Training in progress, epoch 2

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:931b63db8161802c7e074616f596d62d6b19c7082f7195c49697202d944ab611
+oid sha256:c3ad96d700520ea3fc21d366cbcff886dbef3794e8eebb56788fa15ccff5a87d
 size 4877660776

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ecd4a61daf0d011cc89d9512bc13fae358a06766d98781e1c766eb21c23d00b
+oid sha256:8fc6005eb07c93ce351d9e99888f2355cb24db44f55498cd32fcb70bfced480f
 size 4932751008

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2bf3599fe963ac3d19145291d3c3db499a707fd8a4198e34a2ff97e8c74a3b7
+oid sha256:de218256d8e4196b52b23344c3a2631299230267ef201150562408e13a677958
 size 4330865200

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a5a43d8d04f9ceb10976b33b3c3649c8e5175e5087dcd2bf0d25a8a64164146
+oid sha256:115673f738d89664ac0a10bc0be5bc0e2416286c7af3c83ef4cab3f841f4240e
 size 1089994880

trainer_log.jsonl

@@ -162,3 +162,81 @@
 {"current_steps": 162, "total_steps": 390, "loss": 0.4606, "lr": 2.9055877207392752e-05, "epoch": 2.070287539936102, "percentage": 41.54, "elapsed_time": "1:06:04", "remaining_time": "1:33:00"}
 {"current_steps": 163, "total_steps": 390, "loss": 0.4515, "lr": 2.8895910234918828e-05, "epoch": 2.083067092651757, "percentage": 41.79, "elapsed_time": "1:06:28", "remaining_time": "1:32:34"}
 {"current_steps": 164, "total_steps": 390, "loss": 0.4727, "lr": 2.873523061783426e-05, "epoch": 2.0958466453674123, "percentage": 42.05, "elapsed_time": "1:06:51", "remaining_time": "1:32:08"}
+{"current_steps": 165, "total_steps": 390, "loss": 0.4446, "lr": 2.8573851228061084e-05, "epoch": 2.108626198083067, "percentage": 42.31, "elapsed_time": "1:07:16", "remaining_time": "1:31:44"}
+{"current_steps": 166, "total_steps": 390, "loss": 0.4564, "lr": 2.8411784993579633e-05, "epoch": 2.121405750798722, "percentage": 42.56, "elapsed_time": "1:07:40", "remaining_time": "1:31:18"}
+{"current_steps": 167, "total_steps": 390, "loss": 0.4427, "lr": 2.8249044897392814e-05, "epoch": 2.134185303514377, "percentage": 42.82, "elapsed_time": "1:08:03", "remaining_time": "1:30:52"}
+{"current_steps": 168, "total_steps": 390, "loss": 0.4547, "lr": 2.80856439764861e-05, "epoch": 2.146964856230032, "percentage": 43.08, "elapsed_time": "1:08:26", "remaining_time": "1:30:25"}
+{"current_steps": 169, "total_steps": 390, "loss": 0.4438, "lr": 2.792159532078314e-05, "epoch": 2.159744408945687, "percentage": 43.33, "elapsed_time": "1:08:48", "remaining_time": "1:29:59"}
+{"current_steps": 170, "total_steps": 390, "loss": 0.4395, "lr": 2.77569120720971e-05, "epoch": 2.1725239616613417, "percentage": 43.59, "elapsed_time": "1:09:10", "remaining_time": "1:29:31"}
+{"current_steps": 171, "total_steps": 390, "loss": 0.4576, "lr": 2.7591607423077932e-05, "epoch": 2.1853035143769968, "percentage": 43.85, "elapsed_time": "1:09:33", "remaining_time": "1:29:05"}
+{"current_steps": 172, "total_steps": 390, "loss": 0.448, "lr": 2.7425694616155474e-05, "epoch": 2.198083067092652, "percentage": 44.1, "elapsed_time": "1:09:54", "remaining_time": "1:28:36"}
+{"current_steps": 173, "total_steps": 390, "loss": 0.4754, "lr": 2.7259186942478656e-05, "epoch": 2.2108626198083066, "percentage": 44.36, "elapsed_time": "1:10:18", "remaining_time": "1:28:11"}
+{"current_steps": 174, "total_steps": 390, "loss": 0.4535, "lr": 2.7092097740850712e-05, "epoch": 2.2236421725239617, "percentage": 44.62, "elapsed_time": "1:10:41", "remaining_time": "1:27:45"}
+{"current_steps": 175, "total_steps": 390, "loss": 0.4568, "lr": 2.692444039666066e-05, "epoch": 2.236421725239617, "percentage": 44.87, "elapsed_time": "1:11:05", "remaining_time": "1:27:20"}
+{"current_steps": 176, "total_steps": 390, "loss": 0.4528, "lr": 2.6756228340810946e-05, "epoch": 2.2492012779552715, "percentage": 45.13, "elapsed_time": "1:11:29", "remaining_time": "1:26:55"}
+{"current_steps": 177, "total_steps": 390, "loss": 0.4411, "lr": 2.6587475048641596e-05, "epoch": 2.2619808306709266, "percentage": 45.38, "elapsed_time": "1:11:53", "remaining_time": "1:26:30"}
+{"current_steps": 178, "total_steps": 390, "loss": 0.4633, "lr": 2.6418194038850634e-05, "epoch": 2.2747603833865817, "percentage": 45.64, "elapsed_time": "1:12:16", "remaining_time": "1:26:04"}
+{"current_steps": 179, "total_steps": 390, "loss": 0.4501, "lr": 2.624839887241115e-05, "epoch": 2.2875399361022364, "percentage": 45.9, "elapsed_time": "1:12:40", "remaining_time": "1:25:39"}
+{"current_steps": 180, "total_steps": 390, "loss": 0.4631, "lr": 2.607810315148494e-05, "epoch": 2.3003194888178915, "percentage": 46.15, "elapsed_time": "1:13:03", "remaining_time": "1:25:13"}
+{"current_steps": 181, "total_steps": 390, "loss": 0.4512, "lr": 2.5907320518332827e-05, "epoch": 2.313099041533546, "percentage": 46.41, "elapsed_time": "1:13:24", "remaining_time": "1:24:46"}
+{"current_steps": 182, "total_steps": 390, "loss": 0.4539, "lr": 2.5736064654221808e-05, "epoch": 2.3258785942492013, "percentage": 46.67, "elapsed_time": "1:13:47", "remaining_time": "1:24:19"}
+{"current_steps": 183, "total_steps": 390, "loss": 0.4583, "lr": 2.5564349278329056e-05, "epoch": 2.3386581469648564, "percentage": 46.92, "elapsed_time": "1:14:09", "remaining_time": "1:23:53"}
+{"current_steps": 184, "total_steps": 390, "loss": 0.4625, "lr": 2.539218814664288e-05, "epoch": 2.351437699680511, "percentage": 47.18, "elapsed_time": "1:14:32", "remaining_time": "1:23:27"}
+{"current_steps": 185, "total_steps": 390, "loss": 0.455, "lr": 2.521959505086075e-05, "epoch": 2.364217252396166, "percentage": 47.44, "elapsed_time": "1:14:55", "remaining_time": "1:23:01"}
+{"current_steps": 186, "total_steps": 390, "loss": 0.4474, "lr": 2.5046583817284437e-05, "epoch": 2.376996805111821, "percentage": 47.69, "elapsed_time": "1:15:19", "remaining_time": "1:22:36"}
+{"current_steps": 187, "total_steps": 390, "loss": 0.4484, "lr": 2.487316830571244e-05, "epoch": 2.389776357827476, "percentage": 47.95, "elapsed_time": "1:15:41", "remaining_time": "1:22:10"}
+{"current_steps": 188, "total_steps": 390, "loss": 0.4402, "lr": 2.4699362408329646e-05, "epoch": 2.402555910543131, "percentage": 48.21, "elapsed_time": "1:16:04", "remaining_time": "1:21:44"}
+{"current_steps": 189, "total_steps": 390, "loss": 0.4424, "lr": 2.4525180048594452e-05, "epoch": 2.415335463258786, "percentage": 48.46, "elapsed_time": "1:16:26", "remaining_time": "1:21:18"}
+{"current_steps": 190, "total_steps": 390, "loss": 0.4623, "lr": 2.435063518012335e-05, "epoch": 2.428115015974441, "percentage": 48.72, "elapsed_time": "1:16:49", "remaining_time": "1:20:52"}
+{"current_steps": 191, "total_steps": 390, "loss": 0.4589, "lr": 2.4175741785573177e-05, "epoch": 2.440894568690096, "percentage": 48.97, "elapsed_time": "1:17:13", "remaining_time": "1:20:27"}
+{"current_steps": 192, "total_steps": 390, "loss": 0.4501, "lr": 2.4000513875520892e-05, "epoch": 2.4536741214057507, "percentage": 49.23, "elapsed_time": "1:17:36", "remaining_time": "1:20:02"}
+{"current_steps": 193, "total_steps": 390, "loss": 0.4522, "lr": 2.3824965487341247e-05, "epoch": 2.466453674121406, "percentage": 49.49, "elapsed_time": "1:18:00", "remaining_time": "1:19:37"}
+{"current_steps": 194, "total_steps": 390, "loss": 0.4535, "lr": 2.3649110684082258e-05, "epoch": 2.479233226837061, "percentage": 49.74, "elapsed_time": "1:18:24", "remaining_time": "1:19:12"}
+{"current_steps": 195, "total_steps": 390, "loss": 0.4601, "lr": 2.3472963553338614e-05, "epoch": 2.4920127795527156, "percentage": 50.0, "elapsed_time": "1:18:47", "remaining_time": "1:18:47"}
+{"current_steps": 196, "total_steps": 390, "loss": 0.4466, "lr": 2.3296538206123134e-05, "epoch": 2.5047923322683707, "percentage": 50.26, "elapsed_time": "1:19:11", "remaining_time": "1:18:22"}
+{"current_steps": 197, "total_steps": 390, "loss": 0.4716, "lr": 2.311984877573636e-05, "epoch": 2.5175718849840254, "percentage": 50.51, "elapsed_time": "1:19:33", "remaining_time": "1:17:56"}
+{"current_steps": 198, "total_steps": 390, "loss": 0.4427, "lr": 2.2942909416634326e-05, "epoch": 2.5303514376996805, "percentage": 50.77, "elapsed_time": "1:19:57", "remaining_time": "1:17:31"}
+{"current_steps": 199, "total_steps": 390, "loss": 0.4488, "lr": 2.2765734303294666e-05, "epoch": 2.543130990415335, "percentage": 51.03, "elapsed_time": "1:20:20", "remaining_time": "1:17:06"}
+{"current_steps": 200, "total_steps": 390, "loss": 0.4438, "lr": 2.2588337629081107e-05, "epoch": 2.5559105431309903, "percentage": 51.28, "elapsed_time": "1:20:43", "remaining_time": "1:16:41"}
+{"current_steps": 201, "total_steps": 390, "loss": 0.4718, "lr": 2.2410733605106462e-05, "epoch": 2.5686900958466454, "percentage": 51.54, "elapsed_time": "1:21:07", "remaining_time": "1:16:16"}
+{"current_steps": 202, "total_steps": 390, "loss": 0.4441, "lr": 2.2232936459094158e-05, "epoch": 2.5814696485623, "percentage": 51.79, "elapsed_time": "1:21:31", "remaining_time": "1:15:52"}
+{"current_steps": 203, "total_steps": 390, "loss": 0.4738, "lr": 2.205496043423849e-05, "epoch": 2.594249201277955, "percentage": 52.05, "elapsed_time": "1:21:53", "remaining_time": "1:15:26"}
+{"current_steps": 204, "total_steps": 390, "loss": 0.4346, "lr": 2.1876819788063586e-05, "epoch": 2.6070287539936103, "percentage": 52.31, "elapsed_time": "1:22:16", "remaining_time": "1:15:00"}
+{"current_steps": 205, "total_steps": 390, "loss": 0.4428, "lr": 2.16985287912813e-05, "epoch": 2.619808306709265, "percentage": 52.56, "elapsed_time": "1:22:39", "remaining_time": "1:14:35"}
+{"current_steps": 206, "total_steps": 390, "loss": 0.4532, "lr": 2.1520101726647922e-05, "epoch": 2.63258785942492, "percentage": 52.82, "elapsed_time": "1:23:02", "remaining_time": "1:14:10"}
+{"current_steps": 207, "total_steps": 390, "loss": 0.4504, "lr": 2.1341552887820048e-05, "epoch": 2.6453674121405752, "percentage": 53.08, "elapsed_time": "1:23:26", "remaining_time": "1:13:45"}
+{"current_steps": 208, "total_steps": 390, "loss": 0.4614, "lr": 2.1162896578209517e-05, "epoch": 2.65814696485623, "percentage": 53.33, "elapsed_time": "1:23:47", "remaining_time": "1:13:18"}
+{"current_steps": 209, "total_steps": 390, "loss": 0.4678, "lr": 2.0984147109837564e-05, "epoch": 2.670926517571885, "percentage": 53.59, "elapsed_time": "1:24:11", "remaining_time": "1:12:54"}
+{"current_steps": 210, "total_steps": 390, "loss": 0.4359, "lr": 2.0805318802188307e-05, "epoch": 2.68370607028754, "percentage": 53.85, "elapsed_time": "1:24:32", "remaining_time": "1:12:28"}
+{"current_steps": 211, "total_steps": 390, "loss": 0.4686, "lr": 2.0626425981061608e-05, "epoch": 2.696485623003195, "percentage": 54.1, "elapsed_time": "1:24:56", "remaining_time": "1:12:03"}
+{"current_steps": 212, "total_steps": 390, "loss": 0.4494, "lr": 2.0447482977425465e-05, "epoch": 2.70926517571885, "percentage": 54.36, "elapsed_time": "1:25:17", "remaining_time": "1:11:36"}
+{"current_steps": 213, "total_steps": 390, "loss": 0.4618, "lr": 2.0268504126267952e-05, "epoch": 2.722044728434505, "percentage": 54.62, "elapsed_time": "1:25:38", "remaining_time": "1:11:10"}
+{"current_steps": 214, "total_steps": 390, "loss": 0.4501, "lr": 2.008950376544887e-05, "epoch": 2.7348242811501597, "percentage": 54.87, "elapsed_time": "1:26:02", "remaining_time": "1:10:45"}
+{"current_steps": 215, "total_steps": 390, "loss": 0.4712, "lr": 1.9910496234551132e-05, "epoch": 2.747603833865815, "percentage": 55.13, "elapsed_time": "1:26:25", "remaining_time": "1:10:21"}
+{"current_steps": 216, "total_steps": 390, "loss": 0.4462, "lr": 1.9731495873732055e-05, "epoch": 2.7603833865814695, "percentage": 55.38, "elapsed_time": "1:26:49", "remaining_time": "1:09:56"}
+{"current_steps": 217, "total_steps": 390, "loss": 0.4542, "lr": 1.9552517022574542e-05, "epoch": 2.7731629392971247, "percentage": 55.64, "elapsed_time": "1:27:12", "remaining_time": "1:09:31"}
+{"current_steps": 218, "total_steps": 390, "loss": 0.4552, "lr": 1.93735740189384e-05, "epoch": 2.7859424920127793, "percentage": 55.9, "elapsed_time": "1:27:35", "remaining_time": "1:09:06"}
+{"current_steps": 219, "total_steps": 390, "loss": 0.4618, "lr": 1.9194681197811703e-05, "epoch": 2.7987220447284344, "percentage": 56.15, "elapsed_time": "1:27:58", "remaining_time": "1:08:41"}
+{"current_steps": 220, "total_steps": 390, "loss": 0.4695, "lr": 1.901585289016244e-05, "epoch": 2.8115015974440896, "percentage": 56.41, "elapsed_time": "1:28:21", "remaining_time": "1:08:16"}
+{"current_steps": 221, "total_steps": 390, "loss": 0.4423, "lr": 1.8837103421790486e-05, "epoch": 2.8242811501597442, "percentage": 56.67, "elapsed_time": "1:28:42", "remaining_time": "1:07:50"}
+{"current_steps": 222, "total_steps": 390, "loss": 0.4422, "lr": 1.8658447112179952e-05, "epoch": 2.8370607028753994, "percentage": 56.92, "elapsed_time": "1:29:06", "remaining_time": "1:07:26"}
+{"current_steps": 223, "total_steps": 390, "loss": 0.4569, "lr": 1.8479898273352084e-05, "epoch": 2.8498402555910545, "percentage": 57.18, "elapsed_time": "1:29:28", "remaining_time": "1:07:00"}
+{"current_steps": 224, "total_steps": 390, "loss": 0.4619, "lr": 1.83014712087187e-05, "epoch": 2.862619808306709, "percentage": 57.44, "elapsed_time": "1:29:50", "remaining_time": "1:06:35"}
+{"current_steps": 225, "total_steps": 390, "loss": 0.4678, "lr": 1.8123180211936417e-05, "epoch": 2.8753993610223643, "percentage": 57.69, "elapsed_time": "1:30:14", "remaining_time": "1:06:10"}
+{"current_steps": 226, "total_steps": 390, "loss": 0.452, "lr": 1.794503956576152e-05, "epoch": 2.8881789137380194, "percentage": 57.95, "elapsed_time": "1:30:37", "remaining_time": "1:05:45"}
+{"current_steps": 227, "total_steps": 390, "loss": 0.4658, "lr": 1.776706354090585e-05, "epoch": 2.900958466453674, "percentage": 58.21, "elapsed_time": "1:31:01", "remaining_time": "1:05:21"}
+{"current_steps": 228, "total_steps": 390, "loss": 0.4421, "lr": 1.758926639489354e-05, "epoch": 2.913738019169329, "percentage": 58.46, "elapsed_time": "1:31:24", "remaining_time": "1:04:56"}
+{"current_steps": 229, "total_steps": 390, "loss": 0.4466, "lr": 1.7411662370918893e-05, "epoch": 2.9265175718849843, "percentage": 58.72, "elapsed_time": "1:31:47", "remaining_time": "1:04:31"}
+{"current_steps": 230, "total_steps": 390, "loss": 0.4397, "lr": 1.7234265696705344e-05, "epoch": 2.939297124600639, "percentage": 58.97, "elapsed_time": "1:32:10", "remaining_time": "1:04:07"}
+{"current_steps": 231, "total_steps": 390, "loss": 0.4546, "lr": 1.7057090583365678e-05, "epoch": 2.952076677316294, "percentage": 59.23, "elapsed_time": "1:32:32", "remaining_time": "1:03:41"}
+{"current_steps": 232, "total_steps": 390, "loss": 0.4526, "lr": 1.6880151224263646e-05, "epoch": 2.9648562300319488, "percentage": 59.49, "elapsed_time": "1:32:55", "remaining_time": "1:03:17"}
+{"current_steps": 233, "total_steps": 390, "loss": 0.4393, "lr": 1.6703461793876876e-05, "epoch": 2.977635782747604, "percentage": 59.74, "elapsed_time": "1:33:17", "remaining_time": "1:02:51"}
+{"current_steps": 234, "total_steps": 390, "loss": 0.4578, "lr": 1.6527036446661396e-05, "epoch": 2.9904153354632586, "percentage": 60.0, "elapsed_time": "1:33:40", "remaining_time": "1:02:26"}
+{"current_steps": 235, "total_steps": 390, "loss": 0.4189, "lr": 1.635088931591775e-05, "epoch": 3.0031948881789137, "percentage": 60.26, "elapsed_time": "1:35:54", "remaining_time": "1:03:15"}
+{"current_steps": 236, "total_steps": 390, "loss": 0.3669, "lr": 1.6175034512658753e-05, "epoch": 3.015974440894569, "percentage": 60.51, "elapsed_time": "1:36:17", "remaining_time": "1:02:49"}
+{"current_steps": 237, "total_steps": 390, "loss": 0.3889, "lr": 1.5999486124479115e-05, "epoch": 3.0287539936102235, "percentage": 60.77, "elapsed_time": "1:36:41", "remaining_time": "1:02:25"}
+{"current_steps": 238, "total_steps": 390, "loss": 0.4011, "lr": 1.5824258214426833e-05, "epoch": 3.0415335463258786, "percentage": 61.03, "elapsed_time": "1:37:04", "remaining_time": "1:01:59"}
+{"current_steps": 239, "total_steps": 390, "loss": 0.3673, "lr": 1.5649364819876655e-05, "epoch": 3.0543130990415337, "percentage": 61.28, "elapsed_time": "1:37:27", "remaining_time": "1:01:34"}
+{"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"}