Training in progress, epoch 4

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:852696bef8cffe46211dcbe688cb3ea678cdb5888f07348f38681e20f3580ed8
+oid sha256:2519d8c385afd280382c7ac69fe958f9cf2ff4181853b8b9b8e01b0b40a52970
 size 4877660776

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a9be627d076f1cb84f9c713e424106266338c1c39e6b7af67ae726212e3470d
+oid sha256:908f4f77036fb0ad1e80dc575647227fefa9ca406d83d77bb9d2b9bb4a8517c7
 size 4932751008

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6baedfb987436144866d8b287f3cad4f32c39f82d4fad14d1385149a27922f01
+oid sha256:e24f631fcff5c9de32fcf9e2233bd27e7d3b308aaf34972f7ed65c75a83f7981
 size 4330865200

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d7f133f86cacca177607166236c1cebc4fc11a0e57669c1a4c490ee16796678
+oid sha256:f3de0fdb8c2adc0bd98507df788cea8d50a0ab5577d8280111f4b7e2226f77f4
 size 1089994880

trainer_log.jsonl

@@ -242,3 +242,83 @@
 {"current_steps": 242, "total_steps": 390, "loss": 0.1696, "lr": 1.5126831694287564e-05, "epoch": 3.0926517571884986, "percentage": 62.05, "elapsed_time": "1:13:27", "remaining_time": "0:44:55"}
 {"current_steps": 243, "total_steps": 390, "loss": 0.1992, "lr": 1.4953416182715566e-05, "epoch": 3.1054313099041533, "percentage": 62.31, "elapsed_time": "1:13:46", "remaining_time": "0:44:37"}
 {"current_steps": 244, "total_steps": 390, "loss": 0.1906, "lr": 1.478040494913926e-05, "epoch": 3.1182108626198084, "percentage": 62.56, "elapsed_time": "1:14:03", "remaining_time": "0:44:18"}
+{"current_steps": 245, "total_steps": 390, "loss": 0.2129, "lr": 1.460781185335713e-05, "epoch": 3.130990415335463, "percentage": 62.82, "elapsed_time": "1:14:23", "remaining_time": "0:44:01"}
+{"current_steps": 246, "total_steps": 390, "loss": 0.1978, "lr": 1.443565072167095e-05, "epoch": 3.143769968051118, "percentage": 63.08, "elapsed_time": "1:14:44", "remaining_time": "0:43:45"}
+{"current_steps": 247, "total_steps": 390, "loss": 0.1865, "lr": 1.4263935345778202e-05, "epoch": 3.1565495207667733, "percentage": 63.33, "elapsed_time": "1:15:00", "remaining_time": "0:43:25"}
+{"current_steps": 248, "total_steps": 390, "loss": 0.2018, "lr": 1.409267948166718e-05, "epoch": 3.169329073482428, "percentage": 63.59, "elapsed_time": "1:15:20", "remaining_time": "0:43:08"}
+{"current_steps": 249, "total_steps": 390, "loss": 0.209, "lr": 1.3921896848515064e-05, "epoch": 3.182108626198083, "percentage": 63.85, "elapsed_time": "1:15:34", "remaining_time": "0:42:47"}
+{"current_steps": 250, "total_steps": 390, "loss": 0.226, "lr": 1.3751601127588849e-05, "epoch": 3.194888178913738, "percentage": 64.1, "elapsed_time": "1:15:48", "remaining_time": "0:42:27"}
+{"current_steps": 251, "total_steps": 390, "loss": 0.1875, "lr": 1.3581805961149371e-05, "epoch": 3.207667731629393, "percentage": 64.36, "elapsed_time": "1:16:04", "remaining_time": "0:42:07"}
+{"current_steps": 252, "total_steps": 390, "loss": 0.178, "lr": 1.341252495135841e-05, "epoch": 3.220447284345048, "percentage": 64.62, "elapsed_time": "1:16:22", "remaining_time": "0:41:49"}
+{"current_steps": 253, "total_steps": 390, "loss": 0.2084, "lr": 1.324377165918906e-05, "epoch": 3.2332268370607027, "percentage": 64.87, "elapsed_time": "1:16:43", "remaining_time": "0:41:32"}
+{"current_steps": 254, "total_steps": 390, "loss": 0.1705, "lr": 1.3075559603339354e-05, "epoch": 3.246006389776358, "percentage": 65.13, "elapsed_time": "1:16:57", "remaining_time": "0:41:12"}
+{"current_steps": 255, "total_steps": 390, "loss": 0.2058, "lr": 1.2907902259149287e-05, "epoch": 3.258785942492013, "percentage": 65.38, "elapsed_time": "1:17:12", "remaining_time": "0:40:52"}
+{"current_steps": 256, "total_steps": 390, "loss": 0.1958, "lr": 1.274081305752135e-05, "epoch": 3.2715654952076676, "percentage": 65.64, "elapsed_time": "1:17:31", "remaining_time": "0:40:34"}
+{"current_steps": 257, "total_steps": 390, "loss": 0.2059, "lr": 1.2574305383844528e-05, "epoch": 3.2843450479233227, "percentage": 65.9, "elapsed_time": "1:17:48", "remaining_time": "0:40:15"}
+{"current_steps": 258, "total_steps": 390, "loss": 0.2098, "lr": 1.2408392576922075e-05, "epoch": 3.297124600638978, "percentage": 66.15, "elapsed_time": "1:18:07", "remaining_time": "0:39:58"}
+{"current_steps": 259, "total_steps": 390, "loss": 0.2376, "lr": 1.2243087927902905e-05, "epoch": 3.3099041533546325, "percentage": 66.41, "elapsed_time": "1:18:26", "remaining_time": "0:39:40"}
+{"current_steps": 260, "total_steps": 390, "loss": 0.1694, "lr": 1.2078404679216864e-05, "epoch": 3.3226837060702876, "percentage": 66.67, "elapsed_time": "1:18:42", "remaining_time": "0:39:21"}
+{"current_steps": 261, "total_steps": 390, "loss": 0.1976, "lr": 1.1914356023513904e-05, "epoch": 3.3354632587859427, "percentage": 66.92, "elapsed_time": "1:18:56", "remaining_time": "0:39:01"}
+{"current_steps": 262, "total_steps": 390, "loss": 0.2217, "lr": 1.1750955102607193e-05, "epoch": 3.3482428115015974, "percentage": 67.18, "elapsed_time": "1:19:10", "remaining_time": "0:38:40"}
+{"current_steps": 263, "total_steps": 390, "loss": 0.1818, "lr": 1.1588215006420374e-05, "epoch": 3.3610223642172525, "percentage": 67.44, "elapsed_time": "1:19:25", "remaining_time": "0:38:21"}
+{"current_steps": 264, "total_steps": 390, "loss": 0.2124, "lr": 1.1426148771938915e-05, "epoch": 3.373801916932907, "percentage": 67.69, "elapsed_time": "1:19:41", "remaining_time": "0:38:02"}
+{"current_steps": 265, "total_steps": 390, "loss": 0.1761, "lr": 1.1264769382165748e-05, "epoch": 3.3865814696485623, "percentage": 67.95, "elapsed_time": "1:19:57", "remaining_time": "0:37:42"}
+{"current_steps": 266, "total_steps": 390, "loss": 0.1937, "lr": 1.110408976508118e-05, "epoch": 3.3993610223642174, "percentage": 68.21, "elapsed_time": "1:20:18", "remaining_time": "0:37:26"}
+{"current_steps": 267, "total_steps": 390, "loss": 0.1983, "lr": 1.094412279260726e-05, "epoch": 3.412140575079872, "percentage": 68.46, "elapsed_time": "1:20:37", "remaining_time": "0:37:08"}
+{"current_steps": 268, "total_steps": 390, "loss": 0.1906, "lr": 1.0784881279576635e-05, "epoch": 3.4249201277955272, "percentage": 68.72, "elapsed_time": "1:20:55", "remaining_time": "0:36:50"}
+{"current_steps": 269, "total_steps": 390, "loss": 0.2081, "lr": 1.0626377982705929e-05, "epoch": 3.437699680511182, "percentage": 68.97, "elapsed_time": "1:21:10", "remaining_time": "0:36:30"}
+{"current_steps": 270, "total_steps": 390, "loss": 0.1895, "lr": 1.0468625599573842e-05, "epoch": 3.450479233226837, "percentage": 69.23, "elapsed_time": "1:21:29", "remaining_time": "0:36:12"}
+{"current_steps": 271, "total_steps": 390, "loss": 0.189, "lr": 1.0311636767603952e-05, "epoch": 3.463258785942492, "percentage": 69.49, "elapsed_time": "1:21:41", "remaining_time": "0:35:52"}
+{"current_steps": 272, "total_steps": 390, "loss": 0.1834, "lr": 1.0155424063052306e-05, "epoch": 3.476038338658147, "percentage": 69.74, "elapsed_time": "1:21:58", "remaining_time": "0:35:33"}
+{"current_steps": 273, "total_steps": 390, "loss": 0.214, "lr": 1.0000000000000006e-05, "epoch": 3.488817891373802, "percentage": 70.0, "elapsed_time": "1:22:14", "remaining_time": "0:35:14"}
+{"current_steps": 274, "total_steps": 390, "loss": 0.1585, "lr": 9.84537702935065e-06, "epoch": 3.501597444089457, "percentage": 70.26, "elapsed_time": "1:22:26", "remaining_time": "0:34:54"}
+{"current_steps": 275, "total_steps": 390, "loss": 0.2098, "lr": 9.691567537832964e-06, "epoch": 3.5143769968051117, "percentage": 70.51, "elapsed_time": "1:22:42", "remaining_time": "0:34:35"}
+{"current_steps": 276, "total_steps": 390, "loss": 0.2042, "lr": 9.538583847008452e-06, "epoch": 3.527156549520767, "percentage": 70.77, "elapsed_time": "1:22:58", "remaining_time": "0:34:16"}
+{"current_steps": 277, "total_steps": 390, "loss": 0.1823, "lr": 9.386438212284372e-06, "epoch": 3.539936102236422, "percentage": 71.03, "elapsed_time": "1:23:13", "remaining_time": "0:33:56"}
+{"current_steps": 278, "total_steps": 390, "loss": 0.1604, "lr": 9.235142821931928e-06, "epoch": 3.5527156549520766, "percentage": 71.28, "elapsed_time": "1:23:26", "remaining_time": "0:33:36"}
+{"current_steps": 279, "total_steps": 390, "loss": 0.1696, "lr": 9.084709796109907e-06, "epoch": 3.5654952076677318, "percentage": 71.54, "elapsed_time": "1:23:44", "remaining_time": "0:33:19"}
+{"current_steps": 280, "total_steps": 390, "loss": 0.2058, "lr": 8.93515118589373e-06, "epoch": 3.5782747603833864, "percentage": 71.79, "elapsed_time": "1:24:03", "remaining_time": "0:33:01"}
+{"current_steps": 281, "total_steps": 390, "loss": 0.1898, "lr": 8.786478972310023e-06, "epoch": 3.5910543130990416, "percentage": 72.05, "elapsed_time": "1:24:16", "remaining_time": "0:32:41"}
+{"current_steps": 282, "total_steps": 390, "loss": 0.2277, "lr": 8.638705065376887e-06, "epoch": 3.6038338658146962, "percentage": 72.31, "elapsed_time": "1:24:33", "remaining_time": "0:32:22"}
+{"current_steps": 283, "total_steps": 390, "loss": 0.2038, "lr": 8.491841303149728e-06, "epoch": 3.6166134185303513, "percentage": 72.56, "elapsed_time": "1:24:51", "remaining_time": "0:32:04"}
+{"current_steps": 284, "total_steps": 390, "loss": 0.1912, "lr": 8.345899450772975e-06, "epoch": 3.6293929712460065, "percentage": 72.82, "elapsed_time": "1:25:10", "remaining_time": "0:31:47"}
+{"current_steps": 285, "total_steps": 390, "loss": 0.1589, "lr": 8.200891199537549e-06, "epoch": 3.642172523961661, "percentage": 73.08, "elapsed_time": "1:25:26", "remaining_time": "0:31:28"}
+{"current_steps": 286, "total_steps": 390, "loss": 0.1978, "lr": 8.056828165944282e-06, "epoch": 3.6549520766773163, "percentage": 73.33, "elapsed_time": "1:25:41", "remaining_time": "0:31:09"}
+{"current_steps": 287, "total_steps": 390, "loss": 0.1989, "lr": 7.913721890773354e-06, "epoch": 3.6677316293929714, "percentage": 73.59, "elapsed_time": "1:25:55", "remaining_time": "0:30:50"}
+{"current_steps": 288, "total_steps": 390, "loss": 0.2057, "lr": 7.771583838159756e-06, "epoch": 3.680511182108626, "percentage": 73.85, "elapsed_time": "1:26:14", "remaining_time": "0:30:32"}
+{"current_steps": 289, "total_steps": 390, "loss": 0.2062, "lr": 7.630425394674903e-06, "epoch": 3.693290734824281, "percentage": 74.1, "elapsed_time": "1:26:30", "remaining_time": "0:30:14"}
+{"current_steps": 290, "total_steps": 390, "loss": 0.2177, "lr": 7.49025786841445e-06, "epoch": 3.7060702875399363, "percentage": 74.36, "elapsed_time": "1:26:48", "remaining_time": "0:29:56"}
+{"current_steps": 291, "total_steps": 390, "loss": 0.1732, "lr": 7.3510924880924575e-06, "epoch": 3.718849840255591, "percentage": 74.62, "elapsed_time": "1:27:01", "remaining_time": "0:29:36"}
+{"current_steps": 292, "total_steps": 390, "loss": 0.1873, "lr": 7.212940402141808e-06, "epoch": 3.731629392971246, "percentage": 74.87, "elapsed_time": "1:27:19", "remaining_time": "0:29:18"}
+{"current_steps": 293, "total_steps": 390, "loss": 0.1837, "lr": 7.075812677821145e-06, "epoch": 3.744408945686901, "percentage": 75.13, "elapsed_time": "1:27:35", "remaining_time": "0:28:59"}
+{"current_steps": 294, "total_steps": 390, "loss": 0.2002, "lr": 6.939720300328303e-06, "epoch": 3.757188498402556, "percentage": 75.38, "elapsed_time": "1:27:54", "remaining_time": "0:28:42"}
+{"current_steps": 295, "total_steps": 390, "loss": 0.1959, "lr": 6.8046741719202385e-06, "epoch": 3.769968051118211, "percentage": 75.64, "elapsed_time": "1:28:15", "remaining_time": "0:28:25"}
+{"current_steps": 296, "total_steps": 390, "loss": 0.1789, "lr": 6.67068511103971e-06, "epoch": 3.7827476038338657, "percentage": 75.9, "elapsed_time": "1:28:30", "remaining_time": "0:28:06"}
+{"current_steps": 297, "total_steps": 390, "loss": 0.1707, "lr": 6.537763851448593e-06, "epoch": 3.7955271565495208, "percentage": 76.15, "elapsed_time": "1:28:46", "remaining_time": "0:27:47"}
+{"current_steps": 298, "total_steps": 390, "loss": 0.1819, "lr": 6.4059210413680175e-06, "epoch": 3.8083067092651754, "percentage": 76.41, "elapsed_time": "1:29:00", "remaining_time": "0:27:28"}
+{"current_steps": 299, "total_steps": 390, "loss": 0.2039, "lr": 6.275167242625331e-06, "epoch": 3.8210862619808306, "percentage": 76.67, "elapsed_time": "1:29:16", "remaining_time": "0:27:10"}
+{"current_steps": 300, "total_steps": 390, "loss": 0.1827, "lr": 6.145512929808013e-06, "epoch": 3.8338658146964857, "percentage": 76.92, "elapsed_time": "1:29:31", "remaining_time": "0:26:51"}
+{"current_steps": 301, "total_steps": 390, "loss": 0.2014, "lr": 6.016968489424572e-06, "epoch": 3.8466453674121404, "percentage": 77.18, "elapsed_time": "1:29:47", "remaining_time": "0:26:32"}
+{"current_steps": 302, "total_steps": 390, "loss": 0.1957, "lr": 5.889544219072465e-06, "epoch": 3.8594249201277955, "percentage": 77.44, "elapsed_time": "1:30:02", "remaining_time": "0:26:14"}
+{"current_steps": 303, "total_steps": 390, "loss": 0.1858, "lr": 5.7632503266131925e-06, "epoch": 3.8722044728434506, "percentage": 77.69, "elapsed_time": "1:30:17", "remaining_time": "0:25:55"}
+{"current_steps": 304, "total_steps": 390, "loss": 0.2017, "lr": 5.638096929354522e-06, "epoch": 3.8849840255591053, "percentage": 77.95, "elapsed_time": "1:30:33", "remaining_time": "0:25:36"}
+{"current_steps": 305, "total_steps": 390, "loss": 0.1959, "lr": 5.514094053240035e-06, "epoch": 3.8977635782747604, "percentage": 78.21, "elapsed_time": "1:30:50", "remaining_time": "0:25:18"}
+{"current_steps": 306, "total_steps": 390, "loss": 0.1862, "lr": 5.39125163204594e-06, "epoch": 3.9105431309904155, "percentage": 78.46, "elapsed_time": "1:31:04", "remaining_time": "0:25:00"}
+{"current_steps": 307, "total_steps": 390, "loss": 0.2253, "lr": 5.269579506585259e-06, "epoch": 3.92332268370607, "percentage": 78.72, "elapsed_time": "1:31:19", "remaining_time": "0:24:41"}
+{"current_steps": 308, "total_steps": 390, "loss": 0.1802, "lr": 5.149087423919541e-06, "epoch": 3.9361022364217253, "percentage": 78.97, "elapsed_time": "1:31:39", "remaining_time": "0:24:24"}
+{"current_steps": 309, "total_steps": 390, "loss": 0.1976, "lr": 5.029785036577976e-06, "epoch": 3.9488817891373804, "percentage": 79.23, "elapsed_time": "1:31:56", "remaining_time": "0:24:06"}
+{"current_steps": 310, "total_steps": 390, "loss": 0.184, "lr": 4.911681901784198e-06, "epoch": 3.961661341853035, "percentage": 79.49, "elapsed_time": "1:32:14", "remaining_time": "0:23:48"}
+{"current_steps": 311, "total_steps": 390, "loss": 0.1925, "lr": 4.794787480690597e-06, "epoch": 3.97444089456869, "percentage": 79.74, "elapsed_time": "1:32:31", "remaining_time": "0:23:30"}
+{"current_steps": 312, "total_steps": 390, "loss": 0.2046, "lr": 4.679111137620442e-06, "epoch": 3.987220447284345, "percentage": 80.0, "elapsed_time": "1:32:48", "remaining_time": "0:23:12"}
+{"current_steps": 313, "total_steps": 390, "loss": 0.1694, "lr": 4.5646621393177e-06, "epoch": 4.0, "percentage": 80.26, "elapsed_time": "1:33:02", "remaining_time": "0:22:53"}
+{"current_steps": 314, "total_steps": 390, "loss": 0.1533, "lr": 4.451449654204685e-06, "epoch": 4.012779552715655, "percentage": 80.51, "elapsed_time": "1:36:07", "remaining_time": "0:23:15"}
+{"current_steps": 315, "total_steps": 390, "loss": 0.1668, "lr": 4.339482751647557e-06, "epoch": 4.02555910543131, "percentage": 80.77, "elapsed_time": "1:36:22", "remaining_time": "0:22:56"}
+{"current_steps": 316, "total_steps": 390, "loss": 0.1443, "lr": 4.228770401229824e-06, "epoch": 4.038338658146965, "percentage": 81.03, "elapsed_time": "1:36:39", "remaining_time": "0:22:37"}
+{"current_steps": 317, "total_steps": 390, "loss": 0.1268, "lr": 4.119321472033779e-06, "epoch": 4.05111821086262, "percentage": 81.28, "elapsed_time": "1:36:53", "remaining_time": "0:22:18"}
+{"current_steps": 318, "total_steps": 390, "loss": 0.1425, "lr": 4.011144731929981e-06, "epoch": 4.063897763578275, "percentage": 81.54, "elapsed_time": "1:37:09", "remaining_time": "0:21:59"}
+{"current_steps": 319, "total_steps": 390, "loss": 0.1484, "lr": 3.904248846874894e-06, "epoch": 4.07667731629393, "percentage": 81.79, "elapsed_time": "1:37:23", "remaining_time": "0:21:40"}
+{"current_steps": 320, "total_steps": 390, "loss": 0.1675, "lr": 3.7986423802166705e-06, "epoch": 4.0894568690095845, "percentage": 82.05, "elapsed_time": "1:37:41", "remaining_time": "0:21:22"}
+{"current_steps": 321, "total_steps": 390, "loss": 0.1514, "lr": 3.694333792009115e-06, "epoch": 4.102236421725239, "percentage": 82.31, "elapsed_time": "1:37:59", "remaining_time": "0:21:03"}
+{"current_steps": 322, "total_steps": 390, "loss": 0.1448, "lr": 3.5913314383339937e-06, "epoch": 4.115015974440895, "percentage": 82.56, "elapsed_time": "1:38:19", "remaining_time": "0:20:45"}
+{"current_steps": 323, "total_steps": 390, "loss": 0.139, "lr": 3.4896435706316e-06, "epoch": 4.127795527156549, "percentage": 82.82, "elapsed_time": "1:38:34", "remaining_time": "0:20:26"}
+{"current_steps": 324, "total_steps": 390, "loss": 0.1428, "lr": 3.3892783350397675e-06, "epoch": 4.140575079872204, "percentage": 83.08, "elapsed_time": "1:38:49", "remaining_time": "0:20:07"}