Training in progress, epoch 4

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3ad96d700520ea3fc21d366cbcff886dbef3794e8eebb56788fa15ccff5a87d
+oid sha256:037f873343b01dba24025639beaeb77c33f50c5427252223c1c0778e799b4869
 size 4877660776

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fc6005eb07c93ce351d9e99888f2355cb24db44f55498cd32fcb70bfced480f
+oid sha256:a3687e1a8d6a257ebff71632b868c847bcccb9c56cb20bb156b1380717cea386
 size 4932751008

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de218256d8e4196b52b23344c3a2631299230267ef201150562408e13a677958
+oid sha256:8289a4b2055f25844c2e9bab20b107537be5eedd34e4491f7256e114a18b07a1
 size 4330865200

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:115673f738d89664ac0a10bc0be5bc0e2416286c7af3c83ef4cab3f841f4240e
+oid sha256:868a083559300abadda42b67a726de0af124fb035cb113f1b1b1b2b45eccb081
 size 1089994880

trainer_log.jsonl

@@ -240,3 +240,82 @@
 {"current_steps": 240, "total_steps": 390, "loss": 0.3711, "lr": 1.547481995140556e-05, "epoch": 3.0670926517571884, "percentage": 61.54, "elapsed_time": "1:37:50", "remaining_time": "1:01:09"}
 {"current_steps": 241, "total_steps": 390, "loss": 0.3895, "lr": 1.5300637591670357e-05, "epoch": 3.0798722044728435, "percentage": 61.79, "elapsed_time": "1:38:13", "remaining_time": "1:00:43"}
 {"current_steps": 242, "total_steps": 390, "loss": 0.3781, "lr": 1.5126831694287564e-05, "epoch": 3.0926517571884986, "percentage": 62.05, "elapsed_time": "1:38:36", "remaining_time": "1:00:18"}
+{"current_steps": 243, "total_steps": 390, "loss": 0.3944, "lr": 1.4953416182715566e-05, "epoch": 3.1054313099041533, "percentage": 62.31, "elapsed_time": "1:38:58", "remaining_time": "0:59:52"}
+{"current_steps": 244, "total_steps": 390, "loss": 0.3939, "lr": 1.478040494913926e-05, "epoch": 3.1182108626198084, "percentage": 62.56, "elapsed_time": "1:39:21", "remaining_time": "0:59:26"}
+{"current_steps": 245, "total_steps": 390, "loss": 0.3852, "lr": 1.460781185335713e-05, "epoch": 3.130990415335463, "percentage": 62.82, "elapsed_time": "1:39:44", "remaining_time": "0:59:01"}
+{"current_steps": 246, "total_steps": 390, "loss": 0.3671, "lr": 1.443565072167095e-05, "epoch": 3.143769968051118, "percentage": 63.08, "elapsed_time": "1:40:06", "remaining_time": "0:58:36"}
+{"current_steps": 247, "total_steps": 390, "loss": 0.3783, "lr": 1.4263935345778202e-05, "epoch": 3.1565495207667733, "percentage": 63.33, "elapsed_time": "1:40:29", "remaining_time": "0:58:10"}
+{"current_steps": 248, "total_steps": 390, "loss": 0.3954, "lr": 1.409267948166718e-05, "epoch": 3.169329073482428, "percentage": 63.59, "elapsed_time": "1:40:51", "remaining_time": "0:57:45"}
+{"current_steps": 249, "total_steps": 390, "loss": 0.3911, "lr": 1.3921896848515064e-05, "epoch": 3.182108626198083, "percentage": 63.85, "elapsed_time": "1:41:14", "remaining_time": "0:57:19"}
+{"current_steps": 250, "total_steps": 390, "loss": 0.3864, "lr": 1.3751601127588849e-05, "epoch": 3.194888178913738, "percentage": 64.1, "elapsed_time": "1:41:38", "remaining_time": "0:56:54"}
+{"current_steps": 251, "total_steps": 390, "loss": 0.3896, "lr": 1.3581805961149371e-05, "epoch": 3.207667731629393, "percentage": 64.36, "elapsed_time": "1:42:02", "remaining_time": "0:56:30"}
+{"current_steps": 252, "total_steps": 390, "loss": 0.3662, "lr": 1.341252495135841e-05, "epoch": 3.220447284345048, "percentage": 64.62, "elapsed_time": "1:42:24", "remaining_time": "0:56:04"}
+{"current_steps": 253, "total_steps": 390, "loss": 0.3907, "lr": 1.324377165918906e-05, "epoch": 3.2332268370607027, "percentage": 64.87, "elapsed_time": "1:42:47", "remaining_time": "0:55:39"}
+{"current_steps": 254, "total_steps": 390, "loss": 0.3747, "lr": 1.3075559603339354e-05, "epoch": 3.246006389776358, "percentage": 65.13, "elapsed_time": "1:43:10", "remaining_time": "0:55:14"}
+{"current_steps": 255, "total_steps": 390, "loss": 0.388, "lr": 1.2907902259149287e-05, "epoch": 3.258785942492013, "percentage": 65.38, "elapsed_time": "1:43:32", "remaining_time": "0:54:48"}
+{"current_steps": 256, "total_steps": 390, "loss": 0.3653, "lr": 1.274081305752135e-05, "epoch": 3.2715654952076676, "percentage": 65.64, "elapsed_time": "1:43:56", "remaining_time": "0:54:24"}
+{"current_steps": 257, "total_steps": 390, "loss": 0.3739, "lr": 1.2574305383844528e-05, "epoch": 3.2843450479233227, "percentage": 65.9, "elapsed_time": "1:44:19", "remaining_time": "0:53:59"}
+{"current_steps": 258, "total_steps": 390, "loss": 0.3629, "lr": 1.2408392576922075e-05, "epoch": 3.297124600638978, "percentage": 66.15, "elapsed_time": "1:44:42", "remaining_time": "0:53:34"}
+{"current_steps": 259, "total_steps": 390, "loss": 0.3817, "lr": 1.2243087927902905e-05, "epoch": 3.3099041533546325, "percentage": 66.41, "elapsed_time": "1:45:06", "remaining_time": "0:53:09"}
+{"current_steps": 260, "total_steps": 390, "loss": 0.3495, "lr": 1.2078404679216864e-05, "epoch": 3.3226837060702876, "percentage": 66.67, "elapsed_time": "1:45:28", "remaining_time": "0:52:44"}
+{"current_steps": 261, "total_steps": 390, "loss": 0.3641, "lr": 1.1914356023513904e-05, "epoch": 3.3354632587859427, "percentage": 66.92, "elapsed_time": "1:45:50", "remaining_time": "0:52:18"}
+{"current_steps": 262, "total_steps": 390, "loss": 0.3587, "lr": 1.1750955102607193e-05, "epoch": 3.3482428115015974, "percentage": 67.18, "elapsed_time": "1:46:12", "remaining_time": "0:51:53"}
+{"current_steps": 263, "total_steps": 390, "loss": 0.3833, "lr": 1.1588215006420374e-05, "epoch": 3.3610223642172525, "percentage": 67.44, "elapsed_time": "1:46:35", "remaining_time": "0:51:28"}
+{"current_steps": 264, "total_steps": 390, "loss": 0.3752, "lr": 1.1426148771938915e-05, "epoch": 3.373801916932907, "percentage": 67.69, "elapsed_time": "1:46:58", "remaining_time": "0:51:03"}
+{"current_steps": 265, "total_steps": 390, "loss": 0.3647, "lr": 1.1264769382165748e-05, "epoch": 3.3865814696485623, "percentage": 67.95, "elapsed_time": "1:47:20", "remaining_time": "0:50:38"}
+{"current_steps": 266, "total_steps": 390, "loss": 0.3748, "lr": 1.110408976508118e-05, "epoch": 3.3993610223642174, "percentage": 68.21, "elapsed_time": "1:47:44", "remaining_time": "0:50:13"}
+{"current_steps": 267, "total_steps": 390, "loss": 0.3638, "lr": 1.094412279260726e-05, "epoch": 3.412140575079872, "percentage": 68.46, "elapsed_time": "1:48:06", "remaining_time": "0:49:48"}
+{"current_steps": 268, "total_steps": 390, "loss": 0.3846, "lr": 1.0784881279576635e-05, "epoch": 3.4249201277955272, "percentage": 68.72, "elapsed_time": "1:48:30", "remaining_time": "0:49:23"}
+{"current_steps": 269, "total_steps": 390, "loss": 0.386, "lr": 1.0626377982705929e-05, "epoch": 3.437699680511182, "percentage": 68.97, "elapsed_time": "1:48:52", "remaining_time": "0:48:58"}
+{"current_steps": 270, "total_steps": 390, "loss": 0.3826, "lr": 1.0468625599573842e-05, "epoch": 3.450479233226837, "percentage": 69.23, "elapsed_time": "1:49:15", "remaining_time": "0:48:33"}
+{"current_steps": 271, "total_steps": 390, "loss": 0.3897, "lr": 1.0311636767603952e-05, "epoch": 3.463258785942492, "percentage": 69.49, "elapsed_time": "1:49:39", "remaining_time": "0:48:08"}
+{"current_steps": 272, "total_steps": 390, "loss": 0.397, "lr": 1.0155424063052306e-05, "epoch": 3.476038338658147, "percentage": 69.74, "elapsed_time": "1:50:02", "remaining_time": "0:47:44"}
+{"current_steps": 273, "total_steps": 390, "loss": 0.371, "lr": 1.0000000000000006e-05, "epoch": 3.488817891373802, "percentage": 70.0, "elapsed_time": "1:50:25", "remaining_time": "0:47:19"}
+{"current_steps": 274, "total_steps": 390, "loss": 0.3627, "lr": 9.84537702935065e-06, "epoch": 3.501597444089457, "percentage": 70.26, "elapsed_time": "1:50:47", "remaining_time": "0:46:54"}
+{"current_steps": 275, "total_steps": 390, "loss": 0.3752, "lr": 9.691567537832964e-06, "epoch": 3.5143769968051117, "percentage": 70.51, "elapsed_time": "1:51:09", "remaining_time": "0:46:29"}
+{"current_steps": 276, "total_steps": 390, "loss": 0.3562, "lr": 9.538583847008452e-06, "epoch": 3.527156549520767, "percentage": 70.77, "elapsed_time": "1:51:32", "remaining_time": "0:46:04"}
+{"current_steps": 277, "total_steps": 390, "loss": 0.4091, "lr": 9.386438212284372e-06, "epoch": 3.539936102236422, "percentage": 71.03, "elapsed_time": "1:51:54", "remaining_time": "0:45:39"}
+{"current_steps": 278, "total_steps": 390, "loss": 0.3836, "lr": 9.235142821931928e-06, "epoch": 3.5527156549520766, "percentage": 71.28, "elapsed_time": "1:52:17", "remaining_time": "0:45:14"}
+{"current_steps": 279, "total_steps": 390, "loss": 0.3959, "lr": 9.084709796109907e-06, "epoch": 3.5654952076677318, "percentage": 71.54, "elapsed_time": "1:52:40", "remaining_time": "0:44:49"}
+{"current_steps": 280, "total_steps": 390, "loss": 0.385, "lr": 8.93515118589373e-06, "epoch": 3.5782747603833864, "percentage": 71.79, "elapsed_time": "1:53:03", "remaining_time": "0:44:24"}
+{"current_steps": 281, "total_steps": 390, "loss": 0.4043, "lr": 8.786478972310023e-06, "epoch": 3.5910543130990416, "percentage": 72.05, "elapsed_time": "1:53:27", "remaining_time": "0:44:00"}
+{"current_steps": 282, "total_steps": 390, "loss": 0.404, "lr": 8.638705065376887e-06, "epoch": 3.6038338658146962, "percentage": 72.31, "elapsed_time": "1:53:50", "remaining_time": "0:43:35"}
+{"current_steps": 283, "total_steps": 390, "loss": 0.4024, "lr": 8.491841303149728e-06, "epoch": 3.6166134185303513, "percentage": 72.56, "elapsed_time": "1:54:14", "remaining_time": "0:43:11"}
+{"current_steps": 284, "total_steps": 390, "loss": 0.3756, "lr": 8.345899450772975e-06, "epoch": 3.6293929712460065, "percentage": 72.82, "elapsed_time": "1:54:36", "remaining_time": "0:42:46"}
+{"current_steps": 285, "total_steps": 390, "loss": 0.3759, "lr": 8.200891199537549e-06, "epoch": 3.642172523961661, "percentage": 73.08, "elapsed_time": "1:54:59", "remaining_time": "0:42:21"}
+{"current_steps": 286, "total_steps": 390, "loss": 0.3892, "lr": 8.056828165944282e-06, "epoch": 3.6549520766773163, "percentage": 73.33, "elapsed_time": "1:55:22", "remaining_time": "0:41:57"}
+{"current_steps": 287, "total_steps": 390, "loss": 0.3755, "lr": 7.913721890773354e-06, "epoch": 3.6677316293929714, "percentage": 73.59, "elapsed_time": "1:55:44", "remaining_time": "0:41:32"}
+{"current_steps": 288, "total_steps": 390, "loss": 0.3813, "lr": 7.771583838159756e-06, "epoch": 3.680511182108626, "percentage": 73.85, "elapsed_time": "1:56:07", "remaining_time": "0:41:07"}
+{"current_steps": 289, "total_steps": 390, "loss": 0.3971, "lr": 7.630425394674903e-06, "epoch": 3.693290734824281, "percentage": 74.1, "elapsed_time": "1:56:30", "remaining_time": "0:40:42"}
+{"current_steps": 290, "total_steps": 390, "loss": 0.412, "lr": 7.49025786841445e-06, "epoch": 3.7060702875399363, "percentage": 74.36, "elapsed_time": "1:56:53", "remaining_time": "0:40:18"}
+{"current_steps": 291, "total_steps": 390, "loss": 0.3821, "lr": 7.3510924880924575e-06, "epoch": 3.718849840255591, "percentage": 74.62, "elapsed_time": "1:57:16", "remaining_time": "0:39:53"}
+{"current_steps": 292, "total_steps": 390, "loss": 0.3692, "lr": 7.212940402141808e-06, "epoch": 3.731629392971246, "percentage": 74.87, "elapsed_time": "1:57:38", "remaining_time": "0:39:29"}
+{"current_steps": 293, "total_steps": 390, "loss": 0.378, "lr": 7.075812677821145e-06, "epoch": 3.744408945686901, "percentage": 75.13, "elapsed_time": "1:58:01", "remaining_time": "0:39:04"}
+{"current_steps": 294, "total_steps": 390, "loss": 0.3974, "lr": 6.939720300328303e-06, "epoch": 3.757188498402556, "percentage": 75.38, "elapsed_time": "1:58:25", "remaining_time": "0:38:40"}
+{"current_steps": 295, "total_steps": 390, "loss": 0.3766, "lr": 6.8046741719202385e-06, "epoch": 3.769968051118211, "percentage": 75.64, "elapsed_time": "1:58:48", "remaining_time": "0:38:15"}
+{"current_steps": 296, "total_steps": 390, "loss": 0.3522, "lr": 6.67068511103971e-06, "epoch": 3.7827476038338657, "percentage": 75.9, "elapsed_time": "1:59:09", "remaining_time": "0:37:50"}
+{"current_steps": 297, "total_steps": 390, "loss": 0.3841, "lr": 6.537763851448593e-06, "epoch": 3.7955271565495208, "percentage": 76.15, "elapsed_time": "1:59:32", "remaining_time": "0:37:25"}
+{"current_steps": 298, "total_steps": 390, "loss": 0.3901, "lr": 6.4059210413680175e-06, "epoch": 3.8083067092651754, "percentage": 76.41, "elapsed_time": "1:59:55", "remaining_time": "0:37:01"}
+{"current_steps": 299, "total_steps": 390, "loss": 0.3695, "lr": 6.275167242625331e-06, "epoch": 3.8210862619808306, "percentage": 76.67, "elapsed_time": "2:00:18", "remaining_time": "0:36:37"}
+{"current_steps": 300, "total_steps": 390, "loss": 0.3967, "lr": 6.145512929808013e-06, "epoch": 3.8338658146964857, "percentage": 76.92, "elapsed_time": "2:00:42", "remaining_time": "0:36:12"}
+{"current_steps": 301, "total_steps": 390, "loss": 0.3862, "lr": 6.016968489424572e-06, "epoch": 3.8466453674121404, "percentage": 77.18, "elapsed_time": "2:01:05", "remaining_time": "0:35:48"}
+{"current_steps": 302, "total_steps": 390, "loss": 0.392, "lr": 5.889544219072465e-06, "epoch": 3.8594249201277955, "percentage": 77.44, "elapsed_time": "2:01:29", "remaining_time": "0:35:23"}
+{"current_steps": 303, "total_steps": 390, "loss": 0.3914, "lr": 5.7632503266131925e-06, "epoch": 3.8722044728434506, "percentage": 77.69, "elapsed_time": "2:01:52", "remaining_time": "0:34:59"}
+{"current_steps": 304, "total_steps": 390, "loss": 0.3887, "lr": 5.638096929354522e-06, "epoch": 3.8849840255591053, "percentage": 77.95, "elapsed_time": "2:02:16", "remaining_time": "0:34:35"}
+{"current_steps": 305, "total_steps": 390, "loss": 0.3719, "lr": 5.514094053240035e-06, "epoch": 3.8977635782747604, "percentage": 78.21, "elapsed_time": "2:02:40", "remaining_time": "0:34:11"}
+{"current_steps": 306, "total_steps": 390, "loss": 0.3927, "lr": 5.39125163204594e-06, "epoch": 3.9105431309904155, "percentage": 78.46, "elapsed_time": "2:03:03", "remaining_time": "0:33:46"}
+{"current_steps": 307, "total_steps": 390, "loss": 0.391, "lr": 5.269579506585259e-06, "epoch": 3.92332268370607, "percentage": 78.72, "elapsed_time": "2:03:26", "remaining_time": "0:33:22"}
+{"current_steps": 308, "total_steps": 390, "loss": 0.3908, "lr": 5.149087423919541e-06, "epoch": 3.9361022364217253, "percentage": 78.97, "elapsed_time": "2:03:49", "remaining_time": "0:32:57"}
+{"current_steps": 309, "total_steps": 390, "loss": 0.3944, "lr": 5.029785036577976e-06, "epoch": 3.9488817891373804, "percentage": 79.23, "elapsed_time": "2:04:12", "remaining_time": "0:32:33"}
+{"current_steps": 310, "total_steps": 390, "loss": 0.3653, "lr": 4.911681901784198e-06, "epoch": 3.961661341853035, "percentage": 79.49, "elapsed_time": "2:04:35", "remaining_time": "0:32:09"}
+{"current_steps": 311, "total_steps": 390, "loss": 0.3603, "lr": 4.794787480690597e-06, "epoch": 3.97444089456869, "percentage": 79.74, "elapsed_time": "2:04:57", "remaining_time": "0:31:44"}
+{"current_steps": 312, "total_steps": 390, "loss": 0.3792, "lr": 4.679111137620442e-06, "epoch": 3.987220447284345, "percentage": 80.0, "elapsed_time": "2:05:20", "remaining_time": "0:31:20"}
+{"current_steps": 313, "total_steps": 390, "loss": 0.3784, "lr": 4.5646621393177e-06, "epoch": 4.0, "percentage": 80.26, "elapsed_time": "2:05:43", "remaining_time": "0:30:55"}
+{"current_steps": 314, "total_steps": 390, "loss": 0.3544, "lr": 4.451449654204685e-06, "epoch": 4.012779552715655, "percentage": 80.51, "elapsed_time": "2:07:57", "remaining_time": "0:30:58"}
+{"current_steps": 315, "total_steps": 390, "loss": 0.3385, "lr": 4.339482751647557e-06, "epoch": 4.02555910543131, "percentage": 80.77, "elapsed_time": "2:08:20", "remaining_time": "0:30:33"}
+{"current_steps": 316, "total_steps": 390, "loss": 0.3548, "lr": 4.228770401229824e-06, "epoch": 4.038338658146965, "percentage": 81.03, "elapsed_time": "2:08:43", "remaining_time": "0:30:08"}
+{"current_steps": 317, "total_steps": 390, "loss": 0.3442, "lr": 4.119321472033779e-06, "epoch": 4.05111821086262, "percentage": 81.28, "elapsed_time": "2:09:05", "remaining_time": "0:29:43"}
+{"current_steps": 318, "total_steps": 390, "loss": 0.3316, "lr": 4.011144731929981e-06, "epoch": 4.063897763578275, "percentage": 81.54, "elapsed_time": "2:09:29", "remaining_time": "0:29:19"}
+{"current_steps": 319, "total_steps": 390, "loss": 0.3477, "lr": 3.904248846874894e-06, "epoch": 4.07667731629393, "percentage": 81.79, "elapsed_time": "2:09:52", "remaining_time": "0:28:54"}
+{"current_steps": 320, "total_steps": 390, "loss": 0.3305, "lr": 3.7986423802166705e-06, "epoch": 4.0894568690095845, "percentage": 82.05, "elapsed_time": "2:10:14", "remaining_time": "0:28:29"}
+{"current_steps": 321, "total_steps": 390, "loss": 0.3379, "lr": 3.694333792009115e-06, "epoch": 4.102236421725239, "percentage": 82.31, "elapsed_time": "2:10:39", "remaining_time": "0:28:05"}