lr": 1.4747636020819572e-06, "epoch": 2.212257100149477, "percentage": 44.25, "elapsed_time": "0:28:39", "remaining_time": "0:36:07", "throughput": 7049.84, "total_tokens": 12124160} {"current_steps": 1481, "total_steps": 3345, "loss": 0.533, "lr": 1.4736086494387098e-06, "epoch": 2.2137518684603887, "percentage": 44.28, "elapsed_time": "0:28:40", "remaining_time": "0:36:05", "throughput": 7049.85, "total_tokens": 12132352} {"current_steps": 1482, "total_steps": 3345, "loss": 0.6349, "lr": 1.4724534995549742e-06, "epoch": 2.2152466367713006, "percentage": 44.3, "elapsed_time": "0:28:42", "remaining_time": "0:36:04", "throughput": 7049.86, "total_tokens": 12140544} {"current_steps": 1483, "total_steps": 3345, "loss": 0.5561, "lr": 1.4712981534496845e-06, "epoch": 2.216741405082212, "percentage": 44.33, "elapsed_time": "0:28:43", "remaining_time": "0:36:03", "throughput": 7049.87, "total_tokens": 12148736} {"current_steps": 1484, "total_steps": 3345, "loss": 0.4343, "lr": 1.4701426121419474e-06, "epoch": 2.218236173393124, "percentage": 44.36, "elapsed_time": "0:28:44", "remaining_time": "0:36:02", "throughput": 7049.89, "total_tokens": 12156928} {"current_steps": 1485, "total_steps": 3345, "loss": 0.4461, "lr": 1.4689868766510406e-06, "epoch": 2.219730941704036, "percentage": 44.39, "elapsed_time": "0:28:45", "remaining_time": "0:36:01", "throughput": 7049.89, "total_tokens": 12165120} {"current_steps": 1486, "total_steps": 3345, "loss": 0.5753, "lr": 1.4678309479964147e-06, "epoch": 2.2212257100149477, "percentage": 44.42, "elapsed_time": "0:28:46", "remaining_time": "0:36:00", "throughput": 7049.86, "total_tokens": 12173312} {"current_steps": 1487, "total_steps": 3345, "loss": 0.6781, "lr": 1.4666748271976904e-06, "epoch": 2.2227204783258596, "percentage": 44.45, "elapsed_time": "0:28:47", "remaining_time": "0:35:59", "throughput": 7049.87, "total_tokens": 12181504} {"current_steps": 1488, "total_steps": 3345, "loss": 0.5155, "lr": 1.4655185152746571e-06, "epoch": 2.2242152466367715, "percentage": 44.48, "elapsed_time": "0:28:49", "remaining_time": "0:35:57", "throughput": 7049.87, "total_tokens": 12189696} {"current_steps": 1489, "total_steps": 3345, "loss": 0.4227, "lr": 1.4643620132472733e-06, "epoch": 2.225710014947683, "percentage": 44.51, "elapsed_time": "0:28:50", "remaining_time": "0:35:56", "throughput": 7049.89, "total_tokens": 12197888} {"current_steps": 1490, "total_steps": 3345, "loss": 0.3752, "lr": 1.4632053221356647e-06, "epoch": 2.227204783258595, "percentage": 44.54, "elapsed_time": "0:28:51", "remaining_time": "0:35:55", "throughput": 7049.91, "total_tokens": 12206080} {"current_steps": 1491, "total_steps": 3345, "loss": 0.8076, "lr": 1.4620484429601249e-06, "epoch": 2.2286995515695067, "percentage": 44.57, "elapsed_time": "0:28:52", "remaining_time": "0:35:54", "throughput": 7049.93, "total_tokens": 12214272} {"current_steps": 1492, "total_steps": 3345, "loss": 0.4846, "lr": 1.4608913767411122e-06, "epoch": 2.2301943198804186, "percentage": 44.6, "elapsed_time": "0:28:53", "remaining_time": "0:35:53", "throughput": 7049.95, "total_tokens": 12222464} {"current_steps": 1493, "total_steps": 3345, "loss": 0.4203, "lr": 1.459734124499251e-06, "epoch": 2.2316890881913305, "percentage": 44.63, "elapsed_time": "0:28:54", "remaining_time": "0:35:52", "throughput": 7049.96, "total_tokens": 12230656} {"current_steps": 1494, "total_steps": 3345, "loss": 0.4517, "lr": 1.4585766872553283e-06, "epoch": 2.233183856502242, "percentage": 44.66, "elapsed_time": "0:28:56", "remaining_time": "0:35:50", "throughput": 7050.01, "total_tokens": 12238848} {"current_steps": 1495, "total_steps": 3345, "loss": 0.5376, "lr": 1.457419066030296e-06, "epoch": 2.234678624813154, "percentage": 44.69, "elapsed_time": "0:28:57", "remaining_time": "0:35:49", "throughput": 7050.02, "total_tokens": 12247040} {"current_steps": 1496, "total_steps": 3345, "loss": 0.4879, "lr": 1.4562612618452668e-06, "epoch": 2.2361733931240657, "percentage": 44.72, "elapsed_time": "0:28:58", "remaining_time": "0:35:48", "throughput": 7050.04, "total_tokens": 12255232} {"current_steps": 1497, "total_steps": 3345, "loss": 0.369, "lr": 1.4551032757215158e-06, "epoch": 2.2376681614349776, "percentage": 44.75, "elapsed_time": "0:28:59", "remaining_time": "0:35:47", "throughput": 7050.04, "total_tokens": 12263424} {"current_steps": 1498, "total_steps": 3345, "loss": 0.8047, "lr": 1.4539451086804782e-06, "epoch": 2.2391629297458895, "percentage": 44.78, "elapsed_time": "0:29:00", "remaining_time": "0:35:46", "throughput": 7050.05, "total_tokens": 12271616} {"current_steps": 1499, "total_steps": 3345, "loss": 0.6053, "lr": 1.4527867617437483e-06, "epoch": 2.2406576980568014, "percentage": 44.81, "elapsed_time": "0:29:01", "remaining_time": "0:35:45", "throughput": 7050.05, "total_tokens": 12279808} {"current_steps": 1500, "total_steps": 3345, "loss": 0.4277, "lr": 1.4516282359330803e-06, "epoch": 2.242152466367713, "percentage": 44.84, "elapsed_time": "0:29:02", "remaining_time": "0:35:43", "throughput": 7050.06, "total_tokens": 12288000} {"current_steps": 1501, "total_steps": 3345, "loss": 0.3941, "lr": 1.450469532270385e-06, "epoch": 2.2436472346786247, "percentage": 44.87, "elapsed_time": "0:29:04", "remaining_time": "0:35:42", "throughput": 7050.05, "total_tokens": 12296192} {"current_steps": 1502, "total_steps": 3345, "loss": 0.4915, "lr": 1.4493106517777306e-06, "epoch": 2.2451420029895366, "percentage": 44.9, "elapsed_time": "0:29:05", "remaining_time": "0:35:41", "throughput": 7050.06, "total_tokens": 12304384} {"current_steps": 1503, "total_steps": 3345, "loss": 0.7488, "lr": 1.4481515954773412e-06, "epoch": 2.2466367713004485, "percentage": 44.93, "elapsed_time": "0:29:06", "remaining_time": "0:35:40", "throughput": 7050.07, "total_tokens": 12312576} {"current_steps": 1504, "total_steps": 3345, "loss": 0.6875, "lr": 1.4469923643915962e-06, "epoch": 2.2481315396113604, "percentage": 44.96, "elapsed_time": "0:29:07", "remaining_time": "0:35:39", "throughput": 7050.08, "total_tokens": 12320768} {"current_steps": 1505, "total_steps": 3345, "loss": 0.6492, "lr": 1.445832959543029e-06, "epoch": 2.2496263079222723, "percentage": 44.99, "elapsed_time": "0:29:08", "remaining_time": "0:35:38", "throughput": 7050.07, "total_tokens": 12328960} {"current_steps": 1506, "total_steps": 3345, "loss": 0.3015, "lr": 1.4446733819543258e-06, "epoch": 2.2511210762331837, "percentage": 45.02, "elapsed_time": "0:29:09", "remaining_time": "0:35:36", "throughput": 7050.09, "total_tokens": 12337152} {"current_steps": 1507, "total_steps": 3345, "loss": 0.6239, "lr": 1.4435136326483257e-06, "epoch": 2.2526158445440956, "percentage": 45.05, "elapsed_time": "0:29:11", "remaining_time": "0:35:35", "throughput": 7050.11, "total_tokens": 12345344} {"current_steps": 1508, "total_steps": 3345, "loss": 0.5843, "lr": 1.4423537126480198e-06, "epoch": 2.2541106128550075, "percentage": 45.08, "elapsed_time": "0:29:12", "remaining_time": "0:35:34", "throughput": 7050.12, "total_tokens": 12353536} {"current_steps": 1509, "total_steps": 3345, "loss": 0.7626, "lr": 1.4411936229765483e-06, "epoch": 2.2556053811659194, "percentage": 45.11, "elapsed_time": "0:29:13", "remaining_time": "0:35:33", "throughput": 7050.12, "total_tokens": 12361728} {"current_steps": 1510, "total_steps": 3345, "loss": 0.6956, "lr": 1.4400333646572024e-06, "epoch": 2.2571001494768312, "percentage": 45.14, "elapsed_time": "0:29:14", "remaining_time": "0:35:32", "throughput": 7050.13, "total_tokens": 12369920} {"current_steps": 1511, "total_steps": 3345, "loss": 0.6831, "lr": 1.4388729387134215e-06, "epoch": 2.258594917787743, "percentage": 45.17, "elapsed_time": "0:29:15", "remaining_time": "0:35:31", "throughput": 7050.14, "total_tokens": 12378112} {"current_steps": 1512, "total_steps": 3345, "loss": 0.5824, "lr": 1.437712346168793e-06, "epoch": 2.2600896860986546, "percentage": 45.2, "elapsed_time": "0:29:16", "remaining_time": "0:35:29", "throughput": 7050.16, "total_tokens": 12386304} {"current_steps": 1513, "total_steps": 3345, "loss": 0.6431, "lr": 1.436551588047051e-06, "epoch": 2.2615844544095665, "percentage": 45.23, "elapsed_time": "0:29:18", "remaining_time": "0:35:28", "throughput": 7050.17, "total_tokens": 12394496} {"current_steps": 1514, "total_steps": 3345, "loss": 0.4607, "lr": 1.435390665372076e-06, "epoch": 2.2630792227204783, "percentage": 45.26, "elapsed_time": "0:29:19", "remaining_time": "0:35:27", "throughput": 7050.18, "total_tokens": 12402688} {"current_steps": 1515, "total_steps": 3345, "loss": 0.7607, "lr": 1.4342295791678932e-06, "epoch": 2.2645739910313902, "percentage": 45.29, "elapsed_time": "0:29:20", "remaining_time": "0:35:26", "throughput": 7050.18, "total_tokens": 12410880} {"current_steps": 1516, "total_steps": 3345, "loss": 0.6105, "lr": 1.4330683304586723e-06, "epoch": 2.266068759342302, "percentage": 45.32, "elapsed_time": "0:29:21", "remaining_time": "0:35:25", "throughput": 7050.21, "total_tokens": 12419072} {"current_steps": 1517, "total_steps": 3345, "loss": 0.6013, "lr": 1.4319069202687268e-06, "epoch": 2.2675635276532136, "percentage": 45.35, "elapsed_time": "0:29:22", "remaining_time": "0:35:24", "throughput": 7050.24, "total_tokens": 12427264} {"current_steps": 1518, "total_steps": 3345, "loss": 0.566, "lr": 1.430745349622512e-06, "epoch": 2.2690582959641254, "percentage": 45.38, "elapsed_time": "0:29:23", "remaining_time": "0:35:22", "throughput": 7050.27, "total_tokens": 12435456} {"current_steps": 1519, "total_steps": 3345, "loss": 0.9087, "lr": 1.4295836195446246e-06, "epoch": 2.2705530642750373, "percentage": 45.41, "elapsed_time": "0:29:24", "remaining_time": "0:35:21", "throughput": 7050.29, "total_tokens": 12443648} {"current_steps": 1520, "total_steps": 3345, "loss": 0.6111, "lr": 1.4284217310598028e-06, "epoch": 2.2720478325859492, "percentage": 45.44, "elapsed_time": "0:29:26", "remaining_time": "0:35:20", "throughput": 7050.3, "total_tokens": 12451840} {"current_steps": 1521, "total_steps": 3345, "loss": 0.5228, "lr": 1.427259685192924e-06, "epoch": 2.273542600896861, "percentage": 45.47, "elapsed_time": "0:29:27", "remaining_time": "0:35:19", "throughput": 7050.31, "total_tokens": 12460032} {"current_steps": 1522, "total_steps": 3345, "loss": 0.3842, "lr": 1.4260974829690042e-06, "epoch": 2.275037369207773, "percentage": 45.5, "elapsed_time": "0:29:28", "remaining_time": "0:35:18", "throughput": 7050.32, "total_tokens": 12468224} {"current_steps": 1523, "total_steps": 3345, "loss": 0.6203, "lr": 1.4249351254131974e-06, "epoch": 2.2765321375186844, "percentage": 45.53, "elapsed_time": "0:29:29", "remaining_time": "0:35:17", "throughput": 7050.3, "total_tokens": 12476416} {"current_steps": 1524, "total_steps": 3345, "loss": 0.667, "lr": 1.423772613550795e-06, "epoch": 2.2780269058295963, "percentage": 45.56, "elapsed_time": "0:29:30", "remaining_time": "0:35:15", "throughput": 7050.32, "total_tokens": 12484608} {"current_steps": 1525, "total_steps": 3345, "loss": 0.4102, "lr": 1.422609948407224e-06, "epoch": 2.279521674140508, "percentage": 45.59, "elapsed_time": "0:29:31", "remaining_time": "0:35:14", "throughput": 7050.32, "total_tokens": 12492800} {"current_steps": 1526, "total_steps": 3345, "loss": 0.4911, "lr": 1.421447131008047e-06, "epoch": 2.28101644245142, "percentage": 45.62, "elapsed_time": "0:29:33", "remaining_time": "0:35:13", "throughput": 7050.34, "total_tokens": 12500992} {"current_steps": 1527, "total_steps": 3345, "loss": 0.376, "lr": 1.420284162378961e-06, "epoch": 2.282511210762332, "percentage": 45.65, "elapsed_time": "0:29:34", "remaining_time": "0:35:12", "throughput": 7050.35, "total_tokens": 12509184} {"current_steps": 1528, "total_steps": 3345, "loss": 0.5666, "lr": 1.4191210435457962e-06, "epoch": 2.2840059790732434, "percentage": 45.68, "elapsed_time": "0:29:35", "remaining_time": "0:35:11", "throughput": 7050.37, "total_tokens": 12517376} {"current_steps": 1529, "total_steps": 3345, "loss": 0.7303, "lr": 1.4179577755345147e-06, "epoch": 2.2855007473841553, "percentage": 45.71, "elapsed_time": "0:29:36", "remaining_time": "0:35:10", "throughput": 7050.38, "total_tokens": 12525568} {"current_steps": 1530, "total_steps": 3345, "loss": 0.4597, "lr": 1.4167943593712112e-06, "epoch": 2.286995515695067, "percentage": 45.74, "elapsed_time": "0:29:37", "remaining_time": "0:35:08", "throughput": 7050.39, "total_tokens": 12533760} {"current_steps": 1531, "total_steps": 3345, "loss": 0.5444, "lr": 1.415630796082111e-06, "epoch": 2.288490284005979, "percentage": 45.77, "elapsed_time": "0:29:38", "remaining_time": "0:35:07", "throughput": 7050.42, "total_tokens": 12541952} {"current_steps": 1532, "total_steps": 3345, "loss": 0.6142, "lr": 1.4144670866935682e-06, "epoch": 2.289985052316891, "percentage": 45.8, "elapsed_time": "0:29:40", "remaining_time": "0:35:06", "throughput": 7050.45, "total_tokens": 12550144} {"current_steps": 1533, "total_steps": 3345, "loss": 0.4527, "lr": 1.413303232232066e-06, "epoch": 2.291479820627803, "percentage": 45.83, "elapsed_time": "0:29:41", "remaining_time": "0:35:05", "throughput": 7050.46, "total_tokens": 12558336} {"current_steps": 1534, "total_steps": 3345, "loss": 0.5566, "lr": 1.412139233724217e-06, "epoch": 2.2929745889387143, "percentage": 45.86, "elapsed_time": "0:29:42", "remaining_time": "0:35:04", "throughput": 7050.45, "total_tokens": 12566528} {"current_steps": 1535, "total_steps": 3345, "loss": 0.7121, "lr": 1.4109750921967592e-06, "epoch": 2.294469357249626, "percentage": 45.89, "elapsed_time": "0:29:43", "remaining_time": "0:35:03", "throughput": 7050.46, "total_tokens": 12574720} {"current_steps": 1536, "total_steps": 3345, "loss": 0.574, "lr": 1.4098108086765575e-06, "epoch": 2.295964125560538, "percentage": 45.92, "elapsed_time": "0:29:44", "remaining_time": "0:35:01", "throughput": 7050.47, "total_tokens": 12582912} {"current_steps": 1537, "total_steps": 3345, "loss": 0.2697, "lr": 1.408646384190602e-06, "epoch": 2.29745889387145, "percentage": 45.95, "elapsed_time": "0:29:45", "remaining_time": "0:35:00", "throughput": 7050.49, "total_tokens": 12591104} {"current_steps": 1538, "total_steps": 3345, "loss": 0.6895, "lr": 1.4074818197660067e-06, "epoch": 2.298953662182362, "percentage": 45.98, "elapsed_time": "0:29:47", "remaining_time": "0:34:59", "throughput": 7050.5, "total_tokens": 12599296} {"current_steps": 1539, "total_steps": 3345, "loss": 0.4706, "lr": 1.4063171164300099e-06, "epoch": 2.3004484304932733, "percentage": 46.01, "elapsed_time": "0:29:48", "remaining_time": "0:34:58", "throughput": 7050.5, "total_tokens": 12607488} {"current_steps": 1540, "total_steps": 3345, "loss": 0.4359, "lr": 1.4051522752099717e-06, "epoch": 2.301943198804185, "percentage": 46.04, "elapsed_time": "0:29:49", "remaining_time": "0:34:57", "throughput": 7050.51, "total_tokens": 12615680} {"current_steps": 1541, "total_steps": 3345, "loss": 0.2453, "lr": 1.4039872971333734e-06, "epoch": 2.303437967115097, "percentage": 46.07, "elapsed_time": "0:29:50", "remaining_time": "0:34:56", "throughput": 7050.5, "total_tokens": 12623872} {"current_steps": 1542, "total_steps": 3345, "loss": 0.5679, "lr": 1.4028221832278189e-06, "epoch": 2.304932735426009, "percentage": 46.1, "elapsed_time": "0:29:51", "remaining_time": "0:34:54", "throughput": 7050.5, "total_tokens": 12632064} {"current_steps": 1543, "total_steps": 3345, "loss": 0.2487, "lr": 1.4016569345210296e-06, "epoch": 2.306427503736921, "percentage": 46.13, "elapsed_time": "0:29:52", "remaining_time": "0:34:53", "throughput": 7050.53, "total_tokens": 12640256} {"current_steps": 1544, "total_steps": 3345, "loss": 0.4754, "lr": 1.4004915520408474e-06, "epoch": 2.3079222720478327, "percentage": 46.16, "elapsed_time": "0:29:53", "remaining_time": "0:34:52", "throughput": 7050.55, "total_tokens": 12648448} {"current_steps": 1545, "total_steps": 3345, "loss": 0.4652, "lr": 1.3993260368152316e-06, "epoch": 2.3094170403587446, "percentage": 46.19, "elapsed_time": "0:29:55", "remaining_time": "0:34:51", "throughput": 7050.56, "total_tokens": 12656640} {"current_steps": 1546, "total_steps": 3345, "loss": 0.417, "lr": 1.398160389872259e-06, "epoch": 2.310911808669656, "percentage": 46.22, "elapsed_time": "0:29:56", "remaining_time": "0:34:50", "throughput": 7050.59, "total_tokens": 12664832} {"current_steps": 1547, "total_steps": 3345, "loss": 0.607, "lr": 1.3969946122401218e-06, "epoch": 2.312406576980568, "percentage": 46.25, "elapsed_time": "0:29:57", "remaining_time": "0:34:49", "throughput": 7050.59, "total_tokens": 12673024} {"current_steps": 1548, "total_steps": 3345, "loss": 0.6066, "lr": 1.395828704947128e-06, "epoch": 2.31390134529148, "percentage": 46.28, "elapsed_time": "0:29:58", "remaining_time": "0:34:47", "throughput": 7050.6, "total_tokens": 12681216} {"current_steps": 1549, "total_steps": 3345, "loss": 0.4514, "lr": 1.3946626690217003e-06, "epoch": 2.3153961136023917, "percentage": 46.31, "elapsed_time": "0:29:59", "remaining_time": "0:34:46", "throughput": 7050.6, "total_tokens": 12689408} {"current_steps": 1550, "total_steps": 3345, "loss": 0.625, "lr": 1.3934965054923735e-06, "epoch": 2.3168908819133036, "percentage": 46.34, "elapsed_time": "0:30:00", "remaining_time": "0:34:45", "throughput": 7050.6, "total_tokens": 12697600} {"current_steps": 1551, "total_steps": 3345, "loss": 0.5057, "lr": 1.3923302153877965e-06, "epoch": 2.318385650224215, "percentage": 46.37, "elapsed_time": "0:30:02", "remaining_time": "0:34:44", "throughput": 7050.61, "total_tokens": 12705792} {"current_steps": 1552, "total_steps": 3345, "loss": 0.4074, "lr": 1.39116379973673e-06, "epoch": 2.319880418535127, "percentage": 46.4, "elapsed_time": "0:30:03", "remaining_time": "0:34:43", "throughput": 7050.63, "total_tokens": 12713984} {"current_steps": 1553, "total_steps": 3345, "loss": 0.3056, "lr": 1.389997259568044e-06, "epoch": 2.321375186846039, "percentage": 46.43, "elapsed_time": "0:30:04", "remaining_time": "0:34:42", "throughput": 7050.66, "total_tokens": 12722176} {"current_steps": 1554, "total_steps": 3345, "loss": 0.594, "lr": 1.3888305959107187e-06, "epoch": 2.3228699551569507, "percentage": 46.46, "elapsed_time": "0:30:05", "remaining_time": "0:34:40", "throughput": 7050.67, "total_tokens": 12730368} {"current_steps": 1555, "total_steps": 3345, "loss": 0.8439, "lr": 1.3876638097938443e-06, "epoch": 2.3243647234678626, "percentage": 46.49, "elapsed_time": "0:30:06", "remaining_time": "0:34:39", "throughput": 7050.67, "total_tokens": 12738560} {"current_steps": 1556, "total_steps": 3345, "loss": 0.516, "lr": 1.3864969022466178e-06, "epoch": 2.3258594917787745, "percentage": 46.52, "elapsed_time": "0:30:07", "remaining_time": "0:34:38", "throughput": 7050.68, "total_tokens": 12746752} {"current_steps": 1557, "total_steps": 3345, "loss": 0.4841, "lr": 1.3853298742983445e-06, "epoch": 2.327354260089686, "percentage": 46.55, "elapsed_time": "0:30:09", "remaining_time": "0:34:37", "throughput": 7050.69, "total_tokens": 12754944} {"current_steps": 1558, "total_steps": 3345, "loss": 0.4955, "lr": 1.3841627269784341e-06, "epoch": 2.328849028400598, "percentage": 46.58, "elapsed_time": "0:30:10", "remaining_time": "0:34:36", "throughput": 7050.69, "total_tokens": 12763136} {"current_steps": 1559, "total_steps": 3345, "loss": 0.1486, "lr": 1.3829954613164037e-06, "epoch": 2.3303437967115097, "percentage": 46.61, "elapsed_time": "0:30:11", "remaining_time": "0:34:35", "throughput": 7050.7, "total_tokens": 12771328} {"current_steps": 1560, "total_steps": 3345, "loss": 0.7584, "lr": 1.3818280783418731e-06, "epoch": 2.3318385650224216, "percentage": 46.64, "elapsed_time": "0:30:12", "remaining_time": "0:34:33", "throughput": 7050.72, "total_tokens": 12779520} {"current_steps": 1561, "total_steps": 3345, "loss": 0.6276, "lr": 1.380660579084567e-06, "epoch": 2.3333333333333335, "percentage": 46.67, "elapsed_time": "0:30:13", "remaining_time": "0:34:32", "throughput": 7050.72, "total_tokens": 12787712} {"current_steps": 1562, "total_steps": 3345, "loss": 0.3719, "lr": 1.3794929645743114e-06, "epoch": 2.334828101644245, "percentage": 46.7, "elapsed_time": "0:30:14", "remaining_time": "0:34:31", "throughput": 7050.73, "total_tokens": 12795904} {"current_steps": 1563, "total_steps": 3345, "loss": 0.5465, "lr": 1.3783252358410348e-06, "epoch": 2.336322869955157, "percentage": 46.73, "elapsed_time": "0:30:16", "remaining_time": "0:34:30", "throughput": 7050.71, "total_tokens": 12804096} {"current_steps": 1564, "total_steps": 3345, "loss": 0.4694, "lr": 1.377157393914766e-06, "epoch": 2.3378176382660687, "percentage": 46.76, "elapsed_time": "0:30:17", "remaining_time": "0:34:29", "throughput": 7050.71, "total_tokens": 12812288} {"current_steps": 1565, "total_steps": 3345, "loss": 0.6027, "lr": 1.3759894398256335e-06, "epoch": 2.3393124065769806, "percentage": 46.79, "elapsed_time": "0:30:18", "remaining_time": "0:34:28", "throughput": 7050.72, "total_tokens": 12820480} {"current_steps": 1566, "total_steps": 3345, "loss": 0.5729, "lr": 1.3748213746038654e-06, "epoch": 2.3408071748878925, "percentage": 46.82, "elapsed_time": "0:30:19", "remaining_time": "0:34:26", "throughput": 7050.72, "total_tokens": 12828672} {"current_steps": 1567, "total_steps": 3345, "loss": 0.8031, "lr": 1.3736531992797877e-06, "epoch": 2.3423019431988044, "percentage": 46.85, "elapsed_time": "0:30:20", "remaining_time": "0:34:25", "throughput": 7050.72, "total_tokens": 12836864} {"current_steps": 1568, "total_steps": 3345, "loss": 0.3706, "lr": 1.3724849148838227e-06, "epoch": 2.343796711509716, "percentage": 46.88, "elapsed_time": "0:30:21", "remaining_time": "0:34:24", "throughput": 7050.73, "total_tokens": 12845056} {"current_steps": 1569, "total_steps": 3345, "loss": 0.6693, "lr": 1.3713165224464902e-06, "epoch": 2.3452914798206277, "percentage": 46.91, "elapsed_time": "0:30:22", "remaining_time": "0:34:23", "throughput": 7050.71, "total_tokens": 12853248} {"current_steps": 1570, "total_steps": 3345, "loss": 0.504, "lr": 1.370148022998404e-06, "epoch": 2.3467862481315396, "percentage": 46.94, "elapsed_time": "0:30:24", "remaining_time": "0:34:22", "throughput": 7050.71, "total_tokens": 12861440} {"current_steps": 1571, "total_steps": 3345, "loss": 0.6953, "lr": 1.3689794175702733e-06, "epoch": 2.3482810164424515, "percentage": 46.97, "elapsed_time": "0:30:25", "remaining_time": "0:34:21", "throughput": 7050.72, "total_tokens": 12869632} {"current_steps": 1572, "total_steps": 3345, "loss": 0.5927, "lr": 1.3678107071929004e-06, "epoch": 2.3497757847533634, "percentage": 47.0, "elapsed_time": "0:30:26", "remaining_time": "0:34:19", "throughput": 7050.73, "total_tokens": 12877824} {"current_steps": 1573, "total_steps": 3345, "loss": 0.5248, "lr": 1.3666418928971797e-06, "epoch": 2.351270553064275, "percentage": 47.03, "elapsed_time": "0:30:27", "remaining_time": "0:34:18", "throughput": 7050.75, "total_tokens": 12886016} {"current_steps": 1574, "total_steps": 3345, "loss": 0.459, "lr": 1.3654729757140981e-06, "epoch": 2.3527653213751867, "percentage": 47.06, "elapsed_time": "0:30:28", "remaining_time": "0:34:17", "throughput": 7050.76, "total_tokens": 12894208} {"current_steps": 1575, "total_steps": 3345, "loss": 0.6451, "lr": 1.364303956674732e-06, "epoch": 2.3542600896860986, "percentage": 47.09, "elapsed_time": "0:30:29", "remaining_time": "0:34:16", "throughput": 7050.78, "total_tokens": 12902400} {"current_steps": 1576, "total_steps": 3345, "loss": 0.3263, "lr": 1.3631348368102498e-06, "epoch": 2.3557548579970105, "percentage": 47.12, "elapsed_time": "0:30:31", "remaining_time": "0:34:15", "throughput": 7050.78, "total_tokens": 12910592} {"current_steps": 1577, "total_steps": 3345, "loss": 0.4435, "lr": 1.3619656171519068e-06, "epoch": 2.3572496263079223, "percentage": 47.14, "elapsed_time": "0:30:32", "remaining_time": "0:34:14", "throughput": 7050.78, "total_tokens": 12918784} {"current_steps": 1578, "total_steps": 3345, "loss": 0.4669, "lr": 1.3607962987310477e-06, "epoch": 2.3587443946188342, "percentage": 47.17, "elapsed_time": "0:30:33", "remaining_time": "0:34:13", "throughput": 7050.78, "total_tokens": 12926976} {"current_steps": 1579, "total_steps": 3345, "loss": 0.7336, "lr": 1.359626882579103e-06, "epoch": 2.360239162929746, "percentage": 47.2, "elapsed_time": "0:30:34", "remaining_time": "0:34:11", "throughput": 7050.76, "total_tokens": 12935168} {"current_steps": 1580, "total_steps": 3345, "loss": 0.5839, "lr": 1.3584573697275905e-06, "epoch": 2.3617339312406576, "percentage": 47.23, "elapsed_time": "0:30:35", "remaining_time": "0:34:10", "throughput": 7050.74, "total_tokens": 12943360} {"current_steps": 1581, "total_steps": 3345, "loss": 0.4112, "lr": 1.3572877612081125e-06, "epoch": 2.3632286995515694, "percentage": 47.26, "elapsed_time": "0:30:36", "remaining_time": "0:34:09", "throughput": 7050.75, "total_tokens": 12951552} {"current_steps": 1582, "total_steps": 3345, "loss": 0.3603, "lr": 1.3561180580523567e-06, "epoch": 2.3647234678624813, "percentage": 47.29, "elapsed_time": "0:30:38", "remaining_time": "0:34:08", "throughput": 7050.76, "total_tokens": 12959744} {"current_steps": 1583, "total_steps": 3345, "loss": 0.5824, "lr": 1.3549482612920927e-06, "epoch": 2.366218236173393, "percentage": 47.32, "elapsed_time": "0:30:39", "remaining_time": "0:34:07", "throughput": 7050.77, "total_tokens": 12967936} {"current_steps": 1584, "total_steps": 3345, "loss": 0.5797, "lr": 1.3537783719591742e-06, "epoch": 2.367713004484305, "percentage": 47.35, "elapsed_time": "0:30:40", "remaining_time": "0:34:06", "throughput": 7050.78, "total_tokens": 12976128} {"current_steps": 1585, "total_steps": 3345, "loss": 0.5096, "lr": 1.3526083910855364e-06, "epoch": 2.3692077727952165, "percentage": 47.38, "elapsed_time": "0:30:41", "remaining_time": "0:34:04", "throughput": 7050.79, "total_tokens": 12984320} {"current_steps": 1586, "total_steps": 3345, "loss": 0.4941, "lr": 1.3514383197031943e-06, "epoch": 2.3707025411061284, "percentage": 47.41, "elapsed_time": "0:30:42", "remaining_time": "0:34:03", "throughput": 7050.81, "total_tokens": 12992512} {"current_steps": 1587, "total_steps": 3345, "loss": 0.4461, "lr": 1.3502681588442438e-06, "epoch": 2.3721973094170403, "percentage": 47.44, "elapsed_time": "0:30:43", "remaining_time": "0:34:02", "throughput": 7050.81, "total_tokens": 13000704} {"current_steps": 1588, "total_steps": 3345, "loss": 0.6445, "lr": 1.3490979095408581e-06, "epoch": 2.373692077727952, "percentage": 47.47, "elapsed_time": "0:30:45", "remaining_time": "0:34:01", "throughput": 7050.82, "total_tokens": 13008896} {"current_steps": 1589, "total_steps": 3345, "loss": 0.4317, "lr": 1.3479275728252908e-06, "epoch": 2.375186846038864, "percentage": 47.5, "elapsed_time": "0:30:46", "remaining_time": "0:34:00", "throughput": 7050.83, "total_tokens": 13017088} {"current_steps": 1590, "total_steps": 3345, "loss": 0.5473, "lr": 1.3467571497298703e-06, "epoch": 2.376681614349776, "percentage": 47.53, "elapsed_time": "0:30:47", "remaining_time": "0:33:59", "throughput": 7050.82, "total_tokens": 13025280} {"current_steps": 1591, "total_steps": 3345, "loss": 0.6913, "lr": 1.3455866412870025e-06, "epoch": 2.3781763826606874, "percentage": 47.56, "elapsed_time": "0:30:48", "remaining_time": "0:33:57", "throughput": 7050.83, "total_tokens": 13033472} {"current_steps": 1592, "total_steps": 3345, "loss": 0.3194, "lr": 1.3444160485291681e-06, "epoch": 2.3796711509715993, "percentage": 47.59, "elapsed_time": "0:30:49", "remaining_time": "0:33:56", "throughput": 7050.84, "total_tokens": 13041664} {"current_steps": 1593, "total_steps": 3345, "loss": 0.414, "lr": 1.3432453724889233e-06, "epoch": 2.381165919282511, "percentage": 47.62, "elapsed_time": "0:30:50", "remaining_time": "0:33:55", "throughput": 7050.84, "total_tokens": 13049856} {"current_steps": 1594, "total_steps": 3345, "loss": 0.4962, "lr": 1.3420746141988959e-06, "epoch": 2.382660687593423, "percentage": 47.65, "elapsed_time": "0:30:51", "remaining_time": "0:33:54", "throughput": 7050.85, "total_tokens": 13058048} {"current_steps": 1595, "total_steps": 3345, "loss": 0.8833, "lr": 1.3409037746917873e-06, "epoch": 2.384155455904335, "percentage": 47.68, "elapsed_time": "0:30:53", "remaining_time": "0:33:53", "throughput": 7050.85, "total_tokens": 13066240} {"current_steps": 1596, "total_steps": 3345, "loss": 0.4853, "lr": 1.3397328550003707e-06, "epoch": 2.3856502242152464, "percentage": 47.71, "elapsed_time": "0:30:54", "remaining_time": "0:33:52", "throughput": 7050.85, "total_tokens": 13074432} {"current_steps": 1597, "total_steps": 3345, "loss": 0.5368, "lr": 1.3385618561574896e-06, "epoch": 2.3871449925261583, "percentage": 47.74, "elapsed_time": "0:30:55", "remaining_time": "0:33:50", "throughput": 7050.86, "total_tokens": 13082624} {"current_steps": 1598, "total_steps": 3345, "loss": 0.3061, "lr": 1.3373907791960572e-06, "epoch": 2.38863976083707, "percentage": 47.77, "elapsed_time": "0:30:56", "remaining_time": "0:33:49", "throughput": 7050.84, "total_tokens": 13090816} {"current_steps": 1599, "total_steps": 3345, "loss": 0.4578, "lr": 1.336219625149056e-06, "epoch": 2.390134529147982, "percentage": 47.8, "elapsed_time": "0:30:57", "remaining_time": "0:33:48", "throughput": 7050.85, "total_tokens": 13099008} {"current_steps": 1600, "total_steps": 3345, "loss": 0.4667, "lr": 1.3350483950495366e-06, "epoch": 2.391629297458894, "percentage": 47.83, "elapsed_time": "0:30:58", "remaining_time": "0:33:47", "throughput": 7050.86, "total_tokens": 13107200} {"current_steps": 1601, "total_steps": 3345, "loss": 0.617, "lr": 1.333877089930616e-06, "epoch": 2.393124065769806, "percentage": 47.86, "elapsed_time": "0:31:00", "remaining_time": "0:33:46", "throughput": 7050.88, "total_tokens": 13115392} {"current_steps": 1602, "total_steps": 3345, "loss": 0.388, "lr": 1.3327057108254784e-06, "epoch": 2.3946188340807173, "percentage": 47.89, "elapsed_time": "0:31:01", "remaining_time": "0:33:45", "throughput": 7050.9, "total_tokens": 13123584} {"current_steps": 1603, "total_steps": 3345, "loss": 0.4649, "lr": 1.3315342587673725e-06, "epoch": 2.396113602391629, "percentage": 47.92, "elapsed_time": "0:31:02", "remaining_time": "0:33:43", "throughput": 7050.9, "total_tokens": 13131776} {"current_steps": 1604, "total_steps": 3345, "loss": 0.5235, "lr": 1.3303627347896112e-06, "epoch": 2.397608370702541, "percentage": 47.95, "elapsed_time": "0:31:03", "remaining_time": "0:33:42", "throughput": 7050.91, "total_tokens": 13139968} {"current_steps": 1605, "total_steps": 3345, "loss": 0.3369, "lr": 1.3291911399255714e-06, "epoch": 2.399103139013453, "percentage": 47.98, "elapsed_time": "0:31:04", "remaining_time": "0:33:41", "throughput": 7050.93, "total_tokens": 13148160} {"current_steps": 1606, "total_steps": 3345, "loss": 0.6528, "lr": 1.3280194752086922e-06, "epoch": 2.400597907324365, "percentage": 48.01, "elapsed_time": "0:31:05", "remaining_time": "0:33:40", "throughput": 7050.95, "total_tokens": 13156352} {"current_steps": 1607, "total_steps": 3345, "loss": 0.6708, "lr": 1.3268477416724745e-06, "epoch": 2.4020926756352763, "percentage": 48.04, "elapsed_time": "0:31:07", "remaining_time": "0:33:39", "throughput": 7050.97, "total_tokens": 13164544} {"current_steps": 1608, "total_steps": 3345, "loss": 0.6022, "lr": 1.3256759403504798e-06, "epoch": 2.403587443946188, "percentage": 48.07, "elapsed_time": "0:31:08", "remaining_time": "0:33:38", "throughput": 7050.97, "total_tokens": 13172736} {"current_steps": 1609, "total_steps": 3345, "loss": 0.6582, "lr": 1.3245040722763292e-06, "epoch": 2.4050822122571, "percentage": 48.1, "elapsed_time": "0:31:09", "remaining_time": "0:33:36", "throughput": 7050.98, "total_tokens": 13180928} {"current_steps": 1610, "total_steps": 3345, "loss": 0.364, "lr": 1.3233321384837033e-06, "epoch": 2.406576980568012, "percentage": 48.13, "elapsed_time": "0:31:10", "remaining_time": "0:33:35", "throughput": 7050.99, "total_tokens": 13189120} {"current_steps": 1611, "total_steps": 3345, "loss": 0.485, "lr": 1.3221601400063399e-06, "epoch": 2.408071748878924, "percentage": 48.16, "elapsed_time": "0:31:11", "remaining_time": "0:33:34", "throughput": 7050.98, "total_tokens": 13197312} {"current_steps": 1612, "total_steps": 3345, "loss": 0.3422, "lr": 1.3209880778780345e-06, "epoch": 2.4095665171898357, "percentage": 48.19, "elapsed_time": "0:31:12", "remaining_time": "0:33:33", "throughput": 7050.98, "total_tokens": 13205504} {"current_steps": 1613, "total_steps": 3345, "loss": 0.775, "lr": 1.3198159531326386e-06, "epoch": 2.4110612855007476, "percentage": 48.22, "elapsed_time": "0:31:14", "remaining_time": "0:33:32", "throughput": 7050.98, "total_tokens": 13213696} {"current_steps": 1614, "total_steps": 3345, "loss": 0.7247, "lr": 1.318643766804058e-06, "epoch": 2.412556053811659, "percentage": 48.25, "elapsed_time": "0:31:15", "remaining_time": "0:33:31", "throughput": 7050.99, "total_tokens": 13221888} {"current_steps": 1615, "total_steps": 3345, "loss": 0.3833, "lr": 1.3174715199262545e-06, "epoch": 2.414050822122571, "percentage": 48.28, "elapsed_time": "0:31:16", "remaining_time": "0:33:29", "throughput": 7051.01, "total_tokens": 13230080} {"current_steps": 1616, "total_steps": 3345, "loss": 0.4888, "lr": 1.3162992135332413e-06, "epoch": 2.415545590433483, "percentage": 48.31, "elapsed_time": "0:31:17", "remaining_time": "0:33:28", "throughput": 7051.04, "total_tokens": 13238272} {"current_steps": 1617, "total_steps": 3345, "loss": 0.2102, "lr": 1.3151268486590868e-06, "epoch": 2.4170403587443947, "percentage": 48.34, "elapsed_time": "0:31:18", "remaining_time": "0:33:27", "throughput": 7051.05, "total_tokens": 13246464} {"current_steps": 1618, "total_steps": 3345, "loss": 0.3057, "lr": 1.3139544263379078e-06, "epoch": 2.4185351270553066, "percentage": 48.37, "elapsed_time": "0:31:19", "remaining_time": "0:33:26", "throughput": 7051.07, "total_tokens": 13254656} {"current_steps": 1619, "total_steps": 3345, "loss": 0.4922, "lr": 1.3127819476038748e-06, "epoch": 2.420029895366218, "percentage": 48.4, "elapsed_time": "0:31:20", "remaining_time": "0:33:25", "throughput": 7051.08, "total_tokens": 13262848} {"current_steps": 1620, "total_steps": 3345, "loss": 0.6819, "lr": 1.3116094134912054e-06, "epoch": 2.42152466367713, "percentage": 48.43, "elapsed_time": "0:31:22", "remaining_time": "0:33:24", "throughput": 7051.09, "total_tokens": 13271040} {"current_steps": 1621, "total_steps": 3345, "loss": 0.3527, "lr": 1.3104368250341685e-06, "epoch": 2.423019431988042, "percentage": 48.46, "elapsed_time": "0:31:23", "remaining_time": "0:33:22", "throughput": 7051.05, "total_tokens": 13279232} {"current_steps": 1622, "total_steps": 3345, "loss": 0.5329, "lr": 1.3092641832670785e-06, "epoch": 2.4245142002989537, "percentage": 48.49, "elapsed_time": "0:31:24", "remaining_time": "0:33:21", "throughput": 7051.04, "total_tokens": 13287424} {"current_steps": 1623, "total_steps": 3345, "loss": 0.4517, "lr": 1.3080914892242992e-06, "epoch": 2.4260089686098656, "percentage": 48.52, "elapsed_time": "0:31:25", "remaining_time": "0:33:20", "throughput": 7051.07, "total_tokens": 13295616} {"current_steps": 1624, "total_steps": 3345, "loss": 0.3593, "lr": 1.3069187439402378e-06, "epoch": 2.4275037369207775, "percentage": 48.55, "elapsed_time": "0:31:26", "remaining_time": "0:33:19", "throughput": 7051.08, "total_tokens": 13303808} {"current_steps": 1625, "total_steps": 3345, "loss": 0.4311, "lr": 1.30574594844935e-06, "epoch": 2.428998505231689, "percentage": 48.58, "elapsed_time": "0:31:27", "remaining_time": "0:33:18", "throughput": 7051.09, "total_tokens": 13312000} {"current_steps": 1626, "total_steps": 3345, "loss": 0.506, "lr": 1.3045731037861329e-06, "epoch": 2.430493273542601, "percentage": 48.61, "elapsed_time": "0:31:29", "remaining_time": "0:33:17", "throughput": 7051.1, "total_tokens": 13320192} {"current_steps": 1627, "total_steps": 3345, "loss": 0.3215, "lr": 1.3034002109851288e-06, "epoch": 2.4319880418535127, "percentage": 48.64, "elapsed_time": "0:31:30", "remaining_time": "0:33:15", "throughput": 7051.11, "total_tokens": 13328384} {"current_steps": 1628, "total_steps": 3345, "loss": 0.3872, "lr": 1.3022272710809214e-06, "epoch": 2.4334828101644246, "percentage": 48.67, "elapsed_time": "0:31:31", "remaining_time": "0:33:14", "throughput": 7051.12, "total_tokens": 13336576} {"current_steps": 1629, "total_steps": 3345, "loss": 0.6627, "lr": 1.3010542851081362e-06, "epoch": 2.4349775784753365, "percentage": 48.7, "elapsed_time": "0:31:32", "remaining_time": "0:33:13", "throughput": 7051.12, "total_tokens": 13344768} {"current_steps": 1630, "total_steps": 3345, "loss": 0.4777, "lr": 1.29988125410144e-06, "epoch": 2.436472346786248, "percentage": 48.73, "elapsed_time": "0:31:33", "remaining_time": "0:33:12", "throughput": 7051.13, "total_tokens": 13352960} {"current_steps": 1631, "total_steps": 3345, "loss": 0.4169, "lr": 1.298708179095538e-06, "epoch": 2.43796711509716, "percentage": 48.76, "elapsed_time": "0:31:34", "remaining_time": "0:33:11", "throughput": 7051.14, "total_tokens": 13361152} {"current_steps": 1632, "total_steps": 3345, "loss": 0.2999, "lr": 1.2975350611251755e-06, "epoch": 2.4394618834080717, "percentage": 48.79, "elapsed_time": "0:31:36", "remaining_time": "0:33:10", "throughput": 7051.14, "total_tokens": 13369344} {"current_steps": 1633, "total_steps": 3345, "loss": 0.3915, "lr": 1.2963619012251352e-06, "epoch": 2.4409566517189836, "percentage": 48.82, "elapsed_time": "0:31:37", "remaining_time": "0:33:08", "throughput": 7051.15, "total_tokens": 13377536} {"current_steps": 1634, "total_steps": 3345, "loss": 0.549, "lr": 1.2951887004302368e-06, "epoch": 2.4424514200298955, "percentage": 48.85, "elapsed_time": "0:31:38", "remaining_time": "0:33:07", "throughput": 7051.16, "total_tokens": 13385728} {"current_steps": 1635, "total_steps": 3345, "loss": 0.554, "lr": 1.2940154597753357e-06, "epoch": 2.4439461883408073, "percentage": 48.88, "elapsed_time": "0:31:39", "remaining_time": "0:33:06", "throughput": 7051.17, "total_tokens": 13393920} {"current_steps": 1636, "total_steps": 3345, "loss": 0.564, "lr": 1.2928421802953234e-06, "epoch": 2.4454409566517192, "percentage": 48.91, "elapsed_time": "0:31:40", "remaining_time": "0:33:05", "throughput": 7051.19, "total_tokens": 13402112} {"current_steps": 1637, "total_steps": 3345, "loss": 0.3337, "lr": 1.2916688630251248e-06, "epoch": 2.4469357249626307, "percentage": 48.94, "elapsed_time": "0:31:41", "remaining_time": "0:33:04", "throughput": 7051.22, "total_tokens": 13410304} {"current_steps": 1638, "total_steps": 3345, "loss": 0.5705, "lr": 1.2904955089996981e-06, "epoch": 2.4484304932735426, "percentage": 48.97, "elapsed_time": "0:31:43", "remaining_time": "0:33:03", "throughput": 7051.22, "total_tokens": 13418496} {"current_steps": 1639, "total_steps": 3345, "loss": 0.4199, "lr": 1.2893221192540345e-06, "epoch": 2.4499252615844545, "percentage": 49.0, "elapsed_time": "0:31:44", "remaining_time": "0:33:02", "throughput": 7051.23, "total_tokens": 13426688} {"current_steps": 1640, "total_steps": 3345, "loss": 0.4596, "lr": 1.2881486948231562e-06, "epoch": 2.4514200298953663, "percentage": 49.03, "elapsed_time": "0:31:45", "remaining_time": "0:33:00", "throughput": 7051.24, "total_tokens": 13434880} {"current_steps": 1641, "total_steps": 3345, "loss": 0.4473, "lr": 1.2869752367421166e-06, "epoch": 2.452914798206278, "percentage": 49.06, "elapsed_time": "0:31:46", "remaining_time": "0:32:59", "throughput": 7051.26, "total_tokens": 13443072} {"current_steps": 1642, "total_steps": 3345, "loss": 0.6116, "lr": 1.285801746045998e-06, "epoch": 2.4544095665171897, "percentage": 49.09, "elapsed_time": "0:31:47", "remaining_time": "0:32:58", "throughput": 7051.27, "total_tokens": 13451264} {"current_steps": 1643, "total_steps": 3345, "loss": 0.4106, "lr": 1.2846282237699118e-06, "epoch": 2.4559043348281016, "percentage": 49.12, "elapsed_time": "0:31:48", "remaining_time": "0:32:57", "throughput": 7051.27, "total_tokens": 13459456} {"current_steps": 1644, "total_steps": 3345, "loss": 0.6421, "lr": 1.283454670948998e-06, "epoch": 2.4573991031390134, "percentage": 49.15, "elapsed_time": "0:31:49", "remaining_time": "0:32:56", "throughput": 7051.28, "total_tokens": 13467648} {"current_steps": 1645, "total_steps": 3345, "loss": 0.3206, "lr": 1.282281088618422e-06, "epoch": 2.4588938714499253, "percentage": 49.18, "elapsed_time": "0:31:51", "remaining_time": "0:32:55", "throughput": 7051.29, "total_tokens": 13475840} {"current_steps": 1646, "total_steps": 3345, "loss": 0.3737, "lr": 1.281107477813377e-06, "epoch": 2.460388639760837, "percentage": 49.21, "elapsed_time": "0:31:52", "remaining_time": "0:32:53", "throughput": 7051.31, "total_tokens": 13484032} {"current_steps": 1647, "total_steps": 3345, "loss": 0.5516, "lr": 1.2799338395690798e-06, "epoch": 2.461883408071749, "percentage": 49.24, "elapsed_time": "0:31:53", "remaining_time": "0:32:52", "throughput": 7051.31, "total_tokens": 13492224} {"current_steps": 1648, "total_steps": 3345, "loss": 0.3057, "lr": 1.2787601749207717e-06, "epoch": 2.4633781763826605, "percentage": 49.27, "elapsed_time": "0:31:54", "remaining_time": "0:32:51", "throughput": 7051.33, "total_tokens": 13500416} {"current_steps": 1649, "total_steps": 3345, "loss": 0.6033, "lr": 1.2775864849037185e-06, "epoch": 2.4648729446935724, "percentage": 49.3, "elapsed_time": "0:31:55", "remaining_time": "0:32:50", "throughput": 7051.33, "total_tokens": 13508608} {"current_steps": 1650, "total_steps": 3345, "loss": 0.7612, "lr": 1.276412770553207e-06, "epoch": 2.4663677130044843, "percentage": 49.33, "elapsed_time": "0:31:56", "remaining_time": "0:32:49", "throughput": 7051.35, "total_tokens": 13516800} {"current_steps": 1651, "total_steps": 3345, "loss": 0.3037, "lr": 1.2752390329045459e-06, "epoch": 2.467862481315396, "percentage": 49.36, "elapsed_time": "0:31:58", "remaining_time": "0:32:48", "throughput": 7051.36, "total_tokens": 13524992} {"current_steps": 1652, "total_steps": 3345, "loss": 0.6295, "lr": 1.2740652729930644e-06, "epoch": 2.469357249626308, "percentage": 49.39, "elapsed_time": "0:31:59", "remaining_time": "0:32:46", "throughput": 7051.37, "total_tokens": 13533184} {"current_steps": 1653, "total_steps": 3345, "loss": 0.5361, "lr": 1.2728914918541119e-06, "epoch": 2.4708520179372195, "percentage": 49.42, "elapsed_time": "0:32:00", "remaining_time": "0:32:45", "throughput": 7051.39, "total_tokens": 13541376} {"current_steps": 1654, "total_steps": 3345, "loss": 0.5128, "lr": 1.2717176905230558e-06, "epoch": 2.4723467862481314, "percentage": 49.45, "elapsed_time": "0:32:01", "remaining_time": "0:32:44", "throughput": 7051.39, "total_tokens": 13549568} {"current_steps": 1655, "total_steps": 3345, "loss": 0.4527, "lr": 1.2705438700352815e-06, "epoch": 2.4738415545590433, "percentage": 49.48, "elapsed_time": "0:32:02", "remaining_time": "0:32:43", "throughput": 7051.39, "total_tokens": 13557760} {"current_steps": 1656, "total_steps": 3345, "loss": 0.5691, "lr": 1.2693700314261915e-06, "epoch": 2.475336322869955, "percentage": 49.51, "elapsed_time": "0:32:03", "remaining_time": "0:32:42", "throughput": 7051.41, "total_tokens": 13565952} {"current_steps": 1657, "total_steps": 3345, "loss": 0.4901, "lr": 1.2681961757312037e-06, "epoch": 2.476831091180867, "percentage": 49.54, "elapsed_time": "0:32:05", "remaining_time": "0:32:41", "throughput": 7051.43, "total_tokens": 13574144} {"current_steps": 1658, "total_steps": 3345, "loss": 0.603, "lr": 1.2670223039857524e-06, "epoch": 2.478325859491779, "percentage": 49.57, "elapsed_time": "0:32:06", "remaining_time": "0:32:39", "throughput": 7051.45, "total_tokens": 13582336} {"current_steps": 1659, "total_steps": 3345, "loss": 0.5201, "lr": 1.2658484172252845e-06, "epoch": 2.4798206278026904, "percentage": 49.6, "elapsed_time": "0:32:07", "remaining_time": "0:32:38", "throughput": 7051.47, "total_tokens": 13590528} {"current_steps": 1660, "total_steps": 3345, "loss": 0.4974, "lr": 1.2646745164852608e-06, "epoch": 2.4813153961136023, "percentage": 49.63, "elapsed_time": "0:32:08", "remaining_time": "0:32:37", "throughput": 7051.5, "total_tokens": 13598720} {"current_steps": 1661, "total_steps": 3345, "loss": 0.3033, "lr": 1.2635006028011548e-06, "epoch": 2.482810164424514, "percentage": 49.66, "elapsed_time": "0:32:09", "remaining_time": "0:32:36", "throughput": 7051.51, "total_tokens": 13606912} {"current_steps": 1662, "total_steps": 3345, "loss": 0.2703, "lr": 1.262326677208451e-06, "epoch": 2.484304932735426, "percentage": 49.69, "elapsed_time": "0:32:10", "remaining_time": "0:32:35", "throughput": 7051.52, "total_tokens": 13615104} {"current_steps": 1663, "total_steps": 3345, "loss": 0.4472, "lr": 1.2611527407426446e-06, "epoch": 2.485799701046338, "percentage": 49.72, "elapsed_time": "0:32:11", "remaining_time": "0:32:34", "throughput": 7051.54, "total_tokens": 13623296} {"current_steps": 1664, "total_steps": 3345, "loss": 0.2975, "lr": 1.25997879443924e-06, "epoch": 2.4872944693572494, "percentage": 49.75, "elapsed_time": "0:32:13", "remaining_time": "0:32:32", "throughput": 7051.55, "total_tokens": 13631488} {"current_steps": 1665, "total_steps": 3345, "loss": 0.3839, "lr": 1.2588048393337505e-06, "epoch": 2.4887892376681613, "percentage": 49.78, "elapsed_time": "0:32:14", "remaining_time": "0:32:31", "throughput": 7051.56, "total_tokens": 13639680} {"current_steps": 1666, "total_steps": 3345, "loss": 0.4064, "lr": 1.2576308764616976e-06, "epoch": 2.490284005979073, "percentage": 49.81, "elapsed_time": "0:32:15", "remaining_time": "0:32:30", "throughput": 7051.57, "total_tokens": 13647872} {"current_steps": 1667, "total_steps": 3345, "loss": 0.4377, "lr": 1.2564569068586088e-06, "epoch": 2.491778774289985, "percentage": 49.84, "elapsed_time": "0:32:16", "remaining_time": "0:32:29", "throughput": 7051.58, "total_tokens": 13656064} {"current_steps": 1668, "total_steps": 3345, "loss": 0.3999, "lr": 1.2552829315600185e-06, "epoch": 2.493273542600897, "percentage": 49.87, "elapsed_time": "0:32:17", "remaining_time": "0:32:28", "throughput": 7051.59, "total_tokens": 13664256} {"current_steps": 1669, "total_steps": 3345, "loss": 0.6034, "lr": 1.2541089516014651e-06, "epoch": 2.494768310911809, "percentage": 49.9, "elapsed_time": "0:32:18", "remaining_time": "0:32:27", "throughput": 7051.6, "total_tokens": 13672448} {"current_steps": 1670, "total_steps": 3345, "loss": 0.7471, "lr": 1.2529349680184921e-06, "epoch": 2.4962630792227207, "percentage": 49.93, "elapsed_time": "0:32:20", "remaining_time": "0:32:25", "throughput": 7051.61, "total_tokens": 13680640} {"current_steps": 1671, "total_steps": 3345, "loss": 0.7503, "lr": 1.2517609818466453e-06, "epoch": 2.497757847533632, "percentage": 49.96, "elapsed_time": "0:32:21", "remaining_time": "0:32:24", "throughput": 7051.61, "total_tokens": 13688832} {"current_steps": 1672, "total_steps": 3345, "loss": 0.5734, "lr": 1.2505869941214738e-06, "epoch": 2.499252615844544, "percentage": 49.99, "elapsed_time": "0:32:22", "remaining_time": "0:32:23", "throughput": 7051.61, "total_tokens": 13697024} {"current_steps": 1673, "total_steps": 3345, "loss": 0.5854, "lr": 1.2494130058785266e-06, "epoch": 2.500747384155456, "percentage": 50.01, "elapsed_time": "0:32:23", "remaining_time": "0:32:22", "throughput": 7051.62, "total_tokens": 13705216} {"current_steps": 1674, "total_steps": 3345, "loss": 0.5577, "lr": 1.2482390181533547e-06, "epoch": 2.502242152466368, "percentage": 50.04, "elapsed_time": "0:32:24", "remaining_time": "0:32:21", "throughput": 7051.63, "total_tokens": 13713408} {"current_steps": 1675, "total_steps": 3345, "loss": 0.5533, "lr": 1.247065031981508e-06, "epoch": 2.5037369207772793, "percentage": 50.07, "elapsed_time": "0:32:25", "remaining_time": "0:32:20", "throughput": 7051.64, "total_tokens": 13721600} {"current_steps": 1676, "total_steps": 3345, "loss": 0.7842, "lr": 1.245891048398535e-06, "epoch": 2.505231689088191, "percentage": 50.1, "elapsed_time": "0:32:27", "remaining_time": "0:32:18", "throughput": 7051.64, "total_tokens": 13729792} {"current_steps": 1677, "total_steps": 3345, "loss": 0.447, "lr": 1.2447170684399817e-06, "epoch": 2.506726457399103, "percentage": 50.13, "elapsed_time": "0:32:28", "remaining_time": "0:32:17", "throughput": 7051.65, "total_tokens": 13737984} {"current_steps": 1678, "total_steps": 3345, "loss": 0.5944, "lr": 1.2435430931413914e-06, "epoch": 2.508221225710015, "percentage": 50.16, "elapsed_time": "0:32:29", "remaining_time": "0:32:16", "throughput": 7051.65, "total_tokens": 13746176} {"current_steps": 1679, "total_steps": 3345, "loss": 0.4755, "lr": 1.2423691235383029e-06, "epoch": 2.509715994020927, "percentage": 50.19, "elapsed_time": "0:32:30", "remaining_time": "0:32:15", "throughput": 7051.64, "total_tokens": 13754368} {"current_steps": 1680, "total_steps": 3345, "loss": 0.483, "lr": 1.2411951606662497e-06, "epoch": 2.5112107623318387, "percentage": 50.22, "elapsed_time": "0:32:31", "remaining_time": "0:32:14", "throughput": 7051.64, "total_tokens": 13762560} {"current_steps": 1681, "total_steps": 3345, "loss": 0.5902, "lr": 1.2400212055607603e-06, "epoch": 2.5127055306427506, "percentage": 50.25, "elapsed_time": "0:32:32", "remaining_time": "0:32:13", "throughput": 7051.65, "total_tokens": 13770752} {"current_steps": 1682, "total_steps": 3345, "loss": 0.5199, "lr": 1.2388472592573556e-06, "epoch": 2.514200298953662, "percentage": 50.28, "elapsed_time": "0:32:34", "remaining_time": "0:32:11", "throughput": 7051.66, "total_tokens": 13778944} {"current_steps": 1683, "total_steps": 3345, "loss": 0.4744, "lr": 1.2376733227915493e-06, "epoch": 2.515695067264574, "percentage": 50.31, "elapsed_time": "0:32:35", "remaining_time": "0:32:10", "throughput": 7051.67, "total_tokens": 13787136} {"current_steps": 1684, "total_steps": 3345, "loss": 0.4759, "lr": 1.2364993971988456e-06, "epoch": 2.517189835575486, "percentage": 50.34, "elapsed_time": "0:32:36", "remaining_time": "0:32:09", "throughput": 7051.68, "total_tokens": 13795328} {"current_steps": 1685, "total_steps": 3345, "loss": 0.6579, "lr": 1.2353254835147397e-06, "epoch": 2.5186846038863977, "percentage": 50.37, "elapsed_time": "0:32:37", "remaining_time": "0:32:08", "throughput": 7051.71, "total_tokens": 13803520} {"current_steps": 1686, "total_steps": 3345, "loss": 0.4084, "lr": 1.2341515827747161e-06, "epoch": 2.520179372197309, "percentage": 50.4, "elapsed_time": "0:32:38", "remaining_time": "0:32:07", "throughput": 7051.72, "total_tokens": 13811712} {"current_steps": 1687, "total_steps": 3345, "loss": 0.5807, "lr": 1.2329776960142484e-06, "epoch": 2.521674140508221, "percentage": 50.43, "elapsed_time": "0:32:39", "remaining_time": "0:32:06", "throughput": 7051.73, "total_tokens": 13819904} {"current_steps": 1688, "total_steps": 3345, "loss": 0.5237, "lr": 1.2318038242687965e-06, "epoch": 2.523168908819133, "percentage": 50.46, "elapsed_time": "0:32:40", "remaining_time": "0:32:04", "throughput": 7051.74, "total_tokens": 13828096} {"current_steps": 1689, "total_steps": 3345, "loss": 0.5159, "lr": 1.2306299685738091e-06, "epoch": 2.524663677130045, "percentage": 50.49, "elapsed_time": "0:32:42", "remaining_time": "0:32:03", "throughput": 7051.74, "total_tokens": 13836288} {"current_steps": 1690, "total_steps": 3345, "loss": 0.447, "lr": 1.229456129964719e-06, "epoch": 2.5261584454409567, "percentage": 50.52, "elapsed_time": "0:32:43", "remaining_time": "0:32:02", "throughput": 7051.74, "total_tokens": 13844480} {"current_steps": 1691, "total_steps": 3345, "loss": 0.7081, "lr": 1.2282823094769444e-06, "epoch": 2.5276532137518686, "percentage": 50.55, "elapsed_time": "0:32:44", "remaining_time": "0:32:01", "throughput": 7051.74, "total_tokens": 13852672} {"current_steps": 1692, "total_steps": 3345, "loss": 0.9069, "lr": 1.2271085081458881e-06, "epoch": 2.5291479820627805, "percentage": 50.58, "elapsed_time": "0:32:45", "remaining_time": "0:32:00", "throughput": 7051.74, "total_tokens": 13860864} {"current_steps": 1693, "total_steps": 3345, "loss": 0.2933, "lr": 1.2259347270069356e-06, "epoch": 2.5306427503736924, "percentage": 50.61, "elapsed_time": "0:32:46", "remaining_time": "0:31:59", "throughput": 7051.75, "total_tokens": 13869056} {"current_steps": 1694, "total_steps": 3345, "loss": 0.5679, "lr": 1.2247609670954546e-06, "epoch": 2.532137518684604, "percentage": 50.64, "elapsed_time": "0:32:47", "remaining_time": "0:31:57", "throughput": 7051.76, "total_tokens": 13877248} {"current_steps": 1695, "total_steps": 3345, "loss": 0.4303, "lr": 1.2235872294467935e-06, "epoch": 2.5336322869955157, "percentage": 50.67, "elapsed_time": "0:32:49", "remaining_time": "0:31:56", "throughput": 7051.76, "total_tokens": 13885440} {"current_steps": 1696, "total_steps": 3345, "loss": 0.5604, "lr": 1.222413515096282e-06, "epoch": 2.5351270553064276, "percentage": 50.7, "elapsed_time": "0:32:50", "remaining_time": "0:31:55", "throughput": 7051.77, "total_tokens": 13893632} {"current_steps": 1697, "total_steps": 3345, "loss": 0.3534, "lr": 1.2212398250792287e-06, "epoch": 2.5366218236173395, "percentage": 50.73, "elapsed_time": "0:32:51", "remaining_time": "0:31:54", "throughput": 7051.78, "total_tokens": 13901824} {"current_steps": 1698, "total_steps": 3345, "loss": 0.6273, "lr": 1.2200661604309206e-06, "epoch": 2.538116591928251, "percentage": 50.76, "elapsed_time": "0:32:52", "remaining_time": "0:31:53", "throughput": 7051.78, "total_tokens": 13910016} {"current_steps": 1699, "total_steps": 3345, "loss": 0.368, "lr": 1.2188925221866235e-06, "epoch": 2.539611360239163, "percentage": 50.79, "elapsed_time": "0:32:53", "remaining_time": "0:31:52", "throughput": 7051.8, "total_tokens": 13918208} {"current_steps": 1700, "total_steps": 3345, "loss": 0.204, "lr": 1.2177189113815783e-06, "epoch": 2.5411061285500747, "percentage": 50.82, "elapsed_time": "0:32:54", "remaining_time": "0:31:50", "throughput": 7051.81, "total_tokens": 13926400} {"current_steps": 1701, "total_steps": 3345, "loss": 0.5327, "lr": 1.2165453290510027e-06, "epoch": 2.5426008968609866, "percentage": 50.85, "elapsed_time": "0:32:56", "remaining_time": "0:31:49", "throughput": 7051.82, "total_tokens": 13934592} {"current_steps": 1702, "total_steps": 3345, "loss": 0.7207, "lr": 1.2153717762300886e-06, "epoch": 2.5440956651718984, "percentage": 50.88, "elapsed_time": "0:32:57", "remaining_time": "0:31:48", "throughput": 7051.81, "total_tokens": 13942784} {"current_steps": 1703, "total_steps": 3345, "loss": 0.4535, "lr": 1.2141982539540027e-06, "epoch": 2.5455904334828103, "percentage": 50.91, "elapsed_time": "0:32:58", "remaining_time": "0:31:47", "throughput": 7051.82, "total_tokens": 13950976} {"current_steps": 1704, "total_steps": 3345, "loss": 0.5751, "lr": 1.213024763257884e-06, "epoch": 2.547085201793722, "percentage": 50.94, "elapsed_time": "0:32:59", "remaining_time": "0:31:46", "throughput": 7051.83, "total_tokens": 13959168} {"current_steps": 1705, "total_steps": 3345, "loss": 0.4619, "lr": 1.2118513051768444e-06, "epoch": 2.5485799701046337, "percentage": 50.97, "elapsed_time": "0:33:00", "remaining_time": "0:31:45", "throughput": 7051.83, "total_tokens": 13967360} {"current_steps": 1706, "total_steps": 3345, "loss": 0.6155, "lr": 1.2106778807459662e-06, "epoch": 2.5500747384155455, "percentage": 51.0, "elapsed_time": "0:33:01", "remaining_time": "0:31:43", "throughput": 7051.84, "total_tokens": 13975552} {"current_steps": 1707, "total_steps": 3345, "loss": 0.5928, "lr": 1.209504491000302e-06, "epoch": 2.5515695067264574, "percentage": 51.03, "elapsed_time": "0:33:02", "remaining_time": "0:31:42", "throughput": 7051.83, "total_tokens": 13983744} {"current_steps": 1708, "total_steps": 3345, "loss": 0.3749, "lr": 1.2083311369748754e-06, "epoch": 2.5530642750373693, "percentage": 51.06, "elapsed_time": "0:33:04", "remaining_time": "0:31:41", "throughput": 7051.81, "total_tokens": 13991936} {"current_steps": 1709, "total_steps": 3345, "loss": 0.6231, "lr": 1.2071578197046766e-06, "epoch": 2.5545590433482808, "percentage": 51.09, "elapsed_time": "0:33:05", "remaining_time": "0:31:40", "throughput": 7051.79, "total_tokens": 14000128} {"current_steps": 1710, "total_steps": 3345, "loss": 0.4078, "lr": 1.2059845402246643e-06, "epoch": 2.5560538116591927, "percentage": 51.12, "elapsed_time": "0:33:06", "remaining_time": "0:31:39", "throughput": 7051.8, "total_tokens": 14008320} {"current_steps": 1711, "total_steps": 3345, "loss": 0.4821, "lr": 1.2048112995697634e-06, "epoch": 2.5575485799701045, "percentage": 51.15, "elapsed_time": "0:33:07", "remaining_time": "0:31:38", "throughput": 7051.79, "total_tokens": 14016512} {"current_steps": 1712, "total_steps": 3345, "loss": 0.7928, "lr": 1.203638098774865e-06, "epoch": 2.5590433482810164, "percentage": 51.18, "elapsed_time": "0:33:08", "remaining_time": "0:31:37", "throughput": 7051.78, "total_tokens": 14024704} {"current_steps": 1713, "total_steps": 3345, "loss": 0.3459, "lr": 1.2024649388748247e-06, "epoch": 2.5605381165919283, "percentage": 51.21, "elapsed_time": "0:33:09", "remaining_time": "0:31:35", "throughput": 7051.78, "total_tokens": 14032896} {"current_steps": 1714, "total_steps": 3345, "loss": 0.5952, "lr": 1.2012918209044622e-06, "epoch": 2.56203288490284, "percentage": 51.24, "elapsed_time": "0:33:11", "remaining_time": "0:31:34", "throughput": 7051.78, "total_tokens": 14041088} {"current_steps": 1715, "total_steps": 3345, "loss": 0.3422, "lr": 1.2001187458985606e-06, "epoch": 2.563527653213752, "percentage": 51.27, "elapsed_time": "0:33:12", "remaining_time": "0:31:33", "throughput": 7051.78, "total_tokens": 14049280} {"current_steps": 1716, "total_steps": 3345, "loss": 0.5181, "lr": 1.1989457148918642e-06, "epoch": 2.5650224215246635, "percentage": 51.3, "elapsed_time": "0:33:13", "remaining_time": "0:31:32", "throughput": 7051.79, "total_tokens": 14057472} {"current_steps": 1717, "total_steps": 3345, "loss": 0.4561, "lr": 1.197772728919079e-06, "epoch": 2.5665171898355754, "percentage": 51.33, "elapsed_time": "0:33:14", "remaining_time": "0:31:31", "throughput": 7051.76, "total_tokens": 14065664} {"current_steps": 1718, "total_steps": 3345, "loss": 0.677, "lr": 1.1965997890148717e-06, "epoch": 2.5680119581464873, "percentage": 51.36, "elapsed_time": "0:33:15", "remaining_time": "0:31:30", "throughput": 7051.77, "total_tokens": 14073856} {"current_steps": 1719, "total_steps": 3345, "loss": 0.4268, "lr": 1.1954268962138675e-06, "epoch": 2.569506726457399, "percentage": 51.39, "elapsed_time": "0:33:16", "remaining_time": "0:31:28", "throughput": 7051.79, "total_tokens": 14082048} {"current_steps": 1720, "total_steps": 3345, "loss": 0.5566, "lr": 1.1942540515506506e-06, "epoch": 2.5710014947683106, "percentage": 51.42, "elapsed_time": "0:33:18", "remaining_time": "0:31:27", "throughput": 7051.8, "total_tokens": 14090240} {"current_steps": 1721, "total_steps": 3345, "loss": 0.4705, "lr": 1.1930812560597625e-06, "epoch": 2.5724962630792225, "percentage": 51.45, "elapsed_time": "0:33:19", "remaining_time": "0:31:26", "throughput": 7051.82, "total_tokens": 14098432} {"current_steps": 1722, "total_steps": 3345, "loss": 0.3402, "lr": 1.1919085107757017e-06, "epoch": 2.5739910313901344, "percentage": 51.48, "elapsed_time": "0:33:20", "remaining_time": "0:31:25", "throughput": 7051.83, "total_tokens": 14106624} {"current_steps": 1723, "total_steps": 3345, "loss": 0.366, "lr": 1.1907358167329221e-06, "epoch": 2.5754857997010463, "percentage": 51.51, "elapsed_time": "0:33:21", "remaining_time": "0:31:24", "throughput": 7051.84, "total_tokens": 14114816} {"current_steps": 1724, "total_steps": 3345, "loss": 0.7959, "lr": 1.1895631749658317e-06, "epoch": 2.576980568011958, "percentage": 51.54, "elapsed_time": "0:33:22", "remaining_time": "0:31:23", "throughput": 7051.84, "total_tokens": 14123008} {"current_steps": 1725, "total_steps": 3345, "loss": 0.3954, "lr": 1.1883905865087946e-06, "epoch": 2.57847533632287, "percentage": 51.57, "elapsed_time": "0:33:23", "remaining_time": "0:31:21", "throughput": 7051.85, "total_tokens": 14131200} {"current_steps": 1726, "total_steps": 3345, "loss": 0.6914, "lr": 1.1872180523961254e-06, "epoch": 2.579970104633782, "percentage": 51.6, "elapsed_time": "0:33:25", "remaining_time": "0:31:20", "throughput": 7051.87, "total_tokens": 14139392} {"current_steps": 1727, "total_steps": 3345, "loss": 0.5271, "lr": 1.1860455736620922e-06, "epoch": 2.581464872944694, "percentage": 51.63, "elapsed_time": "0:33:26", "remaining_time": "0:31:19", "throughput": 7051.88, "total_tokens": 14147584} {"current_steps": 1728, "total_steps": 3345, "loss": 0.4457, "lr": 1.1848731513409136e-06, "epoch": 2.5829596412556053, "percentage": 51.66, "elapsed_time": "0:33:27", "remaining_time": "0:31:18", "throughput": 7051.89, "total_tokens": 14155776} {"current_steps": 1729, "total_steps": 3345, "loss": 0.3153, "lr": 1.1837007864667589e-06, "epoch": 2.584454409566517, "percentage": 51.69, "elapsed_time": "0:33:28", "remaining_time": "0:31:17", "throughput": 7051.9, "total_tokens": 14163968} {"current_steps": 1730, "total_steps": 3345, "loss": 0.4864, "lr": 1.182528480073746e-06, "epoch": 2.585949177877429, "percentage": 51.72, "elapsed_time": "0:33:29", "remaining_time": "0:31:16", "throughput": 7051.9, "total_tokens": 14172160} {"current_steps": 1731, "total_steps": 3345, "loss": 0.5456, "lr": 1.1813562331959422e-06, "epoch": 2.587443946188341, "percentage": 51.75, "elapsed_time": "0:33:30", "remaining_time": "0:31:14", "throughput": 7051.88, "total_tokens": 14180352} {"current_steps": 1732, "total_steps": 3345, "loss": 0.3237, "lr": 1.1801840468673618e-06, "epoch": 2.5889387144992524, "percentage": 51.78, "elapsed_time": "0:33:32", "remaining_time": "0:31:13", "throughput": 7051.88, "total_tokens": 14188544} {"current_steps": 1733, "total_steps": 3345, "loss": 0.3984, "lr": 1.1790119221219657e-06, "epoch": 2.5904334828101643, "percentage": 51.81, "elapsed_time": "0:33:33", "remaining_time": "0:31:12", "throughput": 7051.86, "total_tokens": 14196736} {"current_steps": 1734, "total_steps": 3345, "loss": 0.5162, "lr": 1.1778398599936603e-06, "epoch": 2.591928251121076, "percentage": 51.84, "elapsed_time": "0:33:34", "remaining_time": "0:31:11", "throughput": 7051.87, "total_tokens": 14204928} {"current_steps": 1735, "total_steps": 3345, "loss": 0.3911, "lr": 1.176667861516297e-06, "epoch": 2.593423019431988, "percentage": 51.87, "elapsed_time": "0:33:35", "remaining_time": "0:31:10", "throughput": 7051.88, "total_tokens": 14213120} {"current_steps": 1736, "total_steps": 3345, "loss": 0.3891, "lr": 1.1754959277236712e-06, "epoch": 2.5949177877429, "percentage": 51.9, "elapsed_time": "0:33:36", "remaining_time": "0:31:09", "throughput": 7051.89, "total_tokens": 14221312} {"current_steps": 1737, "total_steps": 3345, "loss": 0.6112, "lr": 1.1743240596495206e-06, "epoch": 2.596412556053812, "percentage": 51.93, "elapsed_time": "0:33:37", "remaining_time": "0:31:07", "throughput": 7051.91, "total_tokens": 14229504} {"current_steps": 1738, "total_steps": 3345, "loss": 0.6135, "lr": 1.173152258327526e-06, "epoch": 2.5979073243647237, "percentage": 51.96, "elapsed_time": "0:33:38", "remaining_time": "0:31:06", "throughput": 7051.92, "total_tokens": 14237696} {"current_steps": 1739, "total_steps": 3345, "loss": 0.3443, "lr": 1.1719805247913082e-06, "epoch": 2.599402092675635, "percentage": 51.99, "elapsed_time": "0:33:40", "remaining_time": "0:31:05", "throughput": 7051.93, "total_tokens": 14245888} {"current_steps": 1740, "total_steps": 3345, "loss": 0.7098, "lr": 1.1708088600744292e-06, "epoch": 2.600896860986547, "percentage": 52.02, "elapsed_time": "0:33:41", "remaining_time": "0:31:04", "throughput": 7051.93, "total_tokens": 14254080} {"current_steps": 1741, "total_steps": 3345, "loss": 0.5239, "lr": 1.169637265210389e-06, "epoch": 2.602391629297459, "percentage": 52.05, "elapsed_time": "0:33:42", "remaining_time": "0:31:03", "throughput": 7051.94, "total_tokens": 14262272} {"current_steps": 1742, "total_steps": 3345, "loss": 0.6056, "lr": 1.1684657412326277e-06, "epoch": 2.603886397608371, "percentage": 52.08, "elapsed_time": "0:33:43", "remaining_time": "0:31:02", "throughput": 7051.94, "total_tokens": 14270464} {"current_steps": 1743, "total_steps": 3345, "loss": 0.4332, "lr": 1.1672942891745216e-06, "epoch": 2.6053811659192823, "percentage": 52.11, "elapsed_time": "0:33:44", "remaining_time": "0:31:00", "throughput": 7051.93, "total_tokens": 14278656} {"current_steps": 1744, "total_steps": 3345, "loss": 0.4495, "lr": 1.166122910069384e-06, "epoch": 2.606875934230194, "percentage": 52.14, "elapsed_time": "0:33:45", "remaining_time": "0:30:59", "throughput": 7051.93, "total_tokens": 14286848} {"current_steps": 1745, "total_steps": 3345, "loss": 0.462, "lr": 1.1649516049504638e-06, "epoch": 2.608370702541106, "percentage": 52.17, "elapsed_time": "0:33:47", "remaining_time": "0:30:58", "throughput": 7051.93, "total_tokens": 14295040} {"current_steps": 1746, "total_steps": 3345, "loss": 0.3218, "lr": 1.1637803748509443e-06, "epoch": 2.609865470852018, "percentage": 52.2, "elapsed_time": "0:33:48", "remaining_time": "0:30:57", "throughput": 7051.94, "total_tokens": 14303232} {"current_steps": 1747, "total_steps": 3345, "loss": 0.3511, "lr": 1.1626092208039432e-06, "epoch": 2.61136023916293, "percentage": 52.23, "elapsed_time": "0:33:49", "remaining_time": "0:30:56", "throughput": 7051.95, "total_tokens": 14311424} {"current_steps": 1748, "total_steps": 3345, "loss": 0.5153, "lr": 1.1614381438425108e-06, "epoch": 2.6128550074738417, "percentage": 52.26, "elapsed_time": "0:33:50", "remaining_time": "0:30:55", "throughput": 7051.96, "total_tokens": 14319616} {"current_steps": 1749, "total_steps": 3345, "loss": 0.4277, "lr": 1.1602671449996297e-06, "epoch": 2.6143497757847536, "percentage": 52.29, "elapsed_time": "0:33:51", "remaining_time": "0:30:54", "throughput": 7051.98, "total_tokens": 14327808} {"current_steps": 1750, "total_steps": 3345, "loss": 0.3854, "lr": 1.159096225308213e-06, "epoch": 2.615844544095665, "percentage": 52.32, "elapsed_time": "0:33:52", "remaining_time": "0:30:52", "throughput": 7051.99, "total_tokens": 14336000} {"current_steps": 1751, "total_steps": 3345, "loss": 0.5511, "lr": 1.1579253858011045e-06, "epoch": 2.617339312406577, "percentage": 52.35, "elapsed_time": "0:33:54", "remaining_time": "0:30:51", "throughput": 7052.0, "total_tokens": 14344192} {"current_steps": 1752, "total_steps": 3345, "loss": 0.6546, "lr": 1.1567546275110772e-06, "epoch": 2.618834080717489, "percentage": 52.38, "elapsed_time": "0:33:55", "remaining_time": "0:30:50", "throughput": 7052.0, "total_tokens": 14352384} {"current_steps": 1753, "total_steps": 3345, "loss": 0.5943, "lr": 1.155583951470832e-06, "epoch": 2.6203288490284007, "percentage": 52.41, "elapsed_time": "0:33:56", "remaining_time": "0:30:49", "throughput": 7051.99, "total_tokens": 14360576} {"current_steps": 1754, "total_steps": 3345, "loss": 0.6086, "lr": 1.154413358712998e-06, "epoch": 2.621823617339312, "percentage": 52.44, "elapsed_time": "0:33:57", "remaining_time": "0:30:48", "throughput": 7052.0, "total_tokens": 14368768} {"current_steps": 1755, "total_steps": 3345, "loss": 0.6681, "lr": 1.1532428502701303e-06, "epoch": 2.623318385650224, "percentage": 52.47, "elapsed_time": "0:33:58", "remaining_time": "0:30:47", "throughput": 7051.98, "total_tokens": 14376960} {"current_steps": 1756, "total_steps": 3345, "loss": 0.5361, "lr": 1.1520724271747098e-06, "epoch": 2.624813153961136, "percentage": 52.5, "elapsed_time": "0:33:59", "remaining_time": "0:30:45", "throughput": 7051.92, "total_tokens": 14385152} {"current_steps": 1757, "total_steps": 3345, "loss": 0.7406, "lr": 1.1509020904591423e-06, "epoch": 2.626307922272048, "percentage": 52.53, "elapsed_time": "0:34:01", "remaining_time": "0:30:44", "throughput": 7051.87, "total_tokens": 14393344} {"current_steps": 1758, "total_steps": 3345, "loss": 0.4374, "lr": 1.1497318411557564e-06, "epoch": 2.6278026905829597, "percentage": 52.56, "elapsed_time": "0:34:02", "remaining_time": "0:30:43", "throughput": 7051.87, "total_tokens": 14401536} {"current_steps": 1759, "total_steps": 3345, "loss": 0.409, "lr": 1.1485616802968054e-06, "epoch": 2.6292974588938716, "percentage": 52.59, "elapsed_time": "0:34:03", "remaining_time": "0:30:42", "throughput": 7051.87, "total_tokens": 14409728} {"current_steps": 1760, "total_steps": 3345, "loss": 0.4373, "lr": 1.1473916089144634e-06, "epoch": 2.6307922272047835, "percentage": 52.62, "elapsed_time": "0:34:04", "remaining_time": "0:30:41", "throughput": 7051.84, "total_tokens": 14417920} {"current_steps": 1761, "total_steps": 3345, "loss": 0.5959, "lr": 1.1462216280408257e-06, "epoch": 2.6322869955156953, "percentage": 52.65, "elapsed_time": "0:34:05", "remaining_time": "0:30:40", "throughput": 7051.83, "total_tokens": 14426112} {"current_steps": 1762, "total_steps": 3345, "loss": 0.5643, "lr": 1.1450517387079077e-06, "epoch": 2.633781763826607, "percentage": 52.68, "elapsed_time": "0:34:06", "remaining_time": "0:30:38", "throughput": 7051.83, "total_tokens": 14434304} {"current_steps": 1763, "total_steps": 3345, "loss": 0.6091, "lr": 1.1438819419476437e-06, "epoch": 2.6352765321375187, "percentage": 52.71, "elapsed_time": "0:34:08", "remaining_time": "0:30:37", "throughput": 7051.82, "total_tokens": 14442496} {"current_steps": 1764, "total_steps": 3345, "loss": 0.5032, "lr": 1.1427122387918877e-06, "epoch": 2.6367713004484306, "percentage": 52.74, "elapsed_time": "0:34:09", "remaining_time": "0:30:36", "throughput": 7051.82, "total_tokens": 14450688} {"current_steps": 1765, "total_steps": 3345, "loss": 0.6145, "lr": 1.1415426302724099e-06, "epoch": 2.6382660687593424, "percentage": 52.77, "elapsed_time": "0:34:10", "remaining_time": "0:30:35", "throughput": 7051.8, "total_tokens": 14458880} {"current_steps": 1766, "total_steps": 3345, "loss": 0.48, "lr": 1.1403731174208974e-06, "epoch": 2.639760837070254, "percentage": 52.8, "elapsed_time": "0:34:11", "remaining_time": "0:30:34", "throughput": 7051.78, "total_tokens": 14467072} {"current_steps": 1767, "total_steps": 3345, "loss": 0.45, "lr": 1.1392037012689527e-06, "epoch": 2.6412556053811658, "percentage": 52.83, "elapsed_time": "0:34:12", "remaining_time": "0:30:33", "throughput": 7051.76, "total_tokens": 14475264} {"current_steps": 1768, "total_steps": 3345, "loss": 0.5518, "lr": 1.1380343828480934e-06, "epoch": 2.6427503736920777, "percentage": 52.86, "elapsed_time": "0:34:13", "remaining_time": "0:30:31", "throughput": 7051.76, "total_tokens": 14483456} {"current_steps": 1769, "total_steps": 3345, "loss": 0.5193, "lr": 1.1368651631897506e-06, "epoch": 2.6442451420029895, "percentage": 52.88, "elapsed_time": "0:34:15", "remaining_time": "0:30:30", "throughput": 7051.77, "total_tokens": 14491648} {"current_steps": 1770, "total_steps": 3345, "loss": 0.7034, "lr": 1.1356960433252682e-06, "epoch": 2.6457399103139014, "percentage": 52.91, "elapsed_time": "0:34:16", "remaining_time": "0:30:29", "throughput": 7051.78, "total_tokens": 14499840} {"current_steps": 1771, "total_steps": 3345, "loss": 0.4477, "lr": 1.1345270242859027e-06, "epoch": 2.6472346786248133, "percentage": 52.94, "elapsed_time": "0:34:17", "remaining_time": "0:30:28", "throughput": 7051.79, "total_tokens": 14508032} {"current_steps": 1772, "total_steps": 3345, "loss": 0.5842, "lr": 1.1333581071028211e-06, "epoch": 2.648729446935725, "percentage": 52.97, "elapsed_time": "0:34:18", "remaining_time": "0:30:27", "throughput": 7051.81, "total_tokens": 14516224} {"current_steps": 1773, "total_steps": 3345, "loss": 0.5861, "lr": 1.1321892928071003e-06, "epoch": 2.6502242152466366, "percentage": 53.0, "elapsed_time": "0:34:19", "remaining_time": "0:30:26", "throughput": 7051.81, "total_tokens": 14524416} {"current_steps": 1774, "total_steps": 3345, "loss": 0.5181, "lr": 1.131020582429727e-06, "epoch": 2.6517189835575485, "percentage": 53.03, "elapsed_time": "0:34:20", "remaining_time": "0:30:25", "throughput": 7051.82, "total_tokens": 14532608} {"current_steps": 1775, "total_steps": 3345, "loss": 0.5296, "lr": 1.129851977001596e-06, "epoch": 2.6532137518684604, "percentage": 53.06, "elapsed_time": "0:34:21", "remaining_time": "0:30:23", "throughput": 7051.81, "total_tokens": 14540800} {"current_steps": 1776, "total_steps": 3345, "loss": 0.381, "lr": 1.12868347755351e-06, "epoch": 2.6547085201793723, "percentage": 53.09, "elapsed_time": "0:34:23", "remaining_time": "0:30:22", "throughput": 7051.84, "total_tokens": 14548992} {"current_steps": 1777, "total_steps": 3345, "loss": 0.5983, "lr": 1.1275150851161773e-06, "epoch": 2.6562032884902838, "percentage": 53.12, "elapsed_time": "0:34:24", "remaining_time": "0:30:21", "throughput": 7051.83, "total_tokens": 14557184} {"current_steps": 1778, "total_steps": 3345, "loss": 0.5105, "lr": 1.1263468007202127e-06, "epoch": 2.6576980568011956, "percentage": 53.15, "elapsed_time": "0:34:25", "remaining_time": "0:30:20", "throughput": 7051.85, "total_tokens": 14565376} {"current_steps": 1779, "total_steps": 3345, "loss": 0.3402, "lr": 1.1251786253961348e-06, "epoch": 2.6591928251121075, "percentage": 53.18, "elapsed_time": "0:34:26", "remaining_time": "0:30:19", "throughput": 7051.86, "total_tokens": 14573568} {"current_steps": 1780, "total_steps": 3345, "loss": 0.5372, "lr": 1.1240105601743667e-06, "epoch": 2.6606875934230194, "percentage": 53.21, "elapsed_time": "0:34:27", "remaining_time": "0:30:18", "throughput": 7051.86, "total_tokens": 14581760} {"current_steps": 1781, "total_steps": 3345, "loss": 0.5107, "lr": 1.1228426060852344e-06, "epoch": 2.6621823617339313, "percentage": 53.24, "elapsed_time": "0:34:28", "remaining_time": "0:30:16", "throughput": 7051.87, "total_tokens": 14589952} {"current_steps": 1782, "total_steps": 3345, "loss": 0.4108, "lr": 1.1216747641589656e-06, "epoch": 2.663677130044843, "percentage": 53.27, "elapsed_time": "0:34:30", "remaining_time": "0:30:15", "throughput": 7051.88, "total_tokens": 14598144} {"current_steps": 1783, "total_steps": 3345, "loss": 0.5732, "lr": 1.1205070354256888e-06, "epoch": 2.665171898355755, "percentage": 53.3, "elapsed_time": "0:34:31", "remaining_time": "0:30:14", "throughput": 7051.89, "total_tokens": 14606336} {"current_steps": 1784, "total_steps": 3345, "loss": 0.5399, "lr": 1.1193394209154335e-06, "epoch": 2.6666666666666665, "percentage": 53.33, "elapsed_time": "0:34:32", "remaining_time": "0:30:13", "throughput": 7051.9, "total_tokens": 14614528} {"current_steps": 1785, "total_steps": 3345, "loss": 0.2496, "lr": 1.118171921658127e-06, "epoch": 2.6681614349775784, "percentage": 53.36, "elapsed_time": "0:34:33", "remaining_time": "0:30:12", "throughput": 7051.91, "total_tokens": 14622720} {"current_steps": 1786, "total_steps": 3345, "loss": 0.5612, "lr": 1.1170045386835967e-06, "epoch": 2.6696562032884903, "percentage": 53.39, "elapsed_time": "0:34:34", "remaining_time": "0:30:11", "throughput": 7051.9, "total_tokens": 14630912} {"current_steps": 1787, "total_steps": 3345, "loss": 0.3256, "lr": 1.1158372730215663e-06, "epoch": 2.671150971599402, "percentage": 53.42, "elapsed_time": "0:34:35", "remaining_time": "0:30:09", "throughput": 7051.84, "total_tokens": 14639104} {"current_steps": 1788, "total_steps": 3345, "loss": 0.7304, "lr": 1.1146701257016563e-06, "epoch": 2.672645739910314, "percentage": 53.45, "elapsed_time": "0:34:37", "remaining_time": "0:30:08", "throughput": 7051.85, "total_tokens": 14647296} {"current_steps": 1789, "total_steps": 3345, "loss": 0.2706, "lr": 1.1135030977533826e-06, "epoch": 2.6741405082212255, "percentage": 53.48, "elapsed_time": "0:34:38", "remaining_time": "0:30:07", "throughput": 7051.86, "total_tokens": 14655488} {"current_steps": 1790, "total_steps": 3345, "loss": 0.3634, "lr": 1.1123361902061563e-06, "epoch": 2.6756352765321374, "percentage": 53.51, "elapsed_time": "0:34:39", "remaining_time": "0:30:06", "throughput": 7051.87, "total_tokens": 14663680} {"current_steps": 1791, "total_steps": 3345, "loss": 0.3861, "lr": 1.111169404089282e-06, "epoch": 2.6771300448430493, "percentage": 53.54, "elapsed_time": "0:34:40", "remaining_time": "0:30:05", "throughput": 7051.88, "total_tokens": 14671872} {"current_steps": 1792, "total_steps": 3345, "loss": 0.7578, "lr": 1.1100027404319563e-06, "epoch": 2.678624813153961, "percentage": 53.57, "elapsed_time": "0:34:41", "remaining_time": "0:30:04", "throughput": 7051.89, "total_tokens": 14680064} {"current_steps": 1793, "total_steps": 3345, "loss": 0.4594, "lr": 1.1088362002632702e-06, "epoch": 2.680119581464873, "percentage": 53.6, "elapsed_time": "0:34:42", "remaining_time": "0:30:02", "throughput": 7051.92, "total_tokens": 14688256} {"current_steps": 1794, "total_steps": 3345, "loss": 0.3421, "lr": 1.1076697846122035e-06, "epoch": 2.681614349775785, "percentage": 53.63, "elapsed_time": "0:34:44", "remaining_time": "0:30:01", "throughput": 7051.88, "total_tokens": 14696448} {"current_steps": 1795, "total_steps": 3345, "loss": 0.503, "lr": 1.106503494507627e-06, "epoch": 2.683109118086697, "percentage": 53.66, "elapsed_time": "0:34:45", "remaining_time": "0:30:00", "throughput": 7051.87, "total_tokens": 14704640} {"current_steps": 1796, "total_steps": 3345, "loss": 0.6323, "lr": 1.1053373309783003e-06, "epoch": 2.6846038863976083, "percentage": 53.69, "elapsed_time": "0:34:46", "remaining_time": "0:29:59", "throughput": 7051.85, "total_tokens": 14712832} {"current_steps": 1797, "total_steps": 3345, "loss": 0.4181, "lr": 1.1041712950528723e-06, "epoch": 2.68609865470852, "percentage": 53.72, "elapsed_time": "0:34:47", "remaining_time": "0:29:58", "throughput": 7051.83, "total_tokens": 14721024} {"current_steps": 1798, "total_steps": 3345, "loss": 0.4399, "lr": 1.1030053877598786e-06, "epoch": 2.687593423019432, "percentage": 53.75, "elapsed_time": "0:34:48", "remaining_time": "0:29:57", "throughput": 7051.8, "total_tokens": 14729216} {"current_steps": 1799, "total_steps": 3345, "loss": 0.4401, "lr": 1.1018396101277413e-06, "epoch": 2.689088191330344, "percentage": 53.78, "elapsed_time": "0:34:49", "remaining_time": "0:29:55", "throughput": 7051.8, "total_tokens": 14737408} {"current_steps": 1800, "total_steps": 3345, "loss": 0.3834, "lr": 1.1006739631847686e-06, "epoch": 2.6905829596412554, "percentage": 53.81, "elapsed_time": "0:34:51", "remaining_time": "0:29:54", "throughput": 7051.8, "total_tokens": 14745600} {"current_steps": 1801, "total_steps": 3345, "loss": 0.4734, "lr": 1.0995084479591529e-06, "epoch": 2.6920777279521673, "percentage": 53.84, "elapsed_time": "0:34:52", "remaining_time": "0:29:53", "throughput": 7051.79, "total_tokens": 14753792} {"current_steps": 1802, "total_steps": 3345, "loss": 0.6464, "lr": 1.0983430654789708e-06, "epoch": 2.693572496263079, "percentage": 53.87, "elapsed_time": "0:34:53", "remaining_time": "0:29:52", "throughput": 7051.79, "total_tokens": 14761984} {"current_steps": 1803, "total_steps": 3345, "loss": 0.5254, "lr": 1.0971778167721818e-06, "epoch": 2.695067264573991, "percentage": 53.9, "elapsed_time": "0:34:54", "remaining_time": "0:29:51", "throughput": 7051.77, "total_tokens": 14770176} {"current_steps": 1804, "total_steps": 3345, "loss": 0.6582, "lr": 1.0960127028666268e-06, "epoch": 2.696562032884903, "percentage": 53.93, "elapsed_time": "0:34:55", "remaining_time": "0:29:50", "throughput": 7051.78, "total_tokens": 14778368} {"current_steps": 1805, "total_steps": 3345, "loss": 0.4804, "lr": 1.094847724790029e-06, "epoch": 2.698056801195815, "percentage": 53.96, "elapsed_time": "0:34:56", "remaining_time": "0:29:49", "throughput": 7051.79, "total_tokens": 14786560} {"current_steps": 1806, "total_steps": 3345, "loss": 0.5142, "lr": 1.0936828835699908e-06, "epoch": 2.6995515695067267, "percentage": 53.99, "elapsed_time": "0:34:58", "remaining_time": "0:29:47", "throughput": 7051.79, "total_tokens": 14794752} {"current_steps": 1807, "total_steps": 3345, "loss": 0.4007, "lr": 1.092518180233994e-06, "epoch": 2.701046337817638, "percentage": 54.02, "elapsed_time": "0:34:59", "remaining_time": "0:29:46", "throughput": 7051.8, "total_tokens": 14802944} {"current_steps": 1808, "total_steps": 3345, "loss": 0.6593, "lr": 1.0913536158093987e-06, "epoch": 2.70254110612855, "percentage": 54.05, "elapsed_time": "0:35:00", "remaining_time": "0:29:45", "throughput": 7051.81, "total_tokens": 14811136} {"current_steps": 1809, "total_steps": 3345, "loss": 0.5138, "lr": 1.0901891913234425e-06, "epoch": 2.704035874439462, "percentage": 54.08, "elapsed_time": "0:35:01", "remaining_time": "0:29:44", "throughput": 7051.81, "total_tokens": 14819328} {"current_steps": 1810, "total_steps": 3345, "loss": 0.5268, "lr": 1.089024907803241e-06, "epoch": 2.705530642750374, "percentage": 54.11, "elapsed_time": "0:35:02", "remaining_time": "0:29:43", "throughput": 7051.82, "total_tokens": 14827520} {"current_steps": 1811, "total_steps": 3345, "loss": 0.5426, "lr": 1.0878607662757833e-06, "epoch": 2.7070254110612852, "percentage": 54.14, "elapsed_time": "0:35:03", "remaining_time": "0:29:42", "throughput": 7051.82, "total_tokens": 14835712} {"current_steps": 1812, "total_steps": 3345, "loss": 0.5036, "lr": 1.086696767767934e-06, "epoch": 2.708520179372197, "percentage": 54.17, "elapsed_time": "0:35:04", "remaining_time": "0:29:40", "throughput": 7051.82, "total_tokens": 14843904} {"current_steps": 1813, "total_steps": 3345, "loss": 0.3868, "lr": 1.0855329133064323e-06, "epoch": 2.710014947683109, "percentage": 54.2, "elapsed_time": "0:35:06", "remaining_time": "0:29:39", "throughput": 7051.82, "total_tokens": 14852096} {"current_steps": 1814, "total_steps": 3345, "loss": 0.5259, "lr": 1.0843692039178893e-06, "epoch": 2.711509715994021, "percentage": 54.23, "elapsed_time": "0:35:07", "remaining_time": "0:29:38", "throughput": 7051.82, "total_tokens": 14860288} {"current_steps": 1815, "total_steps": 3345, "loss": 0.4825, "lr": 1.083205640628789e-06, "epoch": 2.713004484304933, "percentage": 54.26, "elapsed_time": "0:35:08", "remaining_time": "0:29:37", "throughput": 7051.81, "total_tokens": 14868480} {"current_steps": 1816, "total_steps": 3345, "loss": 0.4234, "lr": 1.0820422244654855e-06, "epoch": 2.7144992526158447, "percentage": 54.29, "elapsed_time": "0:35:09", "remaining_time": "0:29:36", "throughput": 7051.81, "total_tokens": 14876672} {"current_steps": 1817, "total_steps": 3345, "loss": 0.5596, "lr": 1.0808789564542045e-06, "epoch": 2.7159940209267566, "percentage": 54.32, "elapsed_time": "0:35:10", "remaining_time": "0:29:35", "throughput": 7051.8, "total_tokens": 14884864} {"current_steps": 1818, "total_steps": 3345, "loss": 0.326, "lr": 1.0797158376210394e-06, "epoch": 2.717488789237668, "percentage": 54.35, "elapsed_time": "0:35:11", "remaining_time": "0:29:33", "throughput": 7051.81, "total_tokens": 14893056} {"current_steps": 1819, "total_steps": 3345, "loss": 0.6336, "lr": 1.0785528689919531e-06, "epoch": 2.71898355754858, "percentage": 54.38, "elapsed_time": "0:35:13", "remaining_time": "0:29:32", "throughput": 7051.83, "total_tokens": 14901248} {"current_steps": 1820, "total_steps": 3345, "loss": 0.8351, "lr": 1.0773900515927766e-06, "epoch": 2.720478325859492, "percentage": 54.41, "elapsed_time": "0:35:14", "remaining_time": "0:29:31", "throughput": 7051.85, "total_tokens": 14909440} {"current_steps": 1821, "total_steps": 3345, "loss": 0.4288, "lr": 1.0762273864492057e-06, "epoch": 2.7219730941704037, "percentage": 54.44, "elapsed_time": "0:35:15", "remaining_time": "0:29:30", "throughput": 7051.86, "total_tokens": 14917632} {"current_steps": 1822, "total_steps": 3345, "loss": 0.4082, "lr": 1.0750648745868032e-06, "epoch": 2.7234678624813156, "percentage": 54.47, "elapsed_time": "0:35:16", "remaining_time": "0:29:29", "throughput": 7051.89, "total_tokens": 14925824} {"current_steps": 1823, "total_steps": 3345, "loss": 0.4913, "lr": 1.0739025170309965e-06, "epoch": 2.724962630792227, "percentage": 54.5, "elapsed_time": "0:35:17", "remaining_time": "0:29:28", "throughput": 7051.9, "total_tokens": 14934016} {"current_steps": 1824, "total_steps": 3345, "loss": 0.4387, "lr": 1.0727403148070767e-06, "epoch": 2.726457399103139, "percentage": 54.53, "elapsed_time": "0:35:18", "remaining_time": "0:29:26", "throughput": 7051.9, "total_tokens": 14942208} {"current_steps": 1825, "total_steps": 3345, "loss": 0.4291, "lr": 1.0715782689401977e-06, "epoch": 2.7279521674140508, "percentage": 54.56, "elapsed_time": "0:35:20", "remaining_time": "0:29:25", "throughput": 7051.91, "total_tokens": 14950400} {"current_steps": 1826, "total_steps": 3345, "loss": 0.3528, "lr": 1.0704163804553756e-06, "epoch": 2.7294469357249627, "percentage": 54.59, "elapsed_time": "0:35:21", "remaining_time": "0:29:24", "throughput": 7051.92, "total_tokens": 14958592} {"current_steps": 1827, "total_steps": 3345, "loss": 0.5286, "lr": 1.0692546503774884e-06, "epoch": 2.7309417040358746, "percentage": 54.62, "elapsed_time": "0:35:22", "remaining_time": "0:29:23", "throughput": 7051.95, "total_tokens": 14966784} {"current_steps": 1828, "total_steps": 3345, "loss": 0.3742, "lr": 1.0680930797312736e-06, "epoch": 2.7324364723467864, "percentage": 54.65, "elapsed_time": "0:35:23", "remaining_time": "0:29:22", "throughput": 7051.97, "total_tokens": 14974976} {"current_steps": 1829, "total_steps": 3345, "loss": 0.5412, "lr": 1.0669316695413279e-06, "epoch": 2.7339312406576983, "percentage": 54.68, "elapsed_time": "0:35:24", "remaining_time": "0:29:21", "throughput": 7051.98, "total_tokens": 14983168} {"current_steps": 1830, "total_steps": 3345, "loss": 0.5843, "lr": 1.0657704208321073e-06, "epoch": 2.7354260089686098, "percentage": 54.71, "elapsed_time": "0:35:25", "remaining_time": "0:29:19", "throughput": 7052.0, "total_tokens": 14991360} {"current_steps": 1831, "total_steps": 3345, "loss": 0.4617, "lr": 1.0646093346279245e-06, "epoch": 2.7369207772795217, "percentage": 54.74, "elapsed_time": "0:35:26", "remaining_time": "0:29:18", "throughput": 7052.01, "total_tokens": 14999552} {"current_steps": 1832, "total_steps": 3345, "loss": 0.6138, "lr": 1.0634484119529494e-06, "epoch": 2.7384155455904335, "percentage": 54.77, "elapsed_time": "0:35:28", "remaining_time": "0:29:17", "throughput": 7052.02, "total_tokens": 15007744} {"current_steps": 1833, "total_steps": 3345, "loss": 0.5167, "lr": 1.0622876538312074e-06, "epoch": 2.7399103139013454, "percentage": 54.8, "elapsed_time": "0:35:29", "remaining_time": "0:29:16", "throughput": 7052.03, "total_tokens": 15015936} {"current_steps": 1834, "total_steps": 3345, "loss": 0.5619, "lr": 1.0611270612865789e-06, "epoch": 2.741405082212257, "percentage": 54.83, "elapsed_time": "0:35:30", "remaining_time": "0:29:15", "throughput": 7052.04, "total_tokens": 15024128} {"current_steps": 1835, "total_steps": 3345, "loss": 0.8988, "lr": 1.059966635342798e-06, "epoch": 2.7428998505231688, "percentage": 54.86, "elapsed_time": "0:35:31", "remaining_time": "0:29:14", "throughput": 7052.05, "total_tokens": 15032320} {"current_steps": 1836, "total_steps": 3345, "loss": 0.6464, "lr": 1.0588063770234519e-06, "epoch": 2.7443946188340806, "percentage": 54.89, "elapsed_time": "0:35:32", "remaining_time": "0:29:12", "throughput": 7052.04, "total_tokens": 15040512} {"current_steps": 1837, "total_steps": 3345, "loss": 0.4379, "lr": 1.0576462873519807e-06, "epoch": 2.7458893871449925, "percentage": 54.92, "elapsed_time": "0:35:33", "remaining_time": "0:29:11", "throughput": 7052.06, "total_tokens": 15048704} {"current_steps": 1838, "total_steps": 3345, "loss": 0.5834, "lr": 1.0564863673516745e-06, "epoch": 2.7473841554559044, "percentage": 54.95, "elapsed_time": "0:35:35", "remaining_time": "0:29:10", "throughput": 7052.07, "total_tokens": 15056896} {"current_steps": 1839, "total_steps": 3345, "loss": 0.6651, "lr": 1.0553266180456749e-06, "epoch": 2.7488789237668163, "percentage": 54.98, "elapsed_time": "0:35:36", "remaining_time": "0:29:09", "throughput": 7052.08, "total_tokens": 15065088} {"current_steps": 1840, "total_steps": 3345, "loss": 0.579, "lr": 1.0541670404569718e-06, "epoch": 2.750373692077728, "percentage": 55.01, "elapsed_time": "0:35:37", "remaining_time": "0:29:08", "throughput": 7052.1, "total_tokens": 15073280} {"current_steps": 1841, "total_steps": 3345, "loss": 0.5228, "lr": 1.0530076356084043e-06, "epoch": 2.7518684603886396, "percentage": 55.04, "elapsed_time": "0:35:38", "remaining_time": "0:29:07", "throughput": 7052.11, "total_tokens": 15081472} {"current_steps": 1842, "total_steps": 3345, "loss": 0.3969, "lr": 1.0518484045226592e-06, "epoch": 2.7533632286995515, "percentage": 55.07, "elapsed_time": "0:35:39", "remaining_time": "0:29:05", "throughput": 7052.13, "total_tokens": 15089664} {"current_steps": 1843, "total_steps": 3345, "loss": 0.5391, "lr": 1.0506893482222696e-06, "epoch": 2.7548579970104634, "percentage": 55.1, "elapsed_time": "0:35:40", "remaining_time": "0:29:04", "throughput": 7052.14, "total_tokens": 15097856} {"current_steps": 1844, "total_steps": 3345, "loss": 0.7033, "lr": 1.0495304677296153e-06, "epoch": 2.7563527653213753, "percentage": 55.13, "elapsed_time": "0:35:42", "remaining_time": "0:29:03", "throughput": 7052.16, "total_tokens": 15106048} {"current_steps": 1845, "total_steps": 3345, "loss": 0.4525, "lr": 1.04837176406692e-06, "epoch": 2.7578475336322867, "percentage": 55.16, "elapsed_time": "0:35:43", "remaining_time": "0:29:02", "throughput": 7052.17, "total_tokens": 15114240} {"current_steps": 1846, "total_steps": 3345, "loss": 0.4153, "lr": 1.0472132382562519e-06, "epoch": 2.7593423019431986, "percentage": 55.19, "elapsed_time": "0:35:44", "remaining_time": "0:29:01", "throughput": 7052.19, "total_tokens": 15122432} {"current_steps": 1847, "total_steps": 3345, "loss": 0.5707, "lr": 1.0460548913195222e-06, "epoch": 2.7608370702541105, "percentage": 55.22, "elapsed_time": "0:35:45", "remaining_time": "0:29:00", "throughput": 7052.2, "total_tokens": 15130624} {"current_steps": 1848, "total_steps": 3345, "loss": 0.4189, "lr": 1.0448967242784844e-06, "epoch": 2.7623318385650224, "percentage": 55.25, "elapsed_time": "0:35:46", "remaining_time": "0:28:58", "throughput": 7052.21, "total_tokens": 15138816} {"current_steps": 1849, "total_steps": 3345, "loss": 0.6704, "lr": 1.0437387381547336e-06, "epoch": 2.7638266068759343, "percentage": 55.28, "elapsed_time": "0:35:47", "remaining_time": "0:28:57", "throughput": 7052.22, "total_tokens": 15147008} {"current_steps": 1850, "total_steps": 3345, "loss": 0.4378, "lr": 1.0425809339697044e-06, "epoch": 2.765321375186846, "percentage": 55.31, "elapsed_time": "0:35:48", "remaining_time": "0:28:56", "throughput": 7052.24, "total_tokens": 15155200} {"current_steps": 1851, "total_steps": 3345, "loss": 0.5037, "lr": 1.0414233127446722e-06, "epoch": 2.766816143497758, "percentage": 55.34, "elapsed_time": "0:35:50", "remaining_time": "0:28:55", "throughput": 7052.25, "total_tokens": 15163392} {"current_steps": 1852, "total_steps": 3345, "loss": 0.5926, "lr": 1.0402658755007494e-06, "epoch": 2.7683109118086695, "percentage": 55.37, "elapsed_time": "0:35:51", "remaining_time": "0:28:54", "throughput": 7052.27, "total_tokens": 15171584} {"current_steps": 1853, "total_steps": 3345, "loss": 0.5694, "lr": 1.039108623258888e-06, "epoch": 2.7698056801195814, "percentage": 55.4, "elapsed_time": "0:35:52", "remaining_time": "0:28:53", "throughput": 7052.28, "total_tokens": 15179776} {"current_steps": 1854, "total_steps": 3345, "loss": 0.6264, "lr": 1.0379515570398753e-06, "epoch": 2.7713004484304933, "percentage": 55.43, "elapsed_time": "0:35:53", "remaining_time": "0:28:51", "throughput": 7052.3, "total_tokens": 15187968} {"current_steps": 1855, "total_steps": 3345, "loss": 0.5504, "lr": 1.0367946778643357e-06, "epoch": 2.772795216741405, "percentage": 55.46, "elapsed_time": "0:35:54", "remaining_time": "0:28:50", "throughput": 7052.3, "total_tokens": 15196160} {"current_steps": 1856, "total_steps": 3345, "loss": 0.477, "lr": 1.0356379867527275e-06, "epoch": 2.774289985052317, "percentage": 55.49, "elapsed_time": "0:35:55", "remaining_time": "0:28:49", "throughput": 7052.32, "total_tokens": 15204352} {"current_steps": 1857, "total_steps": 3345, "loss": 0.5196, "lr": 1.0344814847253435e-06, "epoch": 2.7757847533632285, "percentage": 55.52, "elapsed_time": "0:35:57", "remaining_time": "0:28:48", "throughput": 7052.32, "total_tokens": 15212544} {"current_steps": 1858, "total_steps": 3345, "loss": 0.561, "lr": 1.0333251728023102e-06, "epoch": 2.7772795216741404, "percentage": 55.55, "elapsed_time": "0:35:58", "remaining_time": "0:28:47", "throughput": 7052.34, "total_tokens": 15220736} {"current_steps": 1859, "total_steps": 3345, "loss": 0.4757, "lr": 1.0321690520035855e-06, "epoch": 2.7787742899850523, "percentage": 55.58, "elapsed_time": "0:35:59", "remaining_time": "0:28:46", "throughput": 7052.35, "total_tokens": 15228928} {"current_steps": 1860, "total_steps": 3345, "loss": 0.3978, "lr": 1.0310131233489596e-06, "epoch": 2.780269058295964, "percentage": 55.61, "elapsed_time": "0:36:00", "remaining_time": "0:28:44", "throughput": 7052.36, "total_tokens": 15237120} {"current_steps": 1861, "total_steps": 3345, "loss": 0.571, "lr": 1.029857387858053e-06, "epoch": 2.781763826606876, "percentage": 55.64, "elapsed_time": "0:36:01", "remaining_time": "0:28:43", "throughput": 7052.37, "total_tokens": 15245312} {"current_steps": 1862, "total_steps": 3345, "loss": 0.4366, "lr": 1.0287018465503153e-06, "epoch": 2.783258594917788, "percentage": 55.67, "elapsed_time": "0:36:02", "remaining_time": "0:28:42", "throughput": 7052.38, "total_tokens": 15253504} {"current_steps": 1863, "total_steps": 3345, "loss": 0.5693, "lr": 1.0275465004450258e-06, "epoch": 2.7847533632287, "percentage": 55.7, "elapsed_time": "0:36:04", "remaining_time": "0:28:41", "throughput": 7052.4, "total_tokens": 15261696} {"current_steps": 1864, "total_steps": 3345, "loss": 0.6533, "lr": 1.0263913505612908e-06, "epoch": 2.7862481315396113, "percentage": 55.72, "elapsed_time": "0:36:05", "remaining_time": "0:28:40", "throughput": 7052.42, "total_tokens": 15269888} {"current_steps": 1865, "total_steps": 3345, "loss": 0.5673, "lr": 1.0252363979180433e-06, "epoch": 2.787742899850523, "percentage": 55.75, "elapsed_time": "0:36:06", "remaining_time": "0:28:39", "throughput": 7052.44, "total_tokens": 15278080} {"current_steps": 1866, "total_steps": 3345, "loss": 0.4117, "lr": 1.024081643534043e-06, "epoch": 2.789237668161435, "percentage": 55.78, "elapsed_time": "0:36:07", "remaining_time": "0:28:37", "throughput": 7052.45, "total_tokens": 15286272} {"current_steps": 1867, "total_steps": 3345, "loss": 0.3215, "lr": 1.0229270884278744e-06, "epoch": 2.790732436472347, "percentage": 55.81, "elapsed_time": "0:36:08", "remaining_time": "0:28:36", "throughput": 7052.48, "total_tokens": 15294464} {"current_steps": 1868, "total_steps": 3345, "loss": 0.7632, "lr": 1.021772733617946e-06, "epoch": 2.7922272047832584, "percentage": 55.84, "elapsed_time": "0:36:09", "remaining_time": "0:28:35", "throughput": 7052.48, "total_tokens": 15302656} {"current_steps": 1869, "total_steps": 3345, "loss": 0.58, "lr": 1.0206185801224908e-06, "epoch": 2.7937219730941703, "percentage": 55.87, "elapsed_time": "0:36:10", "remaining_time": "0:28:34", "throughput": 7052.47, "total_tokens": 15310848} {"current_steps": 1870, "total_steps": 3345, "loss": 0.3912, "lr": 1.0194646289595625e-06, "epoch": 2.795216741405082, "percentage": 55.9, "elapsed_time": "0:36:12", "remaining_time": "0:28:33", "throughput": 7052.48, "total_tokens": 15319040} {"current_steps": 1871, "total_steps": 3345, "loss": 0.3744, "lr": 1.0183108811470375e-06, "epoch": 2.796711509715994, "percentage": 55.93, "elapsed_time": "0:36:13", "remaining_time": "0:28:32", "throughput": 7052.5, "total_tokens": 15327232} {"current_steps": 1872, "total_steps": 3345, "loss": 0.423, "lr": 1.0171573377026125e-06, "epoch": 2.798206278026906, "percentage": 55.96, "elapsed_time": "0:36:14", "remaining_time": "0:28:30", "throughput": 7052.52, "total_tokens": 15335424} {"current_steps": 1873, "total_steps": 3345, "loss": 0.334, "lr": 1.0160039996438038e-06, "epoch": 2.799701046337818, "percentage": 55.99, "elapsed_time": "0:36:15", "remaining_time": "0:28:29", "throughput": 7052.53, "total_tokens": 15343616} {"current_steps": 1874, "total_steps": 3345, "loss": 0.6327, "lr": 1.0148508679879466e-06, "epoch": 2.8011958146487297, "percentage": 56.02, "elapsed_time": "0:36:16", "remaining_time": "0:28:28", "throughput": 7052.53, "total_tokens": 15351808} {"current_steps": 1875, "total_steps": 3345, "loss": 0.6715, "lr": 1.0136979437521938e-06, "epoch": 2.802690582959641, "percentage": 56.05, "elapsed_time": "0:36:17", "remaining_time": "0:28:27", "throughput": 7052.54, "total_tokens": 15360000} {"current_steps": 1876, "total_steps": 3345, "loss": 0.4465, "lr": 1.0125452279535163e-06, "epoch": 2.804185351270553, "percentage": 56.08, "elapsed_time": "0:36:19", "remaining_time": "0:28:26", "throughput": 7052.57, "total_tokens": 15368192} {"current_steps": 1877, "total_steps": 3345, "loss": 0.4662, "lr": 1.0113927216087e-06, "epoch": 2.805680119581465, "percentage": 56.11, "elapsed_time": "0:36:20", "remaining_time": "0:28:25", "throughput": 7052.59, "total_tokens": 15376384} {"current_steps": 1878, "total_steps": 3345, "loss": 0.7286, "lr": 1.0102404257343465e-06, "epoch": 2.807174887892377, "percentage": 56.14, "elapsed_time": "0:36:21", "remaining_time": "0:28:24", "throughput": 7052.61, "total_tokens": 15384576} {"current_steps": 1879, "total_steps": 3345, "loss": 0.675, "lr": 1.0090883413468722e-06, "epoch": 2.8086696562032882, "percentage": 56.17, "elapsed_time": "0:36:22", "remaining_time": "0:28:22", "throughput": 7052.63, "total_tokens": 15392768} {"current_steps": 1880, "total_steps": 3345, "loss": 0.8212, "lr": 1.0079364694625064e-06, "epoch": 2.8101644245142, "percentage": 56.2, "elapsed_time": "0:36:23", "remaining_time": "0:28:21", "throughput": 7052.65, "total_tokens": 15400960} {"current_steps": 1881, "total_steps": 3345, "loss": 0.4688, "lr": 1.0067848110972907e-06, "epoch": 2.811659192825112, "percentage": 56.23, "elapsed_time": "0:36:24", "remaining_time": "0:28:20", "throughput": 7052.66, "total_tokens": 15409152} {"current_steps": 1882, "total_steps": 3345, "loss": 0.7077, "lr": 1.0056333672670792e-06, "epoch": 2.813153961136024, "percentage": 56.26, "elapsed_time": "0:36:26", "remaining_time": "0:28:19", "throughput": 7052.67, "total_tokens": 15417344} {"current_steps": 1883, "total_steps": 3345, "loss": 0.3594, "lr": 1.0044821389875359e-06, "epoch": 2.814648729446936, "percentage": 56.29, "elapsed_time": "0:36:27", "remaining_time": "0:28:18", "throughput": 7052.66, "total_tokens": 15425536} {"current_steps": 1884, "total_steps": 3345, "loss": 0.5331, "lr": 1.003331127274135e-06, "epoch": 2.8161434977578477, "percentage": 56.32, "elapsed_time": "0:36:28", "remaining_time": "0:28:17", "throughput": 7052.67, "total_tokens": 15433728} {"current_steps": 1885, "total_steps": 3345, "loss": 0.5861, "lr": 1.0021803331421597e-06, "epoch": 2.8176382660687596, "percentage": 56.35, "elapsed_time": "0:36:29", "remaining_time": "0:28:15", "throughput": 7052.69, "total_tokens": 15441920} {"current_steps": 1886, "total_steps": 3345, "loss": 0.3662, "lr": 1.001029757606702e-06, "epoch": 2.819133034379671, "percentage": 56.38, "elapsed_time": "0:36:30", "remaining_time": "0:28:14", "throughput": 7052.7, "total_tokens": 15450112} {"current_steps": 1887, "total_steps": 3345, "loss": 0.6307, "lr": 9.998794016826597e-07, "epoch": 2.820627802690583, "percentage": 56.41, "elapsed_time": "0:36:31", "remaining_time": "0:28:13", "throughput": 7052.72, "total_tokens": 15458304} {"current_steps": 1888, "total_steps": 3345, "loss": 0.608, "lr": 9.98729266384738e-07, "epoch": 2.8221225710014948, "percentage": 56.44, "elapsed_time": "0:36:32", "remaining_time": "0:28:12", "throughput": 7052.74, "total_tokens": 15466496} {"current_steps": 1889, "total_steps": 3345, "loss": 0.5883, "lr": 9.975793527274466e-07, "epoch": 2.8236173393124067, "percentage": 56.47, "elapsed_time": "0:36:34", "remaining_time": "0:28:11", "throughput": 7052.74, "total_tokens": 15474688} {"current_steps": 1890, "total_steps": 3345, "loss": 0.4751, "lr": 9.964296617251005e-07, "epoch": 2.8251121076233185, "percentage": 56.5, "elapsed_time": "0:36:35", "remaining_time": "0:28:10", "throughput": 7052.75, "total_tokens": 15482880} {"current_steps": 1891, "total_steps": 3345, "loss": 0.7693, "lr": 9.952801943918175e-07, "epoch": 2.82660687593423, "percentage": 56.53, "elapsed_time": "0:36:36", "remaining_time": "0:28:08", "throughput": 7052.77, "total_tokens": 15491072} {"current_steps": 1892, "total_steps": 3345, "loss": 0.4487, "lr": 9.941309517415192e-07, "epoch": 2.828101644245142, "percentage": 56.56, "elapsed_time": "0:36:37", "remaining_time": "0:28:07", "throughput": 7052.74, "total_tokens": 15499264} {"current_steps": 1893, "total_steps": 3345, "loss": 0.3561, "lr": 9.929819347879282e-07, "epoch": 2.8295964125560538, "percentage": 56.59, "elapsed_time": "0:36:38", "remaining_time": "0:28:06", "throughput": 7052.76, "total_tokens": 15507456} {"current_steps": 1894, "total_steps": 3345, "loss": 0.5286, "lr": 9.918331445445674e-07, "epoch": 2.8310911808669657, "percentage": 56.62, "elapsed_time": "0:36:39", "remaining_time": "0:28:05", "throughput": 7052.77, "total_tokens": 15515648} {"current_steps": 1895, "total_steps": 3345, "loss": 0.479, "lr": 9.906845820247618e-07, "epoch": 2.8325859491778775, "percentage": 56.65, "elapsed_time": "0:36:41", "remaining_time": "0:28:04", "throughput": 7052.78, "total_tokens": 15523840} {"current_steps": 1896, "total_steps": 3345, "loss": 0.5686, "lr": 9.895362482416337e-07, "epoch": 2.8340807174887894, "percentage": 56.68, "elapsed_time": "0:36:42", "remaining_time": "0:28:03", "throughput": 7052.78, "total_tokens": 15532032} {"current_steps": 1897, "total_steps": 3345, "loss": 0.4901, "lr": 9.88388144208104e-07, "epoch": 2.8355754857997013, "percentage": 56.71, "elapsed_time": "0:36:43", "remaining_time": "0:28:01", "throughput": 7052.79, "total_tokens": 15540224} {"current_steps": 1898, "total_steps": 3345, "loss": 0.4056, "lr": 9.872402709368913e-07, "epoch": 2.8370702541106128, "percentage": 56.74, "elapsed_time": "0:36:44", "remaining_time": "0:28:00", "throughput": 7052.81, "total_tokens": 15548416} {"current_steps": 1899, "total_steps": 3345, "loss": 0.4826, "lr": 9.860926294405105e-07, "epoch": 2.8385650224215246, "percentage": 56.77, "elapsed_time": "0:36:45", "remaining_time": "0:27:59", "throughput": 7052.83, "total_tokens": 15556608} {"current_steps": 1900, "total_steps": 3345, "loss": 0.5189, "lr": 9.849452207312721e-07, "epoch": 2.8400597907324365, "percentage": 56.8, "elapsed_time": "0:36:46", "remaining_time": "0:27:58", "throughput": 7052.84, "total_tokens": 15564800} {"current_steps": 1901, "total_steps": 3345, "loss": 0.4554, "lr": 9.837980458212806e-07, "epoch": 2.8415545590433484, "percentage": 56.83, "elapsed_time": "0:36:48", "remaining_time": "0:27:57", "throughput": 7052.86, "total_tokens": 15572992} {"current_steps": 1902, "total_steps": 3345, "loss": 0.4167, "lr": 9.826511057224356e-07, "epoch": 2.84304932735426, "percentage": 56.86, "elapsed_time": "0:36:49", "remaining_time": "0:27:56", "throughput": 7052.87, "total_tokens": 15581184} {"current_steps": 1903, "total_steps": 3345, "loss": 0.4099, "lr": 9.815044014464287e-07, "epoch": 2.8445440956651717, "percentage": 56.89, "elapsed_time": "0:36:50", "remaining_time": "0:27:54", "throughput": 7052.87, "total_tokens": 15589376} {"current_steps": 1904, "total_steps": 3345, "loss": 0.4726, "lr": 9.803579340047434e-07, "epoch": 2.8460388639760836, "percentage": 56.92, "elapsed_time": "0:36:51", "remaining_time": "0:27:53", "throughput": 7052.88, "total_tokens": 15597568} {"current_steps": 1905, "total_steps": 3345, "loss": 0.5835, "lr": 9.792117044086544e-07, "epoch": 2.8475336322869955, "percentage": 56.95, "elapsed_time": "0:36:52", "remaining_time": "0:27:52", "throughput": 7052.89, "total_tokens": 15605760} {"current_steps": 1906, "total_steps": 3345, "loss": 0.4929, "lr": 9.780657136692272e-07, "epoch": 2.8490284005979074, "percentage": 56.98, "elapsed_time": "0:36:53", "remaining_time": "0:27:51", "throughput": 7052.91, "total_tokens": 15613952} {"current_steps": 1907, "total_steps": 3345, "loss": 0.6481, "lr": 9.76919962797316e-07, "epoch": 2.8505231689088193, "percentage": 57.01, "elapsed_time": "0:36:54", "remaining_time": "0:27:50", "throughput": 7052.93, "total_tokens": 15622144} {"current_steps": 1908, "total_steps": 3345, "loss": 0.6521, "lr": 9.75774452803563e-07, "epoch": 2.852017937219731, "percentage": 57.04, "elapsed_time": "0:36:56", "remaining_time": "0:27:49", "throughput": 7052.95, "total_tokens": 15630336} {"current_steps": 1909, "total_steps": 3345, "loss": 0.4323, "lr": 9.746291846983991e-07, "epoch": 2.8535127055306426, "percentage": 57.07, "elapsed_time": "0:36:57", "remaining_time": "0:27:47", "throughput": 7052.97, "total_tokens": 15638528} {"current_steps": 1910, "total_steps": 3345, "loss": 0.5108, "lr": 9.734841594920411e-07, "epoch": 2.8550074738415545, "percentage": 57.1, "elapsed_time": "0:36:58", "remaining_time": "0:27:46", "throughput": 7053.0, "total_tokens": 15646720} {"current_steps": 1911, "total_steps": 3345, "loss": 0.3597, "lr": 9.723393781944912e-07, "epoch": 2.8565022421524664, "percentage": 57.13, "elapsed_time": "0:36:59", "remaining_time": "0:27:45", "throughput": 7053.03, "total_tokens": 15654912} {"current_steps": 1912, "total_steps": 3345, "loss": 0.5788, "lr": 9.711948418155377e-07, "epoch": 2.8579970104633783, "percentage": 57.16, "elapsed_time": "0:37:00", "remaining_time": "0:27:44", "throughput": 7053.04, "total_tokens": 15663104} {"current_steps": 1913, "total_steps": 3345, "loss": 0.6513, "lr": 9.700505513647518e-07, "epoch": 2.8594917787742897, "percentage": 57.19, "elapsed_time": "0:37:01", "remaining_time": "0:27:43", "throughput": 7053.06, "total_tokens": 15671296} {"current_steps": 1914, "total_steps": 3345, "loss": 0.5718, "lr": 9.689065078514876e-07, "epoch": 2.8609865470852016, "percentage": 57.22, "elapsed_time": "0:37:03", "remaining_time": "0:27:42", "throughput": 7053.08, "total_tokens": 15679488} {"current_steps": 1915, "total_steps": 3345, "loss": 0.5753, "lr": 9.677627122848825e-07, "epoch": 2.8624813153961135, "percentage": 57.25, "elapsed_time": "0:37:04", "remaining_time": "0:27:40", "throughput": 7053.09, "total_tokens": 15687680} {"current_steps": 1916, "total_steps": 3345, "loss": 0.4849, "lr": 9.666191656738538e-07, "epoch": 2.8639760837070254, "percentage": 57.28, "elapsed_time": "0:37:05", "remaining_time": "0:27:39", "throughput": 7053.11, "total_tokens": 15695872} {"current_steps": 1917, "total_steps": 3345, "loss": 0.4893, "lr": 9.654758690271005e-07, "epoch": 2.8654708520179373, "percentage": 57.31, "elapsed_time": "0:37:06", "remaining_time": "0:27:38", "throughput": 7053.13, "total_tokens": 15704064} {"current_steps": 1918, "total_steps": 3345, "loss": 0.5969, "lr": 9.643328233531e-07, "epoch": 2.866965620328849, "percentage": 57.34, "elapsed_time": "0:37:07", "remaining_time": "0:27:37", "throughput": 7053.15, "total_tokens": 15712256} {"current_steps": 1919, "total_steps": 3345, "loss": 0.6937, "lr": 9.631900296601094e-07, "epoch": 2.868460388639761, "percentage": 57.37, "elapsed_time": "0:37:08", "remaining_time": "0:27:36", "throughput": 7053.17, "total_tokens": 15720448} {"current_steps": 1920, "total_steps": 3345, "loss": 0.6005, "lr": 9.62047488956163e-07, "epoch": 2.8699551569506725, "percentage": 57.4, "elapsed_time": "0:37:10", "remaining_time": "0:27:35", "throughput": 7053.19, "total_tokens": 15728640} {"current_steps": 1921, "total_steps": 3345, "loss": 0.5827, "lr": 9.609052022490713e-07, "epoch": 2.8714499252615844, "percentage": 57.43, "elapsed_time": "0:37:11", "remaining_time": "0:27:33", "throughput": 7053.2, "total_tokens": 15736832} {"current_steps": 1922, "total_steps": 3345, "loss": 0.5482, "lr": 9.59763170546422e-07, "epoch": 2.8729446935724963, "percentage": 57.46, "elapsed_time": "0:37:12", "remaining_time": "0:27:32", "throughput": 7053.23, "total_tokens": 15745024} {"current_steps": 1923, "total_steps": 3345, "loss": 0.8224, "lr": 9.586213948555769e-07, "epoch": 2.874439461883408, "percentage": 57.49, "elapsed_time": "0:37:13", "remaining_time": "0:27:31", "throughput": 7053.24, "total_tokens": 15753216} {"current_steps": 1924, "total_steps": 3345, "loss": 0.5654, "lr": 9.57479876183672e-07, "epoch": 2.87593423019432, "percentage": 57.52, "elapsed_time": "0:37:14", "remaining_time": "0:27:30", "throughput": 7053.26, "total_tokens": 15761408} {"current_steps": 1925, "total_steps": 3345, "loss": 0.593, "lr": 9.56338615537618e-07, "epoch": 2.8774289985052315, "percentage": 57.55, "elapsed_time": "0:37:15", "remaining_time": "0:27:29", "throughput": 7053.26, "total_tokens": 15769600} {"current_steps": 1926, "total_steps": 3345, "loss": 0.524, "lr": 9.551976139240961e-07, "epoch": 2.8789237668161434, "percentage": 57.58, "elapsed_time": "0:37:16", "remaining_time": "0:27:28", "throughput": 7053.25, "total_tokens": 15777792} {"current_steps": 1927, "total_steps": 3345, "loss": 0.59, "lr": 9.5405687234956e-07, "epoch": 2.8804185351270553, "percentage": 57.61, "elapsed_time": "0:37:18", "remaining_time": "0:27:26", "throughput": 7053.25, "total_tokens": 15785984} {"current_steps": 1928, "total_steps": 3345, "loss": 0.4465, "lr": 9.529163918202334e-07, "epoch": 2.881913303437967, "percentage": 57.64, "elapsed_time": "0:37:19", "remaining_time": "0:27:25", "throughput": 7053.26, "total_tokens": 15794176} {"current_steps": 1929, "total_steps": 3345, "loss": 0.5796, "lr": 9.517761733421113e-07, "epoch": 2.883408071748879, "percentage": 57.67, "elapsed_time": "0:37:20", "remaining_time": "0:27:24", "throughput": 7053.27, "total_tokens": 15802368} {"current_steps": 1930, "total_steps": 3345, "loss": 0.285, "lr": 9.506362179209555e-07, "epoch": 2.884902840059791, "percentage": 57.7, "elapsed_time": "0:37:21", "remaining_time": "0:27:23", "throughput": 7053.29, "total_tokens": 15810560} {"current_steps": 1931, "total_steps": 3345, "loss": 0.448, "lr": 9.494965265622973e-07, "epoch": 2.886397608370703, "percentage": 57.73, "elapsed_time": "0:37:22", "remaining_time": "0:27:22", "throughput": 7053.3, "total_tokens": 15818752} {"current_steps": 1932, "total_steps": 3345, "loss": 0.3856, "lr": 9.48357100271434e-07, "epoch": 2.8878923766816142, "percentage": 57.76, "elapsed_time": "0:37:23", "remaining_time": "0:27:21", "throughput": 7053.33, "total_tokens": 15826944} {"current_steps": 1933, "total_steps": 3345, "loss": 0.4741, "lr": 9.472179400534299e-07, "epoch": 2.889387144992526, "percentage": 57.79, "elapsed_time": "0:37:25", "remaining_time": "0:27:19", "throughput": 7053.32, "total_tokens": 15835136} {"current_steps": 1934, "total_steps": 3345, "loss": 0.5046, "lr": 9.460790469131137e-07, "epoch": 2.890881913303438, "percentage": 57.82, "elapsed_time": "0:37:26", "remaining_time": "0:27:18", "throughput": 7053.33, "total_tokens": 15843328} {"current_steps": 1935, "total_steps": 3345, "loss": 0.6464, "lr": 9.449404218550799e-07, "epoch": 2.89237668161435, "percentage": 57.85, "elapsed_time": "0:37:27", "remaining_time": "0:27:17", "throughput": 7053.35, "total_tokens": 15851520} {"current_steps": 1936, "total_steps": 3345, "loss": 0.3238, "lr": 9.438020658836854e-07, "epoch": 2.8938714499252614, "percentage": 57.88, "elapsed_time": "0:37:28", "remaining_time": "0:27:16", "throughput": 7053.35, "total_tokens": 15859712} {"current_steps": 1937, "total_steps": 3345, "loss": 0.7108, "lr": 9.426639800030498e-07, "epoch": 2.8953662182361732, "percentage": 57.91, "elapsed_time": "0:37:29", "remaining_time": "0:27:15", "throughput": 7053.37, "total_tokens": 15867904} {"current_steps": 1938, "total_steps": 3345, "loss": 0.6699, "lr": 9.415261652170551e-07, "epoch": 2.896860986547085, "percentage": 57.94, "elapsed_time": "0:37:30", "remaining_time": "0:27:14", "throughput": 7053.37, "total_tokens": 15876096} {"current_steps": 1939, "total_steps": 3345, "loss": 0.3326, "lr": 9.403886225293438e-07, "epoch": 2.898355754857997, "percentage": 57.97, "elapsed_time": "0:37:32", "remaining_time": "0:27:12", "throughput": 7053.38, "total_tokens": 15884288} {"current_steps": 1940, "total_steps": 3345, "loss": 0.5659, "lr": 9.392513529433179e-07, "epoch": 2.899850523168909, "percentage": 58.0, "elapsed_time": "0:37:33", "remaining_time": "0:27:11", "throughput": 7053.39, "total_tokens": 15892480} {"current_steps": 1941, "total_steps": 3345, "loss": 0.5819, "lr": 9.381143574621393e-07, "epoch": 2.901345291479821, "percentage": 58.03, "elapsed_time": "0:37:34", "remaining_time": "0:27:10", "throughput": 7053.39, "total_tokens": 15900672} {"current_steps": 1942, "total_steps": 3345, "loss": 0.431, "lr": 9.369776370887279e-07, "epoch": 2.9028400597907327, "percentage": 58.06, "elapsed_time": "0:37:35", "remaining_time": "0:27:09", "throughput": 7053.41, "total_tokens": 15908864} {"current_steps": 1943, "total_steps": 3345, "loss": 0.7788, "lr": 9.358411928257609e-07, "epoch": 2.904334828101644, "percentage": 58.09, "elapsed_time": "0:37:36", "remaining_time": "0:27:08", "throughput": 7053.41, "total_tokens": 15917056} {"current_steps": 1944, "total_steps": 3345, "loss": 0.4497, "lr": 9.347050256756717e-07, "epoch": 2.905829596412556, "percentage": 58.12, "elapsed_time": "0:37:37", "remaining_time": "0:27:07", "throughput": 7053.42, "total_tokens": 15925248} {"current_steps": 1945, "total_steps": 3345, "loss": 0.2665, "lr": 9.335691366406488e-07, "epoch": 2.907324364723468, "percentage": 58.15, "elapsed_time": "0:37:38", "remaining_time": "0:27:05", "throughput": 7053.43, "total_tokens": 15933440} {"current_steps": 1946, "total_steps": 3345, "loss": 0.5336, "lr": 9.324335267226375e-07, "epoch": 2.90881913303438, "percentage": 58.18, "elapsed_time": "0:37:40", "remaining_time": "0:27:04", "throughput": 7053.44, "total_tokens": 15941632} {"current_steps": 1947, "total_steps": 3345, "loss": 0.5203, "lr": 9.312981969233345e-07, "epoch": 2.910313901345291, "percentage": 58.21, "elapsed_time": "0:37:41", "remaining_time": "0:27:03", "throughput": 7053.45, "total_tokens": 15949824} {"current_steps": 1948, "total_steps": 3345, "loss": 0.4414, "lr": 9.301631482441905e-07, "epoch": 2.911808669656203, "percentage": 58.24, "elapsed_time": "0:37:42", "remaining_time": "0:27:02", "throughput": 7053.46, "total_tokens": 15958016} {"current_steps": 1949, "total_steps": 3345, "loss": 0.3801, "lr": 9.290283816864081e-07, "epoch": 2.913303437967115, "percentage": 58.27, "elapsed_time": "0:37:43", "remaining_time": "0:27:01", "throughput": 7053.48, "total_tokens": 15966208} {"current_steps": 1950, "total_steps": 3345, "loss": 0.7367, "lr": 9.278938982509409e-07, "epoch": 2.914798206278027, "percentage": 58.3, "elapsed_time": "0:37:44", "remaining_time": "0:27:00", "throughput": 7053.48, "total_tokens": 15974400} {"current_steps": 1951, "total_steps": 3345, "loss": 0.587, "lr": 9.26759698938493e-07, "epoch": 2.9162929745889388, "percentage": 58.33, "elapsed_time": "0:37:45", "remaining_time": "0:26:59", "throughput": 7053.48, "total_tokens": 15982592} {"current_steps": 1952, "total_steps": 3345, "loss": 0.559, "lr": 9.25625784749518e-07, "epoch": 2.9177877428998507, "percentage": 58.36, "elapsed_time": "0:37:47", "remaining_time": "0:26:57", "throughput": 7053.46, "total_tokens": 15990784} {"current_steps": 1953, "total_steps": 3345, "loss": 0.4765, "lr": 9.244921566842175e-07, "epoch": 2.9192825112107625, "percentage": 58.39, "elapsed_time": "0:37:48", "remaining_time": "0:26:56", "throughput": 7053.47, "total_tokens": 15998976} {"current_steps": 1954, "total_steps": 3345, "loss": 0.3201, "lr": 9.233588157425408e-07, "epoch": 2.920777279521674, "percentage": 58.42, "elapsed_time": "0:37:49", "remaining_time": "0:26:55", "throughput": 7053.48, "total_tokens": 16007168} {"current_steps": 1955, "total_steps": 3345, "loss": 0.5659, "lr": 9.222257629241842e-07, "epoch": 2.922272047832586, "percentage": 58.45, "elapsed_time": "0:37:50", "remaining_time": "0:26:54", "throughput": 7053.48, "total_tokens": 16015360} {"current_steps": 1956, "total_steps": 3345, "loss": 0.512, "lr": 9.210929992285899e-07, "epoch": 2.9237668161434978, "percentage": 58.48, "elapsed_time": "0:37:51", "remaining_time": "0:26:53", "throughput": 7053.47, "total_tokens": 16023552} {"current_steps": 1957, "total_steps": 3345, "loss": 0.311, "lr": 9.199605256549449e-07, "epoch": 2.9252615844544096, "percentage": 58.51, "elapsed_time": "0:37:52", "remaining_time": "0:26:52", "throughput": 7053.5, "total_tokens": 16031744} {"current_steps": 1958, "total_steps": 3345, "loss": 0.271, "lr": 9.188283432021802e-07, "epoch": 2.9267563527653215, "percentage": 58.54, "elapsed_time": "0:37:54", "remaining_time": "0:26:50", "throughput": 7053.52, "total_tokens": 16039936} {"current_steps": 1959, "total_steps": 3345, "loss": 0.5328, "lr": 9.176964528689705e-07, "epoch": 2.928251121076233, "percentage": 58.57, "elapsed_time": "0:37:55", "remaining_time": "0:26:49", "throughput": 7053.54, "total_tokens": 16048128} {"current_steps": 1960, "total_steps": 3345, "loss": 0.4395, "lr": 9.165648556537323e-07, "epoch": 2.929745889387145, "percentage": 58.59, "elapsed_time": "0:37:56", "remaining_time": "0:26:48", "throughput": 7053.55, "total_tokens": 16056320} {"current_steps": 1961, "total_steps": 3345, "loss": 0.3365, "lr": 9.154335525546234e-07, "epoch": 2.9312406576980568, "percentage": 58.62, "elapsed_time": "0:37:57", "remaining_time": "0:26:47", "throughput": 7053.56, "total_tokens": 16064512} {"current_steps": 1962, "total_steps": 3345, "loss": 0.7544, "lr": 9.143025445695425e-07, "epoch": 2.9327354260089686, "percentage": 58.65, "elapsed_time": "0:37:58", "remaining_time": "0:26:46", "throughput": 7053.58, "total_tokens": 16072704} {"current_steps": 1963, "total_steps": 3345, "loss": 0.4024, "lr": 9.131718326961284e-07, "epoch": 2.9342301943198805, "percentage": 58.68, "elapsed_time": "0:37:59", "remaining_time": "0:26:45", "throughput": 7053.6, "total_tokens": 16080896} {"current_steps": 1964, "total_steps": 3345, "loss": 0.506, "lr": 9.120414179317582e-07, "epoch": 2.9357249626307924, "percentage": 58.71, "elapsed_time": "0:38:00", "remaining_time": "0:26:43", "throughput": 7053.62, "total_tokens": 16089088} {"current_steps": 1965, "total_steps": 3345, "loss": 0.669, "lr": 9.109113012735467e-07, "epoch": 2.9372197309417043, "percentage": 58.74, "elapsed_time": "0:38:02", "remaining_time": "0:26:42", "throughput": 7053.63, "total_tokens": 16097280} {"current_steps": 1966, "total_steps": 3345, "loss": 0.4313, "lr": 9.097814837183462e-07, "epoch": 2.9387144992526157, "percentage": 58.77, "elapsed_time": "0:38:03", "remaining_time": "0:26:41", "throughput": 7053.64, "total_tokens": 16105472} {"current_steps": 1967, "total_steps": 3345, "loss": 0.6538, "lr": 9.086519662627447e-07, "epoch": 2.9402092675635276, "percentage": 58.8, "elapsed_time": "0:38:04", "remaining_time": "0:26:40", "throughput": 7053.65, "total_tokens": 16113664} {"current_steps": 1968, "total_steps": 3345, "loss": 0.5492, "lr": 9.075227499030664e-07, "epoch": 2.9417040358744395, "percentage": 58.83, "elapsed_time": "0:38:05", "remaining_time": "0:26:39", "throughput": 7053.66, "total_tokens": 16121856} {"current_steps": 1969, "total_steps": 3345, "loss": 0.3736, "lr": 9.06393835635369e-07, "epoch": 2.9431988041853514, "percentage": 58.86, "elapsed_time": "0:38:06", "remaining_time": "0:26:38", "throughput": 7053.68, "total_tokens": 16130048} {"current_steps": 1970, "total_steps": 3345, "loss": 0.7614, "lr": 9.05265224455444e-07, "epoch": 2.944693572496263, "percentage": 58.89, "elapsed_time": "0:38:07", "remaining_time": "0:26:36", "throughput": 7053.69, "total_tokens": 16138240} {"current_steps": 1971, "total_steps": 3345, "loss": 0.4368, "lr": 9.041369173588155e-07, "epoch": 2.9461883408071747, "percentage": 58.92, "elapsed_time": "0:38:09", "remaining_time": "0:26:35", "throughput": 7053.7, "total_tokens": 16146432} {"current_steps": 1972, "total_steps": 3345, "loss": 0.5469, "lr": 9.030089153407398e-07, "epoch": 2.9476831091180866, "percentage": 58.95, "elapsed_time": "0:38:10", "remaining_time": "0:26:34", "throughput": 7053.71, "total_tokens": 16154624} {"current_steps": 1973, "total_steps": 3345, "loss": 0.5367, "lr": 9.01881219396203e-07, "epoch": 2.9491778774289985, "percentage": 58.98, "elapsed_time": "0:38:11", "remaining_time": "0:26:33", "throughput": 7053.72, "total_tokens": 16162816} {"current_steps": 1974, "total_steps": 3345, "loss": 0.5623, "lr": 9.007538305199228e-07, "epoch": 2.9506726457399104, "percentage": 59.01, "elapsed_time": "0:38:12", "remaining_time": "0:26:32", "throughput": 7053.73, "total_tokens": 16171008} {"current_steps": 1975, "total_steps": 3345, "loss": 0.806, "lr": 8.996267497063452e-07, "epoch": 2.9521674140508223, "percentage": 59.04, "elapsed_time": "0:38:13", "remaining_time": "0:26:31", "throughput": 7053.73, "total_tokens": 16179200} {"current_steps": 1976, "total_steps": 3345, "loss": 0.5989, "lr": 8.98499977949644e-07, "epoch": 2.953662182361734, "percentage": 59.07, "elapsed_time": "0:38:14", "remaining_time": "0:26:29", "throughput": 7053.74, "total_tokens": 16187392} {"current_steps": 1977, "total_steps": 3345, "loss": 0.5901, "lr": 8.973735162437211e-07, "epoch": 2.9551569506726456, "percentage": 59.1, "elapsed_time": "0:38:16", "remaining_time": "0:26:28", "throughput": 7053.76, "total_tokens": 16195584} {"current_steps": 1978, "total_steps": 3345, "loss": 0.5138, "lr": 8.962473655822049e-07, "epoch": 2.9566517189835575, "percentage": 59.13, "elapsed_time": "0:38:17", "remaining_time": "0:26:27", "throughput": 7053.78, "total_tokens": 16203776} {"current_steps": 1979, "total_steps": 3345, "loss": 0.5393, "lr": 8.951215269584481e-07, "epoch": 2.9581464872944694, "percentage": 59.16, "elapsed_time": "0:38:18", "remaining_time": "0:26:26", "throughput": 7053.79, "total_tokens": 16211968} {"current_steps": 1980, "total_steps": 3345, "loss": 0.399, "lr": 8.939960013655311e-07, "epoch": 2.9596412556053813, "percentage": 59.19, "elapsed_time": "0:38:19", "remaining_time": "0:26:25", "throughput": 7053.8, "total_tokens": 16220160} {"current_steps": 1981, "total_steps": 3345, "loss": 0.5462, "lr": 8.928707897962552e-07, "epoch": 2.9611360239162927, "percentage": 59.22, "elapsed_time": "0:38:20", "remaining_time": "0:26:24", "throughput": 7053.81, "total_tokens": 16228352} {"current_steps": 1982, "total_steps": 3345, "loss": 0.5475, "lr": 8.917458932431461e-07, "epoch": 2.9626307922272046, "percentage": 59.25, "elapsed_time": "0:38:21", "remaining_time": "0:26:22", "throughput": 7053.81, "total_tokens": 16236544} {"current_steps": 1983, "total_steps": 3345, "loss": 0.5965, "lr": 8.906213126984511e-07, "epoch": 2.9641255605381165, "percentage": 59.28, "elapsed_time": "0:38:22", "remaining_time": "0:26:21", "throughput": 7053.83, "total_tokens": 16244736} {"current_steps": 1984, "total_steps": 3345, "loss": 0.5793, "lr": 8.894970491541397e-07, "epoch": 2.9656203288490284, "percentage": 59.31, "elapsed_time": "0:38:24", "remaining_time": "0:26:20", "throughput": 7053.85, "total_tokens": 16252928} {"current_steps": 1985, "total_steps": 3345, "loss": 0.3273, "lr": 8.883731036019009e-07, "epoch": 2.9671150971599403, "percentage": 59.34, "elapsed_time": "0:38:25", "remaining_time": "0:26:19", "throughput": 7053.87, "total_tokens": 16261120} {"current_steps": 1986, "total_steps": 3345, "loss": 0.7611, "lr": 8.87249477033143e-07, "epoch": 2.968609865470852, "percentage": 59.37, "elapsed_time": "0:38:26", "remaining_time": "0:26:18", "throughput": 7053.88, "total_tokens": 16269312} {"current_steps": 1987, "total_steps": 3345, "loss": 0.4263, "lr": 8.861261704389938e-07, "epoch": 2.970104633781764, "percentage": 59.4, "elapsed_time": "0:38:27", "remaining_time": "0:26:17", "throughput": 7053.89, "total_tokens": 16277504} {"current_steps": 1988, "total_steps": 3345, "loss": 0.3737, "lr": 8.850031848102984e-07, "epoch": 2.9715994020926755, "percentage": 59.43, "elapsed_time": "0:38:28", "remaining_time": "0:26:15", "throughput": 7053.91, "total_tokens": 16285696} {"current_steps": 1989, "total_steps": 3345, "loss": 0.6198, "lr": 8.838805211376186e-07, "epoch": 2.9730941704035874, "percentage": 59.46, "elapsed_time": "0:38:29", "remaining_time": "0:26:14", "throughput": 7053.92, "total_tokens": 16293888} {"current_steps": 1990, "total_steps": 3345, "loss": 0.6522, "lr": 8.827581804112324e-07, "epoch": 2.9745889387144993, "percentage": 59.49, "elapsed_time": "0:38:31", "remaining_time": "0:26:13", "throughput": 7053.94, "total_tokens": 16302080} {"current_steps": 1991, "total_steps": 3345, "loss": 0.5249, "lr": 8.816361636211333e-07, "epoch": 2.976083707025411, "percentage": 59.52, "elapsed_time": "0:38:32", "remaining_time": "0:26:12", "throughput": 7053.94, "total_tokens": 16310272} {"current_steps": 1992, "total_steps": 3345, "loss": 0.6505, "lr": 8.805144717570286e-07, "epoch": 2.977578475336323, "percentage": 59.55, "elapsed_time": "0:38:33", "remaining_time": "0:26:11", "throughput": 7053.95, "total_tokens": 16318464} {"current_steps": 1993, "total_steps": 3345, "loss": 0.6008, "lr": 8.793931058083388e-07, "epoch": 2.9790732436472345, "percentage": 59.58, "elapsed_time": "0:38:34", "remaining_time": "0:26:10", "throughput": 7053.96, "total_tokens": 16326656} {"current_steps": 1994, "total_steps": 3345, "loss": 0.696, "lr": 8.782720667641975e-07, "epoch": 2.9805680119581464, "percentage": 59.61, "elapsed_time": "0:38:35", "remaining_time": "0:26:08", "throughput": 7053.96, "total_tokens": 16334848} {"current_steps": 1995, "total_steps": 3345, "loss": 0.5899, "lr": 8.771513556134497e-07, "epoch": 2.9820627802690582, "percentage": 59.64, "elapsed_time": "0:38:36", "remaining_time": "0:26:07", "throughput": 7053.98, "total_tokens": 16343040} {"current_steps": 1996, "total_steps": 3345, "loss": 0.5438, "lr": 8.760309733446507e-07, "epoch": 2.98355754857997, "percentage": 59.67, "elapsed_time": "0:38:38", "remaining_time": "0:26:06", "throughput": 7053.99, "total_tokens": 16351232} {"current_steps": 1997, "total_steps": 3345, "loss": 0.3311, "lr": 8.749109209460667e-07, "epoch": 2.985052316890882, "percentage": 59.7, "elapsed_time": "0:38:39", "remaining_time": "0:26:05", "throughput": 7054.0, "total_tokens": 16359424} {"current_steps": 1998, "total_steps": 3345, "loss": 0.4395, "lr": 8.737911994056722e-07, "epoch": 2.986547085201794, "percentage": 59.73, "elapsed_time": "0:38:40", "remaining_time": "0:26:04", "throughput": 7054.01, "total_tokens": 16367616} {"current_steps": 1999, "total_steps": 3345, "loss": 0.7249, "lr": 8.726718097111498e-07, "epoch": 2.988041853512706, "percentage": 59.76, "elapsed_time": "0:38:41", "remaining_time": "0:26:03", "throughput": 7054.02, "total_tokens": 16375808} {"current_steps": 2000, "total_steps": 3345, "loss": 0.6213, "lr": 8.715527528498902e-07, "epoch": 2.9895366218236172, "percentage": 59.79, "elapsed_time": "0:38:42", "remaining_time": "0:26:01", "throughput": 7054.03, "total_tokens": 16384000} {"current_steps": 2001, "total_steps": 3345, "loss": 0.3107, "lr": 8.704340298089893e-07, "epoch": 2.991031390134529, "percentage": 59.82, "elapsed_time": "0:38:43", "remaining_time": "0:26:00", "throughput": 7054.04, "total_tokens": 16392192} {"current_steps": 2002, "total_steps": 3345, "loss": 0.5489, "lr": 8.693156415752495e-07, "epoch": 2.992526158445441, "percentage": 59.85, "elapsed_time": "0:38:44", "remaining_time": "0:25:59", "throughput": 7054.05, "total_tokens": 16400384} {"current_steps": 2003, "total_steps": 3345, "loss": 0.5171, "lr": 8.681975891351774e-07, "epoch": 2.994020926756353, "percentage": 59.88, "elapsed_time": "0:38:46", "remaining_time": "0:25:58", "throughput": 7054.05, "total_tokens": 16408576} {"current_steps": 2004, "total_steps": 3345, "loss": 0.3335, "lr": 8.670798734749835e-07, "epoch": 2.9955156950672643, "percentage": 59.91, "elapsed_time": "0:38:47", "remaining_time": "0:25:57", "throughput": 7054.06, "total_tokens": 16416768} {"current_steps": 2005, "total_steps": 3345, "loss": 0.5454, "lr": 8.659624955805815e-07, "epoch": 2.9970104633781762, "percentage": 59.94, "elapsed_time": "0:38:48", "remaining_time": "0:25:56", "throughput": 7054.07, "total_tokens": 16424960} {"current_steps": 2006, "total_steps": 3345, "loss": 0.5734, "lr": 8.648454564375866e-07, "epoch": 2.998505231689088, "percentage": 59.97, "elapsed_time": "0:38:49", "remaining_time": "0:25:55", "throughput": 7054.07, "total_tokens": 16433152} {"current_steps": 2007, "total_steps": 3345, "loss": 0.2163, "lr": 8.637287570313159e-07, "epoch": 3.0, "percentage": 60.0, "elapsed_time": "0:38:50", "remaining_time": "0:25:53", "throughput": 7054.13, "total_tokens": 16441344} {"current_steps": 2008, "total_steps": 3345, "loss": 0.1721, "lr": 8.626123983467863e-07, "epoch": 3.001494768310912, "percentage": 60.03, "elapsed_time": "0:38:51", "remaining_time": "0:25:52", "throughput": 7054.08, "total_tokens": 16449536} {"current_steps": 2009, "total_steps": 3345, "loss": 0.1529, "lr": 8.614963813687144e-07, "epoch": 3.0029895366218238, "percentage": 60.06, "elapsed_time": "0:38:53", "remaining_time": "0:25:51", "throughput": 7054.1, "total_tokens": 16457728} {"current_steps": 2010, "total_steps": 3345, "loss": 0.2111, "lr": 8.603807070815152e-07, "epoch": 3.004484304932735, "percentage": 60.09, "elapsed_time": "0:38:54", "remaining_time": "0:25:50", "throughput": 7054.1, "total_tokens": 16465920} {"current_steps": 2011, "total_steps": 3345, "loss": 0.2931, "lr": 8.592653764693015e-07, "epoch": 3.005979073243647, "percentage": 60.12, "elapsed_time": "0:38:55", "remaining_time": "0:25:49", "throughput": 7054.12, "total_tokens": 16474112} {"current_steps": 2012, "total_steps": 3345, "loss": 0.1864, "lr": 8.581503905158833e-07, "epoch": 3.007473841554559, "percentage": 60.15, "elapsed_time": "0:38:56", "remaining_time": "0:25:48", "throughput": 7054.12, "total_tokens": 16482304} {"current_steps": 2013, "total_steps": 3345, "loss": 0.2949, "lr": 8.570357502047653e-07, "epoch": 3.008968609865471, "percentage": 60.18, "elapsed_time": "0:38:57", "remaining_time": "0:25:46", "throughput": 7054.12, "total_tokens": 16490496} {"current_steps": 2014, "total_steps": 3345, "loss": 0.2988, "lr": 8.559214565191495e-07, "epoch": 3.0104633781763828, "percentage": 60.21, "elapsed_time": "0:38:58", "remaining_time": "0:25:45", "throughput": 7054.13, "total_tokens": 16498688} {"current_steps": 2015, "total_steps": 3345, "loss": 0.2966, "lr": 8.548075104419306e-07, "epoch": 3.0119581464872947, "percentage": 60.24, "elapsed_time": "0:39:00", "remaining_time": "0:25:44", "throughput": 7054.14, "total_tokens": 16506880} {"current_steps": 2016, "total_steps": 3345, "loss": 0.2651, "lr": 8.536939129556965e-07, "epoch": 3.013452914798206, "percentage": 60.27, "elapsed_time": "0:39:01", "remaining_time": "0:25:43", "throughput": 7054.15, "total_tokens": 16515072} {"current_steps": 2017, "total_steps": 3345, "loss": 0.4437, "lr": 8.525806650427287e-07, "epoch": 3.014947683109118, "percentage": 60.3, "elapsed_time": "0:39:02", "remaining_time": "0:25:42", "throughput": 7054.16, "total_tokens": 16523264} {"current_steps": 2018, "total_steps": 3345, "loss": 0.3404, "lr": 8.514677676849994e-07, "epoch": 3.01644245142003, "percentage": 60.33, "elapsed_time": "0:39:03", "remaining_time": "0:25:41", "throughput": 7054.17, "total_tokens": 16531456} {"current_steps": 2019, "total_steps": 3345, "loss": 0.2562, "lr": 8.503552218641724e-07, "epoch": 3.0179372197309418, "percentage": 60.36, "elapsed_time": "0:39:04", "remaining_time": "0:25:39", "throughput": 7054.19, "total_tokens": 16539648} {"current_steps": 2020, "total_steps": 3345, "loss": 0.5524, "lr": 8.492430285616005e-07, "epoch": 3.0194319880418536, "percentage": 60.39, "elapsed_time": "0:39:05", "remaining_time": "0:25:38", "throughput": 7054.21, "total_tokens": 16547840} {"current_steps": 2021, "total_steps": 3345, "loss": 0.1784, "lr": 8.481311887583263e-07, "epoch": 3.0209267563527655, "percentage": 60.42, "elapsed_time": "0:39:06", "remaining_time": "0:25:37", "throughput": 7054.22, "total_tokens": 16556032} {"current_steps": 2022, "total_steps": 3345, "loss": 0.2758, "lr": 8.470197034350801e-07, "epoch": 3.022421524663677, "percentage": 60.45, "elapsed_time": "0:39:08", "remaining_time": "0:25:36", "throughput": 7054.23, "total_tokens": 16564224} {"current_steps": 2023, "total_steps": 3345, "loss": 0.2001, "lr": 8.459085735722797e-07, "epoch": 3.023916292974589, "percentage": 60.48, "elapsed_time": "0:39:09", "remaining_time": "0:25:35", "throughput": 7054.24, "total_tokens": 16572416} {"current_steps": 2024, "total_steps": 3345, "loss": 0.3755, "lr": 8.447978001500296e-07, "epoch": 3.0254110612855007, "percentage": 60.51, "elapsed_time": "0:39:10", "remaining_time": "0:25:34", "throughput": 7054.25, "total_tokens": 16580608} {"current_steps": 2025, "total_steps": 3345, "loss": 0.3532, "lr": 8.436873841481196e-07, "epoch": 3.0269058295964126, "percentage": 60.54, "elapsed_time": "0:39:11", "remaining_time": "0:25:32", "throughput": 7054.25, "total_tokens": 16588800} {"current_steps": 2026, "total_steps": 3345, "loss": 0.2308, "lr": 8.425773265460247e-07, "epoch": 3.0284005979073245, "percentage": 60.57, "elapsed_time": "0:39:12", "remaining_time": "0:25:31", "throughput": 7054.26, "total_tokens": 16596992} {"current_steps": 2027, "total_steps": 3345, "loss": 0.1829, "lr": 8.414676283229026e-07, "epoch": 3.029895366218236, "percentage": 60.6, "elapsed_time": "0:39:13", "remaining_time": "0:25:30", "throughput": 7054.22, "total_tokens": 16605184} {"current_steps": 2028, "total_steps": 3345, "loss": 0.0971, "lr": 8.403582904575952e-07, "epoch": 3.031390134529148, "percentage": 60.63, "elapsed_time": "0:39:15", "remaining_time": "0:25:29", "throughput": 7054.24, "total_tokens": 16613376} {"current_steps": 2029, "total_steps": 3345, "loss": 0.3635, "lr": 8.392493139286259e-07, "epoch": 3.0328849028400597, "percentage": 60.66, "elapsed_time": "0:39:16", "remaining_time": "0:25:28", "throughput": 7054.26, "total_tokens": 16621568} {"current_steps": 2030, "total_steps": 3345, "loss": 0.2287, "lr": 8.381406997141997e-07, "epoch": 3.0343796711509716, "percentage": 60.69, "elapsed_time": "0:39:17", "remaining_time": "0:25:27", "throughput": 7054.27, "total_tokens": 16629760} {"current_steps": 2031, "total_steps": 3345, "loss": 0.2505, "lr": 8.370324487922022e-07, "epoch": 3.0358744394618835, "percentage": 60.72, "elapsed_time": "0:39:18", "remaining_time": "0:25:25", "throughput": 7054.29, "total_tokens": 16637952} {"current_steps": 2032, "total_steps": 3345, "loss": 0.2819, "lr": 8.359245621401978e-07, "epoch": 3.0373692077727954, "percentage": 60.75, "elapsed_time": "0:39:19", "remaining_time": "0:25:24", "throughput": 7054.3, "total_tokens": 16646144} {"current_steps": 2033, "total_steps": 3345, "loss": 0.2968, "lr": 8.348170407354303e-07, "epoch": 3.038863976083707, "percentage": 60.78, "elapsed_time": "0:39:20", "remaining_time": "0:25:23", "throughput": 7054.31, "total_tokens": 16654336} {"current_steps": 2034, "total_steps": 3345, "loss": 0.2187, "lr": 8.337098855548209e-07, "epoch": 3.0403587443946187, "percentage": 60.81, "elapsed_time": "0:39:22", "remaining_time": "0:25:22", "throughput": 7054.32, "total_tokens": 16662528} {"current_steps": 2035, "total_steps": 3345, "loss": 0.4678, "lr": 8.32603097574968e-07, "epoch": 3.0418535127055306, "percentage": 60.84, "elapsed_time": "0:39:23", "remaining_time": "0:25:21", "throughput": 7054.34, "total_tokens": 16670720} {"current_steps": 2036, "total_steps": 3345, "loss": 0.3078, "lr": 8.314966777721458e-07, "epoch": 3.0433482810164425, "percentage": 60.87, "elapsed_time": "0:39:24", "remaining_time": "0:25:20", "throughput": 7054.35, "total_tokens": 16678912} {"current_steps": 2037, "total_steps": 3345, "loss": 0.5245, "lr": 8.303906271223043e-07, "epoch": 3.0448430493273544, "percentage": 60.9, "elapsed_time": "0:39:25", "remaining_time": "0:25:18", "throughput": 7054.35, "total_tokens": 16687104} {"current_steps": 2038, "total_steps": 3345, "loss": 0.2915, "lr": 8.292849466010671e-07, "epoch": 3.0463378176382663, "percentage": 60.93, "elapsed_time": "0:39:26", "remaining_time": "0:25:17", "throughput": 7054.36, "total_tokens": 16695296} {"current_steps": 2039, "total_steps": 3345, "loss": 0.1637, "lr": 8.281796371837318e-07, "epoch": 3.0478325859491777, "percentage": 60.96, "elapsed_time": "0:39:27", "remaining_time": "0:25:16", "throughput": 7054.37, "total_tokens": 16703488} {"current_steps": 2040, "total_steps": 3345, "loss": 0.1591, "lr": 8.270746998452689e-07, "epoch": 3.0493273542600896, "percentage": 60.99, "elapsed_time": "0:39:28", "remaining_time": "0:25:15", "throughput": 7054.38, "total_tokens": 16711680} {"current_steps": 2041, "total_steps": 3345, "loss": 0.3447, "lr": 8.259701355603203e-07, "epoch": 3.0508221225710015, "percentage": 61.02, "elapsed_time": "0:39:30", "remaining_time": "0:25:14", "throughput": 7054.39, "total_tokens": 16719872} {"current_steps": 2042, "total_steps": 3345, "loss": 0.21, "lr": 8.248659453031988e-07, "epoch": 3.0523168908819134, "percentage": 61.05, "elapsed_time": "0:39:31", "remaining_time": "0:25:13", "throughput": 7054.4, "total_tokens": 16728064} {"current_steps": 2043, "total_steps": 3345, "loss": 0.2197, "lr": 8.237621300478873e-07, "epoch": 3.0538116591928253, "percentage": 61.08, "elapsed_time": "0:39:32", "remaining_time": "0:25:11", "throughput": 7054.42, "total_tokens": 16736256} {"current_steps": 2044, "total_steps": 3345, "loss": 0.2258, "lr": 8.226586907680384e-07, "epoch": 3.0553064275037367, "percentage": 61.11, "elapsed_time": "0:39:33", "remaining_time": "0:25:10", "throughput": 7054.44, "total_tokens": 16744448} {"current_steps": 2045, "total_steps": 3345, "loss": 0.4801, "lr": 8.215556284369724e-07, "epoch": 3.0568011958146486, "percentage": 61.14, "elapsed_time": "0:39:34", "remaining_time": "0:25:09", "throughput": 7054.45, "total_tokens": 16752640} {"current_steps": 2046, "total_steps": 3345, "loss": 0.2645, "lr": 8.204529440276772e-07, "epoch": 3.0582959641255605, "percentage": 61.17, "elapsed_time": "0:39:35", "remaining_time": "0:25:08", "throughput": 7054.46, "total_tokens": 16760832} {"current_steps": 2047, "total_steps": 3345, "loss": 0.1356, "lr": 8.193506385128077e-07, "epoch": 3.0597907324364724, "percentage": 61.2, "elapsed_time": "0:39:37", "remaining_time": "0:25:07", "throughput": 7054.47, "total_tokens": 16769024} {"current_steps": 2048, "total_steps": 3345, "loss": 0.3644, "lr": 8.182487128646848e-07, "epoch": 3.0612855007473843, "percentage": 61.23, "elapsed_time": "0:39:38", "remaining_time": "0:25:06", "throughput": 7054.48, "total_tokens": 16777216} {"current_steps": 2049, "total_steps": 3345, "loss": 0.5603, "lr": 8.171471680552935e-07, "epoch": 3.062780269058296, "percentage": 61.26, "elapsed_time": "0:39:39", "remaining_time": "0:25:04", "throughput": 7054.49, "total_tokens": 16785408} {"current_steps": 2050, "total_steps": 3345, "loss": 0.4926, "lr": 8.160460050562837e-07, "epoch": 3.0642750373692076, "percentage": 61.29, "elapsed_time": "0:39:40", "remaining_time": "0:25:03", "throughput": 7054.49, "total_tokens": 16793600} {"current_steps": 2051, "total_steps": 3345, "loss": 0.1203, "lr": 8.149452248389678e-07, "epoch": 3.0657698056801195, "percentage": 61.32, "elapsed_time": "0:39:41", "remaining_time": "0:25:02", "throughput": 7054.51, "total_tokens": 16801792} {"current_steps": 2052, "total_steps": 3345, "loss": 0.2942, "lr": 8.138448283743209e-07, "epoch": 3.0672645739910314, "percentage": 61.35, "elapsed_time": "0:39:42", "remaining_time": "0:25:01", "throughput": 7054.53, "total_tokens": 16809984} {"current_steps": 2053, "total_steps": 3345, "loss": 0.097, "lr": 8.127448166329799e-07, "epoch": 3.0687593423019432, "percentage": 61.38, "elapsed_time": "0:39:44", "remaining_time": "0:25:00", "throughput": 7054.54, "total_tokens": 16818176} {"current_steps": 2054, "total_steps": 3345, "loss": 0.4703, "lr": 8.116451905852415e-07, "epoch": 3.070254110612855, "percentage": 61.41, "elapsed_time": "0:39:45", "remaining_time": "0:24:59", "throughput": 7054.53, "total_tokens": 16826368} {"current_steps": 2055, "total_steps": 3345, "loss": 0.2539, "lr": 8.105459512010629e-07, "epoch": 3.071748878923767, "percentage": 61.43, "elapsed_time": "0:39:46", "remaining_time": "0:24:57", "throughput": 7054.54, "total_tokens": 16834560} {"current_steps": 2056, "total_steps": 3345, "loss": 0.1965, "lr": 8.094470994500603e-07, "epoch": 3.0732436472346785, "percentage": 61.46, "elapsed_time": "0:39:47", "remaining_time": "0:24:56", "throughput": 7054.55, "total_tokens": 16842752} {"current_steps": 2057, "total_steps": 3345, "loss": 0.31, "lr": 8.083486363015075e-07, "epoch": 3.0747384155455904, "percentage": 61.49, "elapsed_time": "0:39:48", "remaining_time": "0:24:55", "throughput": 7054.55, "total_tokens": 16850944} {"current_steps": 2058, "total_steps": 3345, "loss": 0.3882, "lr": 8.07250562724336e-07, "epoch": 3.0762331838565022, "percentage": 61.52, "elapsed_time": "0:39:49", "remaining_time": "0:24:54", "throughput": 7054.55, "total_tokens": 16859136} {"current_steps": 2059, "total_steps": 3345, "loss": 0.4624, "lr": 8.061528796871332e-07, "epoch": 3.077727952167414, "percentage": 61.55, "elapsed_time": "0:39:50", "remaining_time": "0:24:53", "throughput": 7054.57, "total_tokens": 16867328} {"current_steps": 2060, "total_steps": 3345, "loss": 0.3514, "lr": 8.050555881581421e-07, "epoch": 3.079222720478326, "percentage": 61.58, "elapsed_time": "0:39:52", "remaining_time": "0:24:52", "throughput": 7054.58, "total_tokens": 16875520} {"current_steps": 2061, "total_steps": 3345, "loss": 0.1653, "lr": 8.039586891052607e-07, "epoch": 3.0807174887892375, "percentage": 61.61, "elapsed_time": "0:39:53", "remaining_time": "0:24:51", "throughput": 7054.6, "total_tokens": 16883712} {"current_steps": 2062, "total_steps": 3345, "loss": 0.2082, "lr": 8.028621834960404e-07, "epoch": 3.0822122571001493, "percentage": 61.64, "elapsed_time": "0:39:54", "remaining_time": "0:24:49", "throughput": 7054.61, "total_tokens": 16891904} {"current_steps": 2063, "total_steps": 3345, "loss": 0.3103, "lr": 8.017660722976859e-07, "epoch": 3.0837070254110612, "percentage": 61.67, "elapsed_time": "0:39:55", "remaining_time": "0:24:48", "throughput": 7054.62, "total_tokens": 16900096} {"current_steps": 2064, "total_steps": 3345, "loss": 0.1816, "lr": 8.006703564770537e-07, "epoch": 3.085201793721973, "percentage": 61.7, "elapsed_time": "0:39:56", "remaining_time": "0:24:47", "throughput": 7054.63, "total_tokens": 16908288} {"current_steps": 2065, "total_steps": 3345, "loss": 0.4153, "lr": 7.995750370006516e-07, "epoch": 3.086696562032885, "percentage": 61.73, "elapsed_time": "0:39:57", "remaining_time": "0:24:46", "throughput": 7054.64, "total_tokens": 16916480} {"current_steps": 2066, "total_steps": 3345, "loss": 0.1817, "lr": 7.984801148346386e-07, "epoch": 3.088191330343797, "percentage": 61.76, "elapsed_time": "0:39:59", "remaining_time": "0:24:45", "throughput": 7054.65, "total_tokens": 16924672} {"current_steps": 2067, "total_steps": 3345, "loss": 0.4409, "lr": 7.973855909448216e-07, "epoch": 3.0896860986547083, "percentage": 61.79, "elapsed_time": "0:40:00", "remaining_time": "0:24:44", "throughput": 7054.67, "total_tokens": 16932864} {"current_steps": 2068, "total_steps": 3345, "loss": 0.3415, "lr": 7.962914662966578e-07, "epoch": 3.09118086696562, "percentage": 61.82, "elapsed_time": "0:40:01", "remaining_time": "0:24:42", "throughput": 7054.69, "total_tokens": 16941056} {"current_steps": 2069, "total_steps": 3345, "loss": 0.1533, "lr": 7.951977418552512e-07, "epoch": 3.092675635276532, "percentage": 61.85, "elapsed_time": "0:40:02", "remaining_time": "0:24:41", "throughput": 7054.71, "total_tokens": 16949248} {"current_steps": 2070, "total_steps": 3345, "loss": 0.2987, "lr": 7.94104418585353e-07, "epoch": 3.094170403587444, "percentage": 61.88, "elapsed_time": "0:40:03", "remaining_time": "0:24:40", "throughput": 7054.73, "total_tokens": 16957440} {"current_steps": 2071, "total_steps": 3345, "loss": 0.3147, "lr": 7.930114974513612e-07, "epoch": 3.095665171898356, "percentage": 61.91, "elapsed_time": "0:40:04", "remaining_time": "0:24:39", "throughput": 7054.73, "total_tokens": 16965632} {"current_steps": 2072, "total_steps": 3345, "loss": 0.5797, "lr": 7.919189794173177e-07, "epoch": 3.0971599402092678, "percentage": 61.94, "elapsed_time": "0:40:06", "remaining_time": "0:24:38", "throughput": 7054.75, "total_tokens": 16973824} {"current_steps": 2073, "total_steps": 3345, "loss": 0.1426, "lr": 7.908268654469103e-07, "epoch": 3.098654708520179, "percentage": 61.97, "elapsed_time": "0:40:07", "remaining_time": "0:24:37", "throughput": 7054.76, "total_tokens": 16982016} {"current_steps": 2074, "total_steps": 3345, "loss": 0.069, "lr": 7.897351565034697e-07, "epoch": 3.100149476831091, "percentage": 62.0, "elapsed_time": "0:40:08", "remaining_time": "0:24:35", "throughput": 7054.78, "total_tokens": 16990208} {"current_steps": 2075, "total_steps": 3345, "loss": 0.232, "lr": 7.886438535499694e-07, "epoch": 3.101644245142003, "percentage": 62.03, "elapsed_time": "0:40:09", "remaining_time": "0:24:34", "throughput": 7054.8, "total_tokens": 16998400} {"current_steps": 2076, "total_steps": 3345, "loss": 0.2007, "lr": 7.875529575490249e-07, "epoch": 3.103139013452915, "percentage": 62.06, "elapsed_time": "0:40:10", "remaining_time": "0:24:33", "throughput": 7054.82, "total_tokens": 17006592} {"current_steps": 2077, "total_steps": 3345, "loss": 0.173, "lr": 7.864624694628922e-07, "epoch": 3.1046337817638268, "percentage": 62.09, "elapsed_time": "0:40:11", "remaining_time": "0:24:32", "throughput": 7054.83, "total_tokens": 17014784} {"current_steps": 2078, "total_steps": 3345, "loss": 0.3707, "lr": 7.853723902534682e-07, "epoch": 3.106128550074738, "percentage": 62.12, "elapsed_time": "0:40:12", "remaining_time": "0:24:31", "throughput": 7054.85, "total_tokens": 17022976} {"current_steps": 2079, "total_steps": 3345, "loss": 0.3174, "lr": 7.842827208822887e-07, "epoch": 3.10762331838565, "percentage": 62.15, "elapsed_time": "0:40:14", "remaining_time": "0:24:30", "throughput": 7054.86, "total_tokens": 17031168} {"current_steps": 2080, "total_steps": 3345, "loss": 0.1649, "lr": 7.831934623105284e-07, "epoch": 3.109118086696562, "percentage": 62.18, "elapsed_time": "0:40:15", "remaining_time": "0:24:28", "throughput": 7054.87, "total_tokens": 17039360} {"current_steps": 2081, "total_steps": 3345, "loss": 0.0923, "lr": 7.821046154989987e-07, "epoch": 3.110612855007474, "percentage": 62.21, "elapsed_time": "0:40:16", "remaining_time": "0:24:27", "throughput": 7054.88, "total_tokens": 17047552} {"current_steps": 2082, "total_steps": 3345, "loss": 0.351, "lr": 7.810161814081494e-07, "epoch": 3.1121076233183858, "percentage": 62.24, "elapsed_time": "0:40:17", "remaining_time": "0:24:26", "throughput": 7054.89, "total_tokens": 17055744} {"current_steps": 2083, "total_steps": 3345, "loss": 0.1873, "lr": 7.799281609980652e-07, "epoch": 3.1136023916292976, "percentage": 62.27, "elapsed_time": "0:40:18", "remaining_time": "0:24:25", "throughput": 7054.9, "total_tokens": 17063936} {"current_steps": 2084, "total_steps": 3345, "loss": 0.3822, "lr": 7.788405552284655e-07, "epoch": 3.115097159940209, "percentage": 62.3, "elapsed_time": "0:40:19", "remaining_time": "0:24:24", "throughput": 7054.91, "total_tokens": 17072128} {"current_steps": 2085, "total_steps": 3345, "loss": 0.1963, "lr": 7.77753365058705e-07, "epoch": 3.116591928251121, "percentage": 62.33, "elapsed_time": "0:40:21", "remaining_time": "0:24:23", "throughput": 7054.91, "total_tokens": 17080320} {"current_steps": 2086, "total_steps": 3345, "loss": 0.063, "lr": 7.76666591447771e-07, "epoch": 3.118086696562033, "percentage": 62.36, "elapsed_time": "0:40:22", "remaining_time": "0:24:21", "throughput": 7054.93, "total_tokens": 17088512} {"current_steps": 2087, "total_steps": 3345, "loss": 0.1452, "lr": 7.755802353542835e-07, "epoch": 3.1195814648729447, "percentage": 62.39, "elapsed_time": "0:40:23", "remaining_time": "0:24:20", "throughput": 7054.94, "total_tokens": 17096704} {"current_steps": 2088, "total_steps": 3345, "loss": 0.4699, "lr": 7.744942977364944e-07, "epoch": 3.1210762331838566, "percentage": 62.42, "elapsed_time": "0:40:24", "remaining_time": "0:24:19", "throughput": 7054.95, "total_tokens": 17104896} {"current_steps": 2089, "total_steps": 3345, "loss": 0.31, "lr": 7.734087795522869e-07, "epoch": 3.1225710014947685, "percentage": 62.45, "elapsed_time": "0:40:25", "remaining_time": "0:24:18", "throughput": 7054.95, "total_tokens": 17113088} {"current_steps": 2090, "total_steps": 3345, "loss": 0.1837, "lr": 7.723236817591734e-07, "epoch": 3.12406576980568, "percentage": 62.48, "elapsed_time": "0:40:26", "remaining_time": "0:24:17", "throughput": 7054.95, "total_tokens": 17121280} {"current_steps": 2091, "total_steps": 3345, "loss": 0.3978, "lr": 7.71239005314296e-07, "epoch": 3.125560538116592, "percentage": 62.51, "elapsed_time": "0:40:28", "remaining_time": "0:24:16", "throughput": 7054.97, "total_tokens": 17129472} {"current_steps": 2092, "total_steps": 3345, "loss": 0.2338, "lr": 7.701547511744247e-07, "epoch": 3.1270553064275037, "percentage": 62.54, "elapsed_time": "0:40:29", "remaining_time": "0:24:14", "throughput": 7054.98, "total_tokens": 17137664} {"current_steps": 2093, "total_steps": 3345, "loss": 0.2988, "lr": 7.690709202959576e-07, "epoch": 3.1285500747384156, "percentage": 62.57, "elapsed_time": "0:40:30", "remaining_time": "0:24:13", "throughput": 7054.98, "total_tokens": 17145856} {"current_steps": 2094, "total_steps": 3345, "loss": 0.3614, "lr": 7.679875136349188e-07, "epoch": 3.1300448430493275, "percentage": 62.6, "elapsed_time": "0:40:31", "remaining_time": "0:24:12", "throughput": 7055.0, "total_tokens": 17154048} {"current_steps": 2095, "total_steps": 3345, "loss": 0.2978, "lr": 7.669045321469586e-07, "epoch": 3.131539611360239, "percentage": 62.63, "elapsed_time": "0:40:32", "remaining_time": "0:24:11", "throughput": 7055.01, "total_tokens": 17162240} {"current_steps": 2096, "total_steps": 3345, "loss": 0.4086, "lr": 7.658219767873526e-07, "epoch": 3.133034379671151, "percentage": 62.66, "elapsed_time": "0:40:33", "remaining_time": "0:24:10", "throughput": 7055.03, "total_tokens": 17170432} {"current_steps": 2097, "total_steps": 3345, "loss": 0.3845, "lr": 7.647398485109994e-07, "epoch": 3.1345291479820627, "percentage": 62.69, "elapsed_time": "0:40:34", "remaining_time": "0:24:09", "throughput": 7055.04, "total_tokens": 17178624} {"current_steps": 2098, "total_steps": 3345, "loss": 0.1777, "lr": 7.636581482724223e-07, "epoch": 3.1360239162929746, "percentage": 62.72, "elapsed_time": "0:40:36", "remaining_time": "0:24:07", "throughput": 7055.06, "total_tokens": 17186816} {"current_steps": 2099, "total_steps": 3345, "loss": 0.2143, "lr": 7.625768770257661e-07, "epoch": 3.1375186846038865, "percentage": 62.75, "elapsed_time": "0:40:37", "remaining_time": "0:24:06", "throughput": 7055.07, "total_tokens": 17195008} {"current_steps": 2100, "total_steps": 3345, "loss": 0.3779, "lr": 7.614960357247975e-07, "epoch": 3.1390134529147984, "percentage": 62.78, "elapsed_time": "0:40:38", "remaining_time": "0:24:05", "throughput": 7055.08, "total_tokens": 17203200} {"current_steps": 2101, "total_steps": 3345, "loss": 0.2399, "lr": 7.604156253229038e-07, "epoch": 3.14050822122571, "percentage": 62.81, "elapsed_time": "0:40:39", "remaining_time": "0:24:04", "throughput": 7055.09, "total_tokens": 17211392} {"current_steps": 2102, "total_steps": 3345, "loss": 0.331, "lr": 7.593356467730923e-07, "epoch": 3.1420029895366217, "percentage": 62.84, "elapsed_time": "0:40:40", "remaining_time": "0:24:03", "throughput": 7055.1, "total_tokens": 17219584} {"current_steps": 2103, "total_steps": 3345, "loss": 0.4358, "lr": 7.582561010279893e-07, "epoch": 3.1434977578475336, "percentage": 62.87, "elapsed_time": "0:40:41", "remaining_time": "0:24:02", "throughput": 7055.1, "total_tokens": 17227776} {"current_steps": 2104, "total_steps": 3345, "loss": 0.3985, "lr": 7.571769890398393e-07, "epoch": 3.1449925261584455, "percentage": 62.9, "elapsed_time": "0:40:43", "remaining_time": "0:24:00", "throughput": 7055.1, "total_tokens": 17235968} {"current_steps": 2105, "total_steps": 3345, "loss": 0.3126, "lr": 7.560983117605045e-07, "epoch": 3.1464872944693574, "percentage": 62.93, "elapsed_time": "0:40:44", "remaining_time": "0:23:59", "throughput": 7055.11, "total_tokens": 17244160} {"current_steps": 2106, "total_steps": 3345, "loss": 0.4691, "lr": 7.550200701414634e-07, "epoch": 3.1479820627802693, "percentage": 62.96, "elapsed_time": "0:40:45", "remaining_time": "0:23:58", "throughput": 7055.12, "total_tokens": 17252352} {"current_steps": 2107, "total_steps": 3345, "loss": 0.3746, "lr": 7.539422651338105e-07, "epoch": 3.1494768310911807, "percentage": 62.99, "elapsed_time": "0:40:46", "remaining_time": "0:23:57", "throughput": 7055.13, "total_tokens": 17260544} {"current_steps": 2108, "total_steps": 3345, "loss": 0.4273, "lr": 7.528648976882544e-07, "epoch": 3.1509715994020926, "percentage": 63.02, "elapsed_time": "0:40:47", "remaining_time": "0:23:56", "throughput": 7055.14, "total_tokens": 17268736} {"current_steps": 2109, "total_steps": 3345, "loss": 0.2034, "lr": 7.517879687551187e-07, "epoch": 3.1524663677130045, "percentage": 63.05, "elapsed_time": "0:40:48", "remaining_time": "0:23:55", "throughput": 7055.16, "total_tokens": 17276928} {"current_steps": 2110, "total_steps": 3345, "loss": 0.1586, "lr": 7.507114792843395e-07, "epoch": 3.1539611360239164, "percentage": 63.08, "elapsed_time": "0:40:49", "remaining_time": "0:23:54", "throughput": 7055.15, "total_tokens": 17285120} {"current_steps": 2111, "total_steps": 3345, "loss": 0.1071, "lr": 7.496354302254656e-07, "epoch": 3.1554559043348283, "percentage": 63.11, "elapsed_time": "0:40:51", "remaining_time": "0:23:52", "throughput": 7055.16, "total_tokens": 17293312} {"current_steps": 2112, "total_steps": 3345, "loss": 0.4141, "lr": 7.485598225276574e-07, "epoch": 3.15695067264574, "percentage": 63.14, "elapsed_time": "0:40:52", "remaining_time": "0:23:51", "throughput": 7055.17, "total_tokens": 17301504} {"current_steps": 2113, "total_steps": 3345, "loss": 0.3831, "lr": 7.474846571396859e-07, "epoch": 3.1584454409566516, "percentage": 63.17, "elapsed_time": "0:40:53", "remaining_time": "0:23:50", "throughput": 7055.18, "total_tokens": 17309696} {"current_steps": 2114, "total_steps": 3345, "loss": 0.2828, "lr": 7.46409935009931e-07, "epoch": 3.1599402092675635, "percentage": 63.2, "elapsed_time": "0:40:54", "remaining_time": "0:23:49", "throughput": 7055.19, "total_tokens": 17317888} {"current_steps": 2115, "total_steps": 3345, "loss": 0.442, "lr": 7.453356570863839e-07, "epoch": 3.1614349775784754, "percentage": 63.23, "elapsed_time": "0:40:55", "remaining_time": "0:23:48", "throughput": 7055.2, "total_tokens": 17326080} {"current_steps": 2116, "total_steps": 3345, "loss": 0.2262, "lr": 7.442618243166418e-07, "epoch": 3.1629297458893872, "percentage": 63.26, "elapsed_time": "0:40:56", "remaining_time": "0:23:47", "throughput": 7055.21, "total_tokens": 17334272} {"current_steps": 2117, "total_steps": 3345, "loss": 0.4382, "lr": 7.431884376479099e-07, "epoch": 3.164424514200299, "percentage": 63.29, "elapsed_time": "0:40:58", "remaining_time": "0:23:45", "throughput": 7055.21, "total_tokens": 17342464} {"current_steps": 2118, "total_steps": 3345, "loss": 0.3231, "lr": 7.421154980270004e-07, "epoch": 3.1659192825112106, "percentage": 63.32, "elapsed_time": "0:40:59", "remaining_time": "0:23:44", "throughput": 7055.22, "total_tokens": 17350656} {"current_steps": 2119, "total_steps": 3345, "loss": 0.0988, "lr": 7.410430064003305e-07, "epoch": 3.1674140508221225, "percentage": 63.35, "elapsed_time": "0:41:00", "remaining_time": "0:23:43", "throughput": 7055.23, "total_tokens": 17358848} {"current_steps": 2120, "total_steps": 3345, "loss": 0.2827, "lr": 7.399709637139227e-07, "epoch": 3.1689088191330343, "percentage": 63.38, "elapsed_time": "0:41:01", "remaining_time": "0:23:42", "throughput": 7055.24, "total_tokens": 17367040} {"current_steps": 2121, "total_steps": 3345, "loss": 0.2933, "lr": 7.388993709134026e-07, "epoch": 3.1704035874439462, "percentage": 63.41, "elapsed_time": "0:41:02", "remaining_time": "0:23:41", "throughput": 7055.25, "total_tokens": 17375232} {"current_steps": 2122, "total_steps": 3345, "loss": 0.2231, "lr": 7.378282289440008e-07, "epoch": 3.171898355754858, "percentage": 63.44, "elapsed_time": "0:41:03", "remaining_time": "0:23:40", "throughput": 7055.26, "total_tokens": 17383424} {"current_steps": 2123, "total_steps": 3345, "loss": 0.5547, "lr": 7.367575387505485e-07, "epoch": 3.17339312406577, "percentage": 63.47, "elapsed_time": "0:41:05", "remaining_time": "0:23:38", "throughput": 7055.26, "total_tokens": 17391616} {"current_steps": 2124, "total_steps": 3345, "loss": 0.4941, "lr": 7.35687301277479e-07, "epoch": 3.1748878923766815, "percentage": 63.5, "elapsed_time": "0:41:06", "remaining_time": "0:23:37", "throughput": 7055.26, "total_tokens": 17399808} {"current_steps": 2125, "total_steps": 3345, "loss": 0.4419, "lr": 7.346175174688265e-07, "epoch": 3.1763826606875933, "percentage": 63.53, "elapsed_time": "0:41:07", "remaining_time": "0:23:36", "throughput": 7055.28, "total_tokens": 17408000} {"current_steps": 2126, "total_steps": 3345, "loss": 0.3811, "lr": 7.335481882682247e-07, "epoch": 3.1778774289985052, "percentage": 63.56, "elapsed_time": "0:41:08", "remaining_time": "0:23:35", "throughput": 7055.29, "total_tokens": 17416192} {"current_steps": 2127, "total_steps": 3345, "loss": 0.2898, "lr": 7.32479314618906e-07, "epoch": 3.179372197309417, "percentage": 63.59, "elapsed_time": "0:41:09", "remaining_time": "0:23:34", "throughput": 7055.29, "total_tokens": 17424384} {"current_steps": 2128, "total_steps": 3345, "loss": 0.3118, "lr": 7.314108974637019e-07, "epoch": 3.180866965620329, "percentage": 63.62, "elapsed_time": "0:41:10", "remaining_time": "0:23:33", "throughput": 7055.31, "total_tokens": 17432576} {"current_steps": 2129, "total_steps": 3345, "loss": 0.1635, "lr": 7.303429377450405e-07, "epoch": 3.1823617339312404, "percentage": 63.65, "elapsed_time": "0:41:12", "remaining_time": "0:23:31", "throughput": 7055.31, "total_tokens": 17440768} {"current_steps": 2130, "total_steps": 3345, "loss": 0.4591, "lr": 7.292754364049467e-07, "epoch": 3.1838565022421523, "percentage": 63.68, "elapsed_time": "0:41:13", "remaining_time": "0:23:30", "throughput": 7055.32, "total_tokens": 17448960} {"current_steps": 2131, "total_steps": 3345, "loss": 0.4335, "lr": 7.282083943850407e-07, "epoch": 3.185351270553064, "percentage": 63.71, "elapsed_time": "0:41:14", "remaining_time": "0:23:29", "throughput": 7055.33, "total_tokens": 17457152} {"current_steps": 2132, "total_steps": 3345, "loss": 0.124, "lr": 7.271418126265381e-07, "epoch": 3.186846038863976, "percentage": 63.74, "elapsed_time": "0:41:15", "remaining_time": "0:23:28", "throughput": 7055.32, "total_tokens": 17465344} {"current_steps": 2133, "total_steps": 3345, "loss": 0.4375, "lr": 7.260756920702486e-07, "epoch": 3.188340807174888, "percentage": 63.77, "elapsed_time": "0:41:16", "remaining_time": "0:23:27", "throughput": 7055.32, "total_tokens": 17473536} {"current_steps": 2134, "total_steps": 3345, "loss": 0.1004, "lr": 7.250100336565738e-07, "epoch": 3.1898355754858, "percentage": 63.8, "elapsed_time": "0:41:17", "remaining_time": "0:23:26", "throughput": 7055.33, "total_tokens": 17481728} {"current_steps": 2135, "total_steps": 3345, "loss": 0.3189, "lr": 7.239448383255093e-07, "epoch": 3.1913303437967113, "percentage": 63.83, "elapsed_time": "0:41:18", "remaining_time": "0:23:24", "throughput": 7055.33, "total_tokens": 17489920} {"current_steps": 2136, "total_steps": 3345, "loss": 0.2443, "lr": 7.228801070166416e-07, "epoch": 3.192825112107623, "percentage": 63.86, "elapsed_time": "0:41:20", "remaining_time": "0:23:23", "throughput": 7055.34, "total_tokens": 17498112} {"current_steps": 2137, "total_steps": 3345, "loss": 0.3037, "lr": 7.218158406691472e-07, "epoch": 3.194319880418535, "percentage": 63.89, "elapsed_time": "0:41:21", "remaining_time": "0:23:22", "throughput": 7055.35, "total_tokens": 17506304} {"current_steps": 2138, "total_steps": 3345, "loss": 0.1847, "lr": 7.207520402217937e-07, "epoch": 3.195814648729447, "percentage": 63.92, "elapsed_time": "0:41:22", "remaining_time": "0:23:21", "throughput": 7055.36, "total_tokens": 17514496} {"current_steps": 2139, "total_steps": 3345, "loss": 0.2617, "lr": 7.196887066129363e-07, "epoch": 3.197309417040359, "percentage": 63.95, "elapsed_time": "0:41:23", "remaining_time": "0:23:20", "throughput": 7055.36, "total_tokens": 17522688} {"current_steps": 2140, "total_steps": 3345, "loss": 0.409, "lr": 7.186258407805202e-07, "epoch": 3.1988041853512708, "percentage": 63.98, "elapsed_time": "0:41:24", "remaining_time": "0:23:19", "throughput": 7055.37, "total_tokens": 17530880} {"current_steps": 2141, "total_steps": 3345, "loss": 0.3528, "lr": 7.17563443662076e-07, "epoch": 3.200298953662182, "percentage": 64.01, "elapsed_time": "0:41:25", "remaining_time": "0:23:17", "throughput": 7055.37, "total_tokens": 17539072} {"current_steps": 2142, "total_steps": 3345, "loss": 0.3358, "lr": 7.165015161947224e-07, "epoch": 3.201793721973094, "percentage": 64.04, "elapsed_time": "0:41:27", "remaining_time": "0:23:16", "throughput": 7055.37, "total_tokens": 17547264} {"current_steps": 2143, "total_steps": 3345, "loss": 0.1921, "lr": 7.154400593151636e-07, "epoch": 3.203288490284006, "percentage": 64.07, "elapsed_time": "0:41:28", "remaining_time": "0:23:15", "throughput": 7055.38, "total_tokens": 17555456} {"current_steps": 2144, "total_steps": 3345, "loss": 0.3416, "lr": 7.143790739596877e-07, "epoch": 3.204783258594918, "percentage": 64.1, "elapsed_time": "0:41:29", "remaining_time": "0:23:14", "throughput": 7055.38, "total_tokens": 17563648} {"current_steps": 2145, "total_steps": 3345, "loss": 0.1991, "lr": 7.133185610641684e-07, "epoch": 3.2062780269058297, "percentage": 64.13, "elapsed_time": "0:41:30", "remaining_time": "0:23:13", "throughput": 7055.38, "total_tokens": 17571840} {"current_steps": 2146, "total_steps": 3345, "loss": 0.0518, "lr": 7.122585215640607e-07, "epoch": 3.2077727952167416, "percentage": 64.16, "elapsed_time": "0:41:31", "remaining_time": "0:23:12", "throughput": 7055.39, "total_tokens": 17580032} {"current_steps": 2147, "total_steps": 3345, "loss": 0.3131, "lr": 7.111989563944044e-07, "epoch": 3.209267563527653, "percentage": 64.19, "elapsed_time": "0:41:32", "remaining_time": "0:23:10", "throughput": 7055.39, "total_tokens": 17588224} {"current_steps": 2148, "total_steps": 3345, "loss": 0.2437, "lr": 7.101398664898179e-07, "epoch": 3.210762331838565, "percentage": 64.22, "elapsed_time": "0:41:34", "remaining_time": "0:23:09", "throughput": 7055.39, "total_tokens": 17596416} {"current_steps": 2149, "total_steps": 3345, "loss": 0.3286, "lr": 7.090812527845045e-07, "epoch": 3.212257100149477, "percentage": 64.25, "elapsed_time": "0:41:35", "remaining_time": "0:23:08", "throughput": 7055.4, "total_tokens": 17604608} {"current_steps": 2150, "total_steps": 3345, "loss": 0.4189, "lr": 7.080231162122432e-07, "epoch": 3.2137518684603887, "percentage": 64.28, "elapsed_time": "0:41:36", "remaining_time": "0:23:07", "throughput": 7055.4, "total_tokens": 17612800} {"current_steps": 2151, "total_steps": 3345, "loss": 0.3812, "lr": 7.069654577063948e-07, "epoch": 3.2152466367713006, "percentage": 64.3, "elapsed_time": "0:41:37", "remaining_time": "0:23:06", "throughput": 7055.41, "total_tokens": 17620992} {"current_steps": 2152, "total_steps": 3345, "loss": 0.2473, "lr": 7.05908278199898e-07, "epoch": 3.216741405082212, "percentage": 64.33, "elapsed_time": "0:41:38", "remaining_time": "0:23:05", "throughput": 7055.41, "total_tokens": 17629184} {"current_steps": 2153, "total_steps": 3345, "loss": 0.1957, "lr": 7.048515786252675e-07, "epoch": 3.218236173393124, "percentage": 64.36, "elapsed_time": "0:41:39", "remaining_time": "0:23:04", "throughput": 7055.41, "total_tokens": 17637376} {"current_steps": 2154, "total_steps": 3345, "loss": 0.301, "lr": 7.037953599145969e-07, "epoch": 3.219730941704036, "percentage": 64.39, "elapsed_time": "0:41:40", "remaining_time": "0:23:02", "throughput": 7055.42, "total_tokens": 17645568} {"current_steps": 2155, "total_steps": 3345, "loss": 0.3629, "lr": 7.027396229995536e-07, "epoch": 3.2212257100149477, "percentage": 64.42, "elapsed_time": "0:41:42", "remaining_time": "0:23:01", "throughput": 7055.44, "total_tokens": 17653760} {"current_steps": 2156, "total_steps": 3345, "loss": 0.3998, "lr": 7.01684368811382e-07, "epoch": 3.2227204783258596, "percentage": 64.45, "elapsed_time": "0:41:43", "remaining_time": "0:23:00", "throughput": 7055.45, "total_tokens": 17661952} {"current_steps": 2157, "total_steps": 3345, "loss": 0.2081, "lr": 7.006295982808982e-07, "epoch": 3.2242152466367715, "percentage": 64.48, "elapsed_time": "0:41:44", "remaining_time": "0:22:59", "throughput": 7055.45, "total_tokens": 17670144} {"current_steps": 2158, "total_steps": 3345, "loss": 0.3006, "lr": 6.995753123384941e-07, "epoch": 3.225710014947683, "percentage": 64.51, "elapsed_time": "0:41:45", "remaining_time": "0:22:58", "throughput": 7055.46, "total_tokens": 17678336} {"current_steps": 2159, "total_steps": 3345, "loss": 0.3467, "lr": 6.985215119141334e-07, "epoch": 3.227204783258595, "percentage": 64.54, "elapsed_time": "0:41:46", "remaining_time": "0:22:57", "throughput": 7055.47, "total_tokens": 17686528} {"current_steps": 2160, "total_steps": 3345, "loss": 0.2258, "lr": 6.974681979373502e-07, "epoch": 3.2286995515695067, "percentage": 64.57, "elapsed_time": "0:41:47", "remaining_time": "0:22:55", "throughput": 7055.47, "total_tokens": 17694720} {"current_steps": 2161, "total_steps": 3345, "loss": 0.4466, "lr": 6.964153713372518e-07, "epoch": 3.2301943198804186, "percentage": 64.6, "elapsed_time": "0:41:49", "remaining_time": "0:22:54", "throughput": 7055.47, "total_tokens": 17702912} {"current_steps": 2162, "total_steps": 3345, "loss": 0.2511, "lr": 6.953630330425134e-07, "epoch": 3.2316890881913305, "percentage": 64.63, "elapsed_time": "0:41:50", "remaining_time": "0:22:53", "throughput": 7055.47, "total_tokens": 17711104} {"current_steps": 2163, "total_steps": 3345, "loss": 0.4445, "lr": 6.943111839813816e-07, "epoch": 3.233183856502242, "percentage": 64.66, "elapsed_time": "0:41:51", "remaining_time": "0:22:52", "throughput": 7055.45, "total_tokens": 17719296} {"current_steps": 2164, "total_steps": 3345, "loss": 0.4841, "lr": 6.932598250816689e-07, "epoch": 3.234678624813154, "percentage": 64.69, "elapsed_time": "0:41:52", "remaining_time": "0:22:51", "throughput": 7055.45, "total_tokens": 17727488} {"current_steps": 2165, "total_steps": 3345, "loss": 0.2196, "lr": 6.922089572707579e-07, "epoch": 3.2361733931240657, "percentage": 64.72, "elapsed_time": "0:41:53", "remaining_time": "0:22:50", "throughput": 7055.35, "total_tokens": 17735680} {"current_steps": 2166, "total_steps": 3345, "loss": 0.3487, "lr": 6.911585814755967e-07, "epoch": 3.2376681614349776, "percentage": 64.75, "elapsed_time": "0:41:55", "remaining_time": "0:22:48", "throughput": 7055.19, "total_tokens": 17743872} {"current_steps": 2167, "total_steps": 3345, "loss": 0.3233, "lr": 6.901086986226996e-07, "epoch": 3.2391629297458895, "percentage": 64.78, "elapsed_time": "0:41:56", "remaining_time": "0:22:47", "throughput": 7055.01, "total_tokens": 17752064} {"current_steps": 2168, "total_steps": 3345, "loss": 0.1316, "lr": 6.890593096381469e-07, "epoch": 3.2406576980568014, "percentage": 64.81, "elapsed_time": "0:41:57", "remaining_time": "0:22:46", "throughput": 7054.82, "total_tokens": 17760256} {"current_steps": 2169, "total_steps": 3345, "loss": 0.2986, "lr": 6.880104154475816e-07, "epoch": 3.242152466367713, "percentage": 64.84, "elapsed_time": "0:41:58", "remaining_time": "0:22:45", "throughput": 7054.67, "total_tokens": 17768448} {"current_steps": 2170, "total_steps": 3345, "loss": 0.1974, "lr": 6.86962016976212e-07, "epoch": 3.2436472346786247, "percentage": 64.87, "elapsed_time": "0:41:59", "remaining_time": "0:22:44", "throughput": 7054.56, "total_tokens": 17776640} {"current_steps": 2171, "total_steps": 3345, "loss": 0.445, "lr": 6.859141151488076e-07, "epoch": 3.2451420029895366, "percentage": 64.9, "elapsed_time": "0:42:01", "remaining_time": "0:22:43", "throughput": 7054.45, "total_tokens": 17784832} {"current_steps": 2172, "total_steps": 3345, "loss": 0.171, "lr": 6.848667108897014e-07, "epoch": 3.2466367713004485, "percentage": 64.93, "elapsed_time": "0:42:02", "remaining_time": "0:22:42", "throughput": 7054.31, "total_tokens": 17793024} {"current_steps": 2173, "total_steps": 3345, "loss": 0.366, "lr": 6.838198051227857e-07, "epoch": 3.2481315396113604, "percentage": 64.96, "elapsed_time": "0:42:03", "remaining_time": "0:22:41", "throughput": 7054.14, "total_tokens": 17801216} {"current_steps": 2174, "total_steps": 3345, "loss": 0.4708, "lr": 6.827733987715145e-07, "epoch": 3.2496263079222723, "percentage": 64.99, "elapsed_time": "0:42:04", "remaining_time": "0:22:39", "throughput": 7054.05, "total_tokens": 17809408} {"current_steps": 2175, "total_steps": 3345, "loss": 0.4252, "lr": 6.817274927589015e-07, "epoch": 3.2511210762331837, "percentage": 65.02, "elapsed_time": "0:42:05", "remaining_time": "0:22:38", "throughput": 7053.98, "total_tokens": 17817600} {"current_steps": 2176, "total_steps": 3345, "loss": 0.3062, "lr": 6.806820880075171e-07, "epoch": 3.2526158445440956, "percentage": 65.05, "elapsed_time": "0:42:07", "remaining_time": "0:22:37", "throughput": 7053.94, "total_tokens": 17825792} {"current_steps": 2177, "total_steps": 3345, "loss": 0.4028, "lr": 6.796371854394922e-07, "epoch": 3.2541106128550075, "percentage": 65.08, "elapsed_time": "0:42:08", "remaining_time": "0:22:36", "throughput": 7053.91, "total_tokens": 17833984} {"current_steps": 2178, "total_steps": 3345, "loss": 0.3985, "lr": 6.785927859765122e-07, "epoch": 3.2556053811659194, "percentage": 65.11, "elapsed_time": "0:42:09", "remaining_time": "0:22:35", "throughput": 7053.89, "total_tokens": 17842176} {"current_steps": 2179, "total_steps": 3345, "loss": 0.1614, "lr": 6.775488905398211e-07, "epoch": 3.2571001494768312, "percentage": 65.14, "elapsed_time": "0:42:10", "remaining_time": "0:22:34", "throughput": 7053.87, "total_tokens": 17850368} {"current_steps": 2180, "total_steps": 3345, "loss": 0.5438, "lr": 6.765055000502158e-07, "epoch": 3.258594917787743, "percentage": 65.17, "elapsed_time": "0:42:11", "remaining_time": "0:22:32", "throughput": 7053.84, "total_tokens": 17858560} {"current_steps": 2181, "total_steps": 3345, "loss": 0.2921, "lr": 6.754626154280497e-07, "epoch": 3.2600896860986546, "percentage": 65.2, "elapsed_time": "0:42:12", "remaining_time": "0:22:31", "throughput": 7053.82, "total_tokens": 17866752} {"current_steps": 2182, "total_steps": 3345, "loss": 0.2295, "lr": 6.744202375932296e-07, "epoch": 3.2615844544095665, "percentage": 65.23, "elapsed_time": "0:42:14", "remaining_time": "0:22:30", "throughput": 7053.77, "total_tokens": 17874944} {"current_steps": 2183, "total_steps": 3345, "loss": 0.2383, "lr": 6.733783674652149e-07, "epoch": 3.2630792227204783, "percentage": 65.26, "elapsed_time": "0:42:15", "remaining_time": "0:22:29", "throughput": 7053.78, "total_tokens": 17883136} {"current_steps": 2184, "total_steps": 3345, "loss": 0.2258, "lr": 6.723370059630177e-07, "epoch": 3.2645739910313902, "percentage": 65.29, "elapsed_time": "0:42:16", "remaining_time": "0:22:28", "throughput": 7053.77, "total_tokens": 17891328} {"current_steps": 2185, "total_steps": 3345, "loss": 0.218, "lr": 6.712961540052004e-07, "epoch": 3.266068759342302, "percentage": 65.32, "elapsed_time": "0:42:17", "remaining_time": "0:22:27", "throughput": 7053.78, "total_tokens": 17899520} {"current_steps": 2186, "total_steps": 3345, "loss": 0.341, "lr": 6.702558125098776e-07, "epoch": 3.2675635276532136, "percentage": 65.35, "elapsed_time": "0:42:18", "remaining_time": "0:22:26", "throughput": 7053.77, "total_tokens": 17907712} {"current_steps": 2187, "total_steps": 3345, "loss": 0.2213, "lr": 6.692159823947115e-07, "epoch": 3.2690582959641254, "percentage": 65.38, "elapsed_time": "0:42:19", "remaining_time": "0:22:24", "throughput": 7053.76, "total_tokens": 17915904} {"current_steps": 2188, "total_steps": 3345, "loss": 0.2816, "lr": 6.681766645769153e-07, "epoch": 3.2705530642750373, "percentage": 65.41, "elapsed_time": "0:42:21", "remaining_time": "0:22:23", "throughput": 7053.76, "total_tokens": 17924096} {"current_steps": 2189, "total_steps": 3345, "loss": 0.2168, "lr": 6.671378599732484e-07, "epoch": 3.2720478325859492, "percentage": 65.44, "elapsed_time": "0:42:22", "remaining_time": "0:22:22", "throughput": 7053.75, "total_tokens": 17932288} {"current_steps": 2190, "total_steps": 3345, "loss": 0.3362, "lr": 6.660995695000191e-07, "epoch": 3.273542600896861, "percentage": 65.47, "elapsed_time": "0:42:23", "remaining_time": "0:22:21", "throughput": 7053.75, "total_tokens": 17940480} {"current_steps": 2191, "total_steps": 3345, "loss": 0.3435, "lr": 6.650617940730823e-07, "epoch": 3.275037369207773, "percentage": 65.5, "elapsed_time": "0:42:24", "remaining_time": "0:22:20", "throughput": 7053.75, "total_tokens": 17948672} {"current_steps": 2192, "total_steps": 3345, "loss": 0.3292, "lr": 6.640245346078366e-07, "epoch": 3.2765321375186844, "percentage": 65.53, "elapsed_time": "0:42:25", "remaining_time": "0:22:19", "throughput": 7053.73, "total_tokens": 17956864} {"current_steps": 2193, "total_steps": 3345, "loss": 0.3058, "lr": 6.629877920192279e-07, "epoch": 3.2780269058295963, "percentage": 65.56, "elapsed_time": "0:42:26", "remaining_time": "0:22:17", "throughput": 7053.72, "total_tokens": 17965056} {"current_steps": 2194, "total_steps": 3345, "loss": 0.3891, "lr": 6.619515672217438e-07, "epoch": 3.279521674140508, "percentage": 65.59, "elapsed_time": "0:42:28", "remaining_time": "0:22:16", "throughput": 7053.73, "total_tokens": 17973248} {"current_steps": 2195, "total_steps": 3345, "loss": 0.4595, "lr": 6.609158611294178e-07, "epoch": 3.28101644245142, "percentage": 65.62, "elapsed_time": "0:42:29", "remaining_time": "0:22:15", "throughput": 7053.72, "total_tokens": 17981440} {"current_steps": 2196, "total_steps": 3345, "loss": 0.2182, "lr": 6.598806746558231e-07, "epoch": 3.282511210762332, "percentage": 65.65, "elapsed_time": "0:42:30", "remaining_time": "0:22:14", "throughput": 7053.7, "total_tokens": 17989632} {"current_steps": 2197, "total_steps": 3345, "loss": 0.4506, "lr": 6.588460087140766e-07, "epoch": 3.2840059790732434, "percentage": 65.68, "elapsed_time": "0:42:31", "remaining_time": "0:22:13", "throughput": 7053.7, "total_tokens": 17997824} {"current_steps": 2198, "total_steps": 3345, "loss": 0.3301, "lr": 6.578118642168359e-07, "epoch": 3.2855007473841553, "percentage": 65.71, "elapsed_time": "0:42:32", "remaining_time": "0:22:12", "throughput": 7053.69, "total_tokens": 18006016} {"current_steps": 2199, "total_steps": 3345, "loss": 0.3811, "lr": 6.567782420762969e-07, "epoch": 3.286995515695067, "percentage": 65.74, "elapsed_time": "0:42:33", "remaining_time": "0:22:10", "throughput": 7053.69, "total_tokens": 18014208} {"current_steps": 2200, "total_steps": 3345, "loss": 0.3943, "lr": 6.557451432041969e-07, "epoch": 3.288490284005979, "percentage": 65.77, "elapsed_time": "0:42:35", "remaining_time": "0:22:09", "throughput": 7053.69, "total_tokens": 18022400} {"current_steps": 2201, "total_steps": 3345, "loss": 0.3436, "lr": 6.547125685118101e-07, "epoch": 3.289985052316891, "percentage": 65.8, "elapsed_time": "0:42:36", "remaining_time": "0:22:08", "throughput": 7053.68, "total_tokens": 18030592} {"current_steps": 2202, "total_steps": 3345, "loss": 0.2402, "lr": 6.536805189099499e-07, "epoch": 3.291479820627803, "percentage": 65.83, "elapsed_time": "0:42:37", "remaining_time": "0:22:07", "throughput": 7053.69, "total_tokens": 18038784} {"current_steps": 2203, "total_steps": 3345, "loss": 0.4097, "lr": 6.526489953089643e-07, "epoch": 3.2929745889387143, "percentage": 65.86, "elapsed_time": "0:42:38", "remaining_time": "0:22:06", "throughput": 7053.69, "total_tokens": 18046976} {"current_steps": 2204, "total_steps": 3345, "loss": 0.4184, "lr": 6.516179986187396e-07, "epoch": 3.294469357249626, "percentage": 65.89, "elapsed_time": "0:42:39", "remaining_time": "0:22:05", "throughput": 7053.69, "total_tokens": 18055168} {"current_steps": 2205, "total_steps": 3345, "loss": 0.3282, "lr": 6.505875297486955e-07, "epoch": 3.295964125560538, "percentage": 65.92, "elapsed_time": "0:42:40", "remaining_time": "0:22:03", "throughput": 7053.69, "total_tokens": 18063360} {"current_steps": 2206, "total_steps": 3345, "loss": 0.2127, "lr": 6.495575896077873e-07, "epoch": 3.29745889387145, "percentage": 65.95, "elapsed_time": "0:42:41", "remaining_time": "0:22:02", "throughput": 7053.7, "total_tokens": 18071552} {"current_steps": 2207, "total_steps": 3345, "loss": 0.3079, "lr": 6.485281791045039e-07, "epoch": 3.298953662182362, "percentage": 65.98, "elapsed_time": "0:42:43", "remaining_time": "0:22:01", "throughput": 7053.71, "total_tokens": 18079744} {"current_steps": 2208, "total_steps": 3345, "loss": 0.3425, "lr": 6.474992991468658e-07, "epoch": 3.3004484304932733, "percentage": 66.01, "elapsed_time": "0:42:44", "remaining_time": "0:22:00", "throughput": 7053.72, "total_tokens": 18087936} {"current_steps": 2209, "total_steps": 3345, "loss": 0.3907, "lr": 6.464709506424274e-07, "epoch": 3.301943198804185, "percentage": 66.04, "elapsed_time": "0:42:45", "remaining_time": "0:21:59", "throughput": 7053.72, "total_tokens": 18096128} {"current_steps": 2210, "total_steps": 3345, "loss": 0.5713, "lr": 6.454431344982723e-07, "epoch": 3.303437967115097, "percentage": 66.07, "elapsed_time": "0:42:46", "remaining_time": "0:21:58", "throughput": 7053.72, "total_tokens": 18104320} {"current_steps": 2211, "total_steps": 3345, "loss": 0.3512, "lr": 6.444158516210164e-07, "epoch": 3.304932735426009, "percentage": 66.1, "elapsed_time": "0:42:47", "remaining_time": "0:21:56", "throughput": 7053.72, "total_tokens": 18112512} {"current_steps": 2212, "total_steps": 3345, "loss": 0.1877, "lr": 6.433891029168033e-07, "epoch": 3.306427503736921, "percentage": 66.13, "elapsed_time": "0:42:48", "remaining_time": "0:21:55", "throughput": 7053.72, "total_tokens": 18120704} {"current_steps": 2213, "total_steps": 3345, "loss": 0.1531, "lr": 6.423628892913071e-07, "epoch": 3.3079222720478327, "percentage": 66.16, "elapsed_time": "0:42:50", "remaining_time": "0:21:54", "throughput": 7053.73, "total_tokens": 18128896} {"current_steps": 2214, "total_steps": 3345, "loss": 0.333, "lr": 6.413372116497296e-07, "epoch": 3.3094170403587446, "percentage": 66.19, "elapsed_time": "0:42:51", "remaining_time": "0:21:53", "throughput": 7053.74, "total_tokens": 18137088} {"current_steps": 2215, "total_steps": 3345, "loss": 0.4945, "lr": 6.403120708967988e-07, "epoch": 3.310911808669656, "percentage": 66.22, "elapsed_time": "0:42:52", "remaining_time": "0:21:52", "throughput": 7053.75, "total_tokens": 18145280} {"current_steps": 2216, "total_steps": 3345, "loss": 0.2485, "lr": 6.392874679367699e-07, "epoch": 3.312406576980568, "percentage": 66.25, "elapsed_time": "0:42:53", "remaining_time": "0:21:51", "throughput": 7053.76, "total_tokens": 18153472} {"current_steps": 2217, "total_steps": 3345, "loss": 0.2794, "lr": 6.382634036734238e-07, "epoch": 3.31390134529148, "percentage": 66.28, "elapsed_time": "0:42:54", "remaining_time": "0:21:50", "throughput": 7053.77, "total_tokens": 18161664} {"current_steps": 2218, "total_steps": 3345, "loss": 0.3651, "lr": 6.372398790100665e-07, "epoch": 3.3153961136023917, "percentage": 66.31, "elapsed_time": "0:42:55", "remaining_time": "0:21:48", "throughput": 7053.79, "total_tokens": 18169856} {"current_steps": 2219, "total_steps": 3345, "loss": 0.1978, "lr": 6.362168948495267e-07, "epoch": 3.3168908819133036, "percentage": 66.34, "elapsed_time": "0:42:57", "remaining_time": "0:21:47", "throughput": 7053.79, "total_tokens": 18178048} {"current_steps": 2220, "total_steps": 3345, "loss": 0.4391, "lr": 6.35194452094158e-07, "epoch": 3.318385650224215, "percentage": 66.37, "elapsed_time": "0:42:58", "remaining_time": "0:21:46", "throughput": 7053.8, "total_tokens": 18186240} {"current_steps": 2221, "total_steps": 3345, "loss": 0.3683, "lr": 6.341725516458349e-07, "epoch": 3.319880418535127, "percentage": 66.4, "elapsed_time": "0:42:59", "remaining_time": "0:21:45", "throughput": 7053.8, "total_tokens": 18194432} {"current_steps": 2222, "total_steps": 3345, "loss": 0.3545, "lr": 6.331511944059554e-07, "epoch": 3.321375186846039, "percentage": 66.43, "elapsed_time": "0:43:00", "remaining_time": "0:21:44", "throughput": 7053.8, "total_tokens": 18202624} {"current_steps": 2223, "total_steps": 3345, "loss": 0.2865, "lr": 6.321303812754359e-07, "epoch": 3.3228699551569507, "percentage": 66.46, "elapsed_time": "0:43:01", "remaining_time": "0:21:43", "throughput": 7053.79, "total_tokens": 18210816} {"current_steps": 2224, "total_steps": 3345, "loss": 0.4612, "lr": 6.311101131547148e-07, "epoch": 3.3243647234678626, "percentage": 66.49, "elapsed_time": "0:43:02", "remaining_time": "0:21:41", "throughput": 7053.77, "total_tokens": 18219008} {"current_steps": 2225, "total_steps": 3345, "loss": 0.3271, "lr": 6.300903909437497e-07, "epoch": 3.3258594917787745, "percentage": 66.52, "elapsed_time": "0:43:04", "remaining_time": "0:21:40", "throughput": 7053.78, "total_tokens": 18227200} {"current_steps": 2226, "total_steps": 3345, "loss": 0.3054, "lr": 6.29071215542015e-07, "epoch": 3.327354260089686, "percentage": 66.55, "elapsed_time": "0:43:05", "remaining_time": "0:21:39", "throughput": 7053.78, "total_tokens": 18235392} {"current_steps": 2227, "total_steps": 3345, "loss": 0.2042, "lr": 6.280525878485052e-07, "epoch": 3.328849028400598, "percentage": 66.58, "elapsed_time": "0:43:06", "remaining_time": "0:21:38", "throughput": 7053.79, "total_tokens": 18243584} {"current_steps": 2228, "total_steps": 3345, "loss": 0.214, "lr": 6.270345087617291e-07, "epoch": 3.3303437967115097, "percentage": 66.61, "elapsed_time": "0:43:07", "remaining_time": "0:21:37", "throughput": 7053.8, "total_tokens": 18251776} {"current_steps": 2229, "total_steps": 3345, "loss": 0.3119, "lr": 6.260169791797141e-07, "epoch": 3.3318385650224216, "percentage": 66.64, "elapsed_time": "0:43:08", "remaining_time": "0:21:36", "throughput": 7053.8, "total_tokens": 18259968} {"current_steps": 2230, "total_steps": 3345, "loss": 0.354, "lr": 6.250000000000004e-07, "epoch": 3.3333333333333335, "percentage": 66.67, "elapsed_time": "0:43:09", "remaining_time": "0:21:34", "throughput": 7053.8, "total_tokens": 18268160} {"current_steps": 2231, "total_steps": 3345, "loss": 0.2375, "lr": 6.239835721196444e-07, "epoch": 3.334828101644245, "percentage": 66.7, "elapsed_time": "0:43:10", "remaining_time": "0:21:33", "throughput": 7053.8, "total_tokens": 18276352} {"current_steps": 2232, "total_steps": 3345, "loss": 0.3656, "lr": 6.229676964352165e-07, "epoch": 3.336322869955157, "percentage": 66.73, "elapsed_time": "0:43:12", "remaining_time": "0:21:32", "throughput": 7053.81, "total_tokens": 18284544} {"current_steps": 2233, "total_steps": 3345, "loss": 0.4088, "lr": 6.219523738427975e-07, "epoch": 3.3378176382660687, "percentage": 66.76, "elapsed_time": "0:43:13", "remaining_time": "0:21:31", "throughput": 7053.81, "total_tokens": 18292736} {"current_steps": 2234, "total_steps": 3345, "loss": 0.2169, "lr": 6.209376052379845e-07, "epoch": 3.3393124065769806, "percentage": 66.79, "elapsed_time": "0:43:14", "remaining_time": "0:21:30", "throughput": 7053.81, "total_tokens": 18300928} {"current_steps": 2235, "total_steps": 3345, "loss": 0.2442, "lr": 6.199233915158817e-07, "epoch": 3.3408071748878925, "percentage": 66.82, "elapsed_time": "0:43:15", "remaining_time": "0:21:29", "throughput": 7053.83, "total_tokens": 18309120} {"current_steps": 2236, "total_steps": 3345, "loss": 0.2838, "lr": 6.189097335711068e-07, "epoch": 3.3423019431988044, "percentage": 66.85, "elapsed_time": "0:43:16", "remaining_time": "0:21:27", "throughput": 7053.84, "total_tokens": 18317312} {"current_steps": 2237, "total_steps": 3345, "loss": 0.3785, "lr": 6.178966322977853e-07, "epoch": 3.343796711509716, "percentage": 66.88, "elapsed_time": "0:43:17", "remaining_time": "0:21:26", "throughput": 7053.85, "total_tokens": 18325504} {"current_steps": 2238, "total_steps": 3345, "loss": 0.1873, "lr": 6.168840885895534e-07, "epoch": 3.3452914798206277, "percentage": 66.91, "elapsed_time": "0:43:19", "remaining_time": "0:21:25", "throughput": 7053.85, "total_tokens": 18333696} {"current_steps": 2239, "total_steps": 3345, "loss": 0.2514, "lr": 6.158721033395536e-07, "epoch": 3.3467862481315396, "percentage": 66.94, "elapsed_time": "0:43:20", "remaining_time": "0:21:24", "throughput": 7053.86, "total_tokens": 18341888} {"current_steps": 2240, "total_steps": 3345, "loss": 0.4482, "lr": 6.148606774404374e-07, "epoch": 3.3482810164424515, "percentage": 66.97, "elapsed_time": "0:43:21", "remaining_time": "0:21:23", "throughput": 7053.86, "total_tokens": 18350080} {"current_steps": 2241, "total_steps": 3345, "loss": 0.3357, "lr": 6.138498117843626e-07, "epoch": 3.3497757847533634, "percentage": 67.0, "elapsed_time": "0:43:22", "remaining_time": "0:21:22", "throughput": 7053.86, "total_tokens": 18358272} {"current_steps": 2242, "total_steps": 3345, "loss": 0.2823, "lr": 6.128395072629918e-07, "epoch": 3.351270553064275, "percentage": 67.03, "elapsed_time": "0:43:23", "remaining_time": "0:21:20", "throughput": 7053.87, "total_tokens": 18366464} {"current_steps": 2243, "total_steps": 3345, "loss": 0.1519, "lr": 6.118297647674942e-07, "epoch": 3.3527653213751867, "percentage": 67.06, "elapsed_time": "0:43:24", "remaining_time": "0:21:19", "throughput": 7053.88, "total_tokens": 18374656} {"current_steps": 2244, "total_steps": 3345, "loss": 0.3337, "lr": 6.108205851885416e-07, "epoch": 3.3542600896860986, "percentage": 67.09, "elapsed_time": "0:43:26", "remaining_time": "0:21:18", "throughput": 7053.88, "total_tokens": 18382848} {"current_steps": 2245, "total_steps": 3345, "loss": 0.2918, "lr": 6.09811969416311e-07, "epoch": 3.3557548579970105, "percentage": 67.12, "elapsed_time": "0:43:27", "remaining_time": "0:21:17", "throughput": 7053.89, "total_tokens": 18391040} {"current_steps": 2246, "total_steps": 3345, "loss": 0.2911, "lr": 6.0880391834048e-07, "epoch": 3.3572496263079223, "percentage": 67.14, "elapsed_time": "0:43:28", "remaining_time": "0:21:16", "throughput": 7053.89, "total_tokens": 18399232} {"current_steps": 2247, "total_steps": 3345, "loss": 0.2345, "lr": 6.077964328502301e-07, "epoch": 3.3587443946188342, "percentage": 67.17, "elapsed_time": "0:43:29", "remaining_time": "0:21:15", "throughput": 7053.89, "total_tokens": 18407424} {"current_steps": 2248, "total_steps": 3345, "loss": 0.3781, "lr": 6.067895138342431e-07, "epoch": 3.360239162929746, "percentage": 67.2, "elapsed_time": "0:43:30", "remaining_time": "0:21:13", "throughput": 7053.88, "total_tokens": 18415616} {"current_steps": 2249, "total_steps": 3345, "loss": 0.0664, "lr": 6.057831621807005e-07, "epoch": 3.3617339312406576, "percentage": 67.23, "elapsed_time": "0:43:31", "remaining_time": "0:21:12", "throughput": 7053.88, "total_tokens": 18423808} {"current_steps": 2250, "total_steps": 3345, "loss": 0.1181, "lr": 6.047773787772842e-07, "epoch": 3.3632286995515694, "percentage": 67.26, "elapsed_time": "0:43:33", "remaining_time": "0:21:11", "throughput": 7053.89, "total_tokens": 18432000} {"current_steps": 2251, "total_steps": 3345, "loss": 0.3421, "lr": 6.037721645111749e-07, "epoch": 3.3647234678624813, "percentage": 67.29, "elapsed_time": "0:43:34", "remaining_time": "0:21:10", "throughput": 7053.89, "total_tokens": 18440192} {"current_steps": 2252, "total_steps": 3345, "loss": 0.3454, "lr": 6.027675202690511e-07, "epoch": 3.366218236173393, "percentage": 67.32, "elapsed_time": "0:43:35", "remaining_time": "0:21:09", "throughput": 7053.9, "total_tokens": 18448384} {"current_steps": 2253, "total_steps": 3345, "loss": 0.4347, "lr": 6.017634469370875e-07, "epoch": 3.367713004484305, "percentage": 67.35, "elapsed_time": "0:43:36", "remaining_time": "0:21:08", "throughput": 7053.91, "total_tokens": 18456576} {"current_steps": 2254, "total_steps": 3345, "loss": 0.3036, "lr": 6.007599454009571e-07, "epoch": 3.3692077727952165, "percentage": 67.38, "elapsed_time": "0:43:37", "remaining_time": "0:21:07", "throughput": 7053.9, "total_tokens": 18464768} {"current_steps": 2255, "total_steps": 3345, "loss": 0.2367, "lr": 5.997570165458265e-07, "epoch": 3.3707025411061284, "percentage": 67.41, "elapsed_time": "0:43:38", "remaining_time": "0:21:05", "throughput": 7053.89, "total_tokens": 18472960} {"current_steps": 2256, "total_steps": 3345, "loss": 0.2641, "lr": 5.987546612563587e-07, "epoch": 3.3721973094170403, "percentage": 67.44, "elapsed_time": "0:43:39", "remaining_time": "0:21:04", "throughput": 7053.89, "total_tokens": 18481152} {"current_steps": 2257, "total_steps": 3345, "loss": 0.3183, "lr": 5.977528804167105e-07, "epoch": 3.373692077727952, "percentage": 67.47, "elapsed_time": "0:43:41", "remaining_time": "0:21:03", "throughput": 7053.89, "total_tokens": 18489344} {"current_steps": 2258, "total_steps": 3345, "loss": 0.3218, "lr": 5.96751674910531e-07, "epoch": 3.375186846038864, "percentage": 67.5, "elapsed_time": "0:43:42", "remaining_time": "0:21:02", "throughput": 7053.89, "total_tokens": 18497536} {"current_steps": 2259, "total_steps": 3345, "loss": 0.2624, "lr": 5.957510456209634e-07, "epoch": 3.376681614349776, "percentage": 67.53, "elapsed_time": "0:43:43", "remaining_time": "0:21:01", "throughput": 7053.88, "total_tokens": 18505728} {"current_steps": 2260, "total_steps": 3345, "loss": 0.2512, "lr": 5.947509934306408e-07, "epoch": 3.3781763826606874, "percentage": 67.56, "elapsed_time": "0:43:44", "remaining_time": "0:21:00", "throughput": 7053.88, "total_tokens": 18513920} {"current_steps": 2261, "total_steps": 3345, "loss": 0.4499, "lr": 5.93751519221689e-07, "epoch": 3.3796711509715993, "percentage": 67.59, "elapsed_time": "0:43:45", "remaining_time": "0:20:58", "throughput": 7053.87, "total_tokens": 18522112} {"current_steps": 2262, "total_steps": 3345, "loss": 0.3264, "lr": 5.927526238757224e-07, "epoch": 3.381165919282511, "percentage": 67.62, "elapsed_time": "0:43:46", "remaining_time": "0:20:57", "throughput": 7053.86, "total_tokens": 18530304} {"current_steps": 2263, "total_steps": 3345, "loss": 0.1283, "lr": 5.917543082738461e-07, "epoch": 3.382660687593423, "percentage": 67.65, "elapsed_time": "0:43:48", "remaining_time": "0:20:56", "throughput": 7053.87, "total_tokens": 18538496} {"current_steps": 2264, "total_steps": 3345, "loss": 0.4413, "lr": 5.907565732966537e-07, "epoch": 3.384155455904335, "percentage": 67.68, "elapsed_time": "0:43:49", "remaining_time": "0:20:55", "throughput": 7053.87, "total_tokens": 18546688} {"current_steps": 2265, "total_steps": 3345, "loss": 0.2985, "lr": 5.897594198242252e-07, "epoch": 3.3856502242152464, "percentage": 67.71, "elapsed_time": "0:43:50", "remaining_time": "0:20:54", "throughput": 7053.87, "total_tokens": 18554880} {"current_steps": 2266, "total_steps": 3345, "loss": 0.3495, "lr": 5.8876284873613e-07, "epoch": 3.3871449925261583, "percentage": 67.74, "elapsed_time": "0:43:51", "remaining_time": "0:20:53", "throughput": 7053.87, "total_tokens": 18563072} {"current_steps": 2267, "total_steps": 3345, "loss": 0.128, "lr": 5.877668609114207e-07, "epoch": 3.38863976083707, "percentage": 67.77, "elapsed_time": "0:43:52", "remaining_time": "0:20:51", "throughput": 7053.87, "total_tokens": 18571264} {"current_steps": 2268, "total_steps": 3345, "loss": 0.2237, "lr": 5.867714572286391e-07, "epoch": 3.390134529147982, "percentage": 67.8, "elapsed_time": "0:43:53", "remaining_time": "0:20:50", "throughput": 7053.88, "total_tokens": 18579456} {"current_steps": 2269, "total_steps": 3345, "loss": 0.1116, "lr": 5.857766385658088e-07, "epoch": 3.391629297458894, "percentage": 67.83, "elapsed_time": "0:43:55", "remaining_time": "0:20:49", "throughput": 7053.88, "total_tokens": 18587648} {"current_steps": 2270, "total_steps": 3345, "loss": 0.1345, "lr": 5.847824058004391e-07, "epoch": 3.393124065769806, "percentage": 67.86, "elapsed_time": "0:43:56", "remaining_time": "0:20:48", "throughput": 7053.88, "total_tokens": 18595840} {"current_steps": 2271, "total_steps": 3345, "loss": 0.3104, "lr": 5.837887598095208e-07, "epoch": 3.3946188340807173, "percentage": 67.89, "elapsed_time": "0:43:57", "remaining_time": "0:20:47", "throughput": 7053.88, "total_tokens": 18604032} {"current_steps": 2272, "total_steps": 3345, "loss": 0.2525, "lr": 5.827957014695289e-07, "epoch": 3.396113602391629, "percentage": 67.92, "elapsed_time": "0:43:58", "remaining_time": "0:20:46", "throughput": 7053.87, "total_tokens": 18612224} {"current_steps": 2273, "total_steps": 3345, "loss": 0.4094, "lr": 5.818032316564196e-07, "epoch": 3.397608370702541, "percentage": 67.95, "elapsed_time": "0:43:59", "remaining_time": "0:20:44", "throughput": 7053.87, "total_tokens": 18620416} {"current_steps": 2274, "total_steps": 3345, "loss": 0.4181, "lr": 5.808113512456285e-07, "epoch": 3.399103139013453, "percentage": 67.98, "elapsed_time": "0:44:00", "remaining_time": "0:20:43", "throughput": 7053.87, "total_tokens": 18628608} {"current_steps": 2275, "total_steps": 3345, "loss": 0.2264, "lr": 5.798200611120737e-07, "epoch": 3.400597907324365, "percentage": 68.01, "elapsed_time": "0:44:02", "remaining_time": "0:20:42", "throughput": 7053.88, "total_tokens": 18636800} {"current_steps": 2276, "total_steps": 3345, "loss": 0.16, "lr": 5.788293621301504e-07, "epoch": 3.4020926756352763, "percentage": 68.04, "elapsed_time": "0:44:03", "remaining_time": "0:20:41", "throughput": 7053.88, "total_tokens": 18644992} {"current_steps": 2277, "total_steps": 3345, "loss": 0.3718, "lr": 5.778392551737342e-07, "epoch": 3.403587443946188, "percentage": 68.07, "elapsed_time": "0:44:04", "remaining_time": "0:20:40", "throughput": 7053.87, "total_tokens": 18653184} {"current_steps": 2278, "total_steps": 3345, "loss": 0.2342, "lr": 5.768497411161767e-07, "epoch": 3.4050822122571, "percentage": 68.1, "elapsed_time": "0:44:05", "remaining_time": "0:20:39", "throughput": 7053.87, "total_tokens": 18661376} {"current_steps": 2279, "total_steps": 3345, "loss": 0.1064, "lr": 5.758608208303078e-07, "epoch": 3.406576980568012, "percentage": 68.13, "elapsed_time": "0:44:06", "remaining_time": "0:20:37", "throughput": 7053.87, "total_tokens": 18669568} {"current_steps": 2280, "total_steps": 3345, "loss": 0.2853, "lr": 5.74872495188434e-07, "epoch": 3.408071748878924, "percentage": 68.16, "elapsed_time": "0:44:07", "remaining_time": "0:20:36", "throughput": 7053.85, "total_tokens": 18677760} {"current_steps": 2281, "total_steps": 3345, "loss": 0.5256, "lr": 5.738847650623354e-07, "epoch": 3.4095665171898357, "percentage": 68.19, "elapsed_time": "0:44:09", "remaining_time": "0:20:35", "throughput": 7053.81, "total_tokens": 18685952} {"current_steps": 2282, "total_steps": 3345, "loss": 0.2785, "lr": 5.728976313232691e-07, "epoch": 3.4110612855007476, "percentage": 68.22, "elapsed_time": "0:44:10", "remaining_time": "0:20:34", "throughput": 7053.78, "total_tokens": 18694144} {"current_steps": 2283, "total_steps": 3345, "loss": 0.196, "lr": 5.71911094841964e-07, "epoch": 3.412556053811659, "percentage": 68.25, "elapsed_time": "0:44:11", "remaining_time": "0:20:33", "throughput": 7053.77, "total_tokens": 18702336} {"current_steps": 2284, "total_steps": 3345, "loss": 0.3156, "lr": 5.709251564886236e-07, "epoch": 3.414050822122571, "percentage": 68.28, "elapsed_time": "0:44:12", "remaining_time": "0:20:32", "throughput": 7053.77, "total_tokens": 18710528} {"current_steps": 2285, "total_steps": 3345, "loss": 0.2734, "lr": 5.699398171329235e-07, "epoch": 3.415545590433483, "percentage": 68.31, "elapsed_time": "0:44:13", "remaining_time": "0:20:31", "throughput": 7053.77, "total_tokens": 18718720} {"current_steps": 2286, "total_steps": 3345, "loss": 0.2664, "lr": 5.68955077644011e-07, "epoch": 3.4170403587443947, "percentage": 68.34, "elapsed_time": "0:44:14", "remaining_time": "0:20:29", "throughput": 7053.75, "total_tokens": 18726912} {"current_steps": 2287, "total_steps": 3345, "loss": 0.1437, "lr": 5.679709388905036e-07, "epoch": 3.4185351270553066, "percentage": 68.37, "elapsed_time": "0:44:16", "remaining_time": "0:20:28", "throughput": 7053.74, "total_tokens": 18735104} {"current_steps": 2288, "total_steps": 3345, "loss": 0.4291, "lr": 5.669874017404897e-07, "epoch": 3.420029895366218, "percentage": 68.4, "elapsed_time": "0:44:17", "remaining_time": "0:20:27", "throughput": 7053.73, "total_tokens": 18743296} {"current_steps": 2289, "total_steps": 3345, "loss": 0.426, "lr": 5.660044670615271e-07, "epoch": 3.42152466367713, "percentage": 68.43, "elapsed_time": "0:44:18", "remaining_time": "0:20:26", "throughput": 7053.74, "total_tokens": 18751488} {"current_steps": 2290, "total_steps": 3345, "loss": 0.4115, "lr": 5.650221357206409e-07, "epoch": 3.423019431988042, "percentage": 68.46, "elapsed_time": "0:44:19", "remaining_time": "0:20:25", "throughput": 7053.74, "total_tokens": 18759680} {"current_steps": 2291, "total_steps": 3345, "loss": 0.2474, "lr": 5.640404085843258e-07, "epoch": 3.4245142002989537, "percentage": 68.49, "elapsed_time": "0:44:20", "remaining_time": "0:20:24", "throughput": 7053.74, "total_tokens": 18767872} {"current_steps": 2292, "total_steps": 3345, "loss": 0.149, "lr": 5.630592865185421e-07, "epoch": 3.4260089686098656, "percentage": 68.52, "elapsed_time": "0:44:21", "remaining_time": "0:20:22", "throughput": 7053.74, "total_tokens": 18776064} {"current_steps": 2293, "total_steps": 3345, "loss": 0.364, "lr": 5.620787703887173e-07, "epoch": 3.4275037369207775, "percentage": 68.55, "elapsed_time": "0:44:23", "remaining_time": "0:20:21", "throughput": 7053.74, "total_tokens": 18784256} {"current_steps": 2294, "total_steps": 3345, "loss": 0.3692, "lr": 5.610988610597437e-07, "epoch": 3.428998505231689, "percentage": 68.58, "elapsed_time": "0:44:24", "remaining_time": "0:20:20", "throughput": 7053.74, "total_tokens": 18792448} {"current_steps": 2295, "total_steps": 3345, "loss": 0.3962, "lr": 5.601195593959787e-07, "epoch": 3.430493273542601, "percentage": 68.61, "elapsed_time": "0:44:25", "remaining_time": "0:20:19", "throughput": 7053.74, "total_tokens": 18800640} {"current_steps": 2296, "total_steps": 3345, "loss": 0.3199, "lr": 5.591408662612445e-07, "epoch": 3.4319880418535127, "percentage": 68.64, "elapsed_time": "0:44:26", "remaining_time": "0:20:18", "throughput": 7053.74, "total_tokens": 18808832} {"current_steps": 2297, "total_steps": 3345, "loss": 0.4654, "lr": 5.581627825188247e-07, "epoch": 3.4334828101644246, "percentage": 68.67, "elapsed_time": "0:44:27", "remaining_time": "0:20:17", "throughput": 7053.74, "total_tokens": 18817024} {"current_steps": 2298, "total_steps": 3345, "loss": 0.3937, "lr": 5.571853090314673e-07, "epoch": 3.4349775784753365, "percentage": 68.7, "elapsed_time": "0:44:28", "remaining_time": "0:20:15", "throughput": 7053.71, "total_tokens": 18825216} {"current_steps": 2299, "total_steps": 3345, "loss": 0.2271, "lr": 5.562084466613802e-07, "epoch": 3.436472346786248, "percentage": 68.73, "elapsed_time": "0:44:30", "remaining_time": "0:20:14", "throughput": 7053.7, "total_tokens": 18833408} {"current_steps": 2300, "total_steps": 3345, "loss": 0.3332, "lr": 5.552321962702339e-07, "epoch": 3.43796711509716, "percentage": 68.76, "elapsed_time": "0:44:31", "remaining_time": "0:20:13", "throughput": 7053.7, "total_tokens": 18841600} {"current_steps": 2301, "total_steps": 3345, "loss": 0.3582, "lr": 5.542565587191574e-07, "epoch": 3.4394618834080717, "percentage": 68.79, "elapsed_time": "0:44:32", "remaining_time": "0:20:12", "throughput": 7053.7, "total_tokens": 18849792} {"current_steps": 2302, "total_steps": 3345, "loss": 0.3412, "lr": 5.532815348687417e-07, "epoch": 3.4409566517189836, "percentage": 68.82, "elapsed_time": "0:44:33", "remaining_time": "0:20:11", "throughput": 7052.69, "total_tokens": 18857984} {"current_steps": 2303, "total_steps": 3345, "loss": 0.4362, "lr": 5.523071255790331e-07, "epoch": 3.4424514200298955, "percentage": 68.85, "elapsed_time": "0:44:35", "remaining_time": "0:20:10", "throughput": 7052.69, "total_tokens": 18866176} {"current_steps": 2304, "total_steps": 3345, "loss": 0.1838, "lr": 5.513333317095389e-07, "epoch": 3.4439461883408073, "percentage": 68.88, "elapsed_time": "0:44:36", "remaining_time": "0:20:09", "throughput": 7052.69, "total_tokens": 18874368} {"current_steps": 2305, "total_steps": 3345, "loss": 0.3888, "lr": 5.503601541192212e-07, "epoch": 3.4454409566517192, "percentage": 68.91, "elapsed_time": "0:44:37", "remaining_time": "0:20:08", "throughput": 7052.69, "total_tokens": 18882560} {"current_steps": 2306, "total_steps": 3345, "loss": 0.366, "lr": 5.493875936664998e-07, "epoch": 3.4469357249626307, "percentage": 68.94, "elapsed_time": "0:44:38", "remaining_time": "0:20:06", "throughput": 7052.69, "total_tokens": 18890752} {"current_steps": 2307, "total_steps": 3345, "loss": 0.1815, "lr": 5.484156512092504e-07, "epoch": 3.4484304932735426, "percentage": 68.97, "elapsed_time": "0:44:39", "remaining_time": "0:20:05", "throughput": 7052.69, "total_tokens": 18898944} {"current_steps": 2308, "total_steps": 3345, "loss": 0.1684, "lr": 5.474443276048022e-07, "epoch": 3.4499252615844545, "percentage": 69.0, "elapsed_time": "0:44:40", "remaining_time": "0:20:04", "throughput": 7052.71, "total_tokens": 18907136} {"current_steps": 2309, "total_steps": 3345, "loss": 0.2399, "lr": 5.4647362370994e-07, "epoch": 3.4514200298953663, "percentage": 69.03, "elapsed_time": "0:44:41", "remaining_time": "0:20:03", "throughput": 7052.72, "total_tokens": 18915328} {"current_steps": 2310, "total_steps": 3345, "loss": 0.1027, "lr": 5.455035403809006e-07, "epoch": 3.452914798206278, "percentage": 69.06, "elapsed_time": "0:44:43", "remaining_time": "0:20:02", "throughput": 7052.73, "total_tokens": 18923520} {"current_steps": 2311, "total_steps": 3345, "loss": 0.2008, "lr": 5.445340784733747e-07, "epoch": 3.4544095665171897, "percentage": 69.09, "elapsed_time": "0:44:44", "remaining_time": "0:20:01", "throughput": 7052.73, "total_tokens": 18931712} {"current_steps": 2312, "total_steps": 3345, "loss": 0.3376, "lr": 5.435652388425037e-07, "epoch": 3.4559043348281016, "percentage": 69.12, "elapsed_time": "0:44:45", "remaining_time": "0:19:59", "throughput": 7052.73, "total_tokens": 18939904} {"current_steps": 2313, "total_steps": 3345, "loss": 0.3183, "lr": 5.425970223428811e-07, "epoch": 3.4573991031390134, "percentage": 69.15, "elapsed_time": "0:44:46", "remaining_time": "0:19:58", "throughput": 7052.74, "total_tokens": 18948096} {"current_steps": 2314, "total_steps": 3345, "loss": 0.2425, "lr": 5.416294298285504e-07, "epoch": 3.4588938714499253, "percentage": 69.18, "elapsed_time": "0:44:47", "remaining_time": "0:19:57", "throughput": 7052.74, "total_tokens": 18956288} {"current_steps": 2315, "total_steps": 3345, "loss": 0.3144, "lr": 5.406624621530041e-07, "epoch": 3.460388639760837, "percentage": 69.21, "elapsed_time": "0:44:48", "remaining_time": "0:19:56", "throughput": 7052.75, "total_tokens": 18964480} {"current_steps": 2316, "total_steps": 3345, "loss": 0.4568, "lr": 5.396961201691847e-07, "epoch": 3.461883408071749, "percentage": 69.24, "elapsed_time": "0:44:50", "remaining_time": "0:19:55", "throughput": 7052.75, "total_tokens": 18972672} {"current_steps": 2317, "total_steps": 3345, "loss": 0.3461, "lr": 5.387304047294814e-07, "epoch": 3.4633781763826605, "percentage": 69.27, "elapsed_time": "0:44:51", "remaining_time": "0:19:54", "throughput": 7052.75, "total_tokens": 18980864} {"current_steps": 2318, "total_steps": 3345, "loss": 0.4469, "lr": 5.377653166857321e-07, "epoch": 3.4648729446935724, "percentage": 69.3, "elapsed_time": "0:44:52", "remaining_time": "0:19:52", "throughput": 7052.76, "total_tokens": 18989056} {"current_steps": 2319, "total_steps": 3345, "loss": 0.1636, "lr": 5.368008568892201e-07, "epoch": 3.4663677130044843, "percentage": 69.33, "elapsed_time": "0:44:53", "remaining_time": "0:19:51", "throughput": 7052.75, "total_tokens": 18997248} {"current_steps": 2320, "total_steps": 3345, "loss": 0.119, "lr": 5.358370261906762e-07, "epoch": 3.467862481315396, "percentage": 69.36, "elapsed_time": "0:44:54", "remaining_time": "0:19:50", "throughput": 7052.73, "total_tokens": 19005440} {"current_steps": 2321, "total_steps": 3345, "loss": 0.157, "lr": 5.348738254402738e-07, "epoch": 3.469357249626308, "percentage": 69.39, "elapsed_time": "0:44:55", "remaining_time": "0:19:49", "throughput": 7052.73, "total_tokens": 19013632} {"current_steps": 2322, "total_steps": 3345, "loss": 0.4031, "lr": 5.339112554876329e-07, "epoch": 3.4708520179372195, "percentage": 69.42, "elapsed_time": "0:44:57", "remaining_time": "0:19:48", "throughput": 7052.73, "total_tokens": 19021824} {"current_steps": 2323, "total_steps": 3345, "loss": 0.3032, "lr": 5.329493171818162e-07, "epoch": 3.4723467862481314, "percentage": 69.45, "elapsed_time": "0:44:58", "remaining_time": "0:19:47", "throughput": 7052.73, "total_tokens": 19030016} {"current_steps": 2324, "total_steps": 3345, "loss": 0.2232, "lr": 5.319880113713288e-07, "epoch": 3.4738415545590433, "percentage": 69.48, "elapsed_time": "0:44:59", "remaining_time": "0:19:45", "throughput": 7052.72, "total_tokens": 19038208} {"current_steps": 2325, "total_steps": 3345, "loss": 0.1914, "lr": 5.31027338904119e-07, "epoch": 3.475336322869955, "percentage": 69.51, "elapsed_time": "0:45:00", "remaining_time": "0:19:44", "throughput": 7052.71, "total_tokens": 19046400} {"current_steps": 2326, "total_steps": 3345, "loss": 0.4041, "lr": 5.300673006275748e-07, "epoch": 3.476831091180867, "percentage": 69.54, "elapsed_time": "0:45:01", "remaining_time": "0:19:43", "throughput": 7052.71, "total_tokens": 19054592} {"current_steps": 2327, "total_steps": 3345, "loss": 0.2599, "lr": 5.291078973885269e-07, "epoch": 3.478325859491779, "percentage": 69.57, "elapsed_time": "0:45:02", "remaining_time": "0:19:42", "throughput": 7052.72, "total_tokens": 19062784} {"current_steps": 2328, "total_steps": 3345, "loss": 0.2188, "lr": 5.281491300332438e-07, "epoch": 3.4798206278026904, "percentage": 69.6, "elapsed_time": "0:45:04", "remaining_time": "0:19:41", "throughput": 7052.72, "total_tokens": 19070976} {"current_steps": 2329, "total_steps": 3345, "loss": 0.123, "lr": 5.271909994074343e-07, "epoch": 3.4813153961136023, "percentage": 69.63, "elapsed_time": "0:45:05", "remaining_time": "0:19:40", "throughput": 7052.71, "total_tokens": 19079168} {"current_steps": 2330, "total_steps": 3345, "loss": 0.1852, "lr": 5.262335063562459e-07, "epoch": 3.482810164424514, "percentage": 69.66, "elapsed_time": "0:45:06", "remaining_time": "0:19:38", "throughput": 7052.71, "total_tokens": 19087360} {"current_steps": 2331, "total_steps": 3345, "loss": 0.2651, "lr": 5.252766517242621e-07, "epoch": 3.484304932735426, "percentage": 69.69, "elapsed_time": "0:45:07", "remaining_time": "0:19:37", "throughput": 7052.71, "total_tokens": 19095552} {"current_steps": 2332, "total_steps": 3345, "loss": 0.3222, "lr": 5.24320436355505e-07, "epoch": 3.485799701046338, "percentage": 69.72, "elapsed_time": "0:45:08", "remaining_time": "0:19:36", "throughput": 7052.71, "total_tokens": 19103744} {"current_steps": 2333, "total_steps": 3345, "loss": 0.2474, "lr": 5.233648610934315e-07, "epoch": 3.4872944693572494, "percentage": 69.75, "elapsed_time": "0:45:09", "remaining_time": "0:19:35", "throughput": 7052.71, "total_tokens": 19111936} {"current_steps": 2334, "total_steps": 3345, "loss": 0.4141, "lr": 5.224099267809351e-07, "epoch": 3.4887892376681613, "percentage": 69.78, "elapsed_time": "0:45:11", "remaining_time": "0:19:34", "throughput": 7052.71, "total_tokens": 19120128} {"current_steps": 2335, "total_steps": 3345, "loss": 0.3041, "lr": 5.214556342603421e-07, "epoch": 3.490284005979073, "percentage": 69.81, "elapsed_time": "0:45:12", "remaining_time": "0:19:33", "throughput": 7052.71, "total_tokens": 19128320} {"current_steps": 2336, "total_steps": 3345, "loss": 0.2854, "lr": 5.205019843734157e-07, "epoch": 3.491778774289985, "percentage": 69.84, "elapsed_time": "0:45:13", "remaining_time": "0:19:31", "throughput": 7052.71, "total_tokens": 19136512} {"current_steps": 2337, "total_steps": 3345, "loss": 0.4949, "lr": 5.195489779613487e-07, "epoch": 3.493273542600897, "percentage": 69.87, "elapsed_time": "0:45:14", "remaining_time": "0:19:30", "throughput": 7052.69, "total_tokens": 19144704} {"current_steps": 2338, "total_steps": 3345, "loss": 0.199, "lr": 5.185966158647688e-07, "epoch": 3.494768310911809, "percentage": 69.9, "elapsed_time": "0:45:15", "remaining_time": "0:19:29", "throughput": 7052.69, "total_tokens": 19152896} {"current_steps": 2339, "total_steps": 3345, "loss": 0.2912, "lr": 5.176448989237348e-07, "epoch": 3.4962630792227207, "percentage": 69.93, "elapsed_time": "0:45:16", "remaining_time": "0:19:28", "throughput": 7052.69, "total_tokens": 19161088} {"current_steps": 2340, "total_steps": 3345, "loss": 0.2371, "lr": 5.166938279777355e-07, "epoch": 3.497757847533632, "percentage": 69.96, "elapsed_time": "0:45:18", "remaining_time": "0:19:27", "throughput": 7052.69, "total_tokens": 19169280} {"current_steps": 2341, "total_steps": 3345, "loss": 0.3761, "lr": 5.157434038656915e-07, "epoch": 3.499252615844544, "percentage": 69.99, "elapsed_time": "0:45:19", "remaining_time": "0:19:26", "throughput": 7052.68, "total_tokens": 19177472} {"current_steps": 2342, "total_steps": 3345, "loss": 0.2849, "lr": 5.147936274259508e-07, "epoch": 3.500747384155456, "percentage": 70.01, "elapsed_time": "0:45:20", "remaining_time": "0:19:25", "throughput": 7052.69, "total_tokens": 19185664} {"current_steps": 2343, "total_steps": 3345, "loss": 0.1878, "lr": 5.138444994962925e-07, "epoch": 3.502242152466368, "percentage": 70.04, "elapsed_time": "0:45:21", "remaining_time": "0:19:23", "throughput": 7052.7, "total_tokens": 19193856} {"current_steps": 2344, "total_steps": 3345, "loss": 0.1656, "lr": 5.128960209139211e-07, "epoch": 3.5037369207772793, "percentage": 70.07, "elapsed_time": "0:45:22", "remaining_time": "0:19:22", "throughput": 7052.69, "total_tokens": 19202048} {"current_steps": 2345, "total_steps": 3345, "loss": 0.4386, "lr": 5.119481925154703e-07, "epoch": 3.505231689088191, "percentage": 70.1, "elapsed_time": "0:45:23", "remaining_time": "0:19:21", "throughput": 7052.68, "total_tokens": 19210240} {"current_steps": 2346, "total_steps": 3345, "loss": 0.3054, "lr": 5.110010151369999e-07, "epoch": 3.506726457399103, "percentage": 70.13, "elapsed_time": "0:45:24", "remaining_time": "0:19:20", "throughput": 7052.68, "total_tokens": 19218432} {"current_steps": 2347, "total_steps": 3345, "loss": 0.3871, "lr": 5.100544896139944e-07, "epoch": 3.508221225710015, "percentage": 70.16, "elapsed_time": "0:45:26", "remaining_time": "0:19:19", "throughput": 7052.68, "total_tokens": 19226624} {"current_steps": 2348, "total_steps": 3345, "loss": 0.2841, "lr": 5.091086167813646e-07, "epoch": 3.509715994020927, "percentage": 70.19, "elapsed_time": "0:45:27", "remaining_time": "0:19:18", "throughput": 7052.68, "total_tokens": 19234816} {"current_steps": 2349, "total_steps": 3345, "loss": 0.3322, "lr": 5.081633974734447e-07, "epoch": 3.5112107623318387, "percentage": 70.22, "elapsed_time": "0:45:28", "remaining_time": "0:19:16", "throughput": 7052.67, "total_tokens": 19243008} {"current_steps": 2350, "total_steps": 3345, "loss": 0.4741, "lr": 5.072188325239933e-07, "epoch": 3.5127055306427506, "percentage": 70.25, "elapsed_time": "0:45:29", "remaining_time": "0:19:15", "throughput": 7052.67, "total_tokens": 19251200} {"current_steps": 2351, "total_steps": 3345, "loss": 0.1872, "lr": 5.062749227661904e-07, "epoch": 3.514200298953662, "percentage": 70.28, "elapsed_time": "0:45:30", "remaining_time": "0:19:14", "throughput": 7052.66, "total_tokens": 19259392} {"current_steps": 2352, "total_steps": 3345, "loss": 0.3847, "lr": 5.053316690326397e-07, "epoch": 3.515695067264574, "percentage": 70.31, "elapsed_time": "0:45:31", "remaining_time": "0:19:13", "throughput": 7052.67, "total_tokens": 19267584} {"current_steps": 2353, "total_steps": 3345, "loss": 0.1918, "lr": 5.043890721553652e-07, "epoch": 3.517189835575486, "percentage": 70.34, "elapsed_time": "0:45:33", "remaining_time": "0:19:12", "throughput": 7052.67, "total_tokens": 19275776} {"current_steps": 2354, "total_steps": 3345, "loss": 0.1912, "lr": 5.034471329658116e-07, "epoch": 3.5186846038863977, "percentage": 70.37, "elapsed_time": "0:45:34", "remaining_time": "0:19:11", "throughput": 7052.68, "total_tokens": 19283968} {"current_steps": 2355, "total_steps": 3345, "loss": 0.3587, "lr": 5.025058522948444e-07, "epoch": 3.520179372197309, "percentage": 70.4, "elapsed_time": "0:45:35", "remaining_time": "0:19:09", "throughput": 7052.69, "total_tokens": 19292160} {"current_steps": 2356, "total_steps": 3345, "loss": 0.149, "lr": 5.015652309727467e-07, "epoch": 3.521674140508221, "percentage": 70.43, "elapsed_time": "0:45:36", "remaining_time": "0:19:08", "throughput": 7052.7, "total_tokens": 19300352} {"current_steps": 2357, "total_steps": 3345, "loss": 0.3662, "lr": 5.006252698292214e-07, "epoch": 3.523168908819133, "percentage": 70.46, "elapsed_time": "0:45:37", "remaining_time": "0:19:07", "throughput": 7052.7, "total_tokens": 19308544} {"current_steps": 2358, "total_steps": 3345, "loss": 0.321, "lr": 4.996859696933878e-07, "epoch": 3.524663677130045, "percentage": 70.49, "elapsed_time": "0:45:38", "remaining_time": "0:19:06", "throughput": 7052.69, "total_tokens": 19316736} {"current_steps": 2359, "total_steps": 3345, "loss": 0.1831, "lr": 4.987473313937835e-07, "epoch": 3.5261584454409567, "percentage": 70.52, "elapsed_time": "0:45:40", "remaining_time": "0:19:05", "throughput": 7052.68, "total_tokens": 19324928} {"current_steps": 2360, "total_steps": 3345, "loss": 0.3501, "lr": 4.978093557583607e-07, "epoch": 3.5276532137518686, "percentage": 70.55, "elapsed_time": "0:45:41", "remaining_time": "0:19:04", "throughput": 7052.69, "total_tokens": 19333120} {"current_steps": 2361, "total_steps": 3345, "loss": 0.452, "lr": 4.968720436144887e-07, "epoch": 3.5291479820627805, "percentage": 70.58, "elapsed_time": "0:45:42", "remaining_time": "0:19:02", "throughput": 7052.69, "total_tokens": 19341312} {"current_steps": 2362, "total_steps": 3345, "loss": 0.2924, "lr": 4.959353957889511e-07, "epoch": 3.5306427503736924, "percentage": 70.61, "elapsed_time": "0:45:43", "remaining_time": "0:19:01", "throughput": 7052.7, "total_tokens": 19349504} {"current_steps": 2363, "total_steps": 3345, "loss": 0.105, "lr": 4.949994131079441e-07, "epoch": 3.532137518684604, "percentage": 70.64, "elapsed_time": "0:45:44", "remaining_time": "0:19:00", "throughput": 7052.71, "total_tokens": 19357696} {"current_steps": 2364, "total_steps": 3345, "loss": 0.3487, "lr": 4.940640963970797e-07, "epoch": 3.5336322869955157, "percentage": 70.67, "elapsed_time": "0:45:45", "remaining_time": "0:18:59", "throughput": 7052.71, "total_tokens": 19365888} {"current_steps": 2365, "total_steps": 3345, "loss": 0.2123, "lr": 4.9312944648138e-07, "epoch": 3.5351270553064276, "percentage": 70.7, "elapsed_time": "0:45:47", "remaining_time": "0:18:58", "throughput": 7052.72, "total_tokens": 19374080} {"current_steps": 2366, "total_steps": 3345, "loss": 0.3877, "lr": 4.921954641852809e-07, "epoch": 3.5366218236173395, "percentage": 70.73, "elapsed_time": "0:45:48", "remaining_time": "0:18:57", "throughput": 7052.72, "total_tokens": 19382272} {"current_steps": 2367, "total_steps": 3345, "loss": 0.3662, "lr": 4.912621503326277e-07, "epoch": 3.538116591928251, "percentage": 70.76, "elapsed_time": "0:45:49", "remaining_time": "0:18:55", "throughput": 7052.72, "total_tokens": 19390464} {"current_steps": 2368, "total_steps": 3345, "loss": 0.1857, "lr": 4.903295057466773e-07, "epoch": 3.539611360239163, "percentage": 70.79, "elapsed_time": "0:45:50", "remaining_time": "0:18:54", "throughput": 7052.72, "total_tokens": 19398656} {"current_steps": 2369, "total_steps": 3345, "loss": 0.2875, "lr": 4.89397531250096e-07, "epoch": 3.5411061285500747, "percentage": 70.82, "elapsed_time": "0:45:51", "remaining_time": "0:18:53", "throughput": 7052.73, "total_tokens": 19406848} {"current_steps": 2370, "total_steps": 3345, "loss": 0.3669, "lr": 4.884662276649587e-07, "epoch": 3.5426008968609866, "percentage": 70.85, "elapsed_time": "0:45:52", "remaining_time": "0:18:52", "throughput": 7052.73, "total_tokens": 19415040} {"current_steps": 2371, "total_steps": 3345, "loss": 0.3534, "lr": 4.875355958127493e-07, "epoch": 3.5440956651718984, "percentage": 70.88, "elapsed_time": "0:45:54", "remaining_time": "0:18:51", "throughput": 7052.72, "total_tokens": 19423232} {"current_steps": 2372, "total_steps": 3345, "loss": 0.4601, "lr": 4.866056365143578e-07, "epoch": 3.5455904334828103, "percentage": 70.91, "elapsed_time": "0:45:55", "remaining_time": "0:18:50", "throughput": 7052.72, "total_tokens": 19431424} {"current_steps": 2373, "total_steps": 3345, "loss": 0.4774, "lr": 4.856763505900826e-07, "epoch": 3.547085201793722, "percentage": 70.94, "elapsed_time": "0:45:56", "remaining_time": "0:18:49", "throughput": 7052.72, "total_tokens": 19439616} {"current_steps": 2374, "total_steps": 3345, "loss": 0.0643, "lr": 4.847477388596263e-07, "epoch": 3.5485799701046337, "percentage": 70.97, "elapsed_time": "0:45:57", "remaining_time": "0:18:47", "throughput": 7052.74, "total_tokens": 19447808} {"current_steps": 2375, "total_steps": 3345, "loss": 0.2434, "lr": 4.838198021420985e-07, "epoch": 3.5500747384155455, "percentage": 71.0, "elapsed_time": "0:45:58", "remaining_time": "0:18:46", "throughput": 7052.73, "total_tokens": 19456000} {"current_steps": 2376, "total_steps": 3345, "loss": 0.2551, "lr": 4.82892541256012e-07, "epoch": 3.5515695067264574, "percentage": 71.03, "elapsed_time": "0:45:59", "remaining_time": "0:18:45", "throughput": 7052.73, "total_tokens": 19464192} {"current_steps": 2377, "total_steps": 3345, "loss": 0.4088, "lr": 4.819659570192846e-07, "epoch": 3.5530642750373693, "percentage": 71.06, "elapsed_time": "0:46:00", "remaining_time": "0:18:44", "throughput": 7052.73, "total_tokens": 19472384} {"current_steps": 2378, "total_steps": 3345, "loss": 0.3144, "lr": 4.810400502492372e-07, "epoch": 3.5545590433482808, "percentage": 71.09, "elapsed_time": "0:46:02", "remaining_time": "0:18:43", "throughput": 7052.74, "total_tokens": 19480576} {"current_steps": 2379, "total_steps": 3345, "loss": 0.1696, "lr": 4.801148217625915e-07, "epoch": 3.5560538116591927, "percentage": 71.12, "elapsed_time": "0:46:03", "remaining_time": "0:18:42", "throughput": 7052.75, "total_tokens": 19488768} {"current_steps": 2380, "total_steps": 3345, "loss": 0.3633, "lr": 4.791902723754735e-07, "epoch": 3.5575485799701045, "percentage": 71.15, "elapsed_time": "0:46:04", "remaining_time": "0:18:40", "throughput": 7052.74, "total_tokens": 19496960} {"current_steps": 2381, "total_steps": 3345, "loss": 0.2802, "lr": 4.782664029034075e-07, "epoch": 3.5590433482810164, "percentage": 71.18, "elapsed_time": "0:46:05", "remaining_time": "0:18:39", "throughput": 7052.74, "total_tokens": 19505152} {"current_steps": 2382, "total_steps": 3345, "loss": 0.2203, "lr": 4.773432141613203e-07, "epoch": 3.5605381165919283, "percentage": 71.21, "elapsed_time": "0:46:06", "remaining_time": "0:18:38", "throughput": 7052.74, "total_tokens": 19513344} {"current_steps": 2383, "total_steps": 3345, "loss": 0.2727, "lr": 4.7642070696353655e-07, "epoch": 3.56203288490284, "percentage": 71.24, "elapsed_time": "0:46:07", "remaining_time": "0:18:37", "throughput": 7052.76, "total_tokens": 19521536} {"current_steps": 2384, "total_steps": 3345, "loss": 0.3158, "lr": 4.7549888212378064e-07, "epoch": 3.563527653213752, "percentage": 71.27, "elapsed_time": "0:46:09", "remaining_time": "0:18:36", "throughput": 7052.76, "total_tokens": 19529728} {"current_steps": 2385, "total_steps": 3345, "loss": 0.2802, "lr": 4.7457774045517545e-07, "epoch": 3.5650224215246635, "percentage": 71.3, "elapsed_time": "0:46:10", "remaining_time": "0:18:35", "throughput": 7052.77, "total_tokens": 19537920} {"current_steps": 2386, "total_steps": 3345, "loss": 0.3929, "lr": 4.736572827702399e-07, "epoch": 3.5665171898355754, "percentage": 71.33, "elapsed_time": "0:46:11", "remaining_time": "0:18:33", "throughput": 7052.75, "total_tokens": 19546112} {"current_steps": 2387, "total_steps": 3345, "loss": 0.2968, "lr": 4.727375098808906e-07, "epoch": 3.5680119581464873, "percentage": 71.36, "elapsed_time": "0:46:12", "remaining_time": "0:18:32", "throughput": 7052.76, "total_tokens": 19554304} {"current_steps": 2388, "total_steps": 3345, "loss": 0.1778, "lr": 4.7181842259844015e-07, "epoch": 3.569506726457399, "percentage": 71.39, "elapsed_time": "0:46:13", "remaining_time": "0:18:31", "throughput": 7052.77, "total_tokens": 19562496} {"current_steps": 2389, "total_steps": 3345, "loss": 0.3033, "lr": 4.7090002173359616e-07, "epoch": 3.5710014947683106, "percentage": 71.42, "elapsed_time": "0:46:14", "remaining_time": "0:18:30", "throughput": 7052.76, "total_tokens": 19570688} {"current_steps": 2390, "total_steps": 3345, "loss": 0.2022, "lr": 4.699823080964601e-07, "epoch": 3.5724962630792225, "percentage": 71.45, "elapsed_time": "0:46:16", "remaining_time": "0:18:29", "throughput": 7052.77, "total_tokens": 19578880} {"current_steps": 2391, "total_steps": 3345, "loss": 0.2354, "lr": 4.6906528249652874e-07, "epoch": 3.5739910313901344, "percentage": 71.48, "elapsed_time": "0:46:17", "remaining_time": "0:18:28", "throughput": 7052.77, "total_tokens": 19587072} {"current_steps": 2392, "total_steps": 3345, "loss": 0.2947, "lr": 4.681489457426902e-07, "epoch": 3.5754857997010463, "percentage": 71.51, "elapsed_time": "0:46:18", "remaining_time": "0:18:26", "throughput": 7052.77, "total_tokens": 19595264} {"current_steps": 2393, "total_steps": 3345, "loss": 0.3376, "lr": 4.672332986432267e-07, "epoch": 3.576980568011958, "percentage": 71.54, "elapsed_time": "0:46:19", "remaining_time": "0:18:25", "throughput": 7052.78, "total_tokens": 19603456} {"current_steps": 2394, "total_steps": 3345, "loss": 0.3803, "lr": 4.663183420058104e-07, "epoch": 3.57847533632287, "percentage": 71.57, "elapsed_time": "0:46:20", "remaining_time": "0:18:24", "throughput": 7052.79, "total_tokens": 19611648} {"current_steps": 2395, "total_steps": 3345, "loss": 0.3319, "lr": 4.654040766375058e-07, "epoch": 3.579970104633782, "percentage": 71.6, "elapsed_time": "0:46:21", "remaining_time": "0:18:23", "throughput": 7052.81, "total_tokens": 19619840} {"current_steps": 2396, "total_steps": 3345, "loss": 0.488, "lr": 4.6449050334476747e-07, "epoch": 3.581464872944694, "percentage": 71.63, "elapsed_time": "0:46:23", "remaining_time": "0:18:22", "throughput": 7052.81, "total_tokens": 19628032} {"current_steps": 2397, "total_steps": 3345, "loss": 0.2587, "lr": 4.6357762293343865e-07, "epoch": 3.5829596412556053, "percentage": 71.66, "elapsed_time": "0:46:24", "remaining_time": "0:18:21", "throughput": 7052.8, "total_tokens": 19636224} {"current_steps": 2398, "total_steps": 3345, "loss": 0.2786, "lr": 4.626654362087524e-07, "epoch": 3.584454409566517, "percentage": 71.69, "elapsed_time": "0:46:25", "remaining_time": "0:18:19", "throughput": 7052.82, "total_tokens": 19644416} {"current_steps": 2399, "total_steps": 3345, "loss": 0.4095, "lr": 4.617539439753288e-07, "epoch": 3.585949177877429, "percentage": 71.72, "elapsed_time": "0:46:26", "remaining_time": "0:18:18", "throughput": 7052.81, "total_tokens": 19652608} {"current_steps": 2400, "total_steps": 3345, "loss": 0.1934, "lr": 4.6084314703717646e-07, "epoch": 3.587443946188341, "percentage": 71.75, "elapsed_time": "0:46:27", "remaining_time": "0:18:17", "throughput": 7052.82, "total_tokens": 19660800} {"current_steps": 2401, "total_steps": 3345, "loss": 0.4336, "lr": 4.5993304619769056e-07, "epoch": 3.5889387144992524, "percentage": 71.78, "elapsed_time": "0:46:28", "remaining_time": "0:18:16", "throughput": 7052.83, "total_tokens": 19668992} {"current_steps": 2402, "total_steps": 3345, "loss": 0.3571, "lr": 4.5902364225965114e-07, "epoch": 3.5904334828101643, "percentage": 71.81, "elapsed_time": "0:46:29", "remaining_time": "0:18:15", "throughput": 7052.83, "total_tokens": 19677184} {"current_steps": 2403, "total_steps": 3345, "loss": 0.18, "lr": 4.5811493602522446e-07, "epoch": 3.591928251121076, "percentage": 71.84, "elapsed_time": "0:46:31", "remaining_time": "0:18:14", "throughput": 7052.84, "total_tokens": 19685376} {"current_steps": 2404, "total_steps": 3345, "loss": 0.434, "lr": 4.5720692829596155e-07, "epoch": 3.593423019431988, "percentage": 71.87, "elapsed_time": "0:46:32", "remaining_time": "0:18:12", "throughput": 7052.84, "total_tokens": 19693568} {"current_steps": 2405, "total_steps": 3345, "loss": 0.1647, "lr": 4.5629961987279717e-07, "epoch": 3.5949177877429, "percentage": 71.9, "elapsed_time": "0:46:33", "remaining_time": "0:18:11", "throughput": 7052.84, "total_tokens": 19701760} {"current_steps": 2406, "total_steps": 3345, "loss": 0.3357, "lr": 4.5539301155604803e-07, "epoch": 3.596412556053812, "percentage": 71.93, "elapsed_time": "0:46:34", "remaining_time": "0:18:10", "throughput": 7052.84, "total_tokens": 19709952} {"current_steps": 2407, "total_steps": 3345, "loss": 0.1746, "lr": 4.5448710414541535e-07, "epoch": 3.5979073243647237, "percentage": 71.96, "elapsed_time": "0:46:35", "remaining_time": "0:18:09", "throughput": 7052.85, "total_tokens": 19718144} {"current_steps": 2408, "total_steps": 3345, "loss": 0.2305, "lr": 4.5358189843998006e-07, "epoch": 3.599402092675635, "percentage": 71.99, "elapsed_time": "0:46:36", "remaining_time": "0:18:08", "throughput": 7052.85, "total_tokens": 19726336} {"current_steps": 2409, "total_steps": 3345, "loss": 0.1929, "lr": 4.526773952382059e-07, "epoch": 3.600896860986547, "percentage": 72.02, "elapsed_time": "0:46:38", "remaining_time": "0:18:07", "throughput": 7052.83, "total_tokens": 19734528} {"current_steps": 2410, "total_steps": 3345, "loss": 0.3345, "lr": 4.517735953379353e-07, "epoch": 3.602391629297459, "percentage": 72.05, "elapsed_time": "0:46:39", "remaining_time": "0:18:06", "throughput": 7052.84, "total_tokens": 19742720} {"current_steps": 2411, "total_steps": 3345, "loss": 0.2962, "lr": 4.5087049953639163e-07, "epoch": 3.603886397608371, "percentage": 72.08, "elapsed_time": "0:46:40", "remaining_time": "0:18:04", "throughput": 7052.84, "total_tokens": 19750912} {"current_steps": 2412, "total_steps": 3345, "loss": 0.1791, "lr": 4.4996810863017686e-07, "epoch": 3.6053811659192823, "percentage": 72.11, "elapsed_time": "0:46:41", "remaining_time": "0:18:03", "throughput": 7052.84, "total_tokens": 19759104} {"current_steps": 2413, "total_steps": 3345, "loss": 0.2786, "lr": 4.490664234152706e-07, "epoch": 3.606875934230194, "percentage": 72.14, "elapsed_time": "0:46:42", "remaining_time": "0:18:02", "throughput": 7052.84, "total_tokens": 19767296} {"current_steps": 2414, "total_steps": 3345, "loss": 0.4794, "lr": 4.481654446870311e-07, "epoch": 3.608370702541106, "percentage": 72.17, "elapsed_time": "0:46:43", "remaining_time": "0:18:01", "throughput": 7052.84, "total_tokens": 19775488} {"current_steps": 2415, "total_steps": 3345, "loss": 0.316, "lr": 4.4726517324019167e-07, "epoch": 3.609865470852018, "percentage": 72.2, "elapsed_time": "0:46:45", "remaining_time": "0:18:00", "throughput": 7052.85, "total_tokens": 19783680} {"current_steps": 2416, "total_steps": 3345, "loss": 0.3911, "lr": 4.46365609868864e-07, "epoch": 3.61136023916293, "percentage": 72.23, "elapsed_time": "0:46:46", "remaining_time": "0:17:59", "throughput": 7052.83, "total_tokens": 19791872} {"current_steps": 2417, "total_steps": 3345, "loss": 0.2955, "lr": 4.4546675536653303e-07, "epoch": 3.6128550074738417, "percentage": 72.26, "elapsed_time": "0:46:47", "remaining_time": "0:17:57", "throughput": 7052.84, "total_tokens": 19800064} {"current_steps": 2418, "total_steps": 3345, "loss": 0.3022, "lr": 4.4456861052605977e-07, "epoch": 3.6143497757847536, "percentage": 72.29, "elapsed_time": "0:46:48", "remaining_time": "0:17:56", "throughput": 7052.84, "total_tokens": 19808256} {"current_steps": 2419, "total_steps": 3345, "loss": 0.3136, "lr": 4.4367117613967947e-07, "epoch": 3.615844544095665, "percentage": 72.32, "elapsed_time": "0:46:49", "remaining_time": "0:17:55", "throughput": 7052.85, "total_tokens": 19816448} {"current_steps": 2420, "total_steps": 3345, "loss": 0.1561, "lr": 4.4277445299899885e-07, "epoch": 3.617339312406577, "percentage": 72.35, "elapsed_time": "0:46:50", "remaining_time": "0:17:54", "throughput": 7052.86, "total_tokens": 19824640} {"current_steps": 2421, "total_steps": 3345, "loss": 0.3101, "lr": 4.4187844189500005e-07, "epoch": 3.618834080717489, "percentage": 72.38, "elapsed_time": "0:46:52", "remaining_time": "0:17:53", "throughput": 7052.87, "total_tokens": 19832832} {"current_steps": 2422, "total_steps": 3345, "loss": 0.4707, "lr": 4.4098314361803467e-07, "epoch": 3.6203288490284007, "percentage": 72.41, "elapsed_time": "0:46:53", "remaining_time": "0:17:52", "throughput": 7052.86, "total_tokens": 19841024} {"current_steps": 2423, "total_steps": 3345, "loss": 0.1399, "lr": 4.40088558957827e-07, "epoch": 3.621823617339312, "percentage": 72.44, "elapsed_time": "0:46:54", "remaining_time": "0:17:50", "throughput": 7052.85, "total_tokens": 19849216} {"current_steps": 2424, "total_steps": 3345, "loss": 0.4326, "lr": 4.3919468870347067e-07, "epoch": 3.623318385650224, "percentage": 72.47, "elapsed_time": "0:46:55", "remaining_time": "0:17:49", "throughput": 7052.85, "total_tokens": 19857408} {"current_steps": 2425, "total_steps": 3345, "loss": 0.5725, "lr": 4.383015336434307e-07, "epoch": 3.624813153961136, "percentage": 72.5, "elapsed_time": "0:46:56", "remaining_time": "0:17:48", "throughput": 7052.84, "total_tokens": 19865600} {"current_steps": 2426, "total_steps": 3345, "loss": 0.2402, "lr": 4.3740909456553943e-07, "epoch": 3.626307922272048, "percentage": 72.53, "elapsed_time": "0:46:57", "remaining_time": "0:17:47", "throughput": 7052.85, "total_tokens": 19873792} {"current_steps": 2427, "total_steps": 3345, "loss": 0.2271, "lr": 4.365173722569993e-07, "epoch": 3.6278026905829597, "percentage": 72.56, "elapsed_time": "0:46:58", "remaining_time": "0:17:46", "throughput": 7052.85, "total_tokens": 19881984} {"current_steps": 2428, "total_steps": 3345, "loss": 0.2899, "lr": 4.3562636750437995e-07, "epoch": 3.6292974588938716, "percentage": 72.59, "elapsed_time": "0:47:00", "remaining_time": "0:17:45", "throughput": 7052.87, "total_tokens": 19890176} {"current_steps": 2429, "total_steps": 3345, "loss": 0.1349, "lr": 4.3473608109361716e-07, "epoch": 3.6307922272047835, "percentage": 72.62, "elapsed_time": "0:47:01", "remaining_time": "0:17:43", "throughput": 7052.88, "total_tokens": 19898368} {"current_steps": 2430, "total_steps": 3345, "loss": 0.2767, "lr": 4.338465138100147e-07, "epoch": 3.6322869955156953, "percentage": 72.65, "elapsed_time": "0:47:02", "remaining_time": "0:17:42", "throughput": 7052.87, "total_tokens": 19906560} {"current_steps": 2431, "total_steps": 3345, "loss": 0.1374, "lr": 4.329576664382404e-07, "epoch": 3.633781763826607, "percentage": 72.68, "elapsed_time": "0:47:03", "remaining_time": "0:17:41", "throughput": 7052.88, "total_tokens": 19914752} {"current_steps": 2432, "total_steps": 3345, "loss": 0.319, "lr": 4.3206953976232854e-07, "epoch": 3.6352765321375187, "percentage": 72.71, "elapsed_time": "0:47:04", "remaining_time": "0:17:40", "throughput": 7052.88, "total_tokens": 19922944} {"current_steps": 2433, "total_steps": 3345, "loss": 0.4303, "lr": 4.311821345656762e-07, "epoch": 3.6367713004484306, "percentage": 72.74, "elapsed_time": "0:47:05", "remaining_time": "0:17:39", "throughput": 7052.88, "total_tokens": 19931136} {"current_steps": 2434, "total_steps": 3345, "loss": 0.1376, "lr": 4.3029545163104547e-07, "epoch": 3.6382660687593424, "percentage": 72.77, "elapsed_time": "0:47:07", "remaining_time": "0:17:38", "throughput": 7052.85, "total_tokens": 19939328} {"current_steps": 2435, "total_steps": 3345, "loss": 0.3231, "lr": 4.2940949174056084e-07, "epoch": 3.639760837070254, "percentage": 72.8, "elapsed_time": "0:47:08", "remaining_time": "0:17:36", "throughput": 7052.86, "total_tokens": 19947520} {"current_steps": 2436, "total_steps": 3345, "loss": 0.2647, "lr": 4.2852425567570826e-07, "epoch": 3.6412556053811658, "percentage": 72.83, "elapsed_time": "0:47:09", "remaining_time": "0:17:35", "throughput": 7052.85, "total_tokens": 19955712} {"current_steps": 2437, "total_steps": 3345, "loss": 0.3105, "lr": 4.2763974421733606e-07, "epoch": 3.6427503736920777, "percentage": 72.86, "elapsed_time": "0:47:10", "remaining_time": "0:17:34", "throughput": 7052.86, "total_tokens": 19963904} {"current_steps": 2438, "total_steps": 3345, "loss": 0.1624, "lr": 4.2675595814565345e-07, "epoch": 3.6442451420029895, "percentage": 72.88, "elapsed_time": "0:47:11", "remaining_time": "0:17:33", "throughput": 7052.87, "total_tokens": 19972096} {"current_steps": 2439, "total_steps": 3345, "loss": 0.3518, "lr": 4.258728982402298e-07, "epoch": 3.6457399103139014, "percentage": 72.91, "elapsed_time": "0:47:12", "remaining_time": "0:17:32", "throughput": 7052.87, "total_tokens": 19980288} {"current_steps": 2440, "total_steps": 3345, "loss": 0.1148, "lr": 4.249905652799929e-07, "epoch": 3.6472346786248133, "percentage": 72.94, "elapsed_time": "0:47:14", "remaining_time": "0:17:31", "throughput": 7052.86, "total_tokens": 19988480} {"current_steps": 2441, "total_steps": 3345, "loss": 0.2303, "lr": 4.241089600432309e-07, "epoch": 3.648729446935725, "percentage": 72.97, "elapsed_time": "0:47:15", "remaining_time": "0:17:30", "throughput": 7052.86, "total_tokens": 19996672} {"current_steps": 2442, "total_steps": 3345, "loss": 0.241, "lr": 4.232280833075884e-07, "epoch": 3.6502242152466366, "percentage": 73.0, "elapsed_time": "0:47:16", "remaining_time": "0:17:28", "throughput": 7052.87, "total_tokens": 20004864} {"current_steps": 2443, "total_steps": 3345, "loss": 0.4071, "lr": 4.223479358500687e-07, "epoch": 3.6517189835575485, "percentage": 73.03, "elapsed_time": "0:47:17", "remaining_time": "0:17:27", "throughput": 7052.88, "total_tokens": 20013056} {"current_steps": 2444, "total_steps": 3345, "loss": 0.4113, "lr": 4.2146851844703185e-07, "epoch": 3.6532137518684604, "percentage": 73.06, "elapsed_time": "0:47:18", "remaining_time": "0:17:26", "throughput": 7052.88, "total_tokens": 20021248} {"current_steps": 2445, "total_steps": 3345, "loss": 0.3318, "lr": 4.205898318741926e-07, "epoch": 3.6547085201793723, "percentage": 73.09, "elapsed_time": "0:47:19", "remaining_time": "0:17:25", "throughput": 7052.89, "total_tokens": 20029440} {"current_steps": 2446, "total_steps": 3345, "loss": 0.4563, "lr": 4.197118769066225e-07, "epoch": 3.6562032884902838, "percentage": 73.12, "elapsed_time": "0:47:21", "remaining_time": "0:17:24", "throughput": 7052.9, "total_tokens": 20037632} {"current_steps": 2447, "total_steps": 3345, "loss": 0.4199, "lr": 4.188346543187466e-07, "epoch": 3.6576980568011956, "percentage": 73.15, "elapsed_time": "0:47:22", "remaining_time": "0:17:23", "throughput": 7052.91, "total_tokens": 20045824} {"current_steps": 2448, "total_steps": 3345, "loss": 0.3376, "lr": 4.179581648843452e-07, "epoch": 3.6591928251121075, "percentage": 73.18, "elapsed_time": "0:47:23", "remaining_time": "0:17:21", "throughput": 7052.91, "total_tokens": 20054016} {"current_steps": 2449, "total_steps": 3345, "loss": 0.3405, "lr": 4.1708240937655033e-07, "epoch": 3.6606875934230194, "percentage": 73.21, "elapsed_time": "0:47:24", "remaining_time": "0:17:20", "throughput": 7052.92, "total_tokens": 20062208} {"current_steps": 2450, "total_steps": 3345, "loss": 0.3582, "lr": 4.162073885678482e-07, "epoch": 3.6621823617339313, "percentage": 73.24, "elapsed_time": "0:47:25", "remaining_time": "0:17:19", "throughput": 7052.92, "total_tokens": 20070400} {"current_steps": 2451, "total_steps": 3345, "loss": 0.4149, "lr": 4.1533310323007626e-07, "epoch": 3.663677130044843, "percentage": 73.27, "elapsed_time": "0:47:26", "remaining_time": "0:17:18", "throughput": 7052.94, "total_tokens": 20078592} {"current_steps": 2452, "total_steps": 3345, "loss": 0.2707, "lr": 4.1445955413442274e-07, "epoch": 3.665171898355755, "percentage": 73.3, "elapsed_time": "0:47:28", "remaining_time": "0:17:17", "throughput": 7052.94, "total_tokens": 20086784} {"current_steps": 2453, "total_steps": 3345, "loss": 0.0961, "lr": 4.1358674205142763e-07, "epoch": 3.6666666666666665, "percentage": 73.33, "elapsed_time": "0:47:29", "remaining_time": "0:17:16", "throughput": 7052.95, "total_tokens": 20094976} {"current_steps": 2454, "total_steps": 3345, "loss": 0.5522, "lr": 4.1271466775097886e-07, "epoch": 3.6681614349775784, "percentage": 73.36, "elapsed_time": "0:47:30", "remaining_time": "0:17:14", "throughput": 7052.95, "total_tokens": 20103168} {"current_steps": 2455, "total_steps": 3345, "loss": 0.2557, "lr": 4.1184333200231645e-07, "epoch": 3.6696562032884903, "percentage": 73.39, "elapsed_time": "0:47:31", "remaining_time": "0:17:13", "throughput": 7052.95, "total_tokens": 20111360} {"current_steps": 2456, "total_steps": 3345, "loss": 0.2914, "lr": 4.109727355740262e-07, "epoch": 3.671150971599402, "percentage": 73.42, "elapsed_time": "0:47:32", "remaining_time": "0:17:12", "throughput": 7052.96, "total_tokens": 20119552} {"current_steps": 2457, "total_steps": 3345, "loss": 0.2089, "lr": 4.1010287923404374e-07, "epoch": 3.672645739910314, "percentage": 73.45, "elapsed_time": "0:47:33", "remaining_time": "0:17:11", "throughput": 7052.94, "total_tokens": 20127744} {"current_steps": 2458, "total_steps": 3345, "loss": 0.1993, "lr": 4.0923376374965006e-07, "epoch": 3.6741405082212255, "percentage": 73.48, "elapsed_time": "0:47:34", "remaining_time": "0:17:10", "throughput": 7052.95, "total_tokens": 20135936} {"current_steps": 2459, "total_steps": 3345, "loss": 0.3219, "lr": 4.0836538988747427e-07, "epoch": 3.6756352765321374, "percentage": 73.51, "elapsed_time": "0:47:36", "remaining_time": "0:17:09", "throughput": 7052.95, "total_tokens": 20144128} {"current_steps": 2460, "total_steps": 3345, "loss": 0.1559, "lr": 4.074977584134911e-07, "epoch": 3.6771300448430493, "percentage": 73.54, "elapsed_time": "0:47:37", "remaining_time": "0:17:07", "throughput": 7052.95, "total_tokens": 20152320} {"current_steps": 2461, "total_steps": 3345, "loss": 0.3351, "lr": 4.0663087009301895e-07, "epoch": 3.678624813153961, "percentage": 73.57, "elapsed_time": "0:47:38", "remaining_time": "0:17:06", "throughput": 7052.96, "total_tokens": 20160512} {"current_steps": 2462, "total_steps": 3345, "loss": 0.1913, "lr": 4.0576472569072296e-07, "epoch": 3.680119581464873, "percentage": 73.6, "elapsed_time": "0:47:39", "remaining_time": "0:17:05", "throughput": 7052.95, "total_tokens": 20168704} {"current_steps": 2463, "total_steps": 3345, "loss": 0.1651, "lr": 4.048993259706098e-07, "epoch": 3.681614349775785, "percentage": 73.63, "elapsed_time": "0:47:40", "remaining_time": "0:17:04", "throughput": 7052.95, "total_tokens": 20176896} {"current_steps": 2464, "total_steps": 3345, "loss": 0.2042, "lr": 4.040346716960313e-07, "epoch": 3.683109118086697, "percentage": 73.66, "elapsed_time": "0:47:41", "remaining_time": "0:17:03", "throughput": 7052.94, "total_tokens": 20185088} {"current_steps": 2465, "total_steps": 3345, "loss": 0.4744, "lr": 4.0317076362968e-07, "epoch": 3.6846038863976083, "percentage": 73.69, "elapsed_time": "0:47:43", "remaining_time": "0:17:02", "throughput": 7052.94, "total_tokens": 20193280} {"current_steps": 2466, "total_steps": 3345, "loss": 0.2138, "lr": 4.023076025335913e-07, "epoch": 3.68609865470852, "percentage": 73.72, "elapsed_time": "0:47:44", "remaining_time": "0:17:00", "throughput": 7052.93, "total_tokens": 20201472} {"current_steps": 2467, "total_steps": 3345, "loss": 0.1665, "lr": 4.0144518916914205e-07, "epoch": 3.687593423019432, "percentage": 73.75, "elapsed_time": "0:47:45", "remaining_time": "0:16:59", "throughput": 7052.93, "total_tokens": 20209664} {"current_steps": 2468, "total_steps": 3345, "loss": 0.5018, "lr": 4.0058352429704824e-07, "epoch": 3.689088191330344, "percentage": 73.78, "elapsed_time": "0:47:46", "remaining_time": "0:16:58", "throughput": 7052.93, "total_tokens": 20217856} {"current_steps": 2469, "total_steps": 3345, "loss": 0.0567, "lr": 3.997226086773667e-07, "epoch": 3.6905829596412554, "percentage": 73.81, "elapsed_time": "0:47:47", "remaining_time": "0:16:57", "throughput": 7052.93, "total_tokens": 20226048} {"current_steps": 2470, "total_steps": 3345, "loss": 0.0861, "lr": 3.9886244306949263e-07, "epoch": 3.6920777279521673, "percentage": 73.84, "elapsed_time": "0:47:48", "remaining_time": "0:16:56", "throughput": 7052.94, "total_tokens": 20234240} {"current_steps": 2471, "total_steps": 3345, "loss": 0.2286, "lr": 3.980030282321602e-07, "epoch": 3.693572496263079, "percentage": 73.87, "elapsed_time": "0:47:50", "remaining_time": "0:16:55", "throughput": 7052.94, "total_tokens": 20242432} {"current_steps": 2472, "total_steps": 3345, "loss": 0.3505, "lr": 3.971443649234413e-07, "epoch": 3.695067264573991, "percentage": 73.9, "elapsed_time": "0:47:51", "remaining_time": "0:16:53", "throughput": 7052.94, "total_tokens": 20250624} {"current_steps": 2473, "total_steps": 3345, "loss": 0.5678, "lr": 3.9628645390074506e-07, "epoch": 3.696562032884903, "percentage": 73.93, "elapsed_time": "0:47:52", "remaining_time": "0:16:52", "throughput": 7052.94, "total_tokens": 20258816} {"current_steps": 2474, "total_steps": 3345, "loss": 0.3816, "lr": 3.95429295920816e-07, "epoch": 3.698056801195815, "percentage": 73.96, "elapsed_time": "0:47:53", "remaining_time": "0:16:51", "throughput": 7052.94, "total_tokens": 20267008} {"current_steps": 2475, "total_steps": 3345, "loss": 0.32, "lr": 3.9457289173973555e-07, "epoch": 3.6995515695067267, "percentage": 73.99, "elapsed_time": "0:47:54", "remaining_time": "0:16:50", "throughput": 7052.93, "total_tokens": 20275200} {"current_steps": 2476, "total_steps": 3345, "loss": 0.2944, "lr": 3.9371724211292014e-07, "epoch": 3.701046337817638, "percentage": 74.02, "elapsed_time": "0:47:55", "remaining_time": "0:16:49", "throughput": 7052.93, "total_tokens": 20283392} {"current_steps": 2477, "total_steps": 3345, "loss": 0.2785, "lr": 3.9286234779511976e-07, "epoch": 3.70254110612855, "percentage": 74.05, "elapsed_time": "0:47:57", "remaining_time": "0:16:48", "throughput": 7052.93, "total_tokens": 20291584} {"current_steps": 2478, "total_steps": 3345, "loss": 0.2637, "lr": 3.9200820954041913e-07, "epoch": 3.704035874439462, "percentage": 74.08, "elapsed_time": "0:47:58", "remaining_time": "0:16:47", "throughput": 7052.93, "total_tokens": 20299776} {"current_steps": 2479, "total_steps": 3345, "loss": 0.2907, "lr": 3.9115482810223523e-07, "epoch": 3.705530642750374, "percentage": 74.11, "elapsed_time": "0:47:59", "remaining_time": "0:16:45", "throughput": 7052.93, "total_tokens": 20307968} {"current_steps": 2480, "total_steps": 3345, "loss": 0.3157, "lr": 3.903022042333185e-07, "epoch": 3.7070254110612852, "percentage": 74.14, "elapsed_time": "0:48:00", "remaining_time": "0:16:44", "throughput": 7052.93, "total_tokens": 20316160} {"current_steps": 2481, "total_steps": 3345, "loss": 0.4281, "lr": 3.894503386857498e-07, "epoch": 3.708520179372197, "percentage": 74.17, "elapsed_time": "0:48:01", "remaining_time": "0:16:43", "throughput": 7052.95, "total_tokens": 20324352} {"current_steps": 2482, "total_steps": 3345, "loss": 0.349, "lr": 3.8859923221094206e-07, "epoch": 3.710014947683109, "percentage": 74.2, "elapsed_time": "0:48:02", "remaining_time": "0:16:42", "throughput": 7052.95, "total_tokens": 20332544} {"current_steps": 2483, "total_steps": 3345, "loss": 0.2435, "lr": 3.8774888555963895e-07, "epoch": 3.711509715994021, "percentage": 74.23, "elapsed_time": "0:48:04", "remaining_time": "0:16:41", "throughput": 7052.95, "total_tokens": 20340736} {"current_steps": 2484, "total_steps": 3345, "loss": 0.3785, "lr": 3.868992994819126e-07, "epoch": 3.713004484304933, "percentage": 74.26, "elapsed_time": "0:48:05", "remaining_time": "0:16:40", "throughput": 7052.94, "total_tokens": 20348928} {"current_steps": 2485, "total_steps": 3345, "loss": 0.2553, "lr": 3.860504747271657e-07, "epoch": 3.7144992526158447, "percentage": 74.29, "elapsed_time": "0:48:06", "remaining_time": "0:16:38", "throughput": 7052.93, "total_tokens": 20357120} {"current_steps": 2486, "total_steps": 3345, "loss": 0.3993, "lr": 3.852024120441279e-07, "epoch": 3.7159940209267566, "percentage": 74.32, "elapsed_time": "0:48:07", "remaining_time": "0:16:37", "throughput": 7052.92, "total_tokens": 20365312} {"current_steps": 2487, "total_steps": 3345, "loss": 0.2096, "lr": 3.8435511218085835e-07, "epoch": 3.717488789237668, "percentage": 74.35, "elapsed_time": "0:48:08", "remaining_time": "0:16:36", "throughput": 7052.9, "total_tokens": 20373504} {"current_steps": 2488, "total_steps": 3345, "loss": 0.2513, "lr": 3.8350857588474136e-07, "epoch": 3.71898355754858, "percentage": 74.38, "elapsed_time": "0:48:09", "remaining_time": "0:16:35", "throughput": 7052.9, "total_tokens": 20381696} {"current_steps": 2489, "total_steps": 3345, "loss": 0.4669, "lr": 3.8266280390249017e-07, "epoch": 3.720478325859492, "percentage": 74.41, "elapsed_time": "0:48:10", "remaining_time": "0:16:34", "throughput": 7052.89, "total_tokens": 20389888} {"current_steps": 2490, "total_steps": 3345, "loss": 0.1766, "lr": 3.818177969801412e-07, "epoch": 3.7219730941704037, "percentage": 74.44, "elapsed_time": "0:48:12", "remaining_time": "0:16:33", "throughput": 7052.89, "total_tokens": 20398080} {"current_steps": 2491, "total_steps": 3345, "loss": 0.3072, "lr": 3.809735558630584e-07, "epoch": 3.7234678624813156, "percentage": 74.47, "elapsed_time": "0:48:13", "remaining_time": "0:16:31", "throughput": 7052.87, "total_tokens": 20406272} {"current_steps": 2492, "total_steps": 3345, "loss": 0.2205, "lr": 3.8013008129592814e-07, "epoch": 3.724962630792227, "percentage": 74.5, "elapsed_time": "0:48:14", "remaining_time": "0:16:30", "throughput": 7052.88, "total_tokens": 20414464} {"current_steps": 2493, "total_steps": 3345, "loss": 0.3981, "lr": 3.7928737402276206e-07, "epoch": 3.726457399103139, "percentage": 74.53, "elapsed_time": "0:48:15", "remaining_time": "0:16:29", "throughput": 7052.88, "total_tokens": 20422656} {"current_steps": 2494, "total_steps": 3345, "loss": 0.5078, "lr": 3.7844543478689473e-07, "epoch": 3.7279521674140508, "percentage": 74.56, "elapsed_time": "0:48:16", "remaining_time": "0:16:28", "throughput": 7052.88, "total_tokens": 20430848} {"current_steps": 2495, "total_steps": 3345, "loss": 0.5201, "lr": 3.776042643309825e-07, "epoch": 3.7294469357249627, "percentage": 74.59, "elapsed_time": "0:48:17", "remaining_time": "0:16:27", "throughput": 7052.88, "total_tokens": 20439040} {"current_steps": 2496, "total_steps": 3345, "loss": 0.1975, "lr": 3.767638633970047e-07, "epoch": 3.7309417040358746, "percentage": 74.62, "elapsed_time": "0:48:19", "remaining_time": "0:16:26", "throughput": 7052.87, "total_tokens": 20447232} {"current_steps": 2497, "total_steps": 3345, "loss": 0.3731, "lr": 3.7592423272626076e-07, "epoch": 3.7324364723467864, "percentage": 74.65, "elapsed_time": "0:48:20", "remaining_time": "0:16:24", "throughput": 7052.87, "total_tokens": 20455424} {"current_steps": 2498, "total_steps": 3345, "loss": 0.3787, "lr": 3.750853730593719e-07, "epoch": 3.7339312406576983, "percentage": 74.68, "elapsed_time": "0:48:21", "remaining_time": "0:16:23", "throughput": 7052.87, "total_tokens": 20463616} {"current_steps": 2499, "total_steps": 3345, "loss": 0.2161, "lr": 3.7424728513627786e-07, "epoch": 3.7354260089686098, "percentage": 74.71, "elapsed_time": "0:48:22", "remaining_time": "0:16:22", "throughput": 7052.86, "total_tokens": 20471808} {"current_steps": 2500, "total_steps": 3345, "loss": 0.243, "lr": 3.7340996969623874e-07, "epoch": 3.7369207772795217, "percentage": 74.74, "elapsed_time": "0:48:23", "remaining_time": "0:16:21", "throughput": 7052.85, "total_tokens": 20480000} {"current_steps": 2501, "total_steps": 3345, "loss": 0.1587, "lr": 3.7257342747783325e-07, "epoch": 3.7384155455904335, "percentage": 74.77, "elapsed_time": "0:48:24", "remaining_time": "0:16:20", "throughput": 7052.86, "total_tokens": 20488192} {"current_steps": 2502, "total_steps": 3345, "loss": 0.2233, "lr": 3.7173765921895685e-07, "epoch": 3.7399103139013454, "percentage": 74.8, "elapsed_time": "0:48:26", "remaining_time": "0:16:19", "throughput": 7052.86, "total_tokens": 20496384} {"current_steps": 2503, "total_steps": 3345, "loss": 0.1806, "lr": 3.70902665656824e-07, "epoch": 3.741405082212257, "percentage": 74.83, "elapsed_time": "0:48:27", "remaining_time": "0:16:17", "throughput": 7052.85, "total_tokens": 20504576} {"current_steps": 2504, "total_steps": 3345, "loss": 0.2071, "lr": 3.700684475279644e-07, "epoch": 3.7428998505231688, "percentage": 74.86, "elapsed_time": "0:48:28", "remaining_time": "0:16:16", "throughput": 7052.84, "total_tokens": 20512768} {"current_steps": 2505, "total_steps": 3345, "loss": 0.2561, "lr": 3.6923500556822435e-07, "epoch": 3.7443946188340806, "percentage": 74.89, "elapsed_time": "0:48:29", "remaining_time": "0:16:15", "throughput": 7052.84, "total_tokens": 20520960} {"current_steps": 2506, "total_steps": 3345, "loss": 0.2927, "lr": 3.6840234051276554e-07, "epoch": 3.7458893871449925, "percentage": 74.92, "elapsed_time": "0:48:30", "remaining_time": "0:16:14", "throughput": 7052.79, "total_tokens": 20529152} {"current_steps": 2507, "total_steps": 3345, "loss": 0.3721, "lr": 3.67570453096065e-07, "epoch": 3.7473841554559044, "percentage": 74.95, "elapsed_time": "0:48:31", "remaining_time": "0:16:13", "throughput": 7052.78, "total_tokens": 20537344} {"current_steps": 2508, "total_steps": 3345, "loss": 0.2668, "lr": 3.6673934405191197e-07, "epoch": 3.7488789237668163, "percentage": 74.98, "elapsed_time": "0:48:33", "remaining_time": "0:16:12", "throughput": 7052.78, "total_tokens": 20545536} {"current_steps": 2509, "total_steps": 3345, "loss": 0.2144, "lr": 3.659090141134108e-07, "epoch": 3.750373692077728, "percentage": 75.01, "elapsed_time": "0:48:34", "remaining_time": "0:16:11", "throughput": 7052.76, "total_tokens": 20553728} {"current_steps": 2510, "total_steps": 3345, "loss": 0.2998, "lr": 3.650794640129786e-07, "epoch": 3.7518684603886396, "percentage": 75.04, "elapsed_time": "0:48:35", "remaining_time": "0:16:09", "throughput": 7052.74, "total_tokens": 20561920} {"current_steps": 2511, "total_steps": 3345, "loss": 0.2584, "lr": 3.642506944823432e-07, "epoch": 3.7533632286995515, "percentage": 75.07, "elapsed_time": "0:48:36", "remaining_time": "0:16:08", "throughput": 7052.74, "total_tokens": 20570112} {"current_steps": 2512, "total_steps": 3345, "loss": 0.5807, "lr": 3.634227062525454e-07, "epoch": 3.7548579970104634, "percentage": 75.1, "elapsed_time": "0:48:37", "remaining_time": "0:16:07", "throughput": 7052.74, "total_tokens": 20578304} {"current_steps": 2513, "total_steps": 3345, "loss": 0.1999, "lr": 3.625955000539355e-07, "epoch": 3.7563527653213753, "percentage": 75.13, "elapsed_time": "0:48:38", "remaining_time": "0:16:06", "throughput": 7052.71, "total_tokens": 20586496} {"current_steps": 2514, "total_steps": 3345, "loss": 0.4811, "lr": 3.617690766161756e-07, "epoch": 3.7578475336322867, "percentage": 75.16, "elapsed_time": "0:48:40", "remaining_time": "0:16:05", "throughput": 7052.7, "total_tokens": 20594688} {"current_steps": 2515, "total_steps": 3345, "loss": 0.3352, "lr": 3.609434366682356e-07, "epoch": 3.7593423019431986, "percentage": 75.19, "elapsed_time": "0:48:41", "remaining_time": "0:16:04", "throughput": 7052.7, "total_tokens": 20602880} {"current_steps": 2516, "total_steps": 3345, "loss": 0.2446, "lr": 3.6011858093839546e-07, "epoch": 3.7608370702541105, "percentage": 75.22, "elapsed_time": "0:48:42", "remaining_time": "0:16:02", "throughput": 7052.69, "total_tokens": 20611072} {"current_steps": 2517, "total_steps": 3345, "loss": 0.5913, "lr": 3.5929451015424347e-07, "epoch": 3.7623318385650224, "percentage": 75.25, "elapsed_time": "0:48:43", "remaining_time": "0:16:01", "throughput": 7052.67, "total_tokens": 20619264} {"current_steps": 2518, "total_steps": 3345, "loss": 0.1316, "lr": 3.584712250426745e-07, "epoch": 3.7638266068759343, "percentage": 75.28, "elapsed_time": "0:48:44", "remaining_time": "0:16:00", "throughput": 7052.67, "total_tokens": 20627456} {"current_steps": 2519, "total_steps": 3345, "loss": 0.5206, "lr": 3.5764872632989166e-07, "epoch": 3.765321375186846, "percentage": 75.31, "elapsed_time": "0:48:45", "remaining_time": "0:15:59", "throughput": 7052.67, "total_tokens": 20635648} {"current_steps": 2520, "total_steps": 3345, "loss": 0.34, "lr": 3.568270147414031e-07, "epoch": 3.766816143497758, "percentage": 75.34, "elapsed_time": "0:48:47", "remaining_time": "0:15:58", "throughput": 7052.67, "total_tokens": 20643840} {"current_steps": 2521, "total_steps": 3345, "loss": 0.3494, "lr": 3.5600609100202396e-07, "epoch": 3.7683109118086695, "percentage": 75.37, "elapsed_time": "0:48:48", "remaining_time": "0:15:57", "throughput": 7052.68, "total_tokens": 20652032} {"current_steps": 2522, "total_steps": 3345, "loss": 0.3497, "lr": 3.551859558358728e-07, "epoch": 3.7698056801195814, "percentage": 75.4, "elapsed_time": "0:48:49", "remaining_time": "0:15:55", "throughput": 7052.68, "total_tokens": 20660224} {"current_steps": 2523, "total_steps": 3345, "loss": 0.2926, "lr": 3.5436660996637507e-07, "epoch": 3.7713004484304933, "percentage": 75.43, "elapsed_time": "0:48:50", "remaining_time": "0:15:54", "throughput": 7052.68, "total_tokens": 20668416} {"current_steps": 2524, "total_steps": 3345, "loss": 0.0908, "lr": 3.535480541162574e-07, "epoch": 3.772795216741405, "percentage": 75.46, "elapsed_time": "0:48:51", "remaining_time": "0:15:53", "throughput": 7052.68, "total_tokens": 20676608} {"current_steps": 2525, "total_steps": 3345, "loss": 0.3029, "lr": 3.527302890075511e-07, "epoch": 3.774289985052317, "percentage": 75.49, "elapsed_time": "0:48:52", "remaining_time": "0:15:52", "throughput": 7052.66, "total_tokens": 20684800} {"current_steps": 2526, "total_steps": 3345, "loss": 0.1728, "lr": 3.5191331536159e-07, "epoch": 3.7757847533632285, "percentage": 75.52, "elapsed_time": "0:48:54", "remaining_time": "0:15:51", "throughput": 7052.67, "total_tokens": 20692992} {"current_steps": 2527, "total_steps": 3345, "loss": 0.3129, "lr": 3.5109713389900836e-07, "epoch": 3.7772795216741404, "percentage": 75.55, "elapsed_time": "0:48:55", "remaining_time": "0:15:50", "throughput": 7052.64, "total_tokens": 20701184} {"current_steps": 2528, "total_steps": 3345, "loss": 0.3573, "lr": 3.5028174533974376e-07, "epoch": 3.7787742899850523, "percentage": 75.58, "elapsed_time": "0:48:56", "remaining_time": "0:15:48", "throughput": 7052.64, "total_tokens": 20709376} {"current_steps": 2529, "total_steps": 3345, "loss": 0.2564, "lr": 3.494671504030324e-07, "epoch": 3.780269058295964, "percentage": 75.61, "elapsed_time": "0:48:57", "remaining_time": "0:15:47", "throughput": 7052.65, "total_tokens": 20717568} {"current_steps": 2530, "total_steps": 3345, "loss": 0.3523, "lr": 3.4865334980741225e-07, "epoch": 3.781763826606876, "percentage": 75.64, "elapsed_time": "0:48:58", "remaining_time": "0:15:46", "throughput": 7052.64, "total_tokens": 20725760} {"current_steps": 2531, "total_steps": 3345, "loss": 0.5112, "lr": 3.4784034427071856e-07, "epoch": 3.783258594917788, "percentage": 75.67, "elapsed_time": "0:48:59", "remaining_time": "0:15:45", "throughput": 7052.63, "total_tokens": 20733952} {"current_steps": 2532, "total_steps": 3345, "loss": 0.2302, "lr": 3.4702813451008733e-07, "epoch": 3.7847533632287, "percentage": 75.7, "elapsed_time": "0:49:01", "remaining_time": "0:15:44", "throughput": 7052.63, "total_tokens": 20742144} {"current_steps": 2533, "total_steps": 3345, "loss": 0.5147, "lr": 3.4621672124195163e-07, "epoch": 3.7862481315396113, "percentage": 75.72, "elapsed_time": "0:49:02", "remaining_time": "0:15:43", "throughput": 7052.64, "total_tokens": 20750336} {"current_steps": 2534, "total_steps": 3345, "loss": 0.2623, "lr": 3.454061051820415e-07, "epoch": 3.787742899850523, "percentage": 75.75, "elapsed_time": "0:49:03", "remaining_time": "0:15:42", "throughput": 7052.63, "total_tokens": 20758528} {"current_steps": 2535, "total_steps": 3345, "loss": 0.2644, "lr": 3.4459628704538506e-07, "epoch": 3.789237668161435, "percentage": 75.78, "elapsed_time": "0:49:04", "remaining_time": "0:15:40", "throughput": 7052.64, "total_tokens": 20766720} {"current_steps": 2536, "total_steps": 3345, "loss": 0.1977, "lr": 3.4378726754630514e-07, "epoch": 3.790732436472347, "percentage": 75.81, "elapsed_time": "0:49:05", "remaining_time": "0:15:39", "throughput": 7052.65, "total_tokens": 20774912} {"current_steps": 2537, "total_steps": 3345, "loss": 0.2709, "lr": 3.429790473984214e-07, "epoch": 3.7922272047832584, "percentage": 75.84, "elapsed_time": "0:49:06", "remaining_time": "0:15:38", "throughput": 7052.65, "total_tokens": 20783104} {"current_steps": 2538, "total_steps": 3345, "loss": 0.3705, "lr": 3.4217162731464735e-07, "epoch": 3.7937219730941703, "percentage": 75.87, "elapsed_time": "0:49:08", "remaining_time": "0:15:37", "throughput": 7052.66, "total_tokens": 20791296} {"current_steps": 2539, "total_steps": 3345, "loss": 0.2966, "lr": 3.4136500800719135e-07, "epoch": 3.795216741405082, "percentage": 75.9, "elapsed_time": "0:49:09", "remaining_time": "0:15:36", "throughput": 7052.66, "total_tokens": 20799488} {"current_steps": 2540, "total_steps": 3345, "loss": 0.1387, "lr": 3.405591901875556e-07, "epoch": 3.796711509715994, "percentage": 75.93, "elapsed_time": "0:49:10", "remaining_time": "0:15:35", "throughput": 7052.66, "total_tokens": 20807680} {"current_steps": 2541, "total_steps": 3345, "loss": 0.4423, "lr": 3.3975417456653503e-07, "epoch": 3.798206278026906, "percentage": 75.96, "elapsed_time": "0:49:11", "remaining_time": "0:15:33", "throughput": 7052.66, "total_tokens": 20815872} {"current_steps": 2542, "total_steps": 3345, "loss": 0.2927, "lr": 3.389499618542172e-07, "epoch": 3.799701046337818, "percentage": 75.99, "elapsed_time": "0:49:12", "remaining_time": "0:15:32", "throughput": 7052.66, "total_tokens": 20824064} {"current_steps": 2543, "total_steps": 3345, "loss": 0.4561, "lr": 3.3814655275998044e-07, "epoch": 3.8011958146487297, "percentage": 76.02, "elapsed_time": "0:49:13", "remaining_time": "0:15:31", "throughput": 7052.66, "total_tokens": 20832256} {"current_steps": 2544, "total_steps": 3345, "loss": 0.2641, "lr": 3.3734394799249614e-07, "epoch": 3.802690582959641, "percentage": 76.05, "elapsed_time": "0:49:14", "remaining_time": "0:15:30", "throughput": 7052.64, "total_tokens": 20840448} {"current_steps": 2545, "total_steps": 3345, "loss": 0.3021, "lr": 3.3654214825972394e-07, "epoch": 3.804185351270553, "percentage": 76.08, "elapsed_time": "0:49:16", "remaining_time": "0:15:29", "throughput": 7052.64, "total_tokens": 20848640} {"current_steps": 2546, "total_steps": 3345, "loss": 0.3328, "lr": 3.357411542689154e-07, "epoch": 3.805680119581465, "percentage": 76.11, "elapsed_time": "0:49:17", "remaining_time": "0:15:28", "throughput": 7052.65, "total_tokens": 20856832} {"current_steps": 2547, "total_steps": 3345, "loss": 0.4348, "lr": 3.3494096672660987e-07, "epoch": 3.807174887892377, "percentage": 76.14, "elapsed_time": "0:49:18", "remaining_time": "0:15:26", "throughput": 7052.65, "total_tokens": 20865024} {"current_steps": 2548, "total_steps": 3345, "loss": 0.296, "lr": 3.341415863386362e-07, "epoch": 3.8086696562032882, "percentage": 76.17, "elapsed_time": "0:49:19", "remaining_time": "0:15:25", "throughput": 7052.65, "total_tokens": 20873216} {"current_steps": 2549, "total_steps": 3345, "loss": 0.2249, "lr": 3.333430138101113e-07, "epoch": 3.8101644245142, "percentage": 76.2, "elapsed_time": "0:49:20", "remaining_time": "0:15:24", "throughput": 7052.64, "total_tokens": 20881408} {"current_steps": 2550, "total_steps": 3345, "loss": 0.1695, "lr": 3.325452498454386e-07, "epoch": 3.811659192825112, "percentage": 76.23, "elapsed_time": "0:49:21", "remaining_time": "0:15:23", "throughput": 7052.62, "total_tokens": 20889600} {"current_steps": 2551, "total_steps": 3345, "loss": 0.4063, "lr": 3.317482951483096e-07, "epoch": 3.813153961136024, "percentage": 76.26, "elapsed_time": "0:49:23", "remaining_time": "0:15:22", "throughput": 7052.61, "total_tokens": 20897792} {"current_steps": 2552, "total_steps": 3345, "loss": 0.2146, "lr": 3.3095215042170075e-07, "epoch": 3.814648729446936, "percentage": 76.29, "elapsed_time": "0:49:24", "remaining_time": "0:15:21", "throughput": 7052.61, "total_tokens": 20905984} {"current_steps": 2553, "total_steps": 3345, "loss": 0.2487, "lr": 3.301568163678749e-07, "epoch": 3.8161434977578477, "percentage": 76.32, "elapsed_time": "0:49:25", "remaining_time": "0:15:19", "throughput": 7052.61, "total_tokens": 20914176} {"current_steps": 2554, "total_steps": 3345, "loss": 0.2233, "lr": 3.2936229368837916e-07, "epoch": 3.8176382660687596, "percentage": 76.35, "elapsed_time": "0:49:26", "remaining_time": "0:15:18", "throughput": 7052.6, "total_tokens": 20922368} {"current_steps": 2555, "total_steps": 3345, "loss": 0.3344, "lr": 3.2856858308404545e-07, "epoch": 3.819133034379671, "percentage": 76.38, "elapsed_time": "0:49:27", "remaining_time": "0:15:17", "throughput": 7052.6, "total_tokens": 20930560} {"current_steps": 2556, "total_steps": 3345, "loss": 0.1892, "lr": 3.2777568525498916e-07, "epoch": 3.820627802690583, "percentage": 76.41, "elapsed_time": "0:49:28", "remaining_time": "0:15:16", "throughput": 7052.59, "total_tokens": 20938752} {"current_steps": 2557, "total_steps": 3345, "loss": 0.2162, "lr": 3.2698360090060886e-07, "epoch": 3.8221225710014948, "percentage": 76.44, "elapsed_time": "0:49:30", "remaining_time": "0:15:15", "throughput": 7052.59, "total_tokens": 20946944} {"current_steps": 2558, "total_steps": 3345, "loss": 0.141, "lr": 3.261923307195859e-07, "epoch": 3.8236173393124067, "percentage": 76.47, "elapsed_time": "0:49:31", "remaining_time": "0:15:14", "throughput": 7052.58, "total_tokens": 20955136} {"current_steps": 2559, "total_steps": 3345, "loss": 0.2337, "lr": 3.254018754098823e-07, "epoch": 3.8251121076233185, "percentage": 76.5, "elapsed_time": "0:49:32", "remaining_time": "0:15:12", "throughput": 7052.56, "total_tokens": 20963328} {"current_steps": 2560, "total_steps": 3345, "loss": 0.1536, "lr": 3.2461223566874284e-07, "epoch": 3.82660687593423, "percentage": 76.53, "elapsed_time": "0:49:33", "remaining_time": "0:15:11", "throughput": 7052.55, "total_tokens": 20971520} {"current_steps": 2561, "total_steps": 3345, "loss": 0.4246, "lr": 3.238234121926914e-07, "epoch": 3.828101644245142, "percentage": 76.56, "elapsed_time": "0:49:34", "remaining_time": "0:15:10", "throughput": 7052.55, "total_tokens": 20979712} {"current_steps": 2562, "total_steps": 3345, "loss": 0.0852, "lr": 3.2303540567753326e-07, "epoch": 3.8295964125560538, "percentage": 76.59, "elapsed_time": "0:49:35", "remaining_time": "0:15:09", "throughput": 7052.55, "total_tokens": 20987904} {"current_steps": 2563, "total_steps": 3345, "loss": 0.4695, "lr": 3.222482168183516e-07, "epoch": 3.8310911808669657, "percentage": 76.62, "elapsed_time": "0:49:37", "remaining_time": "0:15:08", "throughput": 7052.55, "total_tokens": 20996096} {"current_steps": 2564, "total_steps": 3345, "loss": 0.0781, "lr": 3.214618463095097e-07, "epoch": 3.8325859491778775, "percentage": 76.65, "elapsed_time": "0:49:38", "remaining_time": "0:15:07", "throughput": 7052.55, "total_tokens": 21004288} {"current_steps": 2565, "total_steps": 3345, "loss": 0.2637, "lr": 3.206762948446486e-07, "epoch": 3.8340807174887894, "percentage": 76.68, "elapsed_time": "0:49:39", "remaining_time": "0:15:06", "throughput": 7052.54, "total_tokens": 21012480} {"current_steps": 2566, "total_steps": 3345, "loss": 0.2367, "lr": 3.198915631166863e-07, "epoch": 3.8355754857997013, "percentage": 76.71, "elapsed_time": "0:49:40", "remaining_time": "0:15:04", "throughput": 7052.54, "total_tokens": 21020672} {"current_steps": 2567, "total_steps": 3345, "loss": 0.449, "lr": 3.1910765181781863e-07, "epoch": 3.8370702541106128, "percentage": 76.74, "elapsed_time": "0:49:41", "remaining_time": "0:15:03", "throughput": 7052.53, "total_tokens": 21028864} {"current_steps": 2568, "total_steps": 3345, "loss": 0.3567, "lr": 3.183245616395166e-07, "epoch": 3.8385650224215246, "percentage": 76.77, "elapsed_time": "0:49:42", "remaining_time": "0:15:02", "throughput": 7052.53, "total_tokens": 21037056} {"current_steps": 2569, "total_steps": 3345, "loss": 0.1929, "lr": 3.1754229327252833e-07, "epoch": 3.8400597907324365, "percentage": 76.8, "elapsed_time": "0:49:44", "remaining_time": "0:15:01", "throughput": 7052.49, "total_tokens": 21045248} {"current_steps": 2570, "total_steps": 3345, "loss": 0.2765, "lr": 3.1676084740687565e-07, "epoch": 3.8415545590433484, "percentage": 76.83, "elapsed_time": "0:49:45", "remaining_time": "0:15:00", "throughput": 7052.49, "total_tokens": 21053440} {"current_steps": 2571, "total_steps": 3345, "loss": 0.297, "lr": 3.1598022473185565e-07, "epoch": 3.84304932735426, "percentage": 76.86, "elapsed_time": "0:49:46", "remaining_time": "0:14:59", "throughput": 7052.49, "total_tokens": 21061632} {"current_steps": 2572, "total_steps": 3345, "loss": 0.2355, "lr": 3.152004259360399e-07, "epoch": 3.8445440956651717, "percentage": 76.89, "elapsed_time": "0:49:47", "remaining_time": "0:14:57", "throughput": 7052.48, "total_tokens": 21069824} {"current_steps": 2573, "total_steps": 3345, "loss": 0.2862, "lr": 3.1442145170727145e-07, "epoch": 3.8460388639760836, "percentage": 76.92, "elapsed_time": "0:49:48", "remaining_time": "0:14:56", "throughput": 7052.48, "total_tokens": 21078016} {"current_steps": 2574, "total_steps": 3345, "loss": 0.3102, "lr": 3.136433027326677e-07, "epoch": 3.8475336322869955, "percentage": 76.95, "elapsed_time": "0:49:49", "remaining_time": "0:14:55", "throughput": 7052.47, "total_tokens": 21086208} {"current_steps": 2575, "total_steps": 3345, "loss": 0.2542, "lr": 3.1286597969861736e-07, "epoch": 3.8490284005979074, "percentage": 76.98, "elapsed_time": "0:49:51", "remaining_time": "0:14:54", "throughput": 7052.47, "total_tokens": 21094400} {"current_steps": 2576, "total_steps": 3345, "loss": 0.2378, "lr": 3.1208948329078113e-07, "epoch": 3.8505231689088193, "percentage": 77.01, "elapsed_time": "0:49:52", "remaining_time": "0:14:53", "throughput": 7052.47, "total_tokens": 21102592} {"current_steps": 2577, "total_steps": 3345, "loss": 0.4713, "lr": 3.113138141940894e-07, "epoch": 3.852017937219731, "percentage": 77.04, "elapsed_time": "0:49:53", "remaining_time": "0:14:52", "throughput": 7052.46, "total_tokens": 21110784} {"current_steps": 2578, "total_steps": 3345, "loss": 0.3141, "lr": 3.105389730927444e-07, "epoch": 3.8535127055306426, "percentage": 77.07, "elapsed_time": "0:49:54", "remaining_time": "0:14:50", "throughput": 7052.45, "total_tokens": 21118976} {"current_steps": 2579, "total_steps": 3345, "loss": 0.4469, "lr": 3.0976496067021634e-07, "epoch": 3.8550074738415545, "percentage": 77.1, "elapsed_time": "0:49:55", "remaining_time": "0:14:49", "throughput": 7052.45, "total_tokens": 21127168} {"current_steps": 2580, "total_steps": 3345, "loss": 0.2442, "lr": 3.089917776092462e-07, "epoch": 3.8565022421524664, "percentage": 77.13, "elapsed_time": "0:49:56", "remaining_time": "0:14:48", "throughput": 7052.45, "total_tokens": 21135360} {"current_steps": 2581, "total_steps": 3345, "loss": 0.203, "lr": 3.082194245918414e-07, "epoch": 3.8579970104633783, "percentage": 77.16, "elapsed_time": "0:49:58", "remaining_time": "0:14:47", "throughput": 7052.44, "total_tokens": 21143552} {"current_steps": 2582, "total_steps": 3345, "loss": 0.2347, "lr": 3.0744790229927906e-07, "epoch": 3.8594917787742897, "percentage": 77.19, "elapsed_time": "0:49:59", "remaining_time": "0:14:46", "throughput": 7052.44, "total_tokens": 21151744} {"current_steps": 2583, "total_steps": 3345, "loss": 0.3475, "lr": 3.0667721141210306e-07, "epoch": 3.8609865470852016, "percentage": 77.22, "elapsed_time": "0:50:00", "remaining_time": "0:14:45", "throughput": 7052.43, "total_tokens": 21159936} {"current_steps": 2584, "total_steps": 3345, "loss": 0.3523, "lr": 3.0590735261012264e-07, "epoch": 3.8624813153961135, "percentage": 77.25, "elapsed_time": "0:50:01", "remaining_time": "0:14:43", "throughput": 7052.43, "total_tokens": 21168128} {"current_steps": 2585, "total_steps": 3345, "loss": 0.2693, "lr": 3.05138326572415e-07, "epoch": 3.8639760837070254, "percentage": 77.28, "elapsed_time": "0:50:02", "remaining_time": "0:14:42", "throughput": 7052.43, "total_tokens": 21176320} {"current_steps": 2586, "total_steps": 3345, "loss": 0.1986, "lr": 3.0437013397732114e-07, "epoch": 3.8654708520179373, "percentage": 77.31, "elapsed_time": "0:50:03", "remaining_time": "0:14:41", "throughput": 7052.43, "total_tokens": 21184512} {"current_steps": 2587, "total_steps": 3345, "loss": 0.4033, "lr": 3.036027755024479e-07, "epoch": 3.866965620328849, "percentage": 77.34, "elapsed_time": "0:50:05", "remaining_time": "0:14:40", "throughput": 7052.43, "total_tokens": 21192704} {"current_steps": 2588, "total_steps": 3345, "loss": 0.2788, "lr": 3.0283625182466634e-07, "epoch": 3.868460388639761, "percentage": 77.37, "elapsed_time": "0:50:06", "remaining_time": "0:14:39", "throughput": 7052.44, "total_tokens": 21200896} {"current_steps": 2589, "total_steps": 3345, "loss": 0.3356, "lr": 3.020705636201103e-07, "epoch": 3.8699551569506725, "percentage": 77.4, "elapsed_time": "0:50:07", "remaining_time": "0:14:38", "throughput": 7052.43, "total_tokens": 21209088} {"current_steps": 2590, "total_steps": 3345, "loss": 0.5771, "lr": 3.013057115641775e-07, "epoch": 3.8714499252615844, "percentage": 77.43, "elapsed_time": "0:50:08", "remaining_time": "0:14:36", "throughput": 7052.42, "total_tokens": 21217280} {"current_steps": 2591, "total_steps": 3345, "loss": 0.2892, "lr": 3.005416963315279e-07, "epoch": 3.8729446935724963, "percentage": 77.46, "elapsed_time": "0:50:09", "remaining_time": "0:14:35", "throughput": 7052.41, "total_tokens": 21225472} {"current_steps": 2592, "total_steps": 3345, "loss": 0.4253, "lr": 2.997785185960836e-07, "epoch": 3.874439461883408, "percentage": 77.49, "elapsed_time": "0:50:10", "remaining_time": "0:14:34", "throughput": 7052.39, "total_tokens": 21233664} {"current_steps": 2593, "total_steps": 3345, "loss": 0.4246, "lr": 2.9901617903102697e-07, "epoch": 3.87593423019432, "percentage": 77.52, "elapsed_time": "0:50:12", "remaining_time": "0:14:33", "throughput": 7052.39, "total_tokens": 21241856} {"current_steps": 2594, "total_steps": 3345, "loss": 0.4051, "lr": 2.9825467830880237e-07, "epoch": 3.8774289985052315, "percentage": 77.55, "elapsed_time": "0:50:13", "remaining_time": "0:14:32", "throughput": 7052.38, "total_tokens": 21250048} {"current_steps": 2595, "total_steps": 3345, "loss": 0.2833, "lr": 2.974940171011129e-07, "epoch": 3.8789237668161434, "percentage": 77.58, "elapsed_time": "0:50:14", "remaining_time": "0:14:31", "throughput": 7052.37, "total_tokens": 21258240} {"current_steps": 2596, "total_steps": 3345, "loss": 0.1956, "lr": 2.9673419607892247e-07, "epoch": 3.8804185351270553, "percentage": 77.61, "elapsed_time": "0:50:15", "remaining_time": "0:14:30", "throughput": 7052.38, "total_tokens": 21266432} {"current_steps": 2597, "total_steps": 3345, "loss": 0.3806, "lr": 2.959752159124527e-07, "epoch": 3.881913303437967, "percentage": 77.64, "elapsed_time": "0:50:16", "remaining_time": "0:14:28", "throughput": 7052.38, "total_tokens": 21274624} {"current_steps": 2598, "total_steps": 3345, "loss": 0.2953, "lr": 2.9521707727118406e-07, "epoch": 3.883408071748879, "percentage": 77.67, "elapsed_time": "0:50:17", "remaining_time": "0:14:27", "throughput": 7052.37, "total_tokens": 21282816} {"current_steps": 2599, "total_steps": 3345, "loss": 0.216, "lr": 2.9445978082385527e-07, "epoch": 3.884902840059791, "percentage": 77.7, "elapsed_time": "0:50:18", "remaining_time": "0:14:26", "throughput": 7052.37, "total_tokens": 21291008} {"current_steps": 2600, "total_steps": 3345, "loss": 0.2181, "lr": 2.9370332723846083e-07, "epoch": 3.886397608370703, "percentage": 77.73, "elapsed_time": "0:50:20", "remaining_time": "0:14:25", "throughput": 7052.36, "total_tokens": 21299200} {"current_steps": 2601, "total_steps": 3345, "loss": 0.2083, "lr": 2.929477171822534e-07, "epoch": 3.8878923766816142, "percentage": 77.76, "elapsed_time": "0:50:21", "remaining_time": "0:14:24", "throughput": 7052.36, "total_tokens": 21307392} {"current_steps": 2602, "total_steps": 3345, "loss": 0.3183, "lr": 2.921929513217399e-07, "epoch": 3.889387144992526, "percentage": 77.79, "elapsed_time": "0:50:22", "remaining_time": "0:14:23", "throughput": 7052.36, "total_tokens": 21315584} {"current_steps": 2603, "total_steps": 3345, "loss": 0.1886, "lr": 2.9143903032268413e-07, "epoch": 3.890881913303438, "percentage": 77.82, "elapsed_time": "0:50:23", "remaining_time": "0:14:21", "throughput": 7052.34, "total_tokens": 21323776} {"current_steps": 2604, "total_steps": 3345, "loss": 0.2879, "lr": 2.9068595485010313e-07, "epoch": 3.89237668161435, "percentage": 77.85, "elapsed_time": "0:50:24", "remaining_time": "0:14:20", "throughput": 7052.33, "total_tokens": 21331968} {"current_steps": 2605, "total_steps": 3345, "loss": 0.2992, "lr": 2.899337255682695e-07, "epoch": 3.8938714499252614, "percentage": 77.88, "elapsed_time": "0:50:25", "remaining_time": "0:14:19", "throughput": 7052.33, "total_tokens": 21340160} {"current_steps": 2606, "total_steps": 3345, "loss": 0.2582, "lr": 2.8918234314070914e-07, "epoch": 3.8953662182361732, "percentage": 77.91, "elapsed_time": "0:50:27", "remaining_time": "0:14:18", "throughput": 7052.32, "total_tokens": 21348352} {"current_steps": 2607, "total_steps": 3345, "loss": 0.1894, "lr": 2.8843180823019956e-07, "epoch": 3.896860986547085, "percentage": 77.94, "elapsed_time": "0:50:28", "remaining_time": "0:14:17", "throughput": 7052.32, "total_tokens": 21356544} {"current_steps": 2608, "total_steps": 3345, "loss": 0.255, "lr": 2.8768212149877335e-07, "epoch": 3.898355754857997, "percentage": 77.97, "elapsed_time": "0:50:29", "remaining_time": "0:14:16", "throughput": 7052.31, "total_tokens": 21364736} {"current_steps": 2609, "total_steps": 3345, "loss": 0.3871, "lr": 2.8693328360771225e-07, "epoch": 3.899850523168909, "percentage": 78.0, "elapsed_time": "0:50:30", "remaining_time": "0:14:14", "throughput": 7052.31, "total_tokens": 21372928} {"current_steps": 2610, "total_steps": 3345, "loss": 0.1189, "lr": 2.8618529521755134e-07, "epoch": 3.901345291479821, "percentage": 78.03, "elapsed_time": "0:50:31", "remaining_time": "0:14:13", "throughput": 7052.29, "total_tokens": 21381120} {"current_steps": 2611, "total_steps": 3345, "loss": 0.4366, "lr": 2.8543815698807444e-07, "epoch": 3.9028400597907327, "percentage": 78.06, "elapsed_time": "0:50:32", "remaining_time": "0:14:12", "throughput": 7052.28, "total_tokens": 21389312} {"current_steps": 2612, "total_steps": 3345, "loss": 0.2539, "lr": 2.8469186957831724e-07, "epoch": 3.904334828101644, "percentage": 78.09, "elapsed_time": "0:50:34", "remaining_time": "0:14:11", "throughput": 7052.27, "total_tokens": 21397504} {"current_steps": 2613, "total_steps": 3345, "loss": 0.3596, "lr": 2.8394643364656373e-07, "epoch": 3.905829596412556, "percentage": 78.12, "elapsed_time": "0:50:35", "remaining_time": "0:14:10", "throughput": 7052.27, "total_tokens": 21405696} {"current_steps": 2614, "total_steps": 3345, "loss": 0.4558, "lr": 2.8320184985034737e-07, "epoch": 3.907324364723468, "percentage": 78.15, "elapsed_time": "0:50:36", "remaining_time": "0:14:09", "throughput": 7052.27, "total_tokens": 21413888} {"current_steps": 2615, "total_steps": 3345, "loss": 0.3392, "lr": 2.824581188464502e-07, "epoch": 3.90881913303438, "percentage": 78.18, "elapsed_time": "0:50:37", "remaining_time": "0:14:07", "throughput": 7052.26, "total_tokens": 21422080} {"current_steps": 2616, "total_steps": 3345, "loss": 0.361, "lr": 2.817152412909012e-07, "epoch": 3.910313901345291, "percentage": 78.21, "elapsed_time": "0:50:38", "remaining_time": "0:14:06", "throughput": 7052.27, "total_tokens": 21430272} {"current_steps": 2617, "total_steps": 3345, "loss": 0.1429, "lr": 2.8097321783897764e-07, "epoch": 3.911808669656203, "percentage": 78.24, "elapsed_time": "0:50:39", "remaining_time": "0:14:05", "throughput": 7052.26, "total_tokens": 21438464} {"current_steps": 2618, "total_steps": 3345, "loss": 0.233, "lr": 2.802320491452019e-07, "epoch": 3.913303437967115, "percentage": 78.27, "elapsed_time": "0:50:41", "remaining_time": "0:14:04", "throughput": 7052.26, "total_tokens": 21446656} {"current_steps": 2619, "total_steps": 3345, "loss": 0.2971, "lr": 2.7949173586334433e-07, "epoch": 3.914798206278027, "percentage": 78.3, "elapsed_time": "0:50:42", "remaining_time": "0:14:03", "throughput": 7052.26, "total_tokens": 21454848} {"current_steps": 2620, "total_steps": 3345, "loss": 0.3571, "lr": 2.787522786464189e-07, "epoch": 3.9162929745889388, "percentage": 78.33, "elapsed_time": "0:50:43", "remaining_time": "0:14:02", "throughput": 7052.24, "total_tokens": 21463040} {"current_steps": 2621, "total_steps": 3345, "loss": 0.407, "lr": 2.7801367814668566e-07, "epoch": 3.9177877428998507, "percentage": 78.36, "elapsed_time": "0:50:44", "remaining_time": "0:14:01", "throughput": 7052.23, "total_tokens": 21471232} {"current_steps": 2622, "total_steps": 3345, "loss": 0.5382, "lr": 2.772759350156487e-07, "epoch": 3.9192825112107625, "percentage": 78.39, "elapsed_time": "0:50:45", "remaining_time": "0:13:59", "throughput": 7052.23, "total_tokens": 21479424} {"current_steps": 2623, "total_steps": 3345, "loss": 0.3516, "lr": 2.765390499040553e-07, "epoch": 3.920777279521674, "percentage": 78.42, "elapsed_time": "0:50:46", "remaining_time": "0:13:58", "throughput": 7052.23, "total_tokens": 21487616} {"current_steps": 2624, "total_steps": 3345, "loss": 0.1695, "lr": 2.758030234618965e-07, "epoch": 3.922272047832586, "percentage": 78.45, "elapsed_time": "0:50:48", "remaining_time": "0:13:57", "throughput": 7052.22, "total_tokens": 21495808} {"current_steps": 2625, "total_steps": 3345, "loss": 0.3494, "lr": 2.7506785633840585e-07, "epoch": 3.9237668161434978, "percentage": 78.48, "elapsed_time": "0:50:49", "remaining_time": "0:13:56", "throughput": 7052.21, "total_tokens": 21504000} {"current_steps": 2626, "total_steps": 3345, "loss": 0.3505, "lr": 2.743335491820591e-07, "epoch": 3.9252615844544096, "percentage": 78.51, "elapsed_time": "0:50:50", "remaining_time": "0:13:55", "throughput": 7052.2, "total_tokens": 21512192} {"current_steps": 2627, "total_steps": 3345, "loss": 0.3376, "lr": 2.736001026405724e-07, "epoch": 3.9267563527653215, "percentage": 78.54, "elapsed_time": "0:50:51", "remaining_time": "0:13:54", "throughput": 7052.19, "total_tokens": 21520384} {"current_steps": 2628, "total_steps": 3345, "loss": 0.5716, "lr": 2.728675173609044e-07, "epoch": 3.928251121076233, "percentage": 78.57, "elapsed_time": "0:50:52", "remaining_time": "0:13:52", "throughput": 7052.18, "total_tokens": 21528576} {"current_steps": 2629, "total_steps": 3345, "loss": 0.3115, "lr": 2.721357939892523e-07, "epoch": 3.929745889387145, "percentage": 78.59, "elapsed_time": "0:50:53", "remaining_time": "0:13:51", "throughput": 7052.18, "total_tokens": 21536768} {"current_steps": 2630, "total_steps": 3345, "loss": 0.151, "lr": 2.714049331710543e-07, "epoch": 3.9312406576980568, "percentage": 78.62, "elapsed_time": "0:50:55", "remaining_time": "0:13:50", "throughput": 7052.16, "total_tokens": 21544960} {"current_steps": 2631, "total_steps": 3345, "loss": 0.4377, "lr": 2.706749355509877e-07, "epoch": 3.9327354260089686, "percentage": 78.65, "elapsed_time": "0:50:56", "remaining_time": "0:13:49", "throughput": 7052.16, "total_tokens": 21553152} {"current_steps": 2632, "total_steps": 3345, "loss": 0.1774, "lr": 2.699458017729674e-07, "epoch": 3.9342301943198805, "percentage": 78.68, "elapsed_time": "0:50:57", "remaining_time": "0:13:48", "throughput": 7052.16, "total_tokens": 21561344} {"current_steps": 2633, "total_steps": 3345, "loss": 0.2794, "lr": 2.692175324801477e-07, "epoch": 3.9357249626307924, "percentage": 78.71, "elapsed_time": "0:50:58", "remaining_time": "0:13:47", "throughput": 7052.15, "total_tokens": 21569536} {"current_steps": 2634, "total_steps": 3345, "loss": 0.1935, "lr": 2.6849012831491883e-07, "epoch": 3.9372197309417043, "percentage": 78.74, "elapsed_time": "0:50:59", "remaining_time": "0:13:45", "throughput": 7052.13, "total_tokens": 21577728} {"current_steps": 2635, "total_steps": 3345, "loss": 0.1674, "lr": 2.6776358991890947e-07, "epoch": 3.9387144992526157, "percentage": 78.77, "elapsed_time": "0:51:00", "remaining_time": "0:13:44", "throughput": 7052.12, "total_tokens": 21585920} {"current_steps": 2636, "total_steps": 3345, "loss": 0.2142, "lr": 2.670379179329831e-07, "epoch": 3.9402092675635276, "percentage": 78.8, "elapsed_time": "0:51:02", "remaining_time": "0:13:43", "throughput": 7052.12, "total_tokens": 21594112} {"current_steps": 2637, "total_steps": 3345, "loss": 0.2964, "lr": 2.663131129972402e-07, "epoch": 3.9417040358744395, "percentage": 78.83, "elapsed_time": "0:51:03", "remaining_time": "0:13:42", "throughput": 7052.11, "total_tokens": 21602304} {"current_steps": 2638, "total_steps": 3345, "loss": 0.2421, "lr": 2.655891757510161e-07, "epoch": 3.9431988041853514, "percentage": 78.86, "elapsed_time": "0:51:04", "remaining_time": "0:13:41", "throughput": 7052.11, "total_tokens": 21610496} {"current_steps": 2639, "total_steps": 3345, "loss": 0.1761, "lr": 2.648661068328802e-07, "epoch": 3.944693572496263, "percentage": 78.89, "elapsed_time": "0:51:05", "remaining_time": "0:13:40", "throughput": 7052.1, "total_tokens": 21618688} {"current_steps": 2640, "total_steps": 3345, "loss": 0.2412, "lr": 2.641439068806369e-07, "epoch": 3.9461883408071747, "percentage": 78.92, "elapsed_time": "0:51:06", "remaining_time": "0:13:38", "throughput": 7052.1, "total_tokens": 21626880} {"current_steps": 2641, "total_steps": 3345, "loss": 0.2651, "lr": 2.634225765313225e-07, "epoch": 3.9476831091180866, "percentage": 78.95, "elapsed_time": "0:51:07", "remaining_time": "0:13:37", "throughput": 7052.1, "total_tokens": 21635072} {"current_steps": 2642, "total_steps": 3345, "loss": 0.4919, "lr": 2.627021164212089e-07, "epoch": 3.9491778774289985, "percentage": 78.98, "elapsed_time": "0:51:09", "remaining_time": "0:13:36", "throughput": 7052.08, "total_tokens": 21643264} {"current_steps": 2643, "total_steps": 3345, "loss": 0.2141, "lr": 2.619825271857976e-07, "epoch": 3.9506726457399104, "percentage": 79.01, "elapsed_time": "0:51:10", "remaining_time": "0:13:35", "throughput": 7052.08, "total_tokens": 21651456} {"current_steps": 2644, "total_steps": 3345, "loss": 0.2017, "lr": 2.6126380945982396e-07, "epoch": 3.9521674140508223, "percentage": 79.04, "elapsed_time": "0:51:11", "remaining_time": "0:13:34", "throughput": 7052.08, "total_tokens": 21659648} {"current_steps": 2645, "total_steps": 3345, "loss": 0.2292, "lr": 2.6054596387725297e-07, "epoch": 3.953662182361734, "percentage": 79.07, "elapsed_time": "0:51:12", "remaining_time": "0:13:33", "throughput": 7052.07, "total_tokens": 21667840} {"current_steps": 2646, "total_steps": 3345, "loss": 0.3002, "lr": 2.598289910712816e-07, "epoch": 3.9551569506726456, "percentage": 79.1, "elapsed_time": "0:51:13", "remaining_time": "0:13:31", "throughput": 7052.07, "total_tokens": 21676032} {"current_steps": 2647, "total_steps": 3345, "loss": 0.2726, "lr": 2.591128916743367e-07, "epoch": 3.9566517189835575, "percentage": 79.13, "elapsed_time": "0:51:14", "remaining_time": "0:13:30", "throughput": 7052.06, "total_tokens": 21684224} {"current_steps": 2648, "total_steps": 3345, "loss": 0.4709, "lr": 2.583976663180739e-07, "epoch": 3.9581464872944694, "percentage": 79.16, "elapsed_time": "0:51:16", "remaining_time": "0:13:29", "throughput": 7052.05, "total_tokens": 21692416} {"current_steps": 2649, "total_steps": 3345, "loss": 0.2516, "lr": 2.5768331563337913e-07, "epoch": 3.9596412556053813, "percentage": 79.19, "elapsed_time": "0:51:17", "remaining_time": "0:13:28", "throughput": 7052.04, "total_tokens": 21700608} {"current_steps": 2650, "total_steps": 3345, "loss": 0.2693, "lr": 2.5696984025036537e-07, "epoch": 3.9611360239162927, "percentage": 79.22, "elapsed_time": "0:51:18", "remaining_time": "0:13:27", "throughput": 7052.02, "total_tokens": 21708800} {"current_steps": 2651, "total_steps": 3345, "loss": 0.3481, "lr": 2.5625724079837486e-07, "epoch": 3.9626307922272046, "percentage": 79.25, "elapsed_time": "0:51:19", "remaining_time": "0:13:26", "throughput": 7052.0, "total_tokens": 21716992} {"current_steps": 2652, "total_steps": 3345, "loss": 0.0812, "lr": 2.5554551790597614e-07, "epoch": 3.9641255605381165, "percentage": 79.28, "elapsed_time": "0:51:20", "remaining_time": "0:13:25", "throughput": 7051.97, "total_tokens": 21725184} {"current_steps": 2653, "total_steps": 3345, "loss": 0.3989, "lr": 2.548346722009651e-07, "epoch": 3.9656203288490284, "percentage": 79.31, "elapsed_time": "0:51:21", "remaining_time": "0:13:23", "throughput": 7051.96, "total_tokens": 21733376} {"current_steps": 2654, "total_steps": 3345, "loss": 0.2697, "lr": 2.541247043103644e-07, "epoch": 3.9671150971599403, "percentage": 79.34, "elapsed_time": "0:51:23", "remaining_time": "0:13:22", "throughput": 7051.95, "total_tokens": 21741568} {"current_steps": 2655, "total_steps": 3345, "loss": 0.2647, "lr": 2.534156148604207e-07, "epoch": 3.968609865470852, "percentage": 79.37, "elapsed_time": "0:51:24", "remaining_time": "0:13:21", "throughput": 7051.94, "total_tokens": 21749760} {"current_steps": 2656, "total_steps": 3345, "loss": 0.3113, "lr": 2.5270740447660797e-07, "epoch": 3.970104633781764, "percentage": 79.4, "elapsed_time": "0:51:25", "remaining_time": "0:13:20", "throughput": 7051.92, "total_tokens": 21757952} {"current_steps": 2657, "total_steps": 3345, "loss": 0.1188, "lr": 2.520000737836228e-07, "epoch": 3.9715994020926755, "percentage": 79.43, "elapsed_time": "0:51:26", "remaining_time": "0:13:19", "throughput": 7051.91, "total_tokens": 21766144} {"current_steps": 2658, "total_steps": 3345, "loss": 0.2914, "lr": 2.5129362340538725e-07, "epoch": 3.9730941704035874, "percentage": 79.46, "elapsed_time": "0:51:27", "remaining_time": "0:13:18", "throughput": 7051.9, "total_tokens": 21774336} {"current_steps": 2659, "total_steps": 3345, "loss": 0.1577, "lr": 2.5058805396504624e-07, "epoch": 3.9745889387144993, "percentage": 79.49, "elapsed_time": "0:51:28", "remaining_time": "0:13:16", "throughput": 7051.9, "total_tokens": 21782528} {"current_steps": 2660, "total_steps": 3345, "loss": 0.1793, "lr": 2.49883366084968e-07, "epoch": 3.976083707025411, "percentage": 79.52, "elapsed_time": "0:51:30", "remaining_time": "0:13:15", "throughput": 7051.9, "total_tokens": 21790720} {"current_steps": 2661, "total_steps": 3345, "loss": 0.2288, "lr": 2.491795603867422e-07, "epoch": 3.977578475336323, "percentage": 79.55, "elapsed_time": "0:51:31", "remaining_time": "0:13:14", "throughput": 7051.89, "total_tokens": 21798912} {"current_steps": 2662, "total_steps": 3345, "loss": 0.2275, "lr": 2.484766374911819e-07, "epoch": 3.9790732436472345, "percentage": 79.58, "elapsed_time": "0:51:32", "remaining_time": "0:13:13", "throughput": 7051.89, "total_tokens": 21807104} {"current_steps": 2663, "total_steps": 3345, "loss": 0.3321, "lr": 2.477745980183198e-07, "epoch": 3.9805680119581464, "percentage": 79.61, "elapsed_time": "0:51:33", "remaining_time": "0:13:12", "throughput": 7051.88, "total_tokens": 21815296} {"current_steps": 2664, "total_steps": 3345, "loss": 0.3258, "lr": 2.470734425874105e-07, "epoch": 3.9820627802690582, "percentage": 79.64, "elapsed_time": "0:51:34", "remaining_time": "0:13:11", "throughput": 7051.88, "total_tokens": 21823488} {"current_steps": 2665, "total_steps": 3345, "loss": 0.2508, "lr": 2.463731718169289e-07, "epoch": 3.98355754857997, "percentage": 79.67, "elapsed_time": "0:51:35", "remaining_time": "0:13:09", "throughput": 7051.87, "total_tokens": 21831680} {"current_steps": 2666, "total_steps": 3345, "loss": 0.2664, "lr": 2.456737863245683e-07, "epoch": 3.985052316890882, "percentage": 79.7, "elapsed_time": "0:51:37", "remaining_time": "0:13:08", "throughput": 7051.86, "total_tokens": 21839872} {"current_steps": 2667, "total_steps": 3345, "loss": 0.39, "lr": 2.449752867272427e-07, "epoch": 3.986547085201794, "percentage": 79.73, "elapsed_time": "0:51:38", "remaining_time": "0:13:07", "throughput": 7051.86, "total_tokens": 21848064} {"current_steps": 2668, "total_steps": 3345, "loss": 0.2303, "lr": 2.442776736410832e-07, "epoch": 3.988041853512706, "percentage": 79.76, "elapsed_time": "0:51:39", "remaining_time": "0:13:06", "throughput": 7051.85, "total_tokens": 21856256} {"current_steps": 2669, "total_steps": 3345, "loss": 0.3684, "lr": 2.435809476814399e-07, "epoch": 3.9895366218236172, "percentage": 79.79, "elapsed_time": "0:51:40", "remaining_time": "0:13:05", "throughput": 7051.83, "total_tokens": 21864448} {"current_steps": 2670, "total_steps": 3345, "loss": 0.4092, "lr": 2.4288510946288065e-07, "epoch": 3.991031390134529, "percentage": 79.82, "elapsed_time": "0:51:41", "remaining_time": "0:13:04", "throughput": 7051.82, "total_tokens": 21872640} {"current_steps": 2671, "total_steps": 3345, "loss": 0.2299, "lr": 2.421901595991889e-07, "epoch": 3.992526158445441, "percentage": 79.85, "elapsed_time": "0:51:42", "remaining_time": "0:13:02", "throughput": 7051.81, "total_tokens": 21880832} {"current_steps": 2672, "total_steps": 3345, "loss": 0.1602, "lr": 2.414960987033661e-07, "epoch": 3.994020926756353, "percentage": 79.88, "elapsed_time": "0:51:44", "remaining_time": "0:13:01", "throughput": 7051.8, "total_tokens": 21889024} {"current_steps": 2673, "total_steps": 3345, "loss": 0.3524, "lr": 2.408029273876279e-07, "epoch": 3.9955156950672643, "percentage": 79.91, "elapsed_time": "0:51:45", "remaining_time": "0:13:00", "throughput": 7051.8, "total_tokens": 21897216} {"current_steps": 2674, "total_steps": 3345, "loss": 0.304, "lr": 2.4011064626340704e-07, "epoch": 3.9970104633781762, "percentage": 79.94, "elapsed_time": "0:51:46", "remaining_time": "0:12:59", "throughput": 7051.8, "total_tokens": 21905408} {"current_steps": 2675, "total_steps": 3345, "loss": 0.3976, "lr": 2.3941925594134885e-07, "epoch": 3.998505231689088, "percentage": 79.97, "elapsed_time": "0:51:47", "remaining_time": "0:12:58", "throughput": 7051.79, "total_tokens": 21913600} {"current_steps": 2676, "total_steps": 3345, "loss": 0.0613, "lr": 2.387287570313158e-07, "epoch": 4.0, "percentage": 80.0, "elapsed_time": "0:51:48", "remaining_time": "0:12:57", "throughput": 7051.84, "total_tokens": 21921792} {"current_steps": 2677, "total_steps": 3345, "loss": 0.055, "lr": 2.3803915014238136e-07, "epoch": 4.001494768310912, "percentage": 80.03, "elapsed_time": "0:51:49", "remaining_time": "0:12:56", "throughput": 7051.79, "total_tokens": 21929984} {"current_steps": 2678, "total_steps": 3345, "loss": 0.2567, "lr": 2.3735043588283394e-07, "epoch": 4.002989536621824, "percentage": 80.06, "elapsed_time": "0:51:51", "remaining_time": "0:12:54", "throughput": 7051.78, "total_tokens": 21938176} {"current_steps": 2679, "total_steps": 3345, "loss": 0.1607, "lr": 2.366626148601732e-07, "epoch": 4.004484304932736, "percentage": 80.09, "elapsed_time": "0:51:52", "remaining_time": "0:12:53", "throughput": 7051.75, "total_tokens": 21946368} {"current_steps": 2680, "total_steps": 3345, "loss": 0.1832, "lr": 2.35975687681112e-07, "epoch": 4.0059790732436475, "percentage": 80.12, "elapsed_time": "0:51:53", "remaining_time": "0:12:52", "throughput": 7051.71, "total_tokens": 21954560} {"current_steps": 2681, "total_steps": 3345, "loss": 0.2469, "lr": 2.352896549515747e-07, "epoch": 4.007473841554559, "percentage": 80.15, "elapsed_time": "0:51:54", "remaining_time": "0:12:51", "throughput": 7051.7, "total_tokens": 21962752} {"current_steps": 2682, "total_steps": 3345, "loss": 0.2659, "lr": 2.346045172766956e-07, "epoch": 4.00896860986547, "percentage": 80.18, "elapsed_time": "0:51:55", "remaining_time": "0:12:50", "throughput": 7051.69, "total_tokens": 21970944} {"current_steps": 2683, "total_steps": 3345, "loss": 0.4387, "lr": 2.339202752608209e-07, "epoch": 4.010463378176382, "percentage": 80.21, "elapsed_time": "0:51:56", "remaining_time": "0:12:49", "throughput": 7051.67, "total_tokens": 21979136} {"current_steps": 2684, "total_steps": 3345, "loss": 0.0433, "lr": 2.3323692950750555e-07, "epoch": 4.011958146487294, "percentage": 80.24, "elapsed_time": "0:51:58", "remaining_time": "0:12:47", "throughput": 7051.67, "total_tokens": 21987328} {"current_steps": 2685, "total_steps": 3345, "loss": 0.07, "lr": 2.3255448061951513e-07, "epoch": 4.013452914798206, "percentage": 80.27, "elapsed_time": "0:51:59", "remaining_time": "0:12:46", "throughput": 7051.67, "total_tokens": 21995520} {"current_steps": 2686, "total_steps": 3345, "loss": 0.4427, "lr": 2.3187292919882254e-07, "epoch": 4.014947683109118, "percentage": 80.3, "elapsed_time": "0:52:00", "remaining_time": "0:12:45", "throughput": 7051.64, "total_tokens": 22003712} {"current_steps": 2687, "total_steps": 3345, "loss": 0.2786, "lr": 2.3119227584661064e-07, "epoch": 4.01644245142003, "percentage": 80.33, "elapsed_time": "0:52:01", "remaining_time": "0:12:44", "throughput": 7051.63, "total_tokens": 22011904} {"current_steps": 2688, "total_steps": 3345, "loss": 0.1059, "lr": 2.3051252116326944e-07, "epoch": 4.017937219730942, "percentage": 80.36, "elapsed_time": "0:52:02", "remaining_time": "0:12:43", "throughput": 7051.61, "total_tokens": 22020096} {"current_steps": 2689, "total_steps": 3345, "loss": 0.1503, "lr": 2.2983366574839585e-07, "epoch": 4.019431988041854, "percentage": 80.39, "elapsed_time": "0:52:03", "remaining_time": "0:12:42", "throughput": 7051.61, "total_tokens": 22028288} {"current_steps": 2690, "total_steps": 3345, "loss": 0.2317, "lr": 2.291557102007945e-07, "epoch": 4.0209267563527655, "percentage": 80.42, "elapsed_time": "0:52:05", "remaining_time": "0:12:40", "throughput": 7051.61, "total_tokens": 22036480} {"current_steps": 2691, "total_steps": 3345, "loss": 0.1488, "lr": 2.2847865511847506e-07, "epoch": 4.022421524663677, "percentage": 80.45, "elapsed_time": "0:52:06", "remaining_time": "0:12:39", "throughput": 7051.61, "total_tokens": 22044672} {"current_steps": 2692, "total_steps": 3345, "loss": 0.2221, "lr": 2.2780250109865386e-07, "epoch": 4.023916292974589, "percentage": 80.48, "elapsed_time": "0:52:07", "remaining_time": "0:12:38", "throughput": 7051.61, "total_tokens": 22052864} {"current_steps": 2693, "total_steps": 3345, "loss": 0.0265, "lr": 2.2712724873775224e-07, "epoch": 4.025411061285501, "percentage": 80.51, "elapsed_time": "0:52:08", "remaining_time": "0:12:37", "throughput": 7051.61, "total_tokens": 22061056} {"current_steps": 2694, "total_steps": 3345, "loss": 0.1508, "lr": 2.2645289863139643e-07, "epoch": 4.026905829596412, "percentage": 80.54, "elapsed_time": "0:52:09", "remaining_time": "0:12:36", "throughput": 7051.6, "total_tokens": 22069248} {"current_steps": 2695, "total_steps": 3345, "loss": 0.0579, "lr": 2.257794513744159e-07, "epoch": 4.028400597907324, "percentage": 80.57, "elapsed_time": "0:52:10", "remaining_time": "0:12:35", "throughput": 7051.58, "total_tokens": 22077440} {"current_steps": 2696, "total_steps": 3345, "loss": 0.2024, "lr": 2.2510690756084446e-07, "epoch": 4.029895366218236, "percentage": 80.6, "elapsed_time": "0:52:12", "remaining_time": "0:12:33", "throughput": 7051.57, "total_tokens": 22085632} {"current_steps": 2697, "total_steps": 3345, "loss": 0.2524, "lr": 2.2443526778391928e-07, "epoch": 4.031390134529148, "percentage": 80.63, "elapsed_time": "0:52:13", "remaining_time": "0:12:32", "throughput": 7051.56, "total_tokens": 22093824} {"current_steps": 2698, "total_steps": 3345, "loss": 0.25, "lr": 2.2376453263607906e-07, "epoch": 4.03288490284006, "percentage": 80.66, "elapsed_time": "0:52:14", "remaining_time": "0:12:31", "throughput": 7051.55, "total_tokens": 22102016} {"current_steps": 2699, "total_steps": 3345, "loss": 0.3226, "lr": 2.2309470270896581e-07, "epoch": 4.034379671150972, "percentage": 80.69, "elapsed_time": "0:52:15", "remaining_time": "0:12:30", "throughput": 7051.56, "total_tokens": 22110208} {"current_steps": 2700, "total_steps": 3345, "loss": 0.4764, "lr": 2.2242577859342167e-07, "epoch": 4.0358744394618835, "percentage": 80.72, "elapsed_time": "0:52:16", "remaining_time": "0:12:29", "throughput": 7051.56, "total_tokens": 22118400} {"current_steps": 2701, "total_steps": 3345, "loss": 0.1558, "lr": 2.217577608794913e-07, "epoch": 4.037369207772795, "percentage": 80.75, "elapsed_time": "0:52:17", "remaining_time": "0:12:28", "throughput": 7051.56, "total_tokens": 22126592} {"current_steps": 2702, "total_steps": 3345, "loss": 0.1443, "lr": 2.2109065015641848e-07, "epoch": 4.038863976083707, "percentage": 80.78, "elapsed_time": "0:52:18", "remaining_time": "0:12:26", "throughput": 7051.56, "total_tokens": 22134784} {"current_steps": 2703, "total_steps": 3345, "loss": 0.061, "lr": 2.2042444701264765e-07, "epoch": 4.040358744394619, "percentage": 80.81, "elapsed_time": "0:52:20", "remaining_time": "0:12:25", "throughput": 7051.56, "total_tokens": 22142976} {"current_steps": 2704, "total_steps": 3345, "loss": 0.0501, "lr": 2.197591520358232e-07, "epoch": 4.041853512705531, "percentage": 80.84, "elapsed_time": "0:52:21", "remaining_time": "0:12:24", "throughput": 7051.53, "total_tokens": 22151168} {"current_steps": 2705, "total_steps": 3345, "loss": 0.3029, "lr": 2.1909476581278705e-07, "epoch": 4.043348281016442, "percentage": 80.87, "elapsed_time": "0:52:22", "remaining_time": "0:12:23", "throughput": 7051.53, "total_tokens": 22159360} {"current_steps": 2706, "total_steps": 3345, "loss": 0.199, "lr": 2.1843128892958088e-07, "epoch": 4.044843049327354, "percentage": 80.9, "elapsed_time": "0:52:23", "remaining_time": "0:12:22", "throughput": 7051.52, "total_tokens": 22167552} {"current_steps": 2707, "total_steps": 3345, "loss": 0.2678, "lr": 2.177687219714432e-07, "epoch": 4.046337817638266, "percentage": 80.93, "elapsed_time": "0:52:24", "remaining_time": "0:12:21", "throughput": 7051.5, "total_tokens": 22175744} {"current_steps": 2708, "total_steps": 3345, "loss": 0.0467, "lr": 2.1710706552281093e-07, "epoch": 4.047832585949178, "percentage": 80.96, "elapsed_time": "0:52:25", "remaining_time": "0:12:20", "throughput": 7051.51, "total_tokens": 22183936} {"current_steps": 2709, "total_steps": 3345, "loss": 0.0906, "lr": 2.1644632016731643e-07, "epoch": 4.04932735426009, "percentage": 80.99, "elapsed_time": "0:52:27", "remaining_time": "0:12:18", "throughput": 7051.51, "total_tokens": 22192128} {"current_steps": 2710, "total_steps": 3345, "loss": 0.175, "lr": 2.157864864877905e-07, "epoch": 4.0508221225710015, "percentage": 81.02, "elapsed_time": "0:52:28", "remaining_time": "0:12:17", "throughput": 7051.51, "total_tokens": 22200320} {"current_steps": 2711, "total_steps": 3345, "loss": 0.1801, "lr": 2.1512756506625765e-07, "epoch": 4.052316890881913, "percentage": 81.05, "elapsed_time": "0:52:29", "remaining_time": "0:12:16", "throughput": 7051.5, "total_tokens": 22208512} {"current_steps": 2712, "total_steps": 3345, "loss": 0.0136, "lr": 2.14469556483939e-07, "epoch": 4.053811659192825, "percentage": 81.08, "elapsed_time": "0:52:30", "remaining_time": "0:12:15", "throughput": 7051.49, "total_tokens": 22216704} {"current_steps": 2713, "total_steps": 3345, "loss": 0.2221, "lr": 2.1381246132125015e-07, "epoch": 4.055306427503737, "percentage": 81.11, "elapsed_time": "0:52:31", "remaining_time": "0:12:14", "throughput": 7051.49, "total_tokens": 22224896} {"current_steps": 2714, "total_steps": 3345, "loss": 0.3163, "lr": 2.1315628015780064e-07, "epoch": 4.056801195814649, "percentage": 81.14, "elapsed_time": "0:52:32", "remaining_time": "0:12:13", "throughput": 7051.47, "total_tokens": 22233088} {"current_steps": 2715, "total_steps": 3345, "loss": 0.0112, "lr": 2.1250101357239427e-07, "epoch": 4.058295964125561, "percentage": 81.17, "elapsed_time": "0:52:34", "remaining_time": "0:12:11", "throughput": 7051.47, "total_tokens": 22241280} {"current_steps": 2716, "total_steps": 3345, "loss": 0.1743, "lr": 2.1184666214302776e-07, "epoch": 4.059790732436472, "percentage": 81.2, "elapsed_time": "0:52:35", "remaining_time": "0:12:10", "throughput": 7051.47, "total_tokens": 22249472} {"current_steps": 2717, "total_steps": 3345, "loss": 0.17, "lr": 2.1119322644689107e-07, "epoch": 4.061285500747384, "percentage": 81.23, "elapsed_time": "0:52:36", "remaining_time": "0:12:09", "throughput": 7051.47, "total_tokens": 22257664} {"current_steps": 2718, "total_steps": 3345, "loss": 0.1385, "lr": 2.1054070706036545e-07, "epoch": 4.062780269058296, "percentage": 81.26, "elapsed_time": "0:52:37", "remaining_time": "0:12:08", "throughput": 7051.46, "total_tokens": 22265856} {"current_steps": 2719, "total_steps": 3345, "loss": 0.3052, "lr": 2.0988910455902498e-07, "epoch": 4.064275037369208, "percentage": 81.29, "elapsed_time": "0:52:38", "remaining_time": "0:12:07", "throughput": 7051.46, "total_tokens": 22274048} {"current_steps": 2720, "total_steps": 3345, "loss": 0.1584, "lr": 2.0923841951763488e-07, "epoch": 4.0657698056801195, "percentage": 81.32, "elapsed_time": "0:52:39", "remaining_time": "0:12:06", "throughput": 7051.47, "total_tokens": 22282240} {"current_steps": 2721, "total_steps": 3345, "loss": 0.1725, "lr": 2.0858865251014992e-07, "epoch": 4.067264573991031, "percentage": 81.35, "elapsed_time": "0:52:41", "remaining_time": "0:12:05", "throughput": 7050.56, "total_tokens": 22290432} {"current_steps": 2722, "total_steps": 3345, "loss": 0.1586, "lr": 2.0793980410971665e-07, "epoch": 4.068759342301943, "percentage": 81.38, "elapsed_time": "0:52:42", "remaining_time": "0:12:03", "throughput": 7050.56, "total_tokens": 22298624} {"current_steps": 2723, "total_steps": 3345, "loss": 0.0424, "lr": 2.0729187488867e-07, "epoch": 4.070254110612855, "percentage": 81.41, "elapsed_time": "0:52:43", "remaining_time": "0:12:02", "throughput": 7050.56, "total_tokens": 22306816} {"current_steps": 2724, "total_steps": 3345, "loss": 0.3015, "lr": 2.066448654185353e-07, "epoch": 4.071748878923767, "percentage": 81.43, "elapsed_time": "0:52:44", "remaining_time": "0:12:01", "throughput": 7050.56, "total_tokens": 22315008} {"current_steps": 2725, "total_steps": 3345, "loss": 0.0923, "lr": 2.0599877627002553e-07, "epoch": 4.073243647234679, "percentage": 81.46, "elapsed_time": "0:52:46", "remaining_time": "0:12:00", "throughput": 7050.55, "total_tokens": 22323200} {"current_steps": 2726, "total_steps": 3345, "loss": 0.1867, "lr": 2.0535360801304236e-07, "epoch": 4.074738415545591, "percentage": 81.49, "elapsed_time": "0:52:47", "remaining_time": "0:11:59", "throughput": 7050.56, "total_tokens": 22331392} {"current_steps": 2727, "total_steps": 3345, "loss": 0.3143, "lr": 2.0470936121667534e-07, "epoch": 4.076233183856502, "percentage": 81.52, "elapsed_time": "0:52:49", "remaining_time": "0:11:58", "throughput": 7049.28, "total_tokens": 22339584} {"current_steps": 2728, "total_steps": 3345, "loss": 0.0459, "lr": 2.0406603644920086e-07, "epoch": 4.077727952167414, "percentage": 81.55, "elapsed_time": "0:52:50", "remaining_time": "0:11:57", "throughput": 7049.29, "total_tokens": 22347776} {"current_steps": 2729, "total_steps": 3345, "loss": 0.0487, "lr": 2.0342363427808264e-07, "epoch": 4.079222720478326, "percentage": 81.58, "elapsed_time": "0:52:52", "remaining_time": "0:11:56", "throughput": 7047.82, "total_tokens": 22355968} {"current_steps": 2730, "total_steps": 3345, "loss": 0.1559, "lr": 2.027821552699695e-07, "epoch": 4.0807174887892375, "percentage": 81.61, "elapsed_time": "0:52:53", "remaining_time": "0:11:54", "throughput": 7047.82, "total_tokens": 22364160} {"current_steps": 2731, "total_steps": 3345, "loss": 0.0908, "lr": 2.0214159999069726e-07, "epoch": 4.082212257100149, "percentage": 81.64, "elapsed_time": "0:52:54", "remaining_time": "0:11:53", "throughput": 7047.81, "total_tokens": 22372352} {"current_steps": 2732, "total_steps": 3345, "loss": 0.4209, "lr": 2.0150196900528537e-07, "epoch": 4.083707025411061, "percentage": 81.67, "elapsed_time": "0:52:55", "remaining_time": "0:11:52", "throughput": 7047.78, "total_tokens": 22380544} {"current_steps": 2733, "total_steps": 3345, "loss": 0.2359, "lr": 2.008632628779397e-07, "epoch": 4.085201793721973, "percentage": 81.7, "elapsed_time": "0:52:56", "remaining_time": "0:11:51", "throughput": 7047.78, "total_tokens": 22388736} {"current_steps": 2734, "total_steps": 3345, "loss": 0.2789, "lr": 2.0022548217204894e-07, "epoch": 4.086696562032885, "percentage": 81.73, "elapsed_time": "0:52:57", "remaining_time": "0:11:50", "throughput": 7047.78, "total_tokens": 22396928} {"current_steps": 2735, "total_steps": 3345, "loss": 0.0486, "lr": 1.9958862745018626e-07, "epoch": 4.088191330343797, "percentage": 81.76, "elapsed_time": "0:52:59", "remaining_time": "0:11:49", "throughput": 7047.78, "total_tokens": 22405120} {"current_steps": 2736, "total_steps": 3345, "loss": 0.108, "lr": 1.989526992741081e-07, "epoch": 4.089686098654709, "percentage": 81.79, "elapsed_time": "0:53:00", "remaining_time": "0:11:47", "throughput": 7047.77, "total_tokens": 22413312} {"current_steps": 2737, "total_steps": 3345, "loss": 0.2501, "lr": 1.983176982047526e-07, "epoch": 4.091180866965621, "percentage": 81.82, "elapsed_time": "0:53:01", "remaining_time": "0:11:46", "throughput": 7047.77, "total_tokens": 22421504} {"current_steps": 2738, "total_steps": 3345, "loss": 0.1332, "lr": 1.976836248022418e-07, "epoch": 4.0926756352765326, "percentage": 81.85, "elapsed_time": "0:53:02", "remaining_time": "0:11:45", "throughput": 7047.77, "total_tokens": 22429696} {"current_steps": 2739, "total_steps": 3345, "loss": 0.1164, "lr": 1.9705047962587751e-07, "epoch": 4.0941704035874436, "percentage": 81.88, "elapsed_time": "0:53:03", "remaining_time": "0:11:44", "throughput": 7047.77, "total_tokens": 22437888} {"current_steps": 2740, "total_steps": 3345, "loss": 0.0513, "lr": 1.9641826323414464e-07, "epoch": 4.095665171898355, "percentage": 81.91, "elapsed_time": "0:53:04", "remaining_time": "0:11:43", "throughput": 7047.77, "total_tokens": 22446080} {"current_steps": 2741, "total_steps": 3345, "loss": 0.2952, "lr": 1.9578697618470742e-07, "epoch": 4.097159940209267, "percentage": 81.94, "elapsed_time": "0:53:06", "remaining_time": "0:11:42", "throughput": 7047.77, "total_tokens": 22454272} {"current_steps": 2742, "total_steps": 3345, "loss": 0.2879, "lr": 1.9515661903441106e-07, "epoch": 4.098654708520179, "percentage": 81.97, "elapsed_time": "0:53:07", "remaining_time": "0:11:40", "throughput": 7047.77, "total_tokens": 22462464} {"current_steps": 2743, "total_steps": 3345, "loss": 0.0738, "lr": 1.9452719233928025e-07, "epoch": 4.100149476831091, "percentage": 82.0, "elapsed_time": "0:53:08", "remaining_time": "0:11:39", "throughput": 7047.78, "total_tokens": 22470656} {"current_steps": 2744, "total_steps": 3345, "loss": 0.1988, "lr": 1.938986966545195e-07, "epoch": 4.101644245142003, "percentage": 82.03, "elapsed_time": "0:53:09", "remaining_time": "0:11:38", "throughput": 7047.79, "total_tokens": 22478848} {"current_steps": 2745, "total_steps": 3345, "loss": 0.3172, "lr": 1.9327113253451102e-07, "epoch": 4.103139013452915, "percentage": 82.06, "elapsed_time": "0:53:10", "remaining_time": "0:11:37", "throughput": 7047.78, "total_tokens": 22487040} {"current_steps": 2746, "total_steps": 3345, "loss": 0.0716, "lr": 1.926445005328162e-07, "epoch": 4.104633781763827, "percentage": 82.09, "elapsed_time": "0:53:11", "remaining_time": "0:11:36", "throughput": 7047.77, "total_tokens": 22495232} {"current_steps": 2747, "total_steps": 3345, "loss": 0.1608, "lr": 1.9201880120217426e-07, "epoch": 4.106128550074739, "percentage": 82.12, "elapsed_time": "0:53:12", "remaining_time": "0:11:35", "throughput": 7047.77, "total_tokens": 22503424} {"current_steps": 2748, "total_steps": 3345, "loss": 0.2194, "lr": 1.9139403509450065e-07, "epoch": 4.1076233183856505, "percentage": 82.15, "elapsed_time": "0:53:14", "remaining_time": "0:11:33", "throughput": 7047.76, "total_tokens": 22511616} {"current_steps": 2749, "total_steps": 3345, "loss": 0.1116, "lr": 1.9077020276088932e-07, "epoch": 4.109118086696562, "percentage": 82.18, "elapsed_time": "0:53:15", "remaining_time": "0:11:32", "throughput": 7047.76, "total_tokens": 22519808} {"current_steps": 2750, "total_steps": 3345, "loss": 0.1596, "lr": 1.9014730475160892e-07, "epoch": 4.110612855007473, "percentage": 82.21, "elapsed_time": "0:53:16", "remaining_time": "0:11:31", "throughput": 7047.76, "total_tokens": 22528000} {"current_steps": 2751, "total_steps": 3345, "loss": 0.1687, "lr": 1.8952534161610497e-07, "epoch": 4.112107623318385, "percentage": 82.24, "elapsed_time": "0:53:17", "remaining_time": "0:11:30", "throughput": 7047.77, "total_tokens": 22536192} {"current_steps": 2752, "total_steps": 3345, "loss": 0.2473, "lr": 1.8890431390299835e-07, "epoch": 4.113602391629297, "percentage": 82.27, "elapsed_time": "0:53:18", "remaining_time": "0:11:29", "throughput": 7047.78, "total_tokens": 22544384} {"current_steps": 2753, "total_steps": 3345, "loss": 0.0968, "lr": 1.8828422216008404e-07, "epoch": 4.115097159940209, "percentage": 82.3, "elapsed_time": "0:53:19", "remaining_time": "0:11:28", "throughput": 7047.78, "total_tokens": 22552576} {"current_steps": 2754, "total_steps": 3345, "loss": 0.0907, "lr": 1.8766506693433246e-07, "epoch": 4.116591928251121, "percentage": 82.33, "elapsed_time": "0:53:21", "remaining_time": "0:11:26", "throughput": 7047.78, "total_tokens": 22560768} {"current_steps": 2755, "total_steps": 3345, "loss": 0.1645, "lr": 1.870468487718867e-07, "epoch": 4.118086696562033, "percentage": 82.36, "elapsed_time": "0:53:22", "remaining_time": "0:11:25", "throughput": 7047.78, "total_tokens": 22568960} {"current_steps": 2756, "total_steps": 3345, "loss": 0.0915, "lr": 1.8642956821806488e-07, "epoch": 4.119581464872945, "percentage": 82.39, "elapsed_time": "0:53:23", "remaining_time": "0:11:24", "throughput": 7047.79, "total_tokens": 22577152} {"current_steps": 2757, "total_steps": 3345, "loss": 0.1911, "lr": 1.8581322581735632e-07, "epoch": 4.121076233183857, "percentage": 82.42, "elapsed_time": "0:53:24", "remaining_time": "0:11:23", "throughput": 7047.78, "total_tokens": 22585344} {"current_steps": 2758, "total_steps": 3345, "loss": 0.2115, "lr": 1.8519782211342415e-07, "epoch": 4.1225710014947685, "percentage": 82.45, "elapsed_time": "0:53:25", "remaining_time": "0:11:22", "throughput": 7047.77, "total_tokens": 22593536} {"current_steps": 2759, "total_steps": 3345, "loss": 0.1861, "lr": 1.8458335764910324e-07, "epoch": 4.12406576980568, "percentage": 82.48, "elapsed_time": "0:53:26", "remaining_time": "0:11:21", "throughput": 7047.77, "total_tokens": 22601728} {"current_steps": 2760, "total_steps": 3345, "loss": 0.2421, "lr": 1.839698329663993e-07, "epoch": 4.125560538116592, "percentage": 82.51, "elapsed_time": "0:53:28", "remaining_time": "0:11:19", "throughput": 7047.77, "total_tokens": 22609920} {"current_steps": 2761, "total_steps": 3345, "loss": 0.222, "lr": 1.8335724860648982e-07, "epoch": 4.127055306427504, "percentage": 82.54, "elapsed_time": "0:53:29", "remaining_time": "0:11:18", "throughput": 7047.77, "total_tokens": 22618112} {"current_steps": 2762, "total_steps": 3345, "loss": 0.287, "lr": 1.8274560510972246e-07, "epoch": 4.128550074738415, "percentage": 82.57, "elapsed_time": "0:53:30", "remaining_time": "0:11:17", "throughput": 7047.76, "total_tokens": 22626304} {"current_steps": 2763, "total_steps": 3345, "loss": 0.1954, "lr": 1.8213490301561553e-07, "epoch": 4.130044843049327, "percentage": 82.6, "elapsed_time": "0:53:31", "remaining_time": "0:11:16", "throughput": 7047.76, "total_tokens": 22634496} {"current_steps": 2764, "total_steps": 3345, "loss": 0.0251, "lr": 1.8152514286285588e-07, "epoch": 4.131539611360239, "percentage": 82.63, "elapsed_time": "0:53:32", "remaining_time": "0:11:15", "throughput": 7047.76, "total_tokens": 22642688} {"current_steps": 2765, "total_steps": 3345, "loss": 0.1297, "lr": 1.8091632518930063e-07, "epoch": 4.133034379671151, "percentage": 82.66, "elapsed_time": "0:53:33", "remaining_time": "0:11:14", "throughput": 7047.77, "total_tokens": 22650880} {"current_steps": 2766, "total_steps": 3345, "loss": 0.3292, "lr": 1.803084505319745e-07, "epoch": 4.134529147982063, "percentage": 82.69, "elapsed_time": "0:53:35", "remaining_time": "0:11:13", "throughput": 7047.78, "total_tokens": 22659072} {"current_steps": 2767, "total_steps": 3345, "loss": 0.1504, "lr": 1.7970151942707153e-07, "epoch": 4.136023916292975, "percentage": 82.72, "elapsed_time": "0:53:36", "remaining_time": "0:11:11", "throughput": 7047.78, "total_tokens": 22667264} {"current_steps": 2768, "total_steps": 3345, "loss": 0.0739, "lr": 1.7909553240995233e-07, "epoch": 4.1375186846038865, "percentage": 82.75, "elapsed_time": "0:53:37", "remaining_time": "0:11:10", "throughput": 7047.78, "total_tokens": 22675456} {"current_steps": 2769, "total_steps": 3345, "loss": 0.2558, "lr": 1.784904900151456e-07, "epoch": 4.139013452914798, "percentage": 82.78, "elapsed_time": "0:53:38", "remaining_time": "0:11:09", "throughput": 7047.76, "total_tokens": 22683648} {"current_steps": 2770, "total_steps": 3345, "loss": 0.2704, "lr": 1.7788639277634675e-07, "epoch": 4.14050822122571, "percentage": 82.81, "elapsed_time": "0:53:39", "remaining_time": "0:11:08", "throughput": 7047.75, "total_tokens": 22691840} {"current_steps": 2771, "total_steps": 3345, "loss": 0.2207, "lr": 1.772832412264168e-07, "epoch": 4.142002989536622, "percentage": 82.84, "elapsed_time": "0:53:40", "remaining_time": "0:11:07", "throughput": 7047.74, "total_tokens": 22700032} {"current_steps": 2772, "total_steps": 3345, "loss": 0.3248, "lr": 1.7668103589738333e-07, "epoch": 4.143497757847534, "percentage": 82.87, "elapsed_time": "0:53:42", "remaining_time": "0:11:06", "throughput": 7047.75, "total_tokens": 22708224} {"current_steps": 2773, "total_steps": 3345, "loss": 0.0879, "lr": 1.7607977732043882e-07, "epoch": 4.144992526158445, "percentage": 82.9, "elapsed_time": "0:53:43", "remaining_time": "0:11:04", "throughput": 7047.75, "total_tokens": 22716416} {"current_steps": 2774, "total_steps": 3345, "loss": 0.1259, "lr": 1.754794660259408e-07, "epoch": 4.146487294469357, "percentage": 82.93, "elapsed_time": "0:53:44", "remaining_time": "0:11:03", "throughput": 7047.75, "total_tokens": 22724608} {"current_steps": 2775, "total_steps": 3345, "loss": 0.2446, "lr": 1.7488010254341173e-07, "epoch": 4.147982062780269, "percentage": 82.96, "elapsed_time": "0:53:45", "remaining_time": "0:11:02", "throughput": 7047.76, "total_tokens": 22732800} {"current_steps": 2776, "total_steps": 3345, "loss": 0.2669, "lr": 1.7428168740153684e-07, "epoch": 4.149476831091181, "percentage": 82.99, "elapsed_time": "0:53:46", "remaining_time": "0:11:01", "throughput": 7047.77, "total_tokens": 22740992} {"current_steps": 2777, "total_steps": 3345, "loss": 0.2385, "lr": 1.7368422112816584e-07, "epoch": 4.150971599402093, "percentage": 83.02, "elapsed_time": "0:53:47", "remaining_time": "0:11:00", "throughput": 7047.77, "total_tokens": 22749184} {"current_steps": 2778, "total_steps": 3345, "loss": 0.3596, "lr": 1.730877042503111e-07, "epoch": 4.1524663677130045, "percentage": 83.05, "elapsed_time": "0:53:49", "remaining_time": "0:10:59", "throughput": 7047.77, "total_tokens": 22757376} {"current_steps": 2779, "total_steps": 3345, "loss": 0.0505, "lr": 1.7249213729414807e-07, "epoch": 4.153961136023916, "percentage": 83.08, "elapsed_time": "0:53:50", "remaining_time": "0:10:57", "throughput": 7047.78, "total_tokens": 22765568} {"current_steps": 2780, "total_steps": 3345, "loss": 0.112, "lr": 1.718975207850132e-07, "epoch": 4.155455904334828, "percentage": 83.11, "elapsed_time": "0:53:51", "remaining_time": "0:10:56", "throughput": 7047.78, "total_tokens": 22773760} {"current_steps": 2781, "total_steps": 3345, "loss": 0.2222, "lr": 1.713038552474057e-07, "epoch": 4.15695067264574, "percentage": 83.14, "elapsed_time": "0:53:52", "remaining_time": "0:10:55", "throughput": 7047.77, "total_tokens": 22781952} {"current_steps": 2782, "total_steps": 3345, "loss": 0.1948, "lr": 1.70711141204985e-07, "epoch": 4.158445440956652, "percentage": 83.17, "elapsed_time": "0:53:53", "remaining_time": "0:10:54", "throughput": 7047.75, "total_tokens": 22790144} {"current_steps": 2783, "total_steps": 3345, "loss": 0.345, "lr": 1.701193791805722e-07, "epoch": 4.159940209267564, "percentage": 83.2, "elapsed_time": "0:53:54", "remaining_time": "0:10:53", "throughput": 7047.73, "total_tokens": 22798336} {"current_steps": 2784, "total_steps": 3345, "loss": 0.241, "lr": 1.6952856969614767e-07, "epoch": 4.161434977578475, "percentage": 83.23, "elapsed_time": "0:53:56", "remaining_time": "0:10:52", "throughput": 7047.74, "total_tokens": 22806528} {"current_steps": 2785, "total_steps": 3345, "loss": 0.2394, "lr": 1.6893871327285204e-07, "epoch": 4.162929745889387, "percentage": 83.26, "elapsed_time": "0:53:57", "remaining_time": "0:10:50", "throughput": 7047.74, "total_tokens": 22814720} {"current_steps": 2786, "total_steps": 3345, "loss": 0.1486, "lr": 1.6834981043098595e-07, "epoch": 4.164424514200299, "percentage": 83.29, "elapsed_time": "0:53:58", "remaining_time": "0:10:49", "throughput": 7047.75, "total_tokens": 22822912} {"current_steps": 2787, "total_steps": 3345, "loss": 0.1999, "lr": 1.677618616900073e-07, "epoch": 4.165919282511211, "percentage": 83.32, "elapsed_time": "0:53:59", "remaining_time": "0:10:48", "throughput": 7047.76, "total_tokens": 22831104} {"current_steps": 2788, "total_steps": 3345, "loss": 0.0453, "lr": 1.6717486756853405e-07, "epoch": 4.1674140508221225, "percentage": 83.35, "elapsed_time": "0:54:00", "remaining_time": "0:10:47", "throughput": 7047.76, "total_tokens": 22839296} {"current_steps": 2789, "total_steps": 3345, "loss": 0.2881, "lr": 1.6658882858434076e-07, "epoch": 4.168908819133034, "percentage": 83.38, "elapsed_time": "0:54:01", "remaining_time": "0:10:46", "throughput": 7047.76, "total_tokens": 22847488} {"current_steps": 2790, "total_steps": 3345, "loss": 0.1195, "lr": 1.660037452543606e-07, "epoch": 4.170403587443946, "percentage": 83.41, "elapsed_time": "0:54:02", "remaining_time": "0:10:45", "throughput": 7047.76, "total_tokens": 22855680} {"current_steps": 2791, "total_steps": 3345, "loss": 0.2238, "lr": 1.654196180946828e-07, "epoch": 4.171898355754858, "percentage": 83.44, "elapsed_time": "0:54:04", "remaining_time": "0:10:43", "throughput": 7047.77, "total_tokens": 22863872} {"current_steps": 2792, "total_steps": 3345, "loss": 0.098, "lr": 1.6483644762055385e-07, "epoch": 4.17339312406577, "percentage": 83.47, "elapsed_time": "0:54:05", "remaining_time": "0:10:42", "throughput": 7047.78, "total_tokens": 22872064} {"current_steps": 2793, "total_steps": 3345, "loss": 0.2596, "lr": 1.6425423434637656e-07, "epoch": 4.174887892376682, "percentage": 83.5, "elapsed_time": "0:54:06", "remaining_time": "0:10:41", "throughput": 7047.78, "total_tokens": 22880256} {"current_steps": 2794, "total_steps": 3345, "loss": 0.1512, "lr": 1.6367297878570804e-07, "epoch": 4.176382660687594, "percentage": 83.53, "elapsed_time": "0:54:07", "remaining_time": "0:10:40", "throughput": 7047.78, "total_tokens": 22888448} {"current_steps": 2795, "total_steps": 3345, "loss": 0.1385, "lr": 1.630926814512629e-07, "epoch": 4.177877428998505, "percentage": 83.56, "elapsed_time": "0:54:08", "remaining_time": "0:10:39", "throughput": 7047.78, "total_tokens": 22896640} {"current_steps": 2796, "total_steps": 3345, "loss": 0.1179, "lr": 1.625133428549082e-07, "epoch": 4.179372197309417, "percentage": 83.59, "elapsed_time": "0:54:09", "remaining_time": "0:10:38", "throughput": 7047.79, "total_tokens": 22904832} {"current_steps": 2797, "total_steps": 3345, "loss": 0.1799, "lr": 1.6193496350766697e-07, "epoch": 4.180866965620329, "percentage": 83.62, "elapsed_time": "0:54:11", "remaining_time": "0:10:36", "throughput": 7047.79, "total_tokens": 22913024} {"current_steps": 2798, "total_steps": 3345, "loss": 0.2101, "lr": 1.6135754391971488e-07, "epoch": 4.18236173393124, "percentage": 83.65, "elapsed_time": "0:54:12", "remaining_time": "0:10:35", "throughput": 7047.8, "total_tokens": 22921216} {"current_steps": 2799, "total_steps": 3345, "loss": 0.4159, "lr": 1.6078108460038212e-07, "epoch": 4.183856502242152, "percentage": 83.68, "elapsed_time": "0:54:13", "remaining_time": "0:10:34", "throughput": 7047.81, "total_tokens": 22929408} {"current_steps": 2800, "total_steps": 3345, "loss": 0.1882, "lr": 1.6020558605815083e-07, "epoch": 4.185351270553064, "percentage": 83.71, "elapsed_time": "0:54:14", "remaining_time": "0:10:33", "throughput": 7047.8, "total_tokens": 22937600} {"current_steps": 2801, "total_steps": 3345, "loss": 0.046, "lr": 1.5963104880065651e-07, "epoch": 4.186846038863976, "percentage": 83.74, "elapsed_time": "0:54:15", "remaining_time": "0:10:32", "throughput": 7047.8, "total_tokens": 22945792} {"current_steps": 2802, "total_steps": 3345, "loss": 0.1255, "lr": 1.590574733346867e-07, "epoch": 4.188340807174888, "percentage": 83.77, "elapsed_time": "0:54:16", "remaining_time": "0:10:31", "throughput": 7047.81, "total_tokens": 22953984} {"current_steps": 2803, "total_steps": 3345, "loss": 0.2261, "lr": 1.5848486016617953e-07, "epoch": 4.1898355754858, "percentage": 83.8, "elapsed_time": "0:54:18", "remaining_time": "0:10:29", "throughput": 7047.81, "total_tokens": 22962176} {"current_steps": 2804, "total_steps": 3345, "loss": 0.1371, "lr": 1.5791320980022576e-07, "epoch": 4.191330343796712, "percentage": 83.83, "elapsed_time": "0:54:19", "remaining_time": "0:10:28", "throughput": 7047.81, "total_tokens": 22970368} {"current_steps": 2805, "total_steps": 3345, "loss": 0.3322, "lr": 1.573425227410655e-07, "epoch": 4.192825112107624, "percentage": 83.86, "elapsed_time": "0:54:20", "remaining_time": "0:10:27", "throughput": 7047.81, "total_tokens": 22978560} {"current_steps": 2806, "total_steps": 3345, "loss": 0.2949, "lr": 1.5677279949209034e-07, "epoch": 4.1943198804185355, "percentage": 83.89, "elapsed_time": "0:54:21", "remaining_time": "0:10:26", "throughput": 7047.81, "total_tokens": 22986752} {"current_steps": 2807, "total_steps": 3345, "loss": 0.3727, "lr": 1.5620404055584057e-07, "epoch": 4.1958146487294465, "percentage": 83.92, "elapsed_time": "0:54:22", "remaining_time": "0:10:25", "throughput": 7047.81, "total_tokens": 22994944} {"current_steps": 2808, "total_steps": 3345, "loss": 0.2365, "lr": 1.5563624643400708e-07, "epoch": 4.197309417040358, "percentage": 83.95, "elapsed_time": "0:54:23", "remaining_time": "0:10:24", "throughput": 7047.81, "total_tokens": 23003136} {"current_steps": 2809, "total_steps": 3345, "loss": 0.3743, "lr": 1.5506941762742907e-07, "epoch": 4.19880418535127, "percentage": 83.98, "elapsed_time": "0:54:25", "remaining_time": "0:10:23", "throughput": 7047.82, "total_tokens": 23011328} {"current_steps": 2810, "total_steps": 3345, "loss": 0.2281, "lr": 1.5450355463609386e-07, "epoch": 4.200298953662182, "percentage": 84.01, "elapsed_time": "0:54:26", "remaining_time": "0:10:21", "throughput": 7047.82, "total_tokens": 23019520} {"current_steps": 2811, "total_steps": 3345, "loss": 0.0781, "lr": 1.5393865795913759e-07, "epoch": 4.201793721973094, "percentage": 84.04, "elapsed_time": "0:54:27", "remaining_time": "0:10:20", "throughput": 7047.82, "total_tokens": 23027712} {"current_steps": 2812, "total_steps": 3345, "loss": 0.2166, "lr": 1.5337472809484374e-07, "epoch": 4.203288490284006, "percentage": 84.07, "elapsed_time": "0:54:28", "remaining_time": "0:10:19", "throughput": 7047.83, "total_tokens": 23035904} {"current_steps": 2813, "total_steps": 3345, "loss": 0.242, "lr": 1.5281176554064332e-07, "epoch": 4.204783258594918, "percentage": 84.1, "elapsed_time": "0:54:29", "remaining_time": "0:10:18", "throughput": 7047.8, "total_tokens": 23044096} {"current_steps": 2814, "total_steps": 3345, "loss": 0.1383, "lr": 1.522497707931131e-07, "epoch": 4.20627802690583, "percentage": 84.13, "elapsed_time": "0:54:30", "remaining_time": "0:10:17", "throughput": 7047.79, "total_tokens": 23052288} {"current_steps": 2815, "total_steps": 3345, "loss": 0.261, "lr": 1.516887443479774e-07, "epoch": 4.207772795216742, "percentage": 84.16, "elapsed_time": "0:54:32", "remaining_time": "0:10:16", "throughput": 7047.79, "total_tokens": 23060480} {"current_steps": 2816, "total_steps": 3345, "loss": 0.1847, "lr": 1.5112868670010537e-07, "epoch": 4.2092675635276535, "percentage": 84.19, "elapsed_time": "0:54:33", "remaining_time": "0:10:14", "throughput": 7047.79, "total_tokens": 23068672} {"current_steps": 2817, "total_steps": 3345, "loss": 0.0289, "lr": 1.5056959834351236e-07, "epoch": 4.210762331838565, "percentage": 84.22, "elapsed_time": "0:54:34", "remaining_time": "0:10:13", "throughput": 7047.82, "total_tokens": 23076864} {"current_steps": 2818, "total_steps": 3345, "loss": 0.1446, "lr": 1.5001147977135865e-07, "epoch": 4.212257100149476, "percentage": 84.25, "elapsed_time": "0:54:35", "remaining_time": "0:10:12", "throughput": 7047.83, "total_tokens": 23085056} {"current_steps": 2819, "total_steps": 3345, "loss": 0.0512, "lr": 1.4945433147594833e-07, "epoch": 4.213751868460388, "percentage": 84.28, "elapsed_time": "0:54:36", "remaining_time": "0:10:11", "throughput": 7047.83, "total_tokens": 23093248} {"current_steps": 2820, "total_steps": 3345, "loss": 0.2733, "lr": 1.488981539487308e-07, "epoch": 4.2152466367713, "percentage": 84.3, "elapsed_time": "0:54:37", "remaining_time": "0:10:10", "throughput": 7047.84, "total_tokens": 23101440} {"current_steps": 2821, "total_steps": 3345, "loss": 0.0903, "lr": 1.4834294768029805e-07, "epoch": 4.216741405082212, "percentage": 84.33, "elapsed_time": "0:54:38", "remaining_time": "0:10:09", "throughput": 7047.84, "total_tokens": 23109632} {"current_steps": 2822, "total_steps": 3345, "loss": 0.1693, "lr": 1.477887131603864e-07, "epoch": 4.218236173393124, "percentage": 84.36, "elapsed_time": "0:54:40", "remaining_time": "0:10:07", "throughput": 7047.85, "total_tokens": 23117824} {"current_steps": 2823, "total_steps": 3345, "loss": 0.1241, "lr": 1.472354508778738e-07, "epoch": 4.219730941704036, "percentage": 84.39, "elapsed_time": "0:54:41", "remaining_time": "0:10:06", "throughput": 7047.85, "total_tokens": 23126016} {"current_steps": 2824, "total_steps": 3345, "loss": 0.0683, "lr": 1.466831613207817e-07, "epoch": 4.221225710014948, "percentage": 84.42, "elapsed_time": "0:54:42", "remaining_time": "0:10:05", "throughput": 7047.85, "total_tokens": 23134208} {"current_steps": 2825, "total_steps": 3345, "loss": 0.2898, "lr": 1.461318449762733e-07, "epoch": 4.22272047832586, "percentage": 84.45, "elapsed_time": "0:54:43", "remaining_time": "0:10:04", "throughput": 7047.85, "total_tokens": 23142400} {"current_steps": 2826, "total_steps": 3345, "loss": 0.2419, "lr": 1.4558150233065255e-07, "epoch": 4.2242152466367715, "percentage": 84.48, "elapsed_time": "0:54:44", "remaining_time": "0:10:03", "throughput": 7047.85, "total_tokens": 23150592} {"current_steps": 2827, "total_steps": 3345, "loss": 0.1888, "lr": 1.4503213386936582e-07, "epoch": 4.225710014947683, "percentage": 84.51, "elapsed_time": "0:54:45", "remaining_time": "0:10:02", "throughput": 7047.84, "total_tokens": 23158784} {"current_steps": 2828, "total_steps": 3345, "loss": 0.2255, "lr": 1.4448374007699855e-07, "epoch": 4.227204783258595, "percentage": 84.54, "elapsed_time": "0:54:47", "remaining_time": "0:10:00", "throughput": 7047.84, "total_tokens": 23166976} {"current_steps": 2829, "total_steps": 3345, "loss": 0.1783, "lr": 1.4393632143727853e-07, "epoch": 4.228699551569507, "percentage": 84.57, "elapsed_time": "0:54:48", "remaining_time": "0:09:59", "throughput": 7047.83, "total_tokens": 23175168} {"current_steps": 2830, "total_steps": 3345, "loss": 0.2545, "lr": 1.4338987843307132e-07, "epoch": 4.230194319880418, "percentage": 84.6, "elapsed_time": "0:54:49", "remaining_time": "0:09:58", "throughput": 7047.84, "total_tokens": 23183360} {"current_steps": 2831, "total_steps": 3345, "loss": 0.0056, "lr": 1.428444115463834e-07, "epoch": 4.23168908819133, "percentage": 84.63, "elapsed_time": "0:54:50", "remaining_time": "0:09:57", "throughput": 7047.82, "total_tokens": 23191552} {"current_steps": 2832, "total_steps": 3345, "loss": 0.0928, "lr": 1.4229992125835908e-07, "epoch": 4.233183856502242, "percentage": 84.66, "elapsed_time": "0:54:51", "remaining_time": "0:09:56", "throughput": 7047.82, "total_tokens": 23199744} {"current_steps": 2833, "total_steps": 3345, "loss": 0.2354, "lr": 1.4175640804928227e-07, "epoch": 4.234678624813154, "percentage": 84.69, "elapsed_time": "0:54:52", "remaining_time": "0:09:55", "throughput": 7047.81, "total_tokens": 23207936} {"current_steps": 2834, "total_steps": 3345, "loss": 0.4186, "lr": 1.412138723985744e-07, "epoch": 4.236173393124066, "percentage": 84.72, "elapsed_time": "0:54:54", "remaining_time": "0:09:53", "throughput": 7047.82, "total_tokens": 23216128} {"current_steps": 2835, "total_steps": 3345, "loss": 0.0872, "lr": 1.4067231478479464e-07, "epoch": 4.237668161434978, "percentage": 84.75, "elapsed_time": "0:54:55", "remaining_time": "0:09:52", "throughput": 7047.82, "total_tokens": 23224320} {"current_steps": 2836, "total_steps": 3345, "loss": 0.193, "lr": 1.4013173568563978e-07, "epoch": 4.2391629297458895, "percentage": 84.78, "elapsed_time": "0:54:56", "remaining_time": "0:09:51", "throughput": 7047.83, "total_tokens": 23232512} {"current_steps": 2837, "total_steps": 3345, "loss": 0.2055, "lr": 1.3959213557794295e-07, "epoch": 4.240657698056801, "percentage": 84.81, "elapsed_time": "0:54:57", "remaining_time": "0:09:50", "throughput": 7047.84, "total_tokens": 23240704} {"current_steps": 2838, "total_steps": 3345, "loss": 0.213, "lr": 1.390535149376744e-07, "epoch": 4.242152466367713, "percentage": 84.84, "elapsed_time": "0:54:58", "remaining_time": "0:09:49", "throughput": 7047.83, "total_tokens": 23248896} {"current_steps": 2839, "total_steps": 3345, "loss": 0.1517, "lr": 1.3851587423993978e-07, "epoch": 4.243647234678625, "percentage": 84.87, "elapsed_time": "0:54:59", "remaining_time": "0:09:48", "throughput": 7047.83, "total_tokens": 23257088} {"current_steps": 2840, "total_steps": 3345, "loss": 0.0859, "lr": 1.3797921395898084e-07, "epoch": 4.245142002989537, "percentage": 84.9, "elapsed_time": "0:55:01", "remaining_time": "0:09:46", "throughput": 7047.8, "total_tokens": 23265280} {"current_steps": 2841, "total_steps": 3345, "loss": 0.0561, "lr": 1.3744353456817448e-07, "epoch": 4.246636771300448, "percentage": 84.93, "elapsed_time": "0:55:02", "remaining_time": "0:09:45", "throughput": 7047.8, "total_tokens": 23273472} {"current_steps": 2842, "total_steps": 3345, "loss": 0.2077, "lr": 1.3690883654003172e-07, "epoch": 4.24813153961136, "percentage": 84.96, "elapsed_time": "0:55:03", "remaining_time": "0:09:44", "throughput": 7047.81, "total_tokens": 23281664} {"current_steps": 2843, "total_steps": 3345, "loss": 0.0967, "lr": 1.363751203461991e-07, "epoch": 4.249626307922272, "percentage": 84.99, "elapsed_time": "0:55:04", "remaining_time": "0:09:43", "throughput": 7047.81, "total_tokens": 23289856} {"current_steps": 2844, "total_steps": 3345, "loss": 0.1071, "lr": 1.3584238645745582e-07, "epoch": 4.251121076233184, "percentage": 85.02, "elapsed_time": "0:55:05", "remaining_time": "0:09:42", "throughput": 7047.81, "total_tokens": 23298048} {"current_steps": 2845, "total_steps": 3345, "loss": 0.1596, "lr": 1.3531063534371558e-07, "epoch": 4.252615844544096, "percentage": 85.05, "elapsed_time": "0:55:06", "remaining_time": "0:09:41", "throughput": 7047.83, "total_tokens": 23306240} {"current_steps": 2846, "total_steps": 3345, "loss": 0.0663, "lr": 1.3477986747402472e-07, "epoch": 4.2541106128550075, "percentage": 85.08, "elapsed_time": "0:55:08", "remaining_time": "0:09:40", "throughput": 7047.83, "total_tokens": 23314432} {"current_steps": 2847, "total_steps": 3345, "loss": 0.0998, "lr": 1.3425008331656288e-07, "epoch": 4.255605381165919, "percentage": 85.11, "elapsed_time": "0:55:09", "remaining_time": "0:09:38", "throughput": 7047.84, "total_tokens": 23322624} {"current_steps": 2848, "total_steps": 3345, "loss": 0.0533, "lr": 1.3372128333864073e-07, "epoch": 4.257100149476831, "percentage": 85.14, "elapsed_time": "0:55:10", "remaining_time": "0:09:37", "throughput": 7047.84, "total_tokens": 23330816} {"current_steps": 2849, "total_steps": 3345, "loss": 0.1629, "lr": 1.3319346800670236e-07, "epoch": 4.258594917787743, "percentage": 85.17, "elapsed_time": "0:55:11", "remaining_time": "0:09:36", "throughput": 7047.84, "total_tokens": 23339008} {"current_steps": 2850, "total_steps": 3345, "loss": 0.2796, "lr": 1.32666637786322e-07, "epoch": 4.260089686098655, "percentage": 85.2, "elapsed_time": "0:55:12", "remaining_time": "0:09:35", "throughput": 7047.85, "total_tokens": 23347200} {"current_steps": 2851, "total_steps": 3345, "loss": 0.161, "lr": 1.3214079314220586e-07, "epoch": 4.261584454409567, "percentage": 85.23, "elapsed_time": "0:55:13", "remaining_time": "0:09:34", "throughput": 7047.85, "total_tokens": 23355392} {"current_steps": 2852, "total_steps": 3345, "loss": 0.0238, "lr": 1.316159345381904e-07, "epoch": 4.263079222720478, "percentage": 85.26, "elapsed_time": "0:55:14", "remaining_time": "0:09:33", "throughput": 7047.86, "total_tokens": 23363584} {"current_steps": 2853, "total_steps": 3345, "loss": 0.2356, "lr": 1.3109206243724207e-07, "epoch": 4.26457399103139, "percentage": 85.29, "elapsed_time": "0:55:16", "remaining_time": "0:09:31", "throughput": 7047.86, "total_tokens": 23371776} {"current_steps": 2854, "total_steps": 3345, "loss": 0.224, "lr": 1.3056917730145806e-07, "epoch": 4.266068759342302, "percentage": 85.32, "elapsed_time": "0:55:17", "remaining_time": "0:09:30", "throughput": 7047.86, "total_tokens": 23379968} {"current_steps": 2855, "total_steps": 3345, "loss": 0.0591, "lr": 1.3004727959206362e-07, "epoch": 4.267563527653214, "percentage": 85.35, "elapsed_time": "0:55:18", "remaining_time": "0:09:29", "throughput": 7047.86, "total_tokens": 23388160} {"current_steps": 2856, "total_steps": 3345, "loss": 0.1135, "lr": 1.2952636976941408e-07, "epoch": 4.2690582959641254, "percentage": 85.38, "elapsed_time": "0:55:19", "remaining_time": "0:09:28", "throughput": 7047.86, "total_tokens": 23396352} {"current_steps": 2857, "total_steps": 3345, "loss": 0.1609, "lr": 1.2900644829299327e-07, "epoch": 4.270553064275037, "percentage": 85.41, "elapsed_time": "0:55:20", "remaining_time": "0:09:27", "throughput": 7047.87, "total_tokens": 23404544} {"current_steps": 2858, "total_steps": 3345, "loss": 0.1056, "lr": 1.2848751562141243e-07, "epoch": 4.272047832585949, "percentage": 85.44, "elapsed_time": "0:55:21", "remaining_time": "0:09:26", "throughput": 7047.87, "total_tokens": 23412736} {"current_steps": 2859, "total_steps": 3345, "loss": 0.1263, "lr": 1.2796957221241192e-07, "epoch": 4.273542600896861, "percentage": 85.47, "elapsed_time": "0:55:23", "remaining_time": "0:09:24", "throughput": 7047.87, "total_tokens": 23420928} {"current_steps": 2860, "total_steps": 3345, "loss": 0.0936, "lr": 1.2745261852285791e-07, "epoch": 4.275037369207773, "percentage": 85.5, "elapsed_time": "0:55:24", "remaining_time": "0:09:23", "throughput": 7047.87, "total_tokens": 23429120} {"current_steps": 2861, "total_steps": 3345, "loss": 0.2449, "lr": 1.2693665500874502e-07, "epoch": 4.276532137518685, "percentage": 85.53, "elapsed_time": "0:55:25", "remaining_time": "0:09:22", "throughput": 7047.87, "total_tokens": 23437312} {"current_steps": 2862, "total_steps": 3345, "loss": 0.1961, "lr": 1.2642168212519317e-07, "epoch": 4.278026905829597, "percentage": 85.56, "elapsed_time": "0:55:26", "remaining_time": "0:09:21", "throughput": 7047.87, "total_tokens": 23445504} {"current_steps": 2863, "total_steps": 3345, "loss": 0.2828, "lr": 1.2590770032645e-07, "epoch": 4.279521674140508, "percentage": 85.59, "elapsed_time": "0:55:27", "remaining_time": "0:09:20", "throughput": 7047.86, "total_tokens": 23453696} {"current_steps": 2864, "total_steps": 3345, "loss": 0.3929, "lr": 1.2539471006588728e-07, "epoch": 4.28101644245142, "percentage": 85.62, "elapsed_time": "0:55:28", "remaining_time": "0:09:19", "throughput": 7047.86, "total_tokens": 23461888} {"current_steps": 2865, "total_steps": 3345, "loss": 0.2726, "lr": 1.2488271179600332e-07, "epoch": 4.2825112107623315, "percentage": 85.65, "elapsed_time": "0:55:30", "remaining_time": "0:09:17", "throughput": 7047.86, "total_tokens": 23470080} {"current_steps": 2866, "total_steps": 3345, "loss": 0.0682, "lr": 1.2437170596842088e-07, "epoch": 4.284005979073243, "percentage": 85.68, "elapsed_time": "0:55:31", "remaining_time": "0:09:16", "throughput": 7047.88, "total_tokens": 23478272} {"current_steps": 2867, "total_steps": 3345, "loss": 0.3987, "lr": 1.2386169303388735e-07, "epoch": 4.285500747384155, "percentage": 85.71, "elapsed_time": "0:55:32", "remaining_time": "0:09:15", "throughput": 7047.87, "total_tokens": 23486464} {"current_steps": 2868, "total_steps": 3345, "loss": 0.0363, "lr": 1.2335267344227477e-07, "epoch": 4.286995515695067, "percentage": 85.74, "elapsed_time": "0:55:33", "remaining_time": "0:09:14", "throughput": 7047.86, "total_tokens": 23494656} {"current_steps": 2869, "total_steps": 3345, "loss": 0.0307, "lr": 1.2284464764257833e-07, "epoch": 4.288490284005979, "percentage": 85.77, "elapsed_time": "0:55:34", "remaining_time": "0:09:13", "throughput": 7047.86, "total_tokens": 23502848} {"current_steps": 2870, "total_steps": 3345, "loss": 0.0502, "lr": 1.2233761608291706e-07, "epoch": 4.289985052316891, "percentage": 85.8, "elapsed_time": "0:55:35", "remaining_time": "0:09:12", "throughput": 7047.86, "total_tokens": 23511040} {"current_steps": 2871, "total_steps": 3345, "loss": 0.1088, "lr": 1.2183157921053262e-07, "epoch": 4.291479820627803, "percentage": 85.83, "elapsed_time": "0:55:37", "remaining_time": "0:09:10", "throughput": 7047.86, "total_tokens": 23519232} {"current_steps": 2872, "total_steps": 3345, "loss": 0.0699, "lr": 1.213265374717898e-07, "epoch": 4.292974588938715, "percentage": 85.86, "elapsed_time": "0:55:38", "remaining_time": "0:09:09", "throughput": 7047.86, "total_tokens": 23527424} {"current_steps": 2873, "total_steps": 3345, "loss": 0.2265, "lr": 1.2082249131217484e-07, "epoch": 4.294469357249627, "percentage": 85.89, "elapsed_time": "0:55:39", "remaining_time": "0:09:08", "throughput": 7047.86, "total_tokens": 23535616} {"current_steps": 2874, "total_steps": 3345, "loss": 0.2269, "lr": 1.2031944117629674e-07, "epoch": 4.2959641255605385, "percentage": 85.92, "elapsed_time": "0:55:40", "remaining_time": "0:09:07", "throughput": 7047.87, "total_tokens": 23543808} {"current_steps": 2875, "total_steps": 3345, "loss": 0.144, "lr": 1.1981738750788534e-07, "epoch": 4.2974588938714495, "percentage": 85.95, "elapsed_time": "0:55:41", "remaining_time": "0:09:06", "throughput": 7047.87, "total_tokens": 23552000} {"current_steps": 2876, "total_steps": 3345, "loss": 0.2052, "lr": 1.1931633074979133e-07, "epoch": 4.298953662182361, "percentage": 85.98, "elapsed_time": "0:55:42", "remaining_time": "0:09:05", "throughput": 7047.87, "total_tokens": 23560192} {"current_steps": 2877, "total_steps": 3345, "loss": 0.3081, "lr": 1.1881627134398679e-07, "epoch": 4.300448430493273, "percentage": 86.01, "elapsed_time": "0:55:44", "remaining_time": "0:09:03", "throughput": 7047.88, "total_tokens": 23568384} {"current_steps": 2878, "total_steps": 3345, "loss": 0.0525, "lr": 1.183172097315631e-07, "epoch": 4.301943198804185, "percentage": 86.04, "elapsed_time": "0:55:45", "remaining_time": "0:09:02", "throughput": 7047.86, "total_tokens": 23576576} {"current_steps": 2879, "total_steps": 3345, "loss": 0.2018, "lr": 1.1781914635273228e-07, "epoch": 4.303437967115097, "percentage": 86.07, "elapsed_time": "0:55:46", "remaining_time": "0:09:01", "throughput": 7047.86, "total_tokens": 23584768} {"current_steps": 2880, "total_steps": 3345, "loss": 0.402, "lr": 1.1732208164682568e-07, "epoch": 4.304932735426009, "percentage": 86.1, "elapsed_time": "0:55:47", "remaining_time": "0:09:00", "throughput": 7047.86, "total_tokens": 23592960} {"current_steps": 2881, "total_steps": 3345, "loss": 0.1127, "lr": 1.1682601605229355e-07, "epoch": 4.306427503736921, "percentage": 86.13, "elapsed_time": "0:55:48", "remaining_time": "0:08:59", "throughput": 7047.87, "total_tokens": 23601152} {"current_steps": 2882, "total_steps": 3345, "loss": 0.202, "lr": 1.1633095000670474e-07, "epoch": 4.307922272047833, "percentage": 86.16, "elapsed_time": "0:55:49", "remaining_time": "0:08:58", "throughput": 7047.87, "total_tokens": 23609344} {"current_steps": 2883, "total_steps": 3345, "loss": 0.2733, "lr": 1.1583688394674677e-07, "epoch": 4.309417040358745, "percentage": 86.19, "elapsed_time": "0:55:51", "remaining_time": "0:08:56", "throughput": 7047.87, "total_tokens": 23617536} {"current_steps": 2884, "total_steps": 3345, "loss": 0.2267, "lr": 1.1534381830822505e-07, "epoch": 4.3109118086696565, "percentage": 86.22, "elapsed_time": "0:55:52", "remaining_time": "0:08:55", "throughput": 7047.88, "total_tokens": 23625728} {"current_steps": 2885, "total_steps": 3345, "loss": 0.2241, "lr": 1.148517535260621e-07, "epoch": 4.312406576980568, "percentage": 86.25, "elapsed_time": "0:55:53", "remaining_time": "0:08:54", "throughput": 7047.88, "total_tokens": 23633920} {"current_steps": 2886, "total_steps": 3345, "loss": 0.2361, "lr": 1.1436069003429834e-07, "epoch": 4.31390134529148, "percentage": 86.28, "elapsed_time": "0:55:54", "remaining_time": "0:08:53", "throughput": 7047.89, "total_tokens": 23642112} {"current_steps": 2887, "total_steps": 3345, "loss": 0.1661, "lr": 1.1387062826608994e-07, "epoch": 4.315396113602391, "percentage": 86.31, "elapsed_time": "0:55:55", "remaining_time": "0:08:52", "throughput": 7047.88, "total_tokens": 23650304} {"current_steps": 2888, "total_steps": 3345, "loss": 0.0162, "lr": 1.133815686537107e-07, "epoch": 4.316890881913303, "percentage": 86.34, "elapsed_time": "0:55:56", "remaining_time": "0:08:51", "throughput": 7047.89, "total_tokens": 23658496} {"current_steps": 2889, "total_steps": 3345, "loss": 0.1305, "lr": 1.1289351162854927e-07, "epoch": 4.318385650224215, "percentage": 86.37, "elapsed_time": "0:55:57", "remaining_time": "0:08:50", "throughput": 7047.89, "total_tokens": 23666688} {"current_steps": 2890, "total_steps": 3345, "loss": 0.2834, "lr": 1.1240645762111077e-07, "epoch": 4.319880418535127, "percentage": 86.4, "elapsed_time": "0:55:59", "remaining_time": "0:08:48", "throughput": 7047.9, "total_tokens": 23674880} {"current_steps": 2891, "total_steps": 3345, "loss": 0.1383, "lr": 1.1192040706101553e-07, "epoch": 4.321375186846039, "percentage": 86.43, "elapsed_time": "0:56:00", "remaining_time": "0:08:47", "throughput": 7047.9, "total_tokens": 23683072} {"current_steps": 2892, "total_steps": 3345, "loss": 0.0764, "lr": 1.1143536037699813e-07, "epoch": 4.322869955156951, "percentage": 86.46, "elapsed_time": "0:56:01", "remaining_time": "0:08:46", "throughput": 7047.91, "total_tokens": 23691264} {"current_steps": 2893, "total_steps": 3345, "loss": 0.2017, "lr": 1.1095131799690822e-07, "epoch": 4.324364723467863, "percentage": 86.49, "elapsed_time": "0:56:02", "remaining_time": "0:08:45", "throughput": 7047.91, "total_tokens": 23699456} {"current_steps": 2894, "total_steps": 3345, "loss": 0.2697, "lr": 1.1046828034770932e-07, "epoch": 4.3258594917787745, "percentage": 86.52, "elapsed_time": "0:56:03", "remaining_time": "0:08:44", "throughput": 7047.92, "total_tokens": 23707648} {"current_steps": 2895, "total_steps": 3345, "loss": 0.2789, "lr": 1.0998624785547917e-07, "epoch": 4.327354260089686, "percentage": 86.55, "elapsed_time": "0:56:04", "remaining_time": "0:08:43", "throughput": 7047.92, "total_tokens": 23715840} {"current_steps": 2896, "total_steps": 3345, "loss": 0.1538, "lr": 1.0950522094540756e-07, "epoch": 4.328849028400598, "percentage": 86.58, "elapsed_time": "0:56:06", "remaining_time": "0:08:41", "throughput": 7047.93, "total_tokens": 23724032} {"current_steps": 2897, "total_steps": 3345, "loss": 0.3498, "lr": 1.0902520004179934e-07, "epoch": 4.33034379671151, "percentage": 86.61, "elapsed_time": "0:56:07", "remaining_time": "0:08:40", "throughput": 7047.93, "total_tokens": 23732224} {"current_steps": 2898, "total_steps": 3345, "loss": 0.1977, "lr": 1.0854618556807014e-07, "epoch": 4.331838565022421, "percentage": 86.64, "elapsed_time": "0:56:08", "remaining_time": "0:08:39", "throughput": 7047.94, "total_tokens": 23740416} {"current_steps": 2899, "total_steps": 3345, "loss": 0.1345, "lr": 1.0806817794674878e-07, "epoch": 4.333333333333333, "percentage": 86.67, "elapsed_time": "0:56:09", "remaining_time": "0:08:38", "throughput": 7047.94, "total_tokens": 23748608} {"current_steps": 2900, "total_steps": 3345, "loss": 0.2556, "lr": 1.075911775994759e-07, "epoch": 4.334828101644245, "percentage": 86.7, "elapsed_time": "0:56:10", "remaining_time": "0:08:37", "throughput": 7047.96, "total_tokens": 23756800} {"current_steps": 2901, "total_steps": 3345, "loss": 0.1854, "lr": 1.0711518494700312e-07, "epoch": 4.336322869955157, "percentage": 86.73, "elapsed_time": "0:56:11", "remaining_time": "0:08:36", "throughput": 7047.95, "total_tokens": 23764992} {"current_steps": 2902, "total_steps": 3345, "loss": 0.4121, "lr": 1.066402004091939e-07, "epoch": 4.337817638266069, "percentage": 86.76, "elapsed_time": "0:56:13", "remaining_time": "0:08:34", "throughput": 7047.96, "total_tokens": 23773184} {"current_steps": 2903, "total_steps": 3345, "loss": 0.2014, "lr": 1.061662244050217e-07, "epoch": 4.339312406576981, "percentage": 86.79, "elapsed_time": "0:56:14", "remaining_time": "0:08:33", "throughput": 7047.97, "total_tokens": 23781376} {"current_steps": 2904, "total_steps": 3345, "loss": 0.3933, "lr": 1.0569325735257139e-07, "epoch": 4.3408071748878925, "percentage": 86.82, "elapsed_time": "0:56:15", "remaining_time": "0:08:32", "throughput": 7047.97, "total_tokens": 23789568} {"current_steps": 2905, "total_steps": 3345, "loss": 0.0745, "lr": 1.0522129966903646e-07, "epoch": 4.342301943198804, "percentage": 86.85, "elapsed_time": "0:56:16", "remaining_time": "0:08:31", "throughput": 7047.97, "total_tokens": 23797760} {"current_steps": 2906, "total_steps": 3345, "loss": 0.2106, "lr": 1.0475035177072143e-07, "epoch": 4.343796711509716, "percentage": 86.88, "elapsed_time": "0:56:17", "remaining_time": "0:08:30", "throughput": 7047.97, "total_tokens": 23805952} {"current_steps": 2907, "total_steps": 3345, "loss": 0.2754, "lr": 1.0428041407303954e-07, "epoch": 4.345291479820628, "percentage": 86.91, "elapsed_time": "0:56:18", "remaining_time": "0:08:29", "throughput": 7047.97, "total_tokens": 23814144} {"current_steps": 2908, "total_steps": 3345, "loss": 0.0931, "lr": 1.0381148699051268e-07, "epoch": 4.34678624813154, "percentage": 86.94, "elapsed_time": "0:56:20", "remaining_time": "0:08:27", "throughput": 7047.97, "total_tokens": 23822336} {"current_steps": 2909, "total_steps": 3345, "loss": 0.114, "lr": 1.033435709367718e-07, "epoch": 4.348281016442451, "percentage": 86.97, "elapsed_time": "0:56:21", "remaining_time": "0:08:26", "throughput": 7047.97, "total_tokens": 23830528} {"current_steps": 2910, "total_steps": 3345, "loss": 0.2024, "lr": 1.0287666632455562e-07, "epoch": 4.349775784753363, "percentage": 87.0, "elapsed_time": "0:56:22", "remaining_time": "0:08:25", "throughput": 7047.98, "total_tokens": 23838720} {"current_steps": 2911, "total_steps": 3345, "loss": 0.1364, "lr": 1.0241077356571108e-07, "epoch": 4.351270553064275, "percentage": 87.03, "elapsed_time": "0:56:23", "remaining_time": "0:08:24", "throughput": 7047.98, "total_tokens": 23846912} {"current_steps": 2912, "total_steps": 3345, "loss": 0.3239, "lr": 1.019458930711921e-07, "epoch": 4.352765321375187, "percentage": 87.06, "elapsed_time": "0:56:24", "remaining_time": "0:08:23", "throughput": 7047.98, "total_tokens": 23855104} {"current_steps": 2913, "total_steps": 3345, "loss": 0.1687, "lr": 1.0148202525106024e-07, "epoch": 4.354260089686099, "percentage": 87.09, "elapsed_time": "0:56:25", "remaining_time": "0:08:22", "throughput": 7047.98, "total_tokens": 23863296} {"current_steps": 2914, "total_steps": 3345, "loss": 0.1545, "lr": 1.0101917051448335e-07, "epoch": 4.3557548579970105, "percentage": 87.12, "elapsed_time": "0:56:26", "remaining_time": "0:08:20", "throughput": 7047.99, "total_tokens": 23871488} {"current_steps": 2915, "total_steps": 3345, "loss": 0.28, "lr": 1.0055732926973607e-07, "epoch": 4.357249626307922, "percentage": 87.14, "elapsed_time": "0:56:28", "remaining_time": "0:08:19", "throughput": 7047.99, "total_tokens": 23879680} {"current_steps": 2916, "total_steps": 3345, "loss": 0.4336, "lr": 1.0009650192419895e-07, "epoch": 4.358744394618834, "percentage": 87.17, "elapsed_time": "0:56:29", "remaining_time": "0:08:18", "throughput": 7047.99, "total_tokens": 23887872} {"current_steps": 2917, "total_steps": 3345, "loss": 0.2061, "lr": 9.963668888435779e-08, "epoch": 4.360239162929746, "percentage": 87.2, "elapsed_time": "0:56:30", "remaining_time": "0:08:17", "throughput": 7047.98, "total_tokens": 23896064} {"current_steps": 2918, "total_steps": 3345, "loss": 0.2209, "lr": 9.917789055580427e-08, "epoch": 4.361733931240658, "percentage": 87.23, "elapsed_time": "0:56:31", "remaining_time": "0:08:16", "throughput": 7047.98, "total_tokens": 23904256} {"current_steps": 2919, "total_steps": 3345, "loss": 0.2534, "lr": 9.872010734323436e-08, "epoch": 4.36322869955157, "percentage": 87.26, "elapsed_time": "0:56:32", "remaining_time": "0:08:15", "throughput": 7047.98, "total_tokens": 23912448} {"current_steps": 2920, "total_steps": 3345, "loss": 0.1759, "lr": 9.826333965044954e-08, "epoch": 4.364723467862481, "percentage": 87.29, "elapsed_time": "0:56:33", "remaining_time": "0:08:13", "throughput": 7047.96, "total_tokens": 23920640} {"current_steps": 2921, "total_steps": 3345, "loss": 0.1266, "lr": 9.780758788035457e-08, "epoch": 4.366218236173393, "percentage": 87.32, "elapsed_time": "0:56:35", "remaining_time": "0:08:12", "throughput": 7047.95, "total_tokens": 23928832} {"current_steps": 2922, "total_steps": 3345, "loss": 0.2939, "lr": 9.735285243495845e-08, "epoch": 4.367713004484305, "percentage": 87.35, "elapsed_time": "0:56:36", "remaining_time": "0:08:11", "throughput": 7047.95, "total_tokens": 23937024} {"current_steps": 2923, "total_steps": 3345, "loss": 0.0454, "lr": 9.689913371537435e-08, "epoch": 4.3692077727952165, "percentage": 87.38, "elapsed_time": "0:56:37", "remaining_time": "0:08:10", "throughput": 7047.95, "total_tokens": 23945216} {"current_steps": 2924, "total_steps": 3345, "loss": 0.0639, "lr": 9.644643212181726e-08, "epoch": 4.370702541106128, "percentage": 87.41, "elapsed_time": "0:56:38", "remaining_time": "0:08:09", "throughput": 7047.94, "total_tokens": 23953408} {"current_steps": 2925, "total_steps": 3345, "loss": 0.1364, "lr": 9.599474805360637e-08, "epoch": 4.37219730941704, "percentage": 87.44, "elapsed_time": "0:56:39", "remaining_time": "0:08:08", "throughput": 7047.94, "total_tokens": 23961600} {"current_steps": 2926, "total_steps": 3345, "loss": 0.1664, "lr": 9.554408190916214e-08, "epoch": 4.373692077727952, "percentage": 87.47, "elapsed_time": "0:56:40", "remaining_time": "0:08:07", "throughput": 7047.95, "total_tokens": 23969792} {"current_steps": 2927, "total_steps": 3345, "loss": 0.0792, "lr": 9.509443408600827e-08, "epoch": 4.375186846038864, "percentage": 87.5, "elapsed_time": "0:56:42", "remaining_time": "0:08:05", "throughput": 7047.94, "total_tokens": 23977984} {"current_steps": 2928, "total_steps": 3345, "loss": 0.2382, "lr": 9.4645804980769e-08, "epoch": 4.376681614349776, "percentage": 87.53, "elapsed_time": "0:56:43", "remaining_time": "0:08:04", "throughput": 7047.95, "total_tokens": 23986176} {"current_steps": 2929, "total_steps": 3345, "loss": 0.3337, "lr": 9.419819498917112e-08, "epoch": 4.378176382660688, "percentage": 87.56, "elapsed_time": "0:56:44", "remaining_time": "0:08:03", "throughput": 7047.94, "total_tokens": 23994368} {"current_steps": 2930, "total_steps": 3345, "loss": 0.3125, "lr": 9.375160450604173e-08, "epoch": 4.3796711509716, "percentage": 87.59, "elapsed_time": "0:56:45", "remaining_time": "0:08:02", "throughput": 7047.93, "total_tokens": 24002560} {"current_steps": 2931, "total_steps": 3345, "loss": 0.1344, "lr": 9.330603392530932e-08, "epoch": 4.381165919282511, "percentage": 87.62, "elapsed_time": "0:56:46", "remaining_time": "0:08:01", "throughput": 7047.93, "total_tokens": 24010752} {"current_steps": 2932, "total_steps": 3345, "loss": 0.1901, "lr": 9.286148364000172e-08, "epoch": 4.382660687593423, "percentage": 87.65, "elapsed_time": "0:56:47", "remaining_time": "0:08:00", "throughput": 7047.94, "total_tokens": 24018944} {"current_steps": 2933, "total_steps": 3345, "loss": 0.2168, "lr": 9.24179540422479e-08, "epoch": 4.3841554559043345, "percentage": 87.68, "elapsed_time": "0:56:49", "remaining_time": "0:07:58", "throughput": 7047.93, "total_tokens": 24027136} {"current_steps": 2934, "total_steps": 3345, "loss": 0.0671, "lr": 9.197544552327589e-08, "epoch": 4.385650224215246, "percentage": 87.71, "elapsed_time": "0:56:50", "remaining_time": "0:07:57", "throughput": 7047.94, "total_tokens": 24035328} {"current_steps": 2935, "total_steps": 3345, "loss": 0.1986, "lr": 9.153395847341276e-08, "epoch": 4.387144992526158, "percentage": 87.74, "elapsed_time": "0:56:51", "remaining_time": "0:07:56", "throughput": 7047.94, "total_tokens": 24043520} {"current_steps": 2936, "total_steps": 3345, "loss": 0.2154, "lr": 9.10934932820856e-08, "epoch": 4.38863976083707, "percentage": 87.77, "elapsed_time": "0:56:52", "remaining_time": "0:07:55", "throughput": 7047.95, "total_tokens": 24051712} {"current_steps": 2937, "total_steps": 3345, "loss": 0.0444, "lr": 9.06540503378188e-08, "epoch": 4.390134529147982, "percentage": 87.8, "elapsed_time": "0:56:53", "remaining_time": "0:07:54", "throughput": 7047.95, "total_tokens": 24059904} {"current_steps": 2938, "total_steps": 3345, "loss": 0.178, "lr": 9.021563002823627e-08, "epoch": 4.391629297458894, "percentage": 87.83, "elapsed_time": "0:56:54", "remaining_time": "0:07:53", "throughput": 7047.96, "total_tokens": 24068096} {"current_steps": 2939, "total_steps": 3345, "loss": 0.217, "lr": 8.977823274005926e-08, "epoch": 4.393124065769806, "percentage": 87.86, "elapsed_time": "0:56:56", "remaining_time": "0:07:51", "throughput": 7047.96, "total_tokens": 24076288} {"current_steps": 2940, "total_steps": 3345, "loss": 0.1411, "lr": 8.934185885910635e-08, "epoch": 4.394618834080718, "percentage": 87.89, "elapsed_time": "0:56:57", "remaining_time": "0:07:50", "throughput": 7047.96, "total_tokens": 24084480} {"current_steps": 2941, "total_steps": 3345, "loss": 0.1191, "lr": 8.890650877029436e-08, "epoch": 4.39611360239163, "percentage": 87.92, "elapsed_time": "0:56:58", "remaining_time": "0:07:49", "throughput": 7047.97, "total_tokens": 24092672} {"current_steps": 2942, "total_steps": 3345, "loss": 0.151, "lr": 8.847218285763584e-08, "epoch": 4.3976083707025415, "percentage": 87.95, "elapsed_time": "0:56:59", "remaining_time": "0:07:48", "throughput": 7047.97, "total_tokens": 24100864} {"current_steps": 2943, "total_steps": 3345, "loss": 0.1834, "lr": 8.803888150424114e-08, "epoch": 4.3991031390134525, "percentage": 87.98, "elapsed_time": "0:57:00", "remaining_time": "0:07:47", "throughput": 7047.98, "total_tokens": 24109056} {"current_steps": 2944, "total_steps": 3345, "loss": 0.1648, "lr": 8.760660509231564e-08, "epoch": 4.400597907324364, "percentage": 88.01, "elapsed_time": "0:57:01", "remaining_time": "0:07:46", "throughput": 7047.99, "total_tokens": 24117248} {"current_steps": 2945, "total_steps": 3345, "loss": 0.244, "lr": 8.717535400316168e-08, "epoch": 4.402092675635276, "percentage": 88.04, "elapsed_time": "0:57:03", "remaining_time": "0:07:44", "throughput": 7048.0, "total_tokens": 24125440} {"current_steps": 2946, "total_steps": 3345, "loss": 0.0406, "lr": 8.674512861717665e-08, "epoch": 4.403587443946188, "percentage": 88.07, "elapsed_time": "0:57:04", "remaining_time": "0:07:43", "throughput": 7047.99, "total_tokens": 24133632} {"current_steps": 2947, "total_steps": 3345, "loss": 0.0896, "lr": 8.631592931385352e-08, "epoch": 4.4050822122571, "percentage": 88.1, "elapsed_time": "0:57:05", "remaining_time": "0:07:42", "throughput": 7048.0, "total_tokens": 24141824} {"current_steps": 2948, "total_steps": 3345, "loss": 0.2409, "lr": 8.588775647177957e-08, "epoch": 4.406576980568012, "percentage": 88.13, "elapsed_time": "0:57:06", "remaining_time": "0:07:41", "throughput": 7047.99, "total_tokens": 24150016} {"current_steps": 2949, "total_steps": 3345, "loss": 0.2006, "lr": 8.546061046863743e-08, "epoch": 4.408071748878924, "percentage": 88.16, "elapsed_time": "0:57:07", "remaining_time": "0:07:40", "throughput": 7047.99, "total_tokens": 24158208} {"current_steps": 2950, "total_steps": 3345, "loss": 0.2006, "lr": 8.503449168120362e-08, "epoch": 4.409566517189836, "percentage": 88.19, "elapsed_time": "0:57:08", "remaining_time": "0:07:39", "throughput": 7047.99, "total_tokens": 24166400} {"current_steps": 2951, "total_steps": 3345, "loss": 0.1651, "lr": 8.46094004853483e-08, "epoch": 4.411061285500748, "percentage": 88.22, "elapsed_time": "0:57:10", "remaining_time": "0:07:37", "throughput": 7047.97, "total_tokens": 24174592} {"current_steps": 2952, "total_steps": 3345, "loss": 0.1243, "lr": 8.41853372560357e-08, "epoch": 4.4125560538116595, "percentage": 88.25, "elapsed_time": "0:57:11", "remaining_time": "0:07:36", "throughput": 7047.98, "total_tokens": 24182784} {"current_steps": 2953, "total_steps": 3345, "loss": 0.0708, "lr": 8.376230236732285e-08, "epoch": 4.414050822122571, "percentage": 88.28, "elapsed_time": "0:57:12", "remaining_time": "0:07:35", "throughput": 7047.99, "total_tokens": 24190976} {"current_steps": 2954, "total_steps": 3345, "loss": 0.0124, "lr": 8.334029619236017e-08, "epoch": 4.415545590433483, "percentage": 88.31, "elapsed_time": "0:57:13", "remaining_time": "0:07:34", "throughput": 7047.99, "total_tokens": 24199168} {"current_steps": 2955, "total_steps": 3345, "loss": 0.3276, "lr": 8.291931910339016e-08, "epoch": 4.417040358744394, "percentage": 88.34, "elapsed_time": "0:57:14", "remaining_time": "0:07:33", "throughput": 7048.0, "total_tokens": 24207360} {"current_steps": 2956, "total_steps": 3345, "loss": 0.1616, "lr": 8.2499371471748e-08, "epoch": 4.418535127055306, "percentage": 88.37, "elapsed_time": "0:57:15", "remaining_time": "0:07:32", "throughput": 7048.0, "total_tokens": 24215552} {"current_steps": 2957, "total_steps": 3345, "loss": 0.084, "lr": 8.208045366786086e-08, "epoch": 4.420029895366218, "percentage": 88.4, "elapsed_time": "0:57:16", "remaining_time": "0:07:30", "throughput": 7048.0, "total_tokens": 24223744} {"current_steps": 2958, "total_steps": 3345, "loss": 0.2751, "lr": 8.16625660612469e-08, "epoch": 4.42152466367713, "percentage": 88.43, "elapsed_time": "0:57:18", "remaining_time": "0:07:29", "throughput": 7048.0, "total_tokens": 24231936} {"current_steps": 2959, "total_steps": 3345, "loss": 0.4533, "lr": 8.124570902051654e-08, "epoch": 4.423019431988042, "percentage": 88.46, "elapsed_time": "0:57:19", "remaining_time": "0:07:28", "throughput": 7048.01, "total_tokens": 24240128} {"current_steps": 2960, "total_steps": 3345, "loss": 0.1935, "lr": 8.08298829133701e-08, "epoch": 4.424514200298954, "percentage": 88.49, "elapsed_time": "0:57:20", "remaining_time": "0:07:27", "throughput": 7048.01, "total_tokens": 24248320} {"current_steps": 2961, "total_steps": 3345, "loss": 0.359, "lr": 8.041508810659945e-08, "epoch": 4.426008968609866, "percentage": 88.52, "elapsed_time": "0:57:21", "remaining_time": "0:07:26", "throughput": 7048.02, "total_tokens": 24256512} {"current_steps": 2962, "total_steps": 3345, "loss": 0.1949, "lr": 8.000132496608596e-08, "epoch": 4.4275037369207775, "percentage": 88.55, "elapsed_time": "0:57:22", "remaining_time": "0:07:25", "throughput": 7048.02, "total_tokens": 24264704} {"current_steps": 2963, "total_steps": 3345, "loss": 0.1792, "lr": 7.958859385680153e-08, "epoch": 4.428998505231689, "percentage": 88.58, "elapsed_time": "0:57:23", "remaining_time": "0:07:24", "throughput": 7048.01, "total_tokens": 24272896} {"current_steps": 2964, "total_steps": 3345, "loss": 0.1865, "lr": 7.917689514280777e-08, "epoch": 4.430493273542601, "percentage": 88.61, "elapsed_time": "0:57:25", "remaining_time": "0:07:22", "throughput": 7048.02, "total_tokens": 24281088} {"current_steps": 2965, "total_steps": 3345, "loss": 0.2215, "lr": 7.876622918725527e-08, "epoch": 4.431988041853513, "percentage": 88.64, "elapsed_time": "0:57:26", "remaining_time": "0:07:21", "throughput": 7048.01, "total_tokens": 24289280} {"current_steps": 2966, "total_steps": 3345, "loss": 0.1721, "lr": 7.835659635238412e-08, "epoch": 4.433482810164424, "percentage": 88.67, "elapsed_time": "0:57:27", "remaining_time": "0:07:20", "throughput": 7048.01, "total_tokens": 24297472} {"current_steps": 2967, "total_steps": 3345, "loss": 0.1385, "lr": 7.794799699952254e-08, "epoch": 4.434977578475336, "percentage": 88.7, "elapsed_time": "0:57:28", "remaining_time": "0:07:19", "throughput": 7048.0, "total_tokens": 24305664} {"current_steps": 2968, "total_steps": 3345, "loss": 0.0751, "lr": 7.754043148908763e-08, "epoch": 4.436472346786248, "percentage": 88.73, "elapsed_time": "0:57:29", "remaining_time": "0:07:18", "throughput": 7048.01, "total_tokens": 24313856} {"current_steps": 2969, "total_steps": 3345, "loss": 0.2302, "lr": 7.713390018058403e-08, "epoch": 4.43796711509716, "percentage": 88.76, "elapsed_time": "0:57:30", "remaining_time": "0:07:17", "throughput": 7048.02, "total_tokens": 24322048} {"current_steps": 2970, "total_steps": 3345, "loss": 0.2657, "lr": 7.672840343260505e-08, "epoch": 4.439461883408072, "percentage": 88.79, "elapsed_time": "0:57:32", "remaining_time": "0:07:15", "throughput": 7048.02, "total_tokens": 24330240} {"current_steps": 2971, "total_steps": 3345, "loss": 0.2556, "lr": 7.63239416028301e-08, "epoch": 4.440956651718984, "percentage": 88.82, "elapsed_time": "0:57:33", "remaining_time": "0:07:14", "throughput": 7048.02, "total_tokens": 24338432} {"current_steps": 2972, "total_steps": 3345, "loss": 0.2873, "lr": 7.592051504802675e-08, "epoch": 4.4424514200298955, "percentage": 88.85, "elapsed_time": "0:57:34", "remaining_time": "0:07:13", "throughput": 7048.01, "total_tokens": 24346624} {"current_steps": 2973, "total_steps": 3345, "loss": 0.0506, "lr": 7.551812412404949e-08, "epoch": 4.443946188340807, "percentage": 88.88, "elapsed_time": "0:57:35", "remaining_time": "0:07:12", "throughput": 7048.01, "total_tokens": 24354816} {"current_steps": 2974, "total_steps": 3345, "loss": 0.1743, "lr": 7.51167691858383e-08, "epoch": 4.445440956651719, "percentage": 88.91, "elapsed_time": "0:57:36", "remaining_time": "0:07:11", "throughput": 7048.01, "total_tokens": 24363008} {"current_steps": 2975, "total_steps": 3345, "loss": 0.3632, "lr": 7.471645058742052e-08, "epoch": 4.446935724962631, "percentage": 88.94, "elapsed_time": "0:57:37", "remaining_time": "0:07:10", "throughput": 7047.98, "total_tokens": 24371200} {"current_steps": 2976, "total_steps": 3345, "loss": 0.2401, "lr": 7.431716868190802e-08, "epoch": 4.448430493273543, "percentage": 88.97, "elapsed_time": "0:57:39", "remaining_time": "0:07:08", "throughput": 7047.98, "total_tokens": 24379392} {"current_steps": 2977, "total_steps": 3345, "loss": 0.2628, "lr": 7.391892382149976e-08, "epoch": 4.449925261584454, "percentage": 89.0, "elapsed_time": "0:57:40", "remaining_time": "0:07:07", "throughput": 7047.97, "total_tokens": 24387584} {"current_steps": 2978, "total_steps": 3345, "loss": 0.3269, "lr": 7.352171635747848e-08, "epoch": 4.451420029895366, "percentage": 89.03, "elapsed_time": "0:57:41", "remaining_time": "0:07:06", "throughput": 7047.98, "total_tokens": 24395776} {"current_steps": 2979, "total_steps": 3345, "loss": 0.167, "lr": 7.312554664021296e-08, "epoch": 4.452914798206278, "percentage": 89.06, "elapsed_time": "0:57:42", "remaining_time": "0:07:05", "throughput": 7047.98, "total_tokens": 24403968} {"current_steps": 2980, "total_steps": 3345, "loss": 0.0536, "lr": 7.273041501915601e-08, "epoch": 4.45440956651719, "percentage": 89.09, "elapsed_time": "0:57:43", "remaining_time": "0:07:04", "throughput": 7047.98, "total_tokens": 24412160} {"current_steps": 2981, "total_steps": 3345, "loss": 0.1499, "lr": 7.233632184284494e-08, "epoch": 4.4559043348281016, "percentage": 89.12, "elapsed_time": "0:57:44", "remaining_time": "0:07:03", "throughput": 7047.98, "total_tokens": 24420352} {"current_steps": 2982, "total_steps": 3345, "loss": 0.2315, "lr": 7.194326745890129e-08, "epoch": 4.457399103139013, "percentage": 89.15, "elapsed_time": "0:57:46", "remaining_time": "0:07:01", "throughput": 7047.97, "total_tokens": 24428544} {"current_steps": 2983, "total_steps": 3345, "loss": 0.1675, "lr": 7.155125221402964e-08, "epoch": 4.458893871449925, "percentage": 89.18, "elapsed_time": "0:57:47", "remaining_time": "0:07:00", "throughput": 7047.96, "total_tokens": 24436736} {"current_steps": 2984, "total_steps": 3345, "loss": 0.218, "lr": 7.116027645401882e-08, "epoch": 4.460388639760837, "percentage": 89.21, "elapsed_time": "0:57:48", "remaining_time": "0:06:59", "throughput": 7047.96, "total_tokens": 24444928} {"current_steps": 2985, "total_steps": 3345, "loss": 0.1774, "lr": 7.077034052373991e-08, "epoch": 4.461883408071749, "percentage": 89.24, "elapsed_time": "0:57:49", "remaining_time": "0:06:58", "throughput": 7047.97, "total_tokens": 24453120} {"current_steps": 2986, "total_steps": 3345, "loss": 0.2834, "lr": 7.038144476714761e-08, "epoch": 4.463378176382661, "percentage": 89.27, "elapsed_time": "0:57:50", "remaining_time": "0:06:57", "throughput": 7047.98, "total_tokens": 24461312} {"current_steps": 2987, "total_steps": 3345, "loss": 0.1382, "lr": 6.999358952727838e-08, "epoch": 4.464872944693573, "percentage": 89.3, "elapsed_time": "0:57:51", "remaining_time": "0:06:56", "throughput": 7047.98, "total_tokens": 24469504} {"current_steps": 2988, "total_steps": 3345, "loss": 0.1314, "lr": 6.96067751462512e-08, "epoch": 4.466367713004484, "percentage": 89.33, "elapsed_time": "0:57:53", "remaining_time": "0:06:54", "throughput": 7047.98, "total_tokens": 24477696} {"current_steps": 2989, "total_steps": 3345, "loss": 0.1809, "lr": 6.922100196526713e-08, "epoch": 4.467862481315396, "percentage": 89.36, "elapsed_time": "0:57:54", "remaining_time": "0:06:53", "throughput": 7047.99, "total_tokens": 24485888} {"current_steps": 2990, "total_steps": 3345, "loss": 0.1799, "lr": 6.88362703246083e-08, "epoch": 4.469357249626308, "percentage": 89.39, "elapsed_time": "0:57:55", "remaining_time": "0:06:52", "throughput": 7047.97, "total_tokens": 24494080} {"current_steps": 2991, "total_steps": 3345, "loss": 0.2621, "lr": 6.845258056363879e-08, "epoch": 4.4708520179372195, "percentage": 89.42, "elapsed_time": "0:57:56", "remaining_time": "0:06:51", "throughput": 7047.97, "total_tokens": 24502272} {"current_steps": 2992, "total_steps": 3345, "loss": 0.3568, "lr": 6.806993302080275e-08, "epoch": 4.472346786248131, "percentage": 89.45, "elapsed_time": "0:57:57", "remaining_time": "0:06:50", "throughput": 7047.97, "total_tokens": 24510464} {"current_steps": 2993, "total_steps": 3345, "loss": 0.1458, "lr": 6.768832803362587e-08, "epoch": 4.473841554559043, "percentage": 89.48, "elapsed_time": "0:57:58", "remaining_time": "0:06:49", "throughput": 7047.96, "total_tokens": 24518656} {"current_steps": 2994, "total_steps": 3345, "loss": 0.1048, "lr": 6.730776593871377e-08, "epoch": 4.475336322869955, "percentage": 89.51, "elapsed_time": "0:57:59", "remaining_time": "0:06:47", "throughput": 7047.97, "total_tokens": 24526848} {"current_steps": 2995, "total_steps": 3345, "loss": 0.0935, "lr": 6.692824707175221e-08, "epoch": 4.476831091180867, "percentage": 89.54, "elapsed_time": "0:58:01", "remaining_time": "0:06:46", "throughput": 7047.97, "total_tokens": 24535040} {"current_steps": 2996, "total_steps": 3345, "loss": 0.156, "lr": 6.654977176750718e-08, "epoch": 4.478325859491779, "percentage": 89.57, "elapsed_time": "0:58:02", "remaining_time": "0:06:45", "throughput": 7047.97, "total_tokens": 24543232} {"current_steps": 2997, "total_steps": 3345, "loss": 0.3046, "lr": 6.617234035982315e-08, "epoch": 4.479820627802691, "percentage": 89.6, "elapsed_time": "0:58:03", "remaining_time": "0:06:44", "throughput": 7047.98, "total_tokens": 24551424} {"current_steps": 2998, "total_steps": 3345, "loss": 0.1644, "lr": 6.579595318162504e-08, "epoch": 4.481315396113603, "percentage": 89.63, "elapsed_time": "0:58:04", "remaining_time": "0:06:43", "throughput": 7047.98, "total_tokens": 24559616} {"current_steps": 2999, "total_steps": 3345, "loss": 0.2814, "lr": 6.542061056491578e-08, "epoch": 4.482810164424514, "percentage": 89.66, "elapsed_time": "0:58:05", "remaining_time": "0:06:42", "throughput": 7047.97, "total_tokens": 24567808} {"current_steps": 3000, "total_steps": 3345, "loss": 0.1838, "lr": 6.504631284077731e-08, "epoch": 4.484304932735426, "percentage": 89.69, "elapsed_time": "0:58:06", "remaining_time": "0:06:41", "throughput": 7047.98, "total_tokens": 24576000} {"current_steps": 3001, "total_steps": 3345, "loss": 0.0681, "lr": 6.467306033936957e-08, "epoch": 4.4857997010463375, "percentage": 89.72, "elapsed_time": "0:58:08", "remaining_time": "0:06:39", "throughput": 7047.98, "total_tokens": 24584192} {"current_steps": 3002, "total_steps": 3345, "loss": 0.15, "lr": 6.4300853389931e-08, "epoch": 4.487294469357249, "percentage": 89.75, "elapsed_time": "0:58:09", "remaining_time": "0:06:38", "throughput": 7047.98, "total_tokens": 24592384} {"current_steps": 3003, "total_steps": 3345, "loss": 0.1838, "lr": 6.39296923207773e-08, "epoch": 4.488789237668161, "percentage": 89.78, "elapsed_time": "0:58:10", "remaining_time": "0:06:37", "throughput": 7047.99, "total_tokens": 24600576} {"current_steps": 3004, "total_steps": 3345, "loss": 0.0288, "lr": 6.355957745930189e-08, "epoch": 4.490284005979073, "percentage": 89.81, "elapsed_time": "0:58:11", "remaining_time": "0:06:36", "throughput": 7048.0, "total_tokens": 24608768} {"current_steps": 3005, "total_steps": 3345, "loss": 0.3491, "lr": 6.319050913197552e-08, "epoch": 4.491778774289985, "percentage": 89.84, "elapsed_time": "0:58:12", "remaining_time": "0:06:35", "throughput": 7048.0, "total_tokens": 24616960} {"current_steps": 3006, "total_steps": 3345, "loss": 0.3712, "lr": 6.282248766434532e-08, "epoch": 4.493273542600897, "percentage": 89.87, "elapsed_time": "0:58:13", "remaining_time": "0:06:34", "throughput": 7048.01, "total_tokens": 24625152} {"current_steps": 3007, "total_steps": 3345, "loss": 0.1288, "lr": 6.245551338103562e-08, "epoch": 4.494768310911809, "percentage": 89.9, "elapsed_time": "0:58:15", "remaining_time": "0:06:32", "throughput": 7048.01, "total_tokens": 24633344} {"current_steps": 3008, "total_steps": 3345, "loss": 0.2171, "lr": 6.208958660574624e-08, "epoch": 4.496263079222721, "percentage": 89.93, "elapsed_time": "0:58:16", "remaining_time": "0:06:31", "throughput": 7048.02, "total_tokens": 24641536} {"current_steps": 3009, "total_steps": 3345, "loss": 0.2625, "lr": 6.172470766125399e-08, "epoch": 4.497757847533633, "percentage": 89.96, "elapsed_time": "0:58:17", "remaining_time": "0:06:30", "throughput": 7048.0, "total_tokens": 24649728} {"current_steps": 3010, "total_steps": 3345, "loss": 0.2216, "lr": 6.136087686941045e-08, "epoch": 4.4992526158445445, "percentage": 89.99, "elapsed_time": "0:58:18", "remaining_time": "0:06:29", "throughput": 7048.0, "total_tokens": 24657920} {"current_steps": 3011, "total_steps": 3345, "loss": 0.0539, "lr": 6.099809455114347e-08, "epoch": 4.500747384155456, "percentage": 90.01, "elapsed_time": "0:58:19", "remaining_time": "0:06:28", "throughput": 7048.01, "total_tokens": 24666112} {"current_steps": 3012, "total_steps": 3345, "loss": 0.1975, "lr": 6.06363610264557e-08, "epoch": 4.502242152466367, "percentage": 90.04, "elapsed_time": "0:58:20", "remaining_time": "0:06:27", "throughput": 7048.01, "total_tokens": 24674304} {"current_steps": 3013, "total_steps": 3345, "loss": 0.1469, "lr": 6.02756766144244e-08, "epoch": 4.503736920777279, "percentage": 90.07, "elapsed_time": "0:58:22", "remaining_time": "0:06:25", "throughput": 7048.01, "total_tokens": 24682496} {"current_steps": 3014, "total_steps": 3345, "loss": 0.3248, "lr": 5.991604163320175e-08, "epoch": 4.505231689088191, "percentage": 90.1, "elapsed_time": "0:58:23", "remaining_time": "0:06:24", "throughput": 7048.02, "total_tokens": 24690688} {"current_steps": 3015, "total_steps": 3345, "loss": 0.2994, "lr": 5.9557456400014534e-08, "epoch": 4.506726457399103, "percentage": 90.13, "elapsed_time": "0:58:24", "remaining_time": "0:06:23", "throughput": 7048.03, "total_tokens": 24698880} {"current_steps": 3016, "total_steps": 3345, "loss": 0.2562, "lr": 5.9199921231163085e-08, "epoch": 4.508221225710015, "percentage": 90.16, "elapsed_time": "0:58:25", "remaining_time": "0:06:22", "throughput": 7048.03, "total_tokens": 24707072} {"current_steps": 3017, "total_steps": 3345, "loss": 0.3471, "lr": 5.884343644202137e-08, "epoch": 4.509715994020927, "percentage": 90.19, "elapsed_time": "0:58:26", "remaining_time": "0:06:21", "throughput": 7048.03, "total_tokens": 24715264} {"current_steps": 3018, "total_steps": 3345, "loss": 0.0774, "lr": 5.848800234703758e-08, "epoch": 4.511210762331839, "percentage": 90.22, "elapsed_time": "0:58:27", "remaining_time": "0:06:20", "throughput": 7048.03, "total_tokens": 24723456} {"current_steps": 3019, "total_steps": 3345, "loss": 0.105, "lr": 5.813361925973232e-08, "epoch": 4.512705530642751, "percentage": 90.25, "elapsed_time": "0:58:29", "remaining_time": "0:06:18", "throughput": 7048.04, "total_tokens": 24731648} {"current_steps": 3020, "total_steps": 3345, "loss": 0.189, "lr": 5.7780287492699565e-08, "epoch": 4.5142002989536625, "percentage": 90.28, "elapsed_time": "0:58:30", "remaining_time": "0:06:17", "throughput": 7048.06, "total_tokens": 24739840} {"current_steps": 3021, "total_steps": 3345, "loss": 0.3373, "lr": 5.742800735760598e-08, "epoch": 4.515695067264574, "percentage": 90.31, "elapsed_time": "0:58:31", "remaining_time": "0:06:16", "throughput": 7048.06, "total_tokens": 24748032} {"current_steps": 3022, "total_steps": 3345, "loss": 0.1596, "lr": 5.707677916519008e-08, "epoch": 4.517189835575486, "percentage": 90.34, "elapsed_time": "0:58:32", "remaining_time": "0:06:15", "throughput": 7048.06, "total_tokens": 24756224} {"current_steps": 3023, "total_steps": 3345, "loss": 0.0764, "lr": 5.6726603225263494e-08, "epoch": 4.518684603886397, "percentage": 90.37, "elapsed_time": "0:58:33", "remaining_time": "0:06:14", "throughput": 7048.07, "total_tokens": 24764416} {"current_steps": 3024, "total_steps": 3345, "loss": 0.29, "lr": 5.63774798467083e-08, "epoch": 4.520179372197309, "percentage": 90.4, "elapsed_time": "0:58:34", "remaining_time": "0:06:13", "throughput": 7048.07, "total_tokens": 24772608} {"current_steps": 3025, "total_steps": 3345, "loss": 0.1515, "lr": 5.602940933747955e-08, "epoch": 4.521674140508221, "percentage": 90.43, "elapsed_time": "0:58:35", "remaining_time": "0:06:11", "throughput": 7048.08, "total_tokens": 24780800} {"current_steps": 3026, "total_steps": 3345, "loss": 0.1711, "lr": 5.568239200460249e-08, "epoch": 4.523168908819133, "percentage": 90.46, "elapsed_time": "0:58:37", "remaining_time": "0:06:10", "throughput": 7048.09, "total_tokens": 24788992} {"current_steps": 3027, "total_steps": 3345, "loss": 0.2181, "lr": 5.5336428154173924e-08, "epoch": 4.524663677130045, "percentage": 90.49, "elapsed_time": "0:58:38", "remaining_time": "0:06:09", "throughput": 7048.1, "total_tokens": 24797184} {"current_steps": 3028, "total_steps": 3345, "loss": 0.1881, "lr": 5.499151809136155e-08, "epoch": 4.526158445440957, "percentage": 90.52, "elapsed_time": "0:58:39", "remaining_time": "0:06:08", "throughput": 7048.1, "total_tokens": 24805376} {"current_steps": 3029, "total_steps": 3345, "loss": 0.2739, "lr": 5.464766212040285e-08, "epoch": 4.527653213751869, "percentage": 90.55, "elapsed_time": "0:58:40", "remaining_time": "0:06:07", "throughput": 7048.1, "total_tokens": 24813568} {"current_steps": 3030, "total_steps": 3345, "loss": 0.0949, "lr": 5.430486054460629e-08, "epoch": 4.5291479820627805, "percentage": 90.58, "elapsed_time": "0:58:41", "remaining_time": "0:06:06", "throughput": 7048.11, "total_tokens": 24821760} {"current_steps": 3031, "total_steps": 3345, "loss": 0.1931, "lr": 5.39631136663496e-08, "epoch": 4.530642750373692, "percentage": 90.61, "elapsed_time": "0:58:42", "remaining_time": "0:06:04", "throughput": 7048.11, "total_tokens": 24829952} {"current_steps": 3032, "total_steps": 3345, "loss": 0.1788, "lr": 5.3622421787080935e-08, "epoch": 4.532137518684604, "percentage": 90.64, "elapsed_time": "0:58:44", "remaining_time": "0:06:03", "throughput": 7048.12, "total_tokens": 24838144} {"current_steps": 3033, "total_steps": 3345, "loss": 0.1449, "lr": 5.3282785207317e-08, "epoch": 4.533632286995516, "percentage": 90.67, "elapsed_time": "0:58:45", "remaining_time": "0:06:02", "throughput": 7048.13, "total_tokens": 24846336} {"current_steps": 3034, "total_steps": 3345, "loss": 0.2629, "lr": 5.2944204226644536e-08, "epoch": 4.535127055306427, "percentage": 90.7, "elapsed_time": "0:58:46", "remaining_time": "0:06:01", "throughput": 7048.13, "total_tokens": 24854528} {"current_steps": 3035, "total_steps": 3345, "loss": 0.1937, "lr": 5.260667914371839e-08, "epoch": 4.536621823617339, "percentage": 90.73, "elapsed_time": "0:58:47", "remaining_time": "0:06:00", "throughput": 7048.13, "total_tokens": 24862720} {"current_steps": 3036, "total_steps": 3345, "loss": 0.1391, "lr": 5.22702102562625e-08, "epoch": 4.538116591928251, "percentage": 90.76, "elapsed_time": "0:58:48", "remaining_time": "0:05:59", "throughput": 7048.14, "total_tokens": 24870912} {"current_steps": 3037, "total_steps": 3345, "loss": 0.0774, "lr": 5.193479786106875e-08, "epoch": 4.539611360239163, "percentage": 90.79, "elapsed_time": "0:58:49", "remaining_time": "0:05:57", "throughput": 7048.14, "total_tokens": 24879104} {"current_steps": 3038, "total_steps": 3345, "loss": 0.2573, "lr": 5.1600442253997435e-08, "epoch": 4.541106128550075, "percentage": 90.82, "elapsed_time": "0:58:51", "remaining_time": "0:05:56", "throughput": 7048.14, "total_tokens": 24887296} {"current_steps": 3039, "total_steps": 3345, "loss": 0.3049, "lr": 5.126714372997707e-08, "epoch": 4.542600896860987, "percentage": 90.85, "elapsed_time": "0:58:52", "remaining_time": "0:05:55", "throughput": 7048.13, "total_tokens": 24895488} {"current_steps": 3040, "total_steps": 3345, "loss": 0.1924, "lr": 5.093490258300263e-08, "epoch": 4.5440956651718984, "percentage": 90.88, "elapsed_time": "0:58:53", "remaining_time": "0:05:54", "throughput": 7048.13, "total_tokens": 24903680} {"current_steps": 3041, "total_steps": 3345, "loss": 0.3005, "lr": 5.060371910613746e-08, "epoch": 4.54559043348281, "percentage": 90.91, "elapsed_time": "0:58:54", "remaining_time": "0:05:53", "throughput": 7048.12, "total_tokens": 24911872} {"current_steps": 3042, "total_steps": 3345, "loss": 0.1139, "lr": 5.027359359151121e-08, "epoch": 4.547085201793722, "percentage": 90.94, "elapsed_time": "0:58:55", "remaining_time": "0:05:52", "throughput": 7048.13, "total_tokens": 24920064} {"current_steps": 3043, "total_steps": 3345, "loss": 0.1677, "lr": 4.9944526330320955e-08, "epoch": 4.548579970104634, "percentage": 90.97, "elapsed_time": "0:58:56", "remaining_time": "0:05:51", "throughput": 7048.13, "total_tokens": 24928256} {"current_steps": 3044, "total_steps": 3345, "loss": 0.1664, "lr": 4.961651761282979e-08, "epoch": 4.550074738415546, "percentage": 91.0, "elapsed_time": "0:58:58", "remaining_time": "0:05:49", "throughput": 7048.13, "total_tokens": 24936448} {"current_steps": 3045, "total_steps": 3345, "loss": 0.1514, "lr": 4.9289567728367513e-08, "epoch": 4.551569506726457, "percentage": 91.03, "elapsed_time": "0:58:59", "remaining_time": "0:05:48", "throughput": 7048.14, "total_tokens": 24944640} {"current_steps": 3046, "total_steps": 3345, "loss": 0.4601, "lr": 4.896367696532969e-08, "epoch": 4.553064275037369, "percentage": 91.06, "elapsed_time": "0:59:00", "remaining_time": "0:05:47", "throughput": 7048.14, "total_tokens": 24952832} {"current_steps": 3047, "total_steps": 3345, "loss": 0.1597, "lr": 4.8638845611177487e-08, "epoch": 4.554559043348281, "percentage": 91.09, "elapsed_time": "0:59:01", "remaining_time": "0:05:46", "throughput": 7048.14, "total_tokens": 24961024} {"current_steps": 3048, "total_steps": 3345, "loss": 0.2179, "lr": 4.831507395243809e-08, "epoch": 4.556053811659193, "percentage": 91.12, "elapsed_time": "0:59:02", "remaining_time": "0:05:45", "throughput": 7048.15, "total_tokens": 24969216} {"current_steps": 3049, "total_steps": 3345, "loss": 0.0684, "lr": 4.799236227470347e-08, "epoch": 4.5575485799701045, "percentage": 91.15, "elapsed_time": "0:59:03", "remaining_time": "0:05:44", "throughput": 7048.17, "total_tokens": 24977408} {"current_steps": 3050, "total_steps": 3345, "loss": 0.2059, "lr": 4.7670710862631195e-08, "epoch": 4.559043348281016, "percentage": 91.18, "elapsed_time": "0:59:04", "remaining_time": "0:05:42", "throughput": 7048.17, "total_tokens": 24985600} {"current_steps": 3051, "total_steps": 3345, "loss": 0.1354, "lr": 4.7350119999942656e-08, "epoch": 4.560538116591928, "percentage": 91.21, "elapsed_time": "0:59:06", "remaining_time": "0:05:41", "throughput": 7048.17, "total_tokens": 24993792} {"current_steps": 3052, "total_steps": 3345, "loss": 0.1619, "lr": 4.703058996942469e-08, "epoch": 4.56203288490284, "percentage": 91.24, "elapsed_time": "0:59:07", "remaining_time": "0:05:40", "throughput": 7048.17, "total_tokens": 25001984} {"current_steps": 3053, "total_steps": 3345, "loss": 0.1214, "lr": 4.671212105292783e-08, "epoch": 4.563527653213752, "percentage": 91.27, "elapsed_time": "0:59:08", "remaining_time": "0:05:39", "throughput": 7048.17, "total_tokens": 25010176} {"current_steps": 3054, "total_steps": 3345, "loss": 0.207, "lr": 4.639471353136693e-08, "epoch": 4.565022421524664, "percentage": 91.3, "elapsed_time": "0:59:09", "remaining_time": "0:05:38", "throughput": 7048.17, "total_tokens": 25018368} {"current_steps": 3055, "total_steps": 3345, "loss": 0.1773, "lr": 4.607836768472054e-08, "epoch": 4.566517189835576, "percentage": 91.33, "elapsed_time": "0:59:10", "remaining_time": "0:05:37", "throughput": 7048.17, "total_tokens": 25026560} {"current_steps": 3056, "total_steps": 3345, "loss": 0.1323, "lr": 4.5763083792030453e-08, "epoch": 4.568011958146487, "percentage": 91.36, "elapsed_time": "0:59:11", "remaining_time": "0:05:35", "throughput": 7048.17, "total_tokens": 25034752} {"current_steps": 3057, "total_steps": 3345, "loss": 0.0912, "lr": 4.544886213140212e-08, "epoch": 4.569506726457399, "percentage": 91.39, "elapsed_time": "0:59:13", "remaining_time": "0:05:34", "throughput": 7048.18, "total_tokens": 25042944} {"current_steps": 3058, "total_steps": 3345, "loss": 0.0655, "lr": 4.513570298000383e-08, "epoch": 4.571001494768311, "percentage": 91.42, "elapsed_time": "0:59:14", "remaining_time": "0:05:33", "throughput": 7048.18, "total_tokens": 25051136} {"current_steps": 3059, "total_steps": 3345, "loss": 0.2687, "lr": 4.4823606614066843e-08, "epoch": 4.5724962630792225, "percentage": 91.45, "elapsed_time": "0:59:15", "remaining_time": "0:05:32", "throughput": 7048.19, "total_tokens": 25059328} {"current_steps": 3060, "total_steps": 3345, "loss": 0.3747, "lr": 4.4512573308884424e-08, "epoch": 4.573991031390134, "percentage": 91.48, "elapsed_time": "0:59:16", "remaining_time": "0:05:31", "throughput": 7048.19, "total_tokens": 25067520} {"current_steps": 3061, "total_steps": 3345, "loss": 0.0714, "lr": 4.420260333881279e-08, "epoch": 4.575485799701046, "percentage": 91.51, "elapsed_time": "0:59:17", "remaining_time": "0:05:30", "throughput": 7048.2, "total_tokens": 25075712} {"current_steps": 3062, "total_steps": 3345, "loss": 0.3205, "lr": 4.389369697727006e-08, "epoch": 4.576980568011958, "percentage": 91.54, "elapsed_time": "0:59:18", "remaining_time": "0:05:28", "throughput": 7048.2, "total_tokens": 25083904} {"current_steps": 3063, "total_steps": 3345, "loss": 0.2514, "lr": 4.3585854496735746e-08, "epoch": 4.57847533632287, "percentage": 91.57, "elapsed_time": "0:59:20", "remaining_time": "0:05:27", "throughput": 7048.2, "total_tokens": 25092096} {"current_steps": 3064, "total_steps": 3345, "loss": 0.0298, "lr": 4.327907616875141e-08, "epoch": 4.579970104633782, "percentage": 91.6, "elapsed_time": "0:59:21", "remaining_time": "0:05:26", "throughput": 7048.2, "total_tokens": 25100288} {"current_steps": 3065, "total_steps": 3345, "loss": 0.035, "lr": 4.297336226391946e-08, "epoch": 4.581464872944694, "percentage": 91.63, "elapsed_time": "0:59:22", "remaining_time": "0:05:25", "throughput": 7048.2, "total_tokens": 25108480} {"current_steps": 3066, "total_steps": 3345, "loss": 0.3247, "lr": 4.266871305190406e-08, "epoch": 4.582959641255606, "percentage": 91.66, "elapsed_time": "0:59:23", "remaining_time": "0:05:24", "throughput": 7048.21, "total_tokens": 25116672} {"current_steps": 3067, "total_steps": 3345, "loss": 0.1772, "lr": 4.236512880142984e-08, "epoch": 4.584454409566517, "percentage": 91.69, "elapsed_time": "0:59:24", "remaining_time": "0:05:23", "throughput": 7048.24, "total_tokens": 25124864} {"current_steps": 3068, "total_steps": 3345, "loss": 0.1187, "lr": 4.2062609780282035e-08, "epoch": 4.585949177877429, "percentage": 91.72, "elapsed_time": "0:59:25", "remaining_time": "0:05:21", "throughput": 7048.23, "total_tokens": 25133056} {"current_steps": 3069, "total_steps": 3345, "loss": 0.2052, "lr": 4.1761156255306076e-08, "epoch": 4.5874439461883405, "percentage": 91.75, "elapsed_time": "0:59:27", "remaining_time": "0:05:20", "throughput": 7048.24, "total_tokens": 25141248} {"current_steps": 3070, "total_steps": 3345, "loss": 0.1289, "lr": 4.1460768492408153e-08, "epoch": 4.588938714499252, "percentage": 91.78, "elapsed_time": "0:59:28", "remaining_time": "0:05:19", "throughput": 7048.23, "total_tokens": 25149440} {"current_steps": 3071, "total_steps": 3345, "loss": 0.0103, "lr": 4.116144675655381e-08, "epoch": 4.590433482810164, "percentage": 91.81, "elapsed_time": "0:59:29", "remaining_time": "0:05:18", "throughput": 7048.24, "total_tokens": 25157632} {"current_steps": 3072, "total_steps": 3345, "loss": 0.2171, "lr": 4.086319131176839e-08, "epoch": 4.591928251121076, "percentage": 91.84, "elapsed_time": "0:59:30", "remaining_time": "0:05:17", "throughput": 7048.24, "total_tokens": 25165824} {"current_steps": 3073, "total_steps": 3345, "loss": 0.2244, "lr": 4.056600242113684e-08, "epoch": 4.593423019431988, "percentage": 91.87, "elapsed_time": "0:59:31", "remaining_time": "0:05:16", "throughput": 7048.27, "total_tokens": 25174016} {"current_steps": 3074, "total_steps": 3345, "loss": 0.097, "lr": 4.026988034680324e-08, "epoch": 4.5949177877429, "percentage": 91.9, "elapsed_time": "0:59:32", "remaining_time": "0:05:14", "throughput": 7048.27, "total_tokens": 25182208} {"current_steps": 3075, "total_steps": 3345, "loss": 0.1888, "lr": 3.997482534997071e-08, "epoch": 4.596412556053812, "percentage": 91.93, "elapsed_time": "0:59:33", "remaining_time": "0:05:13", "throughput": 7048.28, "total_tokens": 25190400} {"current_steps": 3076, "total_steps": 3345, "loss": 0.2245, "lr": 3.968083769090081e-08, "epoch": 4.597907324364724, "percentage": 91.96, "elapsed_time": "0:59:35", "remaining_time": "0:05:12", "throughput": 7048.29, "total_tokens": 25198592} {"current_steps": 3077, "total_steps": 3345, "loss": 0.3117, "lr": 3.9387917628914e-08, "epoch": 4.599402092675636, "percentage": 91.99, "elapsed_time": "0:59:36", "remaining_time": "0:05:11", "throughput": 7048.29, "total_tokens": 25206784} {"current_steps": 3078, "total_steps": 3345, "loss": 0.1436, "lr": 3.909606542238917e-08, "epoch": 4.600896860986547, "percentage": 92.02, "elapsed_time": "0:59:37", "remaining_time": "0:05:10", "throughput": 7048.29, "total_tokens": 25214976} {"current_steps": 3079, "total_steps": 3345, "loss": 0.1677, "lr": 3.88052813287626e-08, "epoch": 4.602391629297459, "percentage": 92.05, "elapsed_time": "0:59:38", "remaining_time": "0:05:09", "throughput": 7048.3, "total_tokens": 25223168} {"current_steps": 3080, "total_steps": 3345, "loss": 0.0619, "lr": 3.8515565604529124e-08, "epoch": 4.60388639760837, "percentage": 92.08, "elapsed_time": "0:59:39", "remaining_time": "0:05:08", "throughput": 7048.31, "total_tokens": 25231360} {"current_steps": 3081, "total_steps": 3345, "loss": 0.3132, "lr": 3.822691850524071e-08, "epoch": 4.605381165919282, "percentage": 92.11, "elapsed_time": "0:59:40", "remaining_time": "0:05:06", "throughput": 7048.32, "total_tokens": 25239552} {"current_steps": 3082, "total_steps": 3345, "loss": 0.2323, "lr": 3.793934028550689e-08, "epoch": 4.606875934230194, "percentage": 92.14, "elapsed_time": "0:59:42", "remaining_time": "0:05:05", "throughput": 7048.32, "total_tokens": 25247744} {"current_steps": 3083, "total_steps": 3345, "loss": 0.3786, "lr": 3.765283119899446e-08, "epoch": 4.608370702541106, "percentage": 92.17, "elapsed_time": "0:59:43", "remaining_time": "0:05:04", "throughput": 7048.33, "total_tokens": 25255936} {"current_steps": 3084, "total_steps": 3345, "loss": 0.2305, "lr": 3.736739149842711e-08, "epoch": 4.609865470852018, "percentage": 92.2, "elapsed_time": "0:59:44", "remaining_time": "0:05:03", "throughput": 7048.33, "total_tokens": 25264128} {"current_steps": 3085, "total_steps": 3345, "loss": 0.0585, "lr": 3.708302143558509e-08, "epoch": 4.61136023916293, "percentage": 92.23, "elapsed_time": "0:59:45", "remaining_time": "0:05:02", "throughput": 7048.34, "total_tokens": 25272320} {"current_steps": 3086, "total_steps": 3345, "loss": 0.2735, "lr": 3.679972126130526e-08, "epoch": 4.612855007473842, "percentage": 92.26, "elapsed_time": "0:59:46", "remaining_time": "0:05:01", "throughput": 7048.34, "total_tokens": 25280512} {"current_steps": 3087, "total_steps": 3345, "loss": 0.2148, "lr": 3.651749122548093e-08, "epoch": 4.614349775784754, "percentage": 92.29, "elapsed_time": "0:59:47", "remaining_time": "0:04:59", "throughput": 7048.35, "total_tokens": 25288704} {"current_steps": 3088, "total_steps": 3345, "loss": 0.1016, "lr": 3.623633157706086e-08, "epoch": 4.6158445440956655, "percentage": 92.32, "elapsed_time": "0:59:49", "remaining_time": "0:04:58", "throughput": 7048.36, "total_tokens": 25296896} {"current_steps": 3089, "total_steps": 3345, "loss": 0.1864, "lr": 3.595624256405056e-08, "epoch": 4.617339312406577, "percentage": 92.35, "elapsed_time": "0:59:50", "remaining_time": "0:04:57", "throughput": 7048.34, "total_tokens": 25305088} {"current_steps": 3090, "total_steps": 3345, "loss": 0.3552, "lr": 3.567722443351032e-08, "epoch": 4.618834080717489, "percentage": 92.38, "elapsed_time": "0:59:51", "remaining_time": "0:04:56", "throughput": 7048.35, "total_tokens": 25313280} {"current_steps": 3091, "total_steps": 3345, "loss": 0.1026, "lr": 3.539927743155633e-08, "epoch": 4.6203288490284, "percentage": 92.41, "elapsed_time": "0:59:52", "remaining_time": "0:04:55", "throughput": 7048.35, "total_tokens": 25321472} {"current_steps": 3092, "total_steps": 3345, "loss": 0.1511, "lr": 3.5122401803359684e-08, "epoch": 4.621823617339312, "percentage": 92.44, "elapsed_time": "0:59:53", "remaining_time": "0:04:54", "throughput": 7048.35, "total_tokens": 25329664} {"current_steps": 3093, "total_steps": 3345, "loss": 0.2293, "lr": 3.484659779314656e-08, "epoch": 4.623318385650224, "percentage": 92.47, "elapsed_time": "0:59:54", "remaining_time": "0:04:52", "throughput": 7048.36, "total_tokens": 25337856} {"current_steps": 3094, "total_steps": 3345, "loss": 0.367, "lr": 3.457186564419804e-08, "epoch": 4.624813153961136, "percentage": 92.5, "elapsed_time": "0:59:56", "remaining_time": "0:04:51", "throughput": 7048.36, "total_tokens": 25346048} {"current_steps": 3095, "total_steps": 3345, "loss": 0.1158, "lr": 3.4298205598849306e-08, "epoch": 4.626307922272048, "percentage": 92.53, "elapsed_time": "0:59:57", "remaining_time": "0:04:50", "throughput": 7048.37, "total_tokens": 25354240} {"current_steps": 3096, "total_steps": 3345, "loss": 0.2916, "lr": 3.402561789849046e-08, "epoch": 4.62780269058296, "percentage": 92.56, "elapsed_time": "0:59:58", "remaining_time": "0:04:49", "throughput": 7048.37, "total_tokens": 25362432} {"current_steps": 3097, "total_steps": 3345, "loss": 0.3652, "lr": 3.3754102783565e-08, "epoch": 4.629297458893872, "percentage": 92.59, "elapsed_time": "0:59:59", "remaining_time": "0:04:48", "throughput": 7048.37, "total_tokens": 25370624} {"current_steps": 3098, "total_steps": 3345, "loss": 0.1509, "lr": 3.3483660493571076e-08, "epoch": 4.6307922272047835, "percentage": 92.62, "elapsed_time": "1:00:00", "remaining_time": "0:04:47", "throughput": 7048.36, "total_tokens": 25378816} {"current_steps": 3099, "total_steps": 3345, "loss": 0.1739, "lr": 3.321429126705966e-08, "epoch": 4.632286995515695, "percentage": 92.65, "elapsed_time": "1:00:01", "remaining_time": "0:04:45", "throughput": 7048.36, "total_tokens": 25387008} {"current_steps": 3100, "total_steps": 3345, "loss": 0.2469, "lr": 3.29459953416364e-08, "epoch": 4.633781763826607, "percentage": 92.68, "elapsed_time": "1:00:02", "remaining_time": "0:04:44", "throughput": 7048.36, "total_tokens": 25395200} {"current_steps": 3101, "total_steps": 3345, "loss": 0.1296, "lr": 3.267877295395877e-08, "epoch": 4.635276532137519, "percentage": 92.71, "elapsed_time": "1:00:04", "remaining_time": "0:04:43", "throughput": 7048.32, "total_tokens": 25403392} {"current_steps": 3102, "total_steps": 3345, "loss": 0.1767, "lr": 3.2412624339738516e-08, "epoch": 4.63677130044843, "percentage": 92.74, "elapsed_time": "1:00:05", "remaining_time": "0:04:42", "throughput": 7048.32, "total_tokens": 25411584} {"current_steps": 3103, "total_steps": 3345, "loss": 0.3519, "lr": 3.2147549733739514e-08, "epoch": 4.638266068759342, "percentage": 92.77, "elapsed_time": "1:00:06", "remaining_time": "0:04:41", "throughput": 7048.32, "total_tokens": 25419776} {"current_steps": 3104, "total_steps": 3345, "loss": 0.1293, "lr": 3.1883549369778475e-08, "epoch": 4.639760837070254, "percentage": 92.8, "elapsed_time": "1:00:07", "remaining_time": "0:04:40", "throughput": 7048.3, "total_tokens": 25427968} {"current_steps": 3105, "total_steps": 3345, "loss": 0.2251, "lr": 3.162062348072481e-08, "epoch": 4.641255605381166, "percentage": 92.83, "elapsed_time": "1:00:08", "remaining_time": "0:04:38", "throughput": 7048.29, "total_tokens": 25436160} {"current_steps": 3106, "total_steps": 3345, "loss": 0.2904, "lr": 3.135877229849954e-08, "epoch": 4.642750373692078, "percentage": 92.86, "elapsed_time": "1:00:10", "remaining_time": "0:04:37", "throughput": 7048.29, "total_tokens": 25444352} {"current_steps": 3107, "total_steps": 3345, "loss": 0.287, "lr": 3.1097996054076374e-08, "epoch": 4.6442451420029895, "percentage": 92.88, "elapsed_time": "1:00:11", "remaining_time": "0:04:36", "throughput": 7048.28, "total_tokens": 25452544} {"current_steps": 3108, "total_steps": 3345, "loss": 0.1721, "lr": 3.083829497748034e-08, "epoch": 4.645739910313901, "percentage": 92.91, "elapsed_time": "1:00:12", "remaining_time": "0:04:35", "throughput": 7048.28, "total_tokens": 25460736} {"current_steps": 3109, "total_steps": 3345, "loss": 0.4908, "lr": 3.0579669297788465e-08, "epoch": 4.647234678624813, "percentage": 92.94, "elapsed_time": "1:00:13", "remaining_time": "0:04:34", "throughput": 7048.27, "total_tokens": 25468928} {"current_steps": 3110, "total_steps": 3345, "loss": 0.0578, "lr": 3.032211924312911e-08, "epoch": 4.648729446935725, "percentage": 92.97, "elapsed_time": "1:00:14", "remaining_time": "0:04:33", "throughput": 7048.24, "total_tokens": 25477120} {"current_steps": 3111, "total_steps": 3345, "loss": 0.2985, "lr": 3.006564504068152e-08, "epoch": 4.650224215246637, "percentage": 93.0, "elapsed_time": "1:00:15", "remaining_time": "0:04:31", "throughput": 7048.24, "total_tokens": 25485312} {"current_steps": 3112, "total_steps": 3345, "loss": 0.0267, "lr": 2.9810246916676386e-08, "epoch": 4.651718983557549, "percentage": 93.03, "elapsed_time": "1:00:16", "remaining_time": "0:04:30", "throughput": 7048.25, "total_tokens": 25493504} {"current_steps": 3113, "total_steps": 3345, "loss": 0.2093, "lr": 2.9555925096394906e-08, "epoch": 4.65321375186846, "percentage": 93.06, "elapsed_time": "1:00:18", "remaining_time": "0:04:29", "throughput": 7048.25, "total_tokens": 25501696} {"current_steps": 3114, "total_steps": 3345, "loss": 0.1839, "lr": 2.9302679804169147e-08, "epoch": 4.654708520179372, "percentage": 93.09, "elapsed_time": "1:00:19", "remaining_time": "0:04:28", "throughput": 7048.25, "total_tokens": 25509888} {"current_steps": 3115, "total_steps": 3345, "loss": 0.2909, "lr": 2.9050511263381126e-08, "epoch": 4.656203288490284, "percentage": 93.12, "elapsed_time": "1:00:20", "remaining_time": "0:04:27", "throughput": 7048.25, "total_tokens": 25518080} {"current_steps": 3116, "total_steps": 3345, "loss": 0.1302, "lr": 2.8799419696463742e-08, "epoch": 4.657698056801196, "percentage": 93.15, "elapsed_time": "1:00:21", "remaining_time": "0:04:26", "throughput": 7048.25, "total_tokens": 25526272} {"current_steps": 3117, "total_steps": 3345, "loss": 0.3622, "lr": 2.8549405324899415e-08, "epoch": 4.6591928251121075, "percentage": 93.18, "elapsed_time": "1:00:22", "remaining_time": "0:04:24", "throughput": 7048.26, "total_tokens": 25534464} {"current_steps": 3118, "total_steps": 3345, "loss": 0.1198, "lr": 2.8300468369220764e-08, "epoch": 4.660687593423019, "percentage": 93.21, "elapsed_time": "1:00:23", "remaining_time": "0:04:23", "throughput": 7048.26, "total_tokens": 25542656} {"current_steps": 3119, "total_steps": 3345, "loss": 0.2309, "lr": 2.8052609049009638e-08, "epoch": 4.662182361733931, "percentage": 93.24, "elapsed_time": "1:00:25", "remaining_time": "0:04:22", "throughput": 7048.26, "total_tokens": 25550848} {"current_steps": 3120, "total_steps": 3345, "loss": 0.1124, "lr": 2.7805827582897682e-08, "epoch": 4.663677130044843, "percentage": 93.27, "elapsed_time": "1:00:26", "remaining_time": "0:04:21", "throughput": 7048.27, "total_tokens": 25559040} {"current_steps": 3121, "total_steps": 3345, "loss": 0.2485, "lr": 2.7560124188565492e-08, "epoch": 4.665171898355755, "percentage": 93.3, "elapsed_time": "1:00:27", "remaining_time": "0:04:20", "throughput": 7048.27, "total_tokens": 25567232} {"current_steps": 3122, "total_steps": 3345, "loss": 0.1077, "lr": 2.731549908274289e-08, "epoch": 4.666666666666667, "percentage": 93.33, "elapsed_time": "1:00:28", "remaining_time": "0:04:19", "throughput": 7048.27, "total_tokens": 25575424} {"current_steps": 3123, "total_steps": 3345, "loss": 0.037, "lr": 2.7071952481208808e-08, "epoch": 4.668161434977579, "percentage": 93.36, "elapsed_time": "1:00:29", "remaining_time": "0:04:18", "throughput": 7048.27, "total_tokens": 25583616} {"current_steps": 3124, "total_steps": 3345, "loss": 0.1577, "lr": 2.6829484598790146e-08, "epoch": 4.66965620328849, "percentage": 93.39, "elapsed_time": "1:00:30", "remaining_time": "0:04:16", "throughput": 7048.27, "total_tokens": 25591808} {"current_steps": 3125, "total_steps": 3345, "loss": 0.3189, "lr": 2.6588095649363042e-08, "epoch": 4.671150971599402, "percentage": 93.42, "elapsed_time": "1:00:32", "remaining_time": "0:04:15", "throughput": 7048.26, "total_tokens": 25600000} {"current_steps": 3126, "total_steps": 3345, "loss": 0.2025, "lr": 2.6347785845851488e-08, "epoch": 4.672645739910314, "percentage": 93.45, "elapsed_time": "1:00:33", "remaining_time": "0:04:14", "throughput": 7048.27, "total_tokens": 25608192} {"current_steps": 3127, "total_steps": 3345, "loss": 0.3428, "lr": 2.610855540022758e-08, "epoch": 4.6741405082212255, "percentage": 93.48, "elapsed_time": "1:00:34", "remaining_time": "0:04:13", "throughput": 7048.26, "total_tokens": 25616384} {"current_steps": 3128, "total_steps": 3345, "loss": 0.1117, "lr": 2.5870404523511832e-08, "epoch": 4.675635276532137, "percentage": 93.51, "elapsed_time": "1:00:35", "remaining_time": "0:04:12", "throughput": 7048.26, "total_tokens": 25624576} {"current_steps": 3129, "total_steps": 3345, "loss": 0.307, "lr": 2.563333342577176e-08, "epoch": 4.677130044843049, "percentage": 93.54, "elapsed_time": "1:00:36", "remaining_time": "0:04:11", "throughput": 7048.26, "total_tokens": 25632768} {"current_steps": 3130, "total_steps": 3345, "loss": 0.2083, "lr": 2.5397342316123147e-08, "epoch": 4.678624813153961, "percentage": 93.57, "elapsed_time": "1:00:37", "remaining_time": "0:04:09", "throughput": 7048.25, "total_tokens": 25640960} {"current_steps": 3131, "total_steps": 3345, "loss": 0.1039, "lr": 2.5162431402728365e-08, "epoch": 4.680119581464873, "percentage": 93.6, "elapsed_time": "1:00:39", "remaining_time": "0:04:08", "throughput": 7048.25, "total_tokens": 25649152} {"current_steps": 3132, "total_steps": 3345, "loss": 0.3442, "lr": 2.4928600892797637e-08, "epoch": 4.681614349775785, "percentage": 93.63, "elapsed_time": "1:00:40", "remaining_time": "0:04:07", "throughput": 7048.25, "total_tokens": 25657344} {"current_steps": 3133, "total_steps": 3345, "loss": 0.2661, "lr": 2.4695850992587784e-08, "epoch": 4.683109118086697, "percentage": 93.66, "elapsed_time": "1:00:41", "remaining_time": "0:04:06", "throughput": 7048.26, "total_tokens": 25665536} {"current_steps": 3134, "total_steps": 3345, "loss": 0.2395, "lr": 2.4464181907403045e-08, "epoch": 4.684603886397609, "percentage": 93.69, "elapsed_time": "1:00:42", "remaining_time": "0:04:05", "throughput": 7048.25, "total_tokens": 25673728} {"current_steps": 3135, "total_steps": 3345, "loss": 0.2231, "lr": 2.4233593841593295e-08, "epoch": 4.68609865470852, "percentage": 93.72, "elapsed_time": "1:00:43", "remaining_time": "0:04:04", "throughput": 7048.25, "total_tokens": 25681920} {"current_steps": 3136, "total_steps": 3345, "loss": 0.229, "lr": 2.4004086998555692e-08, "epoch": 4.687593423019432, "percentage": 93.75, "elapsed_time": "1:00:44", "remaining_time": "0:04:02", "throughput": 7048.25, "total_tokens": 25690112} {"current_steps": 3137, "total_steps": 3345, "loss": 0.1872, "lr": 2.377566158073344e-08, "epoch": 4.6890881913303435, "percentage": 93.78, "elapsed_time": "1:00:46", "remaining_time": "0:04:01", "throughput": 7048.25, "total_tokens": 25698304} {"current_steps": 3138, "total_steps": 3345, "loss": 0.2369, "lr": 2.3548317789615636e-08, "epoch": 4.690582959641255, "percentage": 93.81, "elapsed_time": "1:00:47", "remaining_time": "0:04:00", "throughput": 7048.26, "total_tokens": 25706496} {"current_steps": 3139, "total_steps": 3345, "loss": 0.31, "lr": 2.3322055825737572e-08, "epoch": 4.692077727952167, "percentage": 93.84, "elapsed_time": "1:00:48", "remaining_time": "0:03:59", "throughput": 7048.26, "total_tokens": 25714688} {"current_steps": 3140, "total_steps": 3345, "loss": 0.3288, "lr": 2.309687588868001e-08, "epoch": 4.693572496263079, "percentage": 93.87, "elapsed_time": "1:00:49", "remaining_time": "0:03:58", "throughput": 7048.26, "total_tokens": 25722880} {"current_steps": 3141, "total_steps": 3345, "loss": 0.1603, "lr": 2.287277817706976e-08, "epoch": 4.695067264573991, "percentage": 93.9, "elapsed_time": "1:00:50", "remaining_time": "0:03:57", "throughput": 7048.26, "total_tokens": 25731072} {"current_steps": 3142, "total_steps": 3345, "loss": 0.1208, "lr": 2.2649762888578287e-08, "epoch": 4.696562032884903, "percentage": 93.93, "elapsed_time": "1:00:51", "remaining_time": "0:03:55", "throughput": 7048.25, "total_tokens": 25739264} {"current_steps": 3143, "total_steps": 3345, "loss": 0.2396, "lr": 2.242783021992309e-08, "epoch": 4.698056801195815, "percentage": 93.96, "elapsed_time": "1:00:53", "remaining_time": "0:03:54", "throughput": 7048.26, "total_tokens": 25747456} {"current_steps": 3144, "total_steps": 3345, "loss": 0.0309, "lr": 2.2206980366866055e-08, "epoch": 4.699551569506727, "percentage": 93.99, "elapsed_time": "1:00:54", "remaining_time": "0:03:53", "throughput": 7048.26, "total_tokens": 25755648} {"current_steps": 3145, "total_steps": 3345, "loss": 0.2145, "lr": 2.1987213524214125e-08, "epoch": 4.701046337817639, "percentage": 94.02, "elapsed_time": "1:00:55", "remaining_time": "0:03:52", "throughput": 7048.27, "total_tokens": 25763840} {"current_steps": 3146, "total_steps": 3345, "loss": 0.1035, "lr": 2.1768529885819317e-08, "epoch": 4.70254110612855, "percentage": 94.05, "elapsed_time": "1:00:56", "remaining_time": "0:03:51", "throughput": 7048.27, "total_tokens": 25772032} {"current_steps": 3147, "total_steps": 3345, "loss": 0.1595, "lr": 2.1550929644577613e-08, "epoch": 4.704035874439462, "percentage": 94.08, "elapsed_time": "1:00:57", "remaining_time": "0:03:50", "throughput": 7048.28, "total_tokens": 25780224} {"current_steps": 3148, "total_steps": 3345, "loss": 0.2202, "lr": 2.1334412992429776e-08, "epoch": 4.705530642750373, "percentage": 94.11, "elapsed_time": "1:00:58", "remaining_time": "0:03:48", "throughput": 7048.28, "total_tokens": 25788416} {"current_steps": 3149, "total_steps": 3345, "loss": 0.1257, "lr": 2.11189801203604e-08, "epoch": 4.707025411061285, "percentage": 94.14, "elapsed_time": "1:00:59", "remaining_time": "0:03:47", "throughput": 7048.28, "total_tokens": 25796608} {"current_steps": 3150, "total_steps": 3345, "loss": 0.294, "lr": 2.0904631218398448e-08, "epoch": 4.708520179372197, "percentage": 94.17, "elapsed_time": "1:01:01", "remaining_time": "0:03:46", "throughput": 7048.28, "total_tokens": 25804800} {"current_steps": 3151, "total_steps": 3345, "loss": 0.2604, "lr": 2.0691366475616425e-08, "epoch": 4.710014947683109, "percentage": 94.2, "elapsed_time": "1:01:02", "remaining_time": "0:03:45", "throughput": 7048.25, "total_tokens": 25812992} {"current_steps": 3152, "total_steps": 3345, "loss": 0.2145, "lr": 2.0479186080130942e-08, "epoch": 4.711509715994021, "percentage": 94.23, "elapsed_time": "1:01:03", "remaining_time": "0:03:44", "throughput": 7048.25, "total_tokens": 25821184} {"current_steps": 3153, "total_steps": 3345, "loss": 0.0272, "lr": 2.0268090219101727e-08, "epoch": 4.713004484304933, "percentage": 94.26, "elapsed_time": "1:01:04", "remaining_time": "0:03:43", "throughput": 7048.25, "total_tokens": 25829376} {"current_steps": 3154, "total_steps": 3345, "loss": 0.0255, "lr": 2.005807907873178e-08, "epoch": 4.714499252615845, "percentage": 94.29, "elapsed_time": "1:01:05", "remaining_time": "0:03:41", "throughput": 7048.26, "total_tokens": 25837568} {"current_steps": 3155, "total_steps": 3345, "loss": 0.1636, "lr": 1.9849152844267917e-08, "epoch": 4.715994020926757, "percentage": 94.32, "elapsed_time": "1:01:06", "remaining_time": "0:03:40", "throughput": 7048.25, "total_tokens": 25845760} {"current_steps": 3156, "total_steps": 3345, "loss": 0.1556, "lr": 1.9641311699999248e-08, "epoch": 4.7174887892376685, "percentage": 94.35, "elapsed_time": "1:01:08", "remaining_time": "0:03:39", "throughput": 7048.25, "total_tokens": 25853952} {"current_steps": 3157, "total_steps": 3345, "loss": 0.2325, "lr": 1.9434555829258294e-08, "epoch": 4.71898355754858, "percentage": 94.38, "elapsed_time": "1:01:09", "remaining_time": "0:03:38", "throughput": 7048.27, "total_tokens": 25862144} {"current_steps": 3158, "total_steps": 3345, "loss": 0.0597, "lr": 1.9228885414419862e-08, "epoch": 4.720478325859492, "percentage": 94.41, "elapsed_time": "1:01:10", "remaining_time": "0:03:37", "throughput": 7048.27, "total_tokens": 25870336} {"current_steps": 3159, "total_steps": 3345, "loss": 0.0889, "lr": 1.902430063690161e-08, "epoch": 4.721973094170403, "percentage": 94.44, "elapsed_time": "1:01:11", "remaining_time": "0:03:36", "throughput": 7048.26, "total_tokens": 25878528} {"current_steps": 3160, "total_steps": 3345, "loss": 0.2047, "lr": 1.882080167716363e-08, "epoch": 4.723467862481315, "percentage": 94.47, "elapsed_time": "1:01:12", "remaining_time": "0:03:35", "throughput": 7048.27, "total_tokens": 25886720} {"current_steps": 3161, "total_steps": 3345, "loss": 0.1998, "lr": 1.8618388714707753e-08, "epoch": 4.724962630792227, "percentage": 94.5, "elapsed_time": "1:01:13", "remaining_time": "0:03:33", "throughput": 7048.28, "total_tokens": 25894912} {"current_steps": 3162, "total_steps": 3345, "loss": 0.1852, "lr": 1.8417061928078378e-08, "epoch": 4.726457399103139, "percentage": 94.53, "elapsed_time": "1:01:15", "remaining_time": "0:03:32", "throughput": 7048.28, "total_tokens": 25903104} {"current_steps": 3163, "total_steps": 3345, "loss": 0.1994, "lr": 1.821682149486151e-08, "epoch": 4.727952167414051, "percentage": 94.56, "elapsed_time": "1:01:16", "remaining_time": "0:03:31", "throughput": 7048.28, "total_tokens": 25911296} {"current_steps": 3164, "total_steps": 3345, "loss": 0.2679, "lr": 1.80176675916853e-08, "epoch": 4.729446935724963, "percentage": 94.59, "elapsed_time": "1:01:17", "remaining_time": "0:03:30", "throughput": 7048.28, "total_tokens": 25919488} {"current_steps": 3165, "total_steps": 3345, "loss": 0.2097, "lr": 1.7819600394218956e-08, "epoch": 4.7309417040358746, "percentage": 94.62, "elapsed_time": "1:01:18", "remaining_time": "0:03:29", "throughput": 7048.28, "total_tokens": 25927680} {"current_steps": 3166, "total_steps": 3345, "loss": 0.0435, "lr": 1.7622620077173413e-08, "epoch": 4.732436472346786, "percentage": 94.65, "elapsed_time": "1:01:19", "remaining_time": "0:03:28", "throughput": 7048.29, "total_tokens": 25935872} {"current_steps": 3167, "total_steps": 3345, "loss": 0.1671, "lr": 1.7426726814300798e-08, "epoch": 4.733931240657698, "percentage": 94.68, "elapsed_time": "1:01:20", "remaining_time": "0:03:26", "throughput": 7048.28, "total_tokens": 25944064} {"current_steps": 3168, "total_steps": 3345, "loss": 0.1802, "lr": 1.7231920778394694e-08, "epoch": 4.73542600896861, "percentage": 94.71, "elapsed_time": "1:01:22", "remaining_time": "0:03:25", "throughput": 7048.28, "total_tokens": 25952256} {"current_steps": 3169, "total_steps": 3345, "loss": 0.2835, "lr": 1.7038202141289455e-08, "epoch": 4.736920777279522, "percentage": 94.74, "elapsed_time": "1:01:23", "remaining_time": "0:03:24", "throughput": 7048.29, "total_tokens": 25960448} {"current_steps": 3170, "total_steps": 3345, "loss": 0.0908, "lr": 1.6845571073859784e-08, "epoch": 4.738415545590433, "percentage": 94.77, "elapsed_time": "1:01:24", "remaining_time": "0:03:23", "throughput": 7048.3, "total_tokens": 25968640} {"current_steps": 3171, "total_steps": 3345, "loss": 0.1722, "lr": 1.6654027746021982e-08, "epoch": 4.739910313901345, "percentage": 94.8, "elapsed_time": "1:01:25", "remaining_time": "0:03:22", "throughput": 7048.3, "total_tokens": 25976832} {"current_steps": 3172, "total_steps": 3345, "loss": 0.2715, "lr": 1.6463572326732014e-08, "epoch": 4.741405082212257, "percentage": 94.83, "elapsed_time": "1:01:26", "remaining_time": "0:03:21", "throughput": 7048.3, "total_tokens": 25985024} {"current_steps": 3173, "total_steps": 3345, "loss": 0.0227, "lr": 1.6274204983986743e-08, "epoch": 4.742899850523169, "percentage": 94.86, "elapsed_time": "1:01:27", "remaining_time": "0:03:19", "throughput": 7048.31, "total_tokens": 25993216} {"current_steps": 3174, "total_steps": 3345, "loss": 0.1503, "lr": 1.6085925884823106e-08, "epoch": 4.744394618834081, "percentage": 94.89, "elapsed_time": "1:01:29", "remaining_time": "0:03:18", "throughput": 7048.31, "total_tokens": 26001408} {"current_steps": 3175, "total_steps": 3345, "loss": 0.3138, "lr": 1.589873519531826e-08, "epoch": 4.7458893871449925, "percentage": 94.92, "elapsed_time": "1:01:30", "remaining_time": "0:03:17", "throughput": 7048.3, "total_tokens": 26009600} {"current_steps": 3176, "total_steps": 3345, "loss": 0.3271, "lr": 1.5712633080589013e-08, "epoch": 4.747384155455904, "percentage": 94.95, "elapsed_time": "1:01:31", "remaining_time": "0:03:16", "throughput": 7048.3, "total_tokens": 26017792} {"current_steps": 3177, "total_steps": 3345, "loss": 0.0886, "lr": 1.5527619704792107e-08, "epoch": 4.748878923766816, "percentage": 94.98, "elapsed_time": "1:01:32", "remaining_time": "0:03:15", "throughput": 7048.3, "total_tokens": 26025984} {"current_steps": 3178, "total_steps": 3345, "loss": 0.1765, "lr": 1.5343695231124223e-08, "epoch": 4.750373692077728, "percentage": 95.01, "elapsed_time": "1:01:33", "remaining_time": "0:03:14", "throughput": 7048.3, "total_tokens": 26034176} {"current_steps": 3179, "total_steps": 3345, "loss": 0.3499, "lr": 1.516085982182086e-08, "epoch": 4.75186846038864, "percentage": 95.04, "elapsed_time": "1:01:34", "remaining_time": "0:03:12", "throughput": 7048.3, "total_tokens": 26042368} {"current_steps": 3180, "total_steps": 3345, "loss": 0.216, "lr": 1.49791136381576e-08, "epoch": 4.753363228699552, "percentage": 95.07, "elapsed_time": "1:01:36", "remaining_time": "0:03:11", "throughput": 7048.3, "total_tokens": 26050560} {"current_steps": 3181, "total_steps": 3345, "loss": 0.215, "lr": 1.4798456840448839e-08, "epoch": 4.754857997010463, "percentage": 95.1, "elapsed_time": "1:01:37", "remaining_time": "0:03:10", "throughput": 7048.3, "total_tokens": 26058752} {"current_steps": 3182, "total_steps": 3345, "loss": 0.2299, "lr": 1.461888958804808e-08, "epoch": 4.756352765321375, "percentage": 95.13, "elapsed_time": "1:01:38", "remaining_time": "0:03:09", "throughput": 7048.31, "total_tokens": 26066944} {"current_steps": 3183, "total_steps": 3345, "loss": 0.2846, "lr": 1.4440412039348068e-08, "epoch": 4.757847533632287, "percentage": 95.16, "elapsed_time": "1:01:39", "remaining_time": "0:03:08", "throughput": 7048.31, "total_tokens": 26075136} {"current_steps": 3184, "total_steps": 3345, "loss": 0.3654, "lr": 1.4263024351779537e-08, "epoch": 4.759342301943199, "percentage": 95.19, "elapsed_time": "1:01:40", "remaining_time": "0:03:07", "throughput": 7048.31, "total_tokens": 26083328} {"current_steps": 3185, "total_steps": 3345, "loss": 0.1574, "lr": 1.4086726681813157e-08, "epoch": 4.7608370702541105, "percentage": 95.22, "elapsed_time": "1:01:41", "remaining_time": "0:03:05", "throughput": 7048.32, "total_tokens": 26091520} {"current_steps": 3186, "total_steps": 3345, "loss": 0.0814, "lr": 1.3911519184956895e-08, "epoch": 4.762331838565022, "percentage": 95.25, "elapsed_time": "1:01:42", "remaining_time": "0:03:04", "throughput": 7048.32, "total_tokens": 26099712} {"current_steps": 3187, "total_steps": 3345, "loss": 0.1235, "lr": 1.3737402015757683e-08, "epoch": 4.763826606875934, "percentage": 95.28, "elapsed_time": "1:01:44", "remaining_time": "0:03:03", "throughput": 7048.33, "total_tokens": 26107904} {"current_steps": 3188, "total_steps": 3345, "loss": 0.2362, "lr": 1.3564375327800722e-08, "epoch": 4.765321375186846, "percentage": 95.31, "elapsed_time": "1:01:45", "remaining_time": "0:03:02", "throughput": 7048.34, "total_tokens": 26116096} {"current_steps": 3189, "total_steps": 3345, "loss": 0.0243, "lr": 1.339243927370934e-08, "epoch": 4.766816143497758, "percentage": 95.34, "elapsed_time": "1:01:46", "remaining_time": "0:03:01", "throughput": 7048.35, "total_tokens": 26124288} {"current_steps": 3190, "total_steps": 3345, "loss": 0.107, "lr": 1.3221594005144306e-08, "epoch": 4.76831091180867, "percentage": 95.37, "elapsed_time": "1:01:47", "remaining_time": "0:03:00", "throughput": 7048.36, "total_tokens": 26132480} {"current_steps": 3191, "total_steps": 3345, "loss": 0.2518, "lr": 1.3051839672804934e-08, "epoch": 4.769805680119582, "percentage": 95.4, "elapsed_time": "1:01:48", "remaining_time": "0:02:58", "throughput": 7048.36, "total_tokens": 26140672} {"current_steps": 3192, "total_steps": 3345, "loss": 0.1361, "lr": 1.2883176426428111e-08, "epoch": 4.771300448430493, "percentage": 95.43, "elapsed_time": "1:01:49", "remaining_time": "0:02:57", "throughput": 7048.35, "total_tokens": 26148864} {"current_steps": 3193, "total_steps": 3345, "loss": 0.1783, "lr": 1.2715604414787613e-08, "epoch": 4.772795216741405, "percentage": 95.46, "elapsed_time": "1:01:51", "remaining_time": "0:02:56", "throughput": 7048.35, "total_tokens": 26157056} {"current_steps": 3194, "total_steps": 3345, "loss": 0.2761, "lr": 1.2549123785695754e-08, "epoch": 4.774289985052317, "percentage": 95.49, "elapsed_time": "1:01:52", "remaining_time": "0:02:55", "throughput": 7048.36, "total_tokens": 26165248} {"current_steps": 3195, "total_steps": 3345, "loss": 0.2663, "lr": 1.2383734686001181e-08, "epoch": 4.7757847533632285, "percentage": 95.52, "elapsed_time": "1:01:53", "remaining_time": "0:02:54", "throughput": 7048.36, "total_tokens": 26173440} {"current_steps": 3196, "total_steps": 3345, "loss": 0.2714, "lr": 1.2219437261590388e-08, "epoch": 4.77727952167414, "percentage": 95.55, "elapsed_time": "1:01:54", "remaining_time": "0:02:53", "throughput": 7048.37, "total_tokens": 26181632} {"current_steps": 3197, "total_steps": 3345, "loss": 0.0481, "lr": 1.205623165738662e-08, "epoch": 4.778774289985052, "percentage": 95.58, "elapsed_time": "1:01:55", "remaining_time": "0:02:52", "throughput": 7048.38, "total_tokens": 26189824} {"current_steps": 3198, "total_steps": 3345, "loss": 0.2056, "lr": 1.1894118017349854e-08, "epoch": 4.780269058295964, "percentage": 95.61, "elapsed_time": "1:01:56", "remaining_time": "0:02:50", "throughput": 7048.38, "total_tokens": 26198016} {"current_steps": 3199, "total_steps": 3345, "loss": 0.3031, "lr": 1.1733096484477652e-08, "epoch": 4.781763826606876, "percentage": 95.64, "elapsed_time": "1:01:58", "remaining_time": "0:02:49", "throughput": 7048.37, "total_tokens": 26206208} {"current_steps": 3200, "total_steps": 3345, "loss": 0.2146, "lr": 1.1573167200803203e-08, "epoch": 4.783258594917788, "percentage": 95.67, "elapsed_time": "1:01:59", "remaining_time": "0:02:48", "throughput": 7048.37, "total_tokens": 26214400} {"current_steps": 3201, "total_steps": 3345, "loss": 0.4704, "lr": 1.1414330307396998e-08, "epoch": 4.7847533632287, "percentage": 95.7, "elapsed_time": "1:02:00", "remaining_time": "0:02:47", "throughput": 7048.37, "total_tokens": 26222592} {"current_steps": 3202, "total_steps": 3345, "loss": 0.1414, "lr": 1.125658594436585e-08, "epoch": 4.786248131539612, "percentage": 95.72, "elapsed_time": "1:02:01", "remaining_time": "0:02:46", "throughput": 7048.37, "total_tokens": 26230784} {"current_steps": 3203, "total_steps": 3345, "loss": 0.1926, "lr": 1.1099934250852484e-08, "epoch": 4.787742899850523, "percentage": 95.75, "elapsed_time": "1:02:02", "remaining_time": "0:02:45", "throughput": 7048.37, "total_tokens": 26238976} {"current_steps": 3204, "total_steps": 3345, "loss": 0.1104, "lr": 1.0944375365036231e-08, "epoch": 4.789237668161435, "percentage": 95.78, "elapsed_time": "1:02:03", "remaining_time": "0:02:43", "throughput": 7048.37, "total_tokens": 26247168} {"current_steps": 3205, "total_steps": 3345, "loss": 0.327, "lr": 1.0789909424132328e-08, "epoch": 4.7907324364723465, "percentage": 95.81, "elapsed_time": "1:02:05", "remaining_time": "0:02:42", "throughput": 7048.34, "total_tokens": 26255360} {"current_steps": 3206, "total_steps": 3345, "loss": 0.1173, "lr": 1.0636536564391786e-08, "epoch": 4.792227204783258, "percentage": 95.84, "elapsed_time": "1:02:06", "remaining_time": "0:02:41", "throughput": 7048.35, "total_tokens": 26263552} {"current_steps": 3207, "total_steps": 3345, "loss": 0.192, "lr": 1.0484256921101666e-08, "epoch": 4.79372197309417, "percentage": 95.87, "elapsed_time": "1:02:07", "remaining_time": "0:02:40", "throughput": 7048.35, "total_tokens": 26271744} {"current_steps": 3208, "total_steps": 3345, "loss": 0.1651, "lr": 1.0333070628584518e-08, "epoch": 4.795216741405082, "percentage": 95.9, "elapsed_time": "1:02:08", "remaining_time": "0:02:39", "throughput": 7048.36, "total_tokens": 26279936} {"current_steps": 3209, "total_steps": 3345, "loss": 0.1494, "lr": 1.0182977820198808e-08, "epoch": 4.796711509715994, "percentage": 95.93, "elapsed_time": "1:02:09", "remaining_time": "0:02:38", "throughput": 7048.37, "total_tokens": 26288128} {"current_steps": 3210, "total_steps": 3345, "loss": 0.2882, "lr": 1.0033978628338214e-08, "epoch": 4.798206278026906, "percentage": 95.96, "elapsed_time": "1:02:10", "remaining_time": "0:02:36", "throughput": 7048.34, "total_tokens": 26296320} {"current_steps": 3211, "total_steps": 3345, "loss": 0.2743, "lr": 9.886073184431632e-09, "epoch": 4.799701046337818, "percentage": 95.99, "elapsed_time": "1:02:12", "remaining_time": "0:02:35", "throughput": 7048.34, "total_tokens": 26304512} {"current_steps": 3212, "total_steps": 3345, "loss": 0.0806, "lr": 9.73926161894359e-09, "epoch": 4.80119581464873, "percentage": 96.02, "elapsed_time": "1:02:13", "remaining_time": "0:02:34", "throughput": 7048.34, "total_tokens": 26312704} {"current_steps": 3213, "total_steps": 3345, "loss": 0.133, "lr": 9.593544061373139e-09, "epoch": 4.802690582959642, "percentage": 96.05, "elapsed_time": "1:02:14", "remaining_time": "0:02:33", "throughput": 7048.34, "total_tokens": 26320896} {"current_steps": 3214, "total_steps": 3345, "loss": 0.1619, "lr": 9.44892064025496e-09, "epoch": 4.804185351270553, "percentage": 96.08, "elapsed_time": "1:02:15", "remaining_time": "0:02:32", "throughput": 7048.34, "total_tokens": 26329088} {"current_steps": 3215, "total_steps": 3345, "loss": 0.1464, "lr": 9.30539148315826e-09, "epoch": 4.805680119581465, "percentage": 96.11, "elapsed_time": "1:02:16", "remaining_time": "0:02:31", "throughput": 7048.35, "total_tokens": 26337280} {"current_steps": 3216, "total_steps": 3345, "loss": 0.1847, "lr": 9.162956716687044e-09, "epoch": 4.807174887892376, "percentage": 96.14, "elapsed_time": "1:02:17", "remaining_time": "0:02:29", "throughput": 7048.35, "total_tokens": 26345472} {"current_steps": 3217, "total_steps": 3345, "loss": 0.0748, "lr": 9.021616466479976e-09, "epoch": 4.808669656203288, "percentage": 96.17, "elapsed_time": "1:02:18", "remaining_time": "0:02:28", "throughput": 7048.35, "total_tokens": 26353664} {"current_steps": 3218, "total_steps": 3345, "loss": 0.2949, "lr": 8.881370857210386e-09, "epoch": 4.8101644245142, "percentage": 96.2, "elapsed_time": "1:02:20", "remaining_time": "0:02:27", "throughput": 7048.36, "total_tokens": 26361856} {"current_steps": 3219, "total_steps": 3345, "loss": 0.0755, "lr": 8.742220012585984e-09, "epoch": 4.811659192825112, "percentage": 96.23, "elapsed_time": "1:02:21", "remaining_time": "0:02:26", "throughput": 7048.37, "total_tokens": 26370048} {"current_steps": 3220, "total_steps": 3345, "loss": 0.1652, "lr": 8.604164055348863e-09, "epoch": 4.813153961136024, "percentage": 96.26, "elapsed_time": "1:02:22", "remaining_time": "0:02:25", "throughput": 7048.36, "total_tokens": 26378240} {"current_steps": 3221, "total_steps": 3345, "loss": 0.3324, "lr": 8.467203107275223e-09, "epoch": 4.814648729446936, "percentage": 96.29, "elapsed_time": "1:02:23", "remaining_time": "0:02:24", "throughput": 7048.36, "total_tokens": 26386432} {"current_steps": 3222, "total_steps": 3345, "loss": 0.129, "lr": 8.331337289175373e-09, "epoch": 4.816143497757848, "percentage": 96.32, "elapsed_time": "1:02:24", "remaining_time": "0:02:22", "throughput": 7048.37, "total_tokens": 26394624} {"current_steps": 3223, "total_steps": 3345, "loss": 0.1816, "lr": 8.196566720893723e-09, "epoch": 4.81763826606876, "percentage": 96.35, "elapsed_time": "1:02:25", "remaining_time": "0:02:21", "throughput": 7048.36, "total_tokens": 26402816} {"current_steps": 3224, "total_steps": 3345, "loss": 0.1364, "lr": 8.062891521308652e-09, "epoch": 4.819133034379671, "percentage": 96.38, "elapsed_time": "1:02:27", "remaining_time": "0:02:20", "throughput": 7048.37, "total_tokens": 26411008} {"current_steps": 3225, "total_steps": 3345, "loss": 0.1751, "lr": 7.930311808332092e-09, "epoch": 4.820627802690583, "percentage": 96.41, "elapsed_time": "1:02:28", "remaining_time": "0:02:19", "throughput": 7048.37, "total_tokens": 26419200} {"current_steps": 3226, "total_steps": 3345, "loss": 0.2053, "lr": 7.798827698910078e-09, "epoch": 4.822122571001495, "percentage": 96.44, "elapsed_time": "1:02:29", "remaining_time": "0:02:18", "throughput": 7048.37, "total_tokens": 26427392} {"current_steps": 3227, "total_steps": 3345, "loss": 0.2444, "lr": 7.668439309021641e-09, "epoch": 4.823617339312406, "percentage": 96.47, "elapsed_time": "1:02:30", "remaining_time": "0:02:17", "throughput": 7048.37, "total_tokens": 26435584} {"current_steps": 3228, "total_steps": 3345, "loss": 0.2084, "lr": 7.539146753679783e-09, "epoch": 4.825112107623318, "percentage": 96.5, "elapsed_time": "1:02:31", "remaining_time": "0:02:15", "throughput": 7048.38, "total_tokens": 26443776} {"current_steps": 3229, "total_steps": 3345, "loss": 0.2692, "lr": 7.410950146930912e-09, "epoch": 4.82660687593423, "percentage": 96.53, "elapsed_time": "1:02:32", "remaining_time": "0:02:14", "throughput": 7048.38, "total_tokens": 26451968} {"current_steps": 3230, "total_steps": 3345, "loss": 0.2169, "lr": 7.283849601854298e-09, "epoch": 4.828101644245142, "percentage": 96.56, "elapsed_time": "1:02:34", "remaining_time": "0:02:13", "throughput": 7048.38, "total_tokens": 26460160} {"current_steps": 3231, "total_steps": 3345, "loss": 0.1072, "lr": 7.15784523056276e-09, "epoch": 4.829596412556054, "percentage": 96.59, "elapsed_time": "1:02:35", "remaining_time": "0:02:12", "throughput": 7048.38, "total_tokens": 26468352} {"current_steps": 3232, "total_steps": 3345, "loss": 0.1333, "lr": 7.032937144202112e-09, "epoch": 4.831091180866966, "percentage": 96.62, "elapsed_time": "1:02:36", "remaining_time": "0:02:11", "throughput": 7048.39, "total_tokens": 26476544} {"current_steps": 3233, "total_steps": 3345, "loss": 0.0523, "lr": 6.909125452951304e-09, "epoch": 4.8325859491778775, "percentage": 96.65, "elapsed_time": "1:02:37", "remaining_time": "0:02:10", "throughput": 7048.4, "total_tokens": 26484736} {"current_steps": 3234, "total_steps": 3345, "loss": 0.1962, "lr": 6.786410266021725e-09, "epoch": 4.834080717488789, "percentage": 96.68, "elapsed_time": "1:02:38", "remaining_time": "0:02:09", "throughput": 7048.41, "total_tokens": 26492928} {"current_steps": 3235, "total_steps": 3345, "loss": 0.2351, "lr": 6.66479169165804e-09, "epoch": 4.835575485799701, "percentage": 96.71, "elapsed_time": "1:02:39", "remaining_time": "0:02:07", "throughput": 7048.42, "total_tokens": 26501120} {"current_steps": 3236, "total_steps": 3345, "loss": 0.1263, "lr": 6.544269837137351e-09, "epoch": 4.837070254110613, "percentage": 96.74, "elapsed_time": "1:02:41", "remaining_time": "0:02:06", "throughput": 7048.42, "total_tokens": 26509312} {"current_steps": 3237, "total_steps": 3345, "loss": 0.147, "lr": 6.4248448087696206e-09, "epoch": 4.838565022421525, "percentage": 96.77, "elapsed_time": "1:02:42", "remaining_time": "0:02:05", "throughput": 7048.42, "total_tokens": 26517504} {"current_steps": 3238, "total_steps": 3345, "loss": 0.2362, "lr": 6.30651671189697e-09, "epoch": 4.840059790732436, "percentage": 96.8, "elapsed_time": "1:02:43", "remaining_time": "0:02:04", "throughput": 7048.42, "total_tokens": 26525696} {"current_steps": 3239, "total_steps": 3345, "loss": 0.3893, "lr": 6.189285650894383e-09, "epoch": 4.841554559043348, "percentage": 96.83, "elapsed_time": "1:02:44", "remaining_time": "0:02:03", "throughput": 7048.43, "total_tokens": 26533888} {"current_steps": 3240, "total_steps": 3345, "loss": 0.1487, "lr": 6.073151729168586e-09, "epoch": 4.84304932735426, "percentage": 96.86, "elapsed_time": "1:02:45", "remaining_time": "0:02:02", "throughput": 7048.44, "total_tokens": 26542080} {"current_steps": 3241, "total_steps": 3345, "loss": 0.2369, "lr": 5.958115049158886e-09, "epoch": 4.844544095665172, "percentage": 96.89, "elapsed_time": "1:02:46", "remaining_time": "0:02:00", "throughput": 7048.44, "total_tokens": 26550272} {"current_steps": 3242, "total_steps": 3345, "loss": 0.1781, "lr": 5.8441757123370306e-09, "epoch": 4.846038863976084, "percentage": 96.92, "elapsed_time": "1:02:47", "remaining_time": "0:01:59", "throughput": 7048.44, "total_tokens": 26558464} {"current_steps": 3243, "total_steps": 3345, "loss": 0.2708, "lr": 5.731333819206236e-09, "epoch": 4.8475336322869955, "percentage": 96.95, "elapsed_time": "1:02:49", "remaining_time": "0:01:58", "throughput": 7048.45, "total_tokens": 26566656} {"current_steps": 3244, "total_steps": 3345, "loss": 0.1853, "lr": 5.619589469302161e-09, "epoch": 4.849028400597907, "percentage": 96.98, "elapsed_time": "1:02:50", "remaining_time": "0:01:57", "throughput": 7048.45, "total_tokens": 26574848} {"current_steps": 3245, "total_steps": 3345, "loss": 0.2485, "lr": 5.508942761191932e-09, "epoch": 4.850523168908819, "percentage": 97.01, "elapsed_time": "1:02:51", "remaining_time": "0:01:56", "throughput": 7048.45, "total_tokens": 26583040} {"current_steps": 3246, "total_steps": 3345, "loss": 0.1015, "lr": 5.399393792474977e-09, "epoch": 4.852017937219731, "percentage": 97.04, "elapsed_time": "1:02:52", "remaining_time": "0:01:55", "throughput": 7048.42, "total_tokens": 26591232} {"current_steps": 3247, "total_steps": 3345, "loss": 0.185, "lr": 5.290942659781778e-09, "epoch": 4.853512705530643, "percentage": 97.07, "elapsed_time": "1:02:53", "remaining_time": "0:01:53", "throughput": 7048.43, "total_tokens": 26599424} {"current_steps": 3248, "total_steps": 3345, "loss": 0.1572, "lr": 5.183589458774979e-09, "epoch": 4.855007473841555, "percentage": 97.1, "elapsed_time": "1:02:54", "remaining_time": "0:01:52", "throughput": 7048.42, "total_tokens": 26607616} {"current_steps": 3249, "total_steps": 3345, "loss": 0.3061, "lr": 5.077334284148694e-09, "epoch": 4.856502242152466, "percentage": 97.13, "elapsed_time": "1:02:56", "remaining_time": "0:01:51", "throughput": 7048.43, "total_tokens": 26615808} {"current_steps": 3250, "total_steps": 3345, "loss": 0.2861, "lr": 4.972177229628089e-09, "epoch": 4.857997010463378, "percentage": 97.16, "elapsed_time": "1:02:57", "remaining_time": "0:01:50", "throughput": 7048.43, "total_tokens": 26624000} {"current_steps": 3251, "total_steps": 3345, "loss": 0.1792, "lr": 4.868118387970355e-09, "epoch": 4.85949177877429, "percentage": 97.19, "elapsed_time": "1:02:58", "remaining_time": "0:01:49", "throughput": 7048.43, "total_tokens": 26632192} {"current_steps": 3252, "total_steps": 3345, "loss": 0.0175, "lr": 4.765157850963181e-09, "epoch": 4.860986547085202, "percentage": 97.22, "elapsed_time": "1:02:59", "remaining_time": "0:01:48", "throughput": 7048.43, "total_tokens": 26640384} {"current_steps": 3253, "total_steps": 3345, "loss": 0.3475, "lr": 4.663295709426419e-09, "epoch": 4.8624813153961135, "percentage": 97.25, "elapsed_time": "1:03:00", "remaining_time": "0:01:46", "throughput": 7048.44, "total_tokens": 26648576} {"current_steps": 3254, "total_steps": 3345, "loss": 0.1274, "lr": 4.562532053210001e-09, "epoch": 4.863976083707025, "percentage": 97.28, "elapsed_time": "1:03:01", "remaining_time": "0:01:45", "throughput": 7048.44, "total_tokens": 26656768} {"current_steps": 3255, "total_steps": 3345, "loss": 0.2784, "lr": 4.462866971195745e-09, "epoch": 4.865470852017937, "percentage": 97.31, "elapsed_time": "1:03:03", "remaining_time": "0:01:44", "throughput": 7048.44, "total_tokens": 26664960} {"current_steps": 3256, "total_steps": 3345, "loss": 0.345, "lr": 4.364300551296108e-09, "epoch": 4.866965620328849, "percentage": 97.34, "elapsed_time": "1:03:04", "remaining_time": "0:01:43", "throughput": 7048.44, "total_tokens": 26673152} {"current_steps": 3257, "total_steps": 3345, "loss": 0.2046, "lr": 4.26683288045418e-09, "epoch": 4.868460388639761, "percentage": 97.37, "elapsed_time": "1:03:05", "remaining_time": "0:01:42", "throughput": 7048.45, "total_tokens": 26681344} {"current_steps": 3258, "total_steps": 3345, "loss": 0.3188, "lr": 4.1704640446445235e-09, "epoch": 4.869955156950673, "percentage": 97.4, "elapsed_time": "1:03:06", "remaining_time": "0:01:41", "throughput": 7048.45, "total_tokens": 26689536} {"current_steps": 3259, "total_steps": 3345, "loss": 0.1478, "lr": 4.075194128871918e-09, "epoch": 4.871449925261585, "percentage": 97.43, "elapsed_time": "1:03:07", "remaining_time": "0:01:39", "throughput": 7048.45, "total_tokens": 26697728} {"current_steps": 3260, "total_steps": 3345, "loss": 0.2663, "lr": 3.981023217171781e-09, "epoch": 4.872944693572496, "percentage": 97.46, "elapsed_time": "1:03:08", "remaining_time": "0:01:38", "throughput": 7048.46, "total_tokens": 26705920} {"current_steps": 3261, "total_steps": 3345, "loss": 0.2, "lr": 3.887951392610584e-09, "epoch": 4.874439461883408, "percentage": 97.49, "elapsed_time": "1:03:10", "remaining_time": "0:01:37", "throughput": 7048.45, "total_tokens": 26714112} {"current_steps": 3262, "total_steps": 3345, "loss": 0.1672, "lr": 3.795978737284878e-09, "epoch": 4.87593423019432, "percentage": 97.52, "elapsed_time": "1:03:11", "remaining_time": "0:01:36", "throughput": 7048.46, "total_tokens": 26722304} {"current_steps": 3263, "total_steps": 3345, "loss": 0.1694, "lr": 3.7051053323217123e-09, "epoch": 4.8774289985052315, "percentage": 97.55, "elapsed_time": "1:03:12", "remaining_time": "0:01:35", "throughput": 7048.47, "total_tokens": 26730496} {"current_steps": 3264, "total_steps": 3345, "loss": 0.1964, "lr": 3.615331257878635e-09, "epoch": 4.878923766816143, "percentage": 97.58, "elapsed_time": "1:03:13", "remaining_time": "0:01:34", "throughput": 7048.46, "total_tokens": 26738688} {"current_steps": 3265, "total_steps": 3345, "loss": 0.1122, "lr": 3.5266565931436902e-09, "epoch": 4.880418535127055, "percentage": 97.61, "elapsed_time": "1:03:14", "remaining_time": "0:01:32", "throughput": 7048.46, "total_tokens": 26746880} {"current_steps": 3266, "total_steps": 3345, "loss": 0.214, "lr": 3.4390814163347273e-09, "epoch": 4.881913303437967, "percentage": 97.64, "elapsed_time": "1:03:15", "remaining_time": "0:01:31", "throughput": 7048.46, "total_tokens": 26755072} {"current_steps": 3267, "total_steps": 3345, "loss": 0.4176, "lr": 3.352605804700093e-09, "epoch": 4.883408071748879, "percentage": 97.67, "elapsed_time": "1:03:17", "remaining_time": "0:01:30", "throughput": 7048.47, "total_tokens": 26763264} {"current_steps": 3268, "total_steps": 3345, "loss": 0.104, "lr": 3.2672298345179376e-09, "epoch": 4.884902840059791, "percentage": 97.7, "elapsed_time": "1:03:18", "remaining_time": "0:01:29", "throughput": 7048.47, "total_tokens": 26771456} {"current_steps": 3269, "total_steps": 3345, "loss": 0.0398, "lr": 3.1829535810966317e-09, "epoch": 4.886397608370703, "percentage": 97.73, "elapsed_time": "1:03:19", "remaining_time": "0:01:28", "throughput": 7048.47, "total_tokens": 26779648} {"current_steps": 3270, "total_steps": 3345, "loss": 0.2778, "lr": 3.0997771187747662e-09, "epoch": 4.887892376681615, "percentage": 97.76, "elapsed_time": "1:03:20", "remaining_time": "0:01:27", "throughput": 7048.47, "total_tokens": 26787840} {"current_steps": 3271, "total_steps": 3345, "loss": 0.3719, "lr": 3.0177005209201804e-09, "epoch": 4.889387144992526, "percentage": 97.79, "elapsed_time": "1:03:21", "remaining_time": "0:01:26", "throughput": 7048.48, "total_tokens": 26796032} {"current_steps": 3272, "total_steps": 3345, "loss": 0.2037, "lr": 2.936723859931212e-09, "epoch": 4.8908819133034385, "percentage": 97.82, "elapsed_time": "1:03:22", "remaining_time": "0:01:24", "throughput": 7048.48, "total_tokens": 26804224} {"current_steps": 3273, "total_steps": 3345, "loss": 0.3443, "lr": 2.856847207235447e-09, "epoch": 4.8923766816143495, "percentage": 97.85, "elapsed_time": "1:03:24", "remaining_time": "0:01:23", "throughput": 7048.47, "total_tokens": 26812416} {"current_steps": 3274, "total_steps": 3345, "loss": 0.2017, "lr": 2.778070633290553e-09, "epoch": 4.893871449925261, "percentage": 97.88, "elapsed_time": "1:03:25", "remaining_time": "0:01:22", "throughput": 7048.48, "total_tokens": 26820608} {"current_steps": 3275, "total_steps": 3345, "loss": 0.2115, "lr": 2.700394207583584e-09, "epoch": 4.895366218236173, "percentage": 97.91, "elapsed_time": "1:03:26", "remaining_time": "0:01:21", "throughput": 7048.48, "total_tokens": 26828800} {"current_steps": 3276, "total_steps": 3345, "loss": 0.2806, "lr": 2.6238179986314006e-09, "epoch": 4.896860986547085, "percentage": 97.94, "elapsed_time": "1:03:27", "remaining_time": "0:01:20", "throughput": 7048.48, "total_tokens": 26836992} {"current_steps": 3277, "total_steps": 3345, "loss": 0.1076, "lr": 2.5483420739801092e-09, "epoch": 4.898355754857997, "percentage": 97.97, "elapsed_time": "1:03:28", "remaining_time": "0:01:19", "throughput": 7048.48, "total_tokens": 26845184} {"current_steps": 3278, "total_steps": 3345, "loss": 0.1628, "lr": 2.4739665002056214e-09, "epoch": 4.899850523168909, "percentage": 98.0, "elapsed_time": "1:03:29", "remaining_time": "0:01:17", "throughput": 7048.48, "total_tokens": 26853376} {"current_steps": 3279, "total_steps": 3345, "loss": 0.2224, "lr": 2.40069134291282e-09, "epoch": 4.901345291479821, "percentage": 98.03, "elapsed_time": "1:03:30", "remaining_time": "0:01:16", "throughput": 7048.48, "total_tokens": 26861568} {"current_steps": 3280, "total_steps": 3345, "loss": 0.2014, "lr": 2.328516666736391e-09, "epoch": 4.902840059790733, "percentage": 98.06, "elapsed_time": "1:03:32", "remaining_time": "0:01:15", "throughput": 7048.48, "total_tokens": 26869760} {"current_steps": 3281, "total_steps": 3345, "loss": 0.0654, "lr": 2.257442535340132e-09, "epoch": 4.904334828101645, "percentage": 98.09, "elapsed_time": "1:03:33", "remaining_time": "0:01:14", "throughput": 7048.5, "total_tokens": 26877952} {"current_steps": 3282, "total_steps": 3345, "loss": 0.1477, "lr": 2.1874690114168095e-09, "epoch": 4.905829596412556, "percentage": 98.12, "elapsed_time": "1:03:34", "remaining_time": "0:01:13", "throughput": 7048.51, "total_tokens": 26886144} {"current_steps": 3283, "total_steps": 3345, "loss": 0.1663, "lr": 2.1185961566888568e-09, "epoch": 4.907324364723468, "percentage": 98.15, "elapsed_time": "1:03:35", "remaining_time": "0:01:12", "throughput": 7048.51, "total_tokens": 26894336} {"current_steps": 3284, "total_steps": 3345, "loss": 0.0869, "lr": 2.0508240319074e-09, "epoch": 4.908819133034379, "percentage": 98.18, "elapsed_time": "1:03:36", "remaining_time": "0:01:10", "throughput": 7048.5, "total_tokens": 26902528} {"current_steps": 3285, "total_steps": 3345, "loss": 0.1582, "lr": 1.984152696852815e-09, "epoch": 4.910313901345291, "percentage": 98.21, "elapsed_time": "1:03:37", "remaining_time": "0:01:09", "throughput": 7048.51, "total_tokens": 26910720} {"current_steps": 3286, "total_steps": 3345, "loss": 0.2445, "lr": 1.9185822103344464e-09, "epoch": 4.911808669656203, "percentage": 98.24, "elapsed_time": "1:03:39", "remaining_time": "0:01:08", "throughput": 7048.51, "total_tokens": 26918912} {"current_steps": 3287, "total_steps": 3345, "loss": 0.0717, "lr": 1.8541126301908908e-09, "epoch": 4.913303437967115, "percentage": 98.27, "elapsed_time": "1:03:40", "remaining_time": "0:01:07", "throughput": 7048.51, "total_tokens": 26927104} {"current_steps": 3288, "total_steps": 3345, "loss": 0.0491, "lr": 1.7907440132891584e-09, "epoch": 4.914798206278027, "percentage": 98.3, "elapsed_time": "1:03:41", "remaining_time": "0:01:06", "throughput": 7048.52, "total_tokens": 26935296} {"current_steps": 3289, "total_steps": 3345, "loss": 0.1106, "lr": 1.7284764155253708e-09, "epoch": 4.916292974588939, "percentage": 98.33, "elapsed_time": "1:03:42", "remaining_time": "0:01:05", "throughput": 7048.52, "total_tokens": 26943488} {"current_steps": 3290, "total_steps": 3345, "loss": 0.0831, "lr": 1.66730989182462e-09, "epoch": 4.917787742899851, "percentage": 98.36, "elapsed_time": "1:03:43", "remaining_time": "0:01:03", "throughput": 7048.52, "total_tokens": 26951680} {"current_steps": 3291, "total_steps": 3345, "loss": 0.0814, "lr": 1.607244496140553e-09, "epoch": 4.9192825112107625, "percentage": 98.39, "elapsed_time": "1:03:44", "remaining_time": "0:01:02", "throughput": 7048.52, "total_tokens": 26959872} {"current_steps": 3292, "total_steps": 3345, "loss": 0.2765, "lr": 1.5482802814555109e-09, "epoch": 4.920777279521674, "percentage": 98.42, "elapsed_time": "1:03:46", "remaining_time": "0:01:01", "throughput": 7048.52, "total_tokens": 26968064} {"current_steps": 3293, "total_steps": 3345, "loss": 0.048, "lr": 1.4904172997806665e-09, "epoch": 4.922272047832586, "percentage": 98.45, "elapsed_time": "1:03:47", "remaining_time": "0:01:00", "throughput": 7048.52, "total_tokens": 26976256} {"current_steps": 3294, "total_steps": 3345, "loss": 0.1166, "lr": 1.4336556021558867e-09, "epoch": 4.923766816143498, "percentage": 98.48, "elapsed_time": "1:03:48", "remaining_time": "0:00:59", "throughput": 7048.52, "total_tokens": 26984448} {"current_steps": 3295, "total_steps": 3345, "loss": 0.1368, "lr": 1.377995238649038e-09, "epoch": 4.925261584454409, "percentage": 98.51, "elapsed_time": "1:03:49", "remaining_time": "0:00:58", "throughput": 7048.52, "total_tokens": 26992640} {"current_steps": 3296, "total_steps": 3345, "loss": 0.1208, "lr": 1.3234362583573746e-09, "epoch": 4.926756352765321, "percentage": 98.54, "elapsed_time": "1:03:50", "remaining_time": "0:00:56", "throughput": 7048.52, "total_tokens": 27000832} {"current_steps": 3297, "total_steps": 3345, "loss": 0.1721, "lr": 1.26997870940615e-09, "epoch": 4.928251121076233, "percentage": 98.57, "elapsed_time": "1:03:51", "remaining_time": "0:00:55", "throughput": 7048.52, "total_tokens": 27009024} {"current_steps": 3298, "total_steps": 3345, "loss": 0.2213, "lr": 1.2176226389488953e-09, "epoch": 4.929745889387145, "percentage": 98.59, "elapsed_time": "1:03:53", "remaining_time": "0:00:54", "throughput": 7048.53, "total_tokens": 27017216} {"current_steps": 3299, "total_steps": 3345, "loss": 0.1103, "lr": 1.1663680931681133e-09, "epoch": 4.931240657698057, "percentage": 98.62, "elapsed_time": "1:03:54", "remaining_time": "0:00:53", "throughput": 7048.52, "total_tokens": 27025408} {"current_steps": 3300, "total_steps": 3345, "loss": 0.1091, "lr": 1.1162151172741664e-09, "epoch": 4.932735426008969, "percentage": 98.65, "elapsed_time": "1:03:55", "remaining_time": "0:00:52", "throughput": 7048.53, "total_tokens": 27033600} {"current_steps": 3301, "total_steps": 3345, "loss": 0.1722, "lr": 1.0671637555059733e-09, "epoch": 4.9342301943198805, "percentage": 98.68, "elapsed_time": "1:03:56", "remaining_time": "0:00:51", "throughput": 7048.54, "total_tokens": 27041792} {"current_steps": 3302, "total_steps": 3345, "loss": 0.1222, "lr": 1.0192140511307291e-09, "epoch": 4.935724962630792, "percentage": 98.71, "elapsed_time": "1:03:57", "remaining_time": "0:00:49", "throughput": 7048.54, "total_tokens": 27049984} {"current_steps": 3303, "total_steps": 3345, "loss": 0.1567, "lr": 9.723660464439067e-10, "epoch": 4.937219730941704, "percentage": 98.74, "elapsed_time": "1:03:58", "remaining_time": "0:00:48", "throughput": 7048.54, "total_tokens": 27058176} {"current_steps": 3304, "total_steps": 3345, "loss": 0.1356, "lr": 9.26619782769117e-10, "epoch": 4.938714499252616, "percentage": 98.77, "elapsed_time": "1:03:59", "remaining_time": "0:00:47", "throughput": 7048.54, "total_tokens": 27066368} {"current_steps": 3305, "total_steps": 3345, "loss": 0.3242, "lr": 8.819753004581099e-10, "epoch": 4.940209267563528, "percentage": 98.8, "elapsed_time": "1:04:01", "remaining_time": "0:00:46", "throughput": 7048.54, "total_tokens": 27074560} {"current_steps": 3306, "total_steps": 3345, "loss": 0.066, "lr": 8.384326388910513e-10, "epoch": 4.941704035874439, "percentage": 98.83, "elapsed_time": "1:04:02", "remaining_time": "0:00:45", "throughput": 7048.55, "total_tokens": 27082752} {"current_steps": 3307, "total_steps": 3345, "loss": 0.2121, "lr": 7.959918364756902e-10, "epoch": 4.943198804185351, "percentage": 98.86, "elapsed_time": "1:04:03", "remaining_time": "0:00:44", "throughput": 7048.56, "total_tokens": 27090944} {"current_steps": 3308, "total_steps": 3345, "loss": 0.1684, "lr": 7.546529306483308e-10, "epoch": 4.944693572496263, "percentage": 98.89, "elapsed_time": "1:04:04", "remaining_time": "0:00:43", "throughput": 7048.56, "total_tokens": 27099136} {"current_steps": 3309, "total_steps": 3345, "loss": 0.1707, "lr": 7.144159578732768e-10, "epoch": 4.946188340807175, "percentage": 98.92, "elapsed_time": "1:04:05", "remaining_time": "0:00:41", "throughput": 7048.55, "total_tokens": 27107328} {"current_steps": 3310, "total_steps": 3345, "loss": 0.061, "lr": 6.752809536424154e-10, "epoch": 4.947683109118087, "percentage": 98.95, "elapsed_time": "1:04:06", "remaining_time": "0:00:40", "throughput": 7048.56, "total_tokens": 27115520} {"current_steps": 3311, "total_steps": 3345, "loss": 0.2809, "lr": 6.372479524761888e-10, "epoch": 4.9491778774289985, "percentage": 98.98, "elapsed_time": "1:04:08", "remaining_time": "0:00:39", "throughput": 7048.56, "total_tokens": 27123712} {"current_steps": 3312, "total_steps": 3345, "loss": 0.1653, "lr": 6.003169879226223e-10, "epoch": 4.95067264573991, "percentage": 99.01, "elapsed_time": "1:04:09", "remaining_time": "0:00:38", "throughput": 7048.56, "total_tokens": 27131904} {"current_steps": 3313, "total_steps": 3345, "loss": 0.1966, "lr": 5.644880925577411e-10, "epoch": 4.952167414050822, "percentage": 99.04, "elapsed_time": "1:04:10", "remaining_time": "0:00:37", "throughput": 7048.56, "total_tokens": 27140096} {"current_steps": 3314, "total_steps": 3345, "loss": 0.2977, "lr": 5.297612979852929e-10, "epoch": 4.953662182361734, "percentage": 99.07, "elapsed_time": "1:04:11", "remaining_time": "0:00:36", "throughput": 7048.56, "total_tokens": 27148288} {"current_steps": 3315, "total_steps": 3345, "loss": 0.3974, "lr": 4.961366348374408e-10, "epoch": 4.955156950672646, "percentage": 99.1, "elapsed_time": "1:04:12", "remaining_time": "0:00:34", "throughput": 7048.57, "total_tokens": 27156480} {"current_steps": 3316, "total_steps": 3345, "loss": 0.0745, "lr": 4.6361413277337675e-10, "epoch": 4.956651718983558, "percentage": 99.13, "elapsed_time": "1:04:13", "remaining_time": "0:00:33", "throughput": 7048.57, "total_tokens": 27164672} {"current_steps": 3317, "total_steps": 3345, "loss": 0.2593, "lr": 4.3219382048070856e-10, "epoch": 4.958146487294469, "percentage": 99.16, "elapsed_time": "1:04:15", "remaining_time": "0:00:32", "throughput": 7048.57, "total_tokens": 27172864} {"current_steps": 3318, "total_steps": 3345, "loss": 0.2552, "lr": 4.0187572567476627e-10, "epoch": 4.959641255605381, "percentage": 99.19, "elapsed_time": "1:04:16", "remaining_time": "0:00:31", "throughput": 7048.58, "total_tokens": 27181056} {"current_steps": 3319, "total_steps": 3345, "loss": 0.2621, "lr": 3.726598750981858e-10, "epoch": 4.961136023916293, "percentage": 99.22, "elapsed_time": "1:04:17", "remaining_time": "0:00:30", "throughput": 7048.58, "total_tokens": 27189248} {"current_steps": 3320, "total_steps": 3345, "loss": 0.0111, "lr": 3.4454629452188025e-10, "epoch": 4.962630792227205, "percentage": 99.25, "elapsed_time": "1:04:18", "remaining_time": "0:00:29", "throughput": 7048.58, "total_tokens": 27197440} {"current_steps": 3321, "total_steps": 3345, "loss": 0.2103, "lr": 3.175350087442075e-10, "epoch": 4.9641255605381165, "percentage": 99.28, "elapsed_time": "1:04:19", "remaining_time": "0:00:27", "throughput": 7048.58, "total_tokens": 27205632} {"current_steps": 3322, "total_steps": 3345, "loss": 0.0421, "lr": 2.9162604159124755e-10, "epoch": 4.965620328849028, "percentage": 99.31, "elapsed_time": "1:04:20", "remaining_time": "0:00:26", "throughput": 7048.58, "total_tokens": 27213824} {"current_steps": 3323, "total_steps": 3345, "loss": 0.1929, "lr": 2.6681941591680247e-10, "epoch": 4.96711509715994, "percentage": 99.34, "elapsed_time": "1:04:22", "remaining_time": "0:00:25", "throughput": 7048.58, "total_tokens": 27222016} {"current_steps": 3324, "total_steps": 3345, "loss": 0.2585, "lr": 2.431151536021192e-10, "epoch": 4.968609865470852, "percentage": 99.37, "elapsed_time": "1:04:23", "remaining_time": "0:00:24", "throughput": 7048.58, "total_tokens": 27230208} {"current_steps": 3325, "total_steps": 3345, "loss": 0.2405, "lr": 2.205132755564443e-10, "epoch": 4.970104633781764, "percentage": 99.4, "elapsed_time": "1:04:24", "remaining_time": "0:00:23", "throughput": 7048.59, "total_tokens": 27238400} {"current_steps": 3326, "total_steps": 3345, "loss": 0.0323, "lr": 1.9901380171619134e-10, "epoch": 4.971599402092676, "percentage": 99.43, "elapsed_time": "1:04:25", "remaining_time": "0:00:22", "throughput": 7048.59, "total_tokens": 27246592} {"current_steps": 3327, "total_steps": 3345, "loss": 0.4157, "lr": 1.7861675104577369e-10, "epoch": 4.973094170403588, "percentage": 99.46, "elapsed_time": "1:04:26", "remaining_time": "0:00:20", "throughput": 7048.59, "total_tokens": 27254784} {"current_steps": 3328, "total_steps": 3345, "loss": 0.3112, "lr": 1.5932214153691062e-10, "epoch": 4.974588938714499, "percentage": 99.49, "elapsed_time": "1:04:27", "remaining_time": "0:00:19", "throughput": 7048.59, "total_tokens": 27262976} {"current_steps": 3329, "total_steps": 3345, "loss": 0.1736, "lr": 1.411299902090435e-10, "epoch": 4.976083707025411, "percentage": 99.52, "elapsed_time": "1:04:29", "remaining_time": "0:00:18", "throughput": 7048.6, "total_tokens": 27271168} {"current_steps": 3330, "total_steps": 3345, "loss": 0.3393, "lr": 1.240403131090584e-10, "epoch": 4.977578475336323, "percentage": 99.55, "elapsed_time": "1:04:30", "remaining_time": "0:00:17", "throughput": 7048.59, "total_tokens": 27279360} {"current_steps": 3331, "total_steps": 3345, "loss": 0.0898, "lr": 1.0805312531128598e-10, "epoch": 4.9790732436472345, "percentage": 99.58, "elapsed_time": "1:04:31", "remaining_time": "0:00:16", "throughput": 7048.59, "total_tokens": 27287552} {"current_steps": 3332, "total_steps": 3345, "loss": 0.2285, "lr": 9.316844091791788e-11, "epoch": 4.980568011958146, "percentage": 99.61, "elapsed_time": "1:04:32", "remaining_time": "0:00:15", "throughput": 7048.6, "total_tokens": 27295744} {"current_steps": 3333, "total_steps": 3345, "loss": 0.2452, "lr": 7.938627305817403e-11, "epoch": 4.982062780269058, "percentage": 99.64, "elapsed_time": "1:04:33", "remaining_time": "0:00:13", "throughput": 7048.6, "total_tokens": 27303936} {"current_steps": 3334, "total_steps": 3345, "loss": 0.3044, "lr": 6.670663388913534e-11, "epoch": 4.98355754857997, "percentage": 99.67, "elapsed_time": "1:04:34", "remaining_time": "0:00:12", "throughput": 7048.6, "total_tokens": 27312128} {"current_steps": 3335, "total_steps": 3345, "loss": 0.3056, "lr": 5.5129534595327325e-11, "epoch": 4.985052316890882, "percentage": 99.7, "elapsed_time": "1:04:35", "remaining_time": "0:00:11", "throughput": 7048.6, "total_tokens": 27320320} {"current_steps": 3336, "total_steps": 3345, "loss": 0.284, "lr": 4.465498538858137e-11, "epoch": 4.986547085201794, "percentage": 99.73, "elapsed_time": "1:04:37", "remaining_time": "0:00:10", "throughput": 7048.61, "total_tokens": 27328512} {"current_steps": 3337, "total_steps": 3345, "loss": 0.2688, "lr": 3.528299550817349e-11, "epoch": 4.988041853512706, "percentage": 99.76, "elapsed_time": "1:04:38", "remaining_time": "0:00:09", "throughput": 7048.6, "total_tokens": 27336704} {"current_steps": 3338, "total_steps": 3345, "loss": 0.2322, "lr": 2.7013573221101875e-11, "epoch": 4.989536621823618, "percentage": 99.79, "elapsed_time": "1:04:39", "remaining_time": "0:00:08", "throughput": 7048.6, "total_tokens": 27344896} {"current_steps": 3339, "total_steps": 3345, "loss": 0.2131, "lr": 1.9846725821531797e-11, "epoch": 4.991031390134529, "percentage": 99.82, "elapsed_time": "1:04:40", "remaining_time": "0:00:06", "throughput": 7048.6, "total_tokens": 27353088} {"current_steps": 3340, "total_steps": 3345, "loss": 0.2778, "lr": 1.378245963135072e-11, "epoch": 4.9925261584454415, "percentage": 99.85, "elapsed_time": "1:04:41", "remaining_time": "0:00:05", "throughput": 7048.6, "total_tokens": 27361280} {"current_steps": 3341, "total_steps": 3345, "loss": 0.1714, "lr": 8.820779999474394e-12, "epoch": 4.9940209267563525, "percentage": 99.88, "elapsed_time": "1:04:42", "remaining_time": "0:00:04", "throughput": 7048.61, "total_tokens": 27369472} {"current_steps": 3342, "total_steps": 3345, "loss": 0.2328, "lr": 4.961691302679539e-12, "epoch": 4.995515695067264, "percentage": 99.91, "elapsed_time": "1:04:44", "remaining_time": "0:00:03", "throughput": 7048.61, "total_tokens": 27377664} {"current_steps": 3343, "total_steps": 3345, "loss": 0.3117, "lr": 2.2051969450487265e-12, "epoch": 4.997010463378176, "percentage": 99.94, "elapsed_time": "1:04:45", "remaining_time": "0:00:02", "throughput": 7048.62, "total_tokens": 27385856} {"current_steps": 3344, "total_steps": 3345, "loss": 0.2151, "lr": 5.512993578316029e-13, "epoch": 4.998505231689088, "percentage": 99.97, "elapsed_time": "1:04:46", "remaining_time": "0:00:01", "throughput": 7048.63, "total_tokens": 27394048} {"current_steps": 3345, "total_steps": 3345, "loss": 0.107, "lr": 0.0, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "1:04:47", "remaining_time": "0:00:00", "throughput": 7048.66, "total_tokens": 27402240}