Training in progress, epoch 2

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5416c2db93860242b5401349a0eb462f414693d0f424b28d4cc44f0b47364fc
+oid sha256:dd7cc1835c2ccc6ec356ba660a22d5d74a08815bdee88e733355aee11f933e10
 size 4877660776

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58de7db3484fffc736cf4522b51bd4c5ea0e4157eafaf9eaf952ce8556fa7304
+oid sha256:4576c021c875c2c589bdc1cc7d311e741c66e85e01155459a365f5047ed5a270
 size 4932751008

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0afcb60420a969073346a0cf9c178eb34bd9cbc0597e27237c1997dec6d3b05f
+oid sha256:7d40f5d81bdeca0dbcc90a3146d61c3a98d0e71f556c0217b2bb7e91323beb35
 size 4330865200

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6e42326fe65045390ba53b2a6fe8f83f5dea9c123e127340a1e5f35a20459f6
+oid sha256:c22e8029468c776fbe84ea1280ee7b5a1faf762e34bc099dbd6ab6d69d56fe0e
 size 1089994880

trainer_log.jsonl

@@ -162,3 +162,81 @@
 {"current_steps": 162, "total_steps": 390, "loss": 0.4664, "lr": 2.9055877207392752e-05, "epoch": 2.070287539936102, "percentage": 41.54, "elapsed_time": "1:06:44", "remaining_time": "1:33:56"}
 {"current_steps": 163, "total_steps": 390, "loss": 0.4594, "lr": 2.8895910234918828e-05, "epoch": 2.083067092651757, "percentage": 41.79, "elapsed_time": "1:07:07", "remaining_time": "1:33:28"}
 {"current_steps": 164, "total_steps": 390, "loss": 0.4535, "lr": 2.873523061783426e-05, "epoch": 2.0958466453674123, "percentage": 42.05, "elapsed_time": "1:07:30", "remaining_time": "1:33:01"}
+{"current_steps": 165, "total_steps": 390, "loss": 0.4469, "lr": 2.8573851228061084e-05, "epoch": 2.108626198083067, "percentage": 42.31, "elapsed_time": "1:07:53", "remaining_time": "1:32:35"}
+{"current_steps": 166, "total_steps": 390, "loss": 0.4453, "lr": 2.8411784993579633e-05, "epoch": 2.121405750798722, "percentage": 42.56, "elapsed_time": "1:08:14", "remaining_time": "1:32:05"}
+{"current_steps": 167, "total_steps": 390, "loss": 0.4447, "lr": 2.8249044897392814e-05, "epoch": 2.134185303514377, "percentage": 42.82, "elapsed_time": "1:08:37", "remaining_time": "1:31:37"}
+{"current_steps": 168, "total_steps": 390, "loss": 0.4627, "lr": 2.80856439764861e-05, "epoch": 2.146964856230032, "percentage": 43.08, "elapsed_time": "1:09:00", "remaining_time": "1:31:10"}
+{"current_steps": 169, "total_steps": 390, "loss": 0.4621, "lr": 2.792159532078314e-05, "epoch": 2.159744408945687, "percentage": 43.33, "elapsed_time": "1:09:23", "remaining_time": "1:30:44"}
+{"current_steps": 170, "total_steps": 390, "loss": 0.4568, "lr": 2.77569120720971e-05, "epoch": 2.1725239616613417, "percentage": 43.59, "elapsed_time": "1:09:46", "remaining_time": "1:30:17"}
+{"current_steps": 171, "total_steps": 390, "loss": 0.4669, "lr": 2.7591607423077932e-05, "epoch": 2.1853035143769968, "percentage": 43.85, "elapsed_time": "1:10:09", "remaining_time": "1:29:50"}
+{"current_steps": 172, "total_steps": 390, "loss": 0.4418, "lr": 2.7425694616155474e-05, "epoch": 2.198083067092652, "percentage": 44.1, "elapsed_time": "1:10:32", "remaining_time": "1:29:24"}
+{"current_steps": 173, "total_steps": 390, "loss": 0.4496, "lr": 2.7259186942478656e-05, "epoch": 2.2108626198083066, "percentage": 44.36, "elapsed_time": "1:10:56", "remaining_time": "1:28:58"}
+{"current_steps": 174, "total_steps": 390, "loss": 0.4599, "lr": 2.7092097740850712e-05, "epoch": 2.2236421725239617, "percentage": 44.62, "elapsed_time": "1:11:19", "remaining_time": "1:28:32"}
+{"current_steps": 175, "total_steps": 390, "loss": 0.4538, "lr": 2.692444039666066e-05, "epoch": 2.236421725239617, "percentage": 44.87, "elapsed_time": "1:11:42", "remaining_time": "1:28:06"}
+{"current_steps": 176, "total_steps": 390, "loss": 0.4423, "lr": 2.6756228340810946e-05, "epoch": 2.2492012779552715, "percentage": 45.13, "elapsed_time": "1:12:05", "remaining_time": "1:27:39"}
+{"current_steps": 177, "total_steps": 390, "loss": 0.4581, "lr": 2.6587475048641596e-05, "epoch": 2.2619808306709266, "percentage": 45.38, "elapsed_time": "1:12:29", "remaining_time": "1:27:14"}
+{"current_steps": 178, "total_steps": 390, "loss": 0.4622, "lr": 2.6418194038850634e-05, "epoch": 2.2747603833865817, "percentage": 45.64, "elapsed_time": "1:12:53", "remaining_time": "1:26:48"}
+{"current_steps": 179, "total_steps": 390, "loss": 0.4666, "lr": 2.624839887241115e-05, "epoch": 2.2875399361022364, "percentage": 45.9, "elapsed_time": "1:13:15", "remaining_time": "1:26:21"}
+{"current_steps": 180, "total_steps": 390, "loss": 0.4681, "lr": 2.607810315148494e-05, "epoch": 2.3003194888178915, "percentage": 46.15, "elapsed_time": "1:13:37", "remaining_time": "1:25:53"}
+{"current_steps": 181, "total_steps": 390, "loss": 0.4539, "lr": 2.5907320518332827e-05, "epoch": 2.313099041533546, "percentage": 46.41, "elapsed_time": "1:14:01", "remaining_time": "1:25:28"}
+{"current_steps": 182, "total_steps": 390, "loss": 0.4427, "lr": 2.5736064654221808e-05, "epoch": 2.3258785942492013, "percentage": 46.67, "elapsed_time": "1:14:24", "remaining_time": "1:25:01"}
+{"current_steps": 183, "total_steps": 390, "loss": 0.4575, "lr": 2.5564349278329056e-05, "epoch": 2.3386581469648564, "percentage": 46.92, "elapsed_time": "1:14:47", "remaining_time": "1:24:35"}
+{"current_steps": 184, "total_steps": 390, "loss": 0.4463, "lr": 2.539218814664288e-05, "epoch": 2.351437699680511, "percentage": 47.18, "elapsed_time": "1:15:10", "remaining_time": "1:24:09"}
+{"current_steps": 185, "total_steps": 390, "loss": 0.4521, "lr": 2.521959505086075e-05, "epoch": 2.364217252396166, "percentage": 47.44, "elapsed_time": "1:15:32", "remaining_time": "1:23:42"}
+{"current_steps": 186, "total_steps": 390, "loss": 0.4608, "lr": 2.5046583817284437e-05, "epoch": 2.376996805111821, "percentage": 47.69, "elapsed_time": "1:15:54", "remaining_time": "1:23:15"}
+{"current_steps": 187, "total_steps": 390, "loss": 0.4835, "lr": 2.487316830571244e-05, "epoch": 2.389776357827476, "percentage": 47.95, "elapsed_time": "1:16:18", "remaining_time": "1:22:49"}
+{"current_steps": 188, "total_steps": 390, "loss": 0.4604, "lr": 2.4699362408329646e-05, "epoch": 2.402555910543131, "percentage": 48.21, "elapsed_time": "1:16:41", "remaining_time": "1:22:24"}
+{"current_steps": 189, "total_steps": 390, "loss": 0.4446, "lr": 2.4525180048594452e-05, "epoch": 2.415335463258786, "percentage": 48.46, "elapsed_time": "1:17:04", "remaining_time": "1:21:57"}
+{"current_steps": 190, "total_steps": 390, "loss": 0.4723, "lr": 2.435063518012335e-05, "epoch": 2.428115015974441, "percentage": 48.72, "elapsed_time": "1:17:27", "remaining_time": "1:21:32"}
+{"current_steps": 191, "total_steps": 390, "loss": 0.4441, "lr": 2.4175741785573177e-05, "epoch": 2.440894568690096, "percentage": 48.97, "elapsed_time": "1:17:50", "remaining_time": "1:21:05"}
+{"current_steps": 192, "total_steps": 390, "loss": 0.4751, "lr": 2.4000513875520892e-05, "epoch": 2.4536741214057507, "percentage": 49.23, "elapsed_time": "1:18:12", "remaining_time": "1:20:39"}
+{"current_steps": 193, "total_steps": 390, "loss": 0.4503, "lr": 2.3824965487341247e-05, "epoch": 2.466453674121406, "percentage": 49.49, "elapsed_time": "1:18:35", "remaining_time": "1:20:13"}
+{"current_steps": 194, "total_steps": 390, "loss": 0.4614, "lr": 2.3649110684082258e-05, "epoch": 2.479233226837061, "percentage": 49.74, "elapsed_time": "1:18:57", "remaining_time": "1:19:46"}
+{"current_steps": 195, "total_steps": 390, "loss": 0.4475, "lr": 2.3472963553338614e-05, "epoch": 2.4920127795527156, "percentage": 50.0, "elapsed_time": "1:19:21", "remaining_time": "1:19:21"}
+{"current_steps": 196, "total_steps": 390, "loss": 0.4717, "lr": 2.3296538206123134e-05, "epoch": 2.5047923322683707, "percentage": 50.26, "elapsed_time": "1:19:43", "remaining_time": "1:18:55"}
+{"current_steps": 197, "total_steps": 390, "loss": 0.4587, "lr": 2.311984877573636e-05, "epoch": 2.5175718849840254, "percentage": 50.51, "elapsed_time": "1:20:05", "remaining_time": "1:18:28"}
+{"current_steps": 198, "total_steps": 390, "loss": 0.471, "lr": 2.2942909416634326e-05, "epoch": 2.5303514376996805, "percentage": 50.77, "elapsed_time": "1:20:28", "remaining_time": "1:18:02"}
+{"current_steps": 199, "total_steps": 390, "loss": 0.4663, "lr": 2.2765734303294666e-05, "epoch": 2.543130990415335, "percentage": 51.03, "elapsed_time": "1:20:51", "remaining_time": "1:17:36"}
+{"current_steps": 200, "total_steps": 390, "loss": 0.4624, "lr": 2.2588337629081107e-05, "epoch": 2.5559105431309903, "percentage": 51.28, "elapsed_time": "1:21:14", "remaining_time": "1:17:10"}
+{"current_steps": 201, "total_steps": 390, "loss": 0.4733, "lr": 2.2410733605106462e-05, "epoch": 2.5686900958466454, "percentage": 51.54, "elapsed_time": "1:21:36", "remaining_time": "1:16:44"}
+{"current_steps": 202, "total_steps": 390, "loss": 0.4719, "lr": 2.2232936459094158e-05, "epoch": 2.5814696485623, "percentage": 51.79, "elapsed_time": "1:21:58", "remaining_time": "1:16:17"}
+{"current_steps": 203, "total_steps": 390, "loss": 0.4643, "lr": 2.205496043423849e-05, "epoch": 2.594249201277955, "percentage": 52.05, "elapsed_time": "1:22:21", "remaining_time": "1:15:52"}
+{"current_steps": 204, "total_steps": 390, "loss": 0.4599, "lr": 2.1876819788063586e-05, "epoch": 2.6070287539936103, "percentage": 52.31, "elapsed_time": "1:22:44", "remaining_time": "1:15:26"}
+{"current_steps": 205, "total_steps": 390, "loss": 0.4611, "lr": 2.16985287912813e-05, "epoch": 2.619808306709265, "percentage": 52.56, "elapsed_time": "1:23:07", "remaining_time": "1:15:01"}
+{"current_steps": 206, "total_steps": 390, "loss": 0.4656, "lr": 2.1520101726647922e-05, "epoch": 2.63258785942492, "percentage": 52.82, "elapsed_time": "1:23:32", "remaining_time": "1:14:36"}
+{"current_steps": 207, "total_steps": 390, "loss": 0.4509, "lr": 2.1341552887820048e-05, "epoch": 2.6453674121405752, "percentage": 53.08, "elapsed_time": "1:23:55", "remaining_time": "1:14:12"}
+{"current_steps": 208, "total_steps": 390, "loss": 0.4552, "lr": 2.1162896578209517e-05, "epoch": 2.65814696485623, "percentage": 53.33, "elapsed_time": "1:24:18", "remaining_time": "1:13:46"}
+{"current_steps": 209, "total_steps": 390, "loss": 0.4587, "lr": 2.0984147109837564e-05, "epoch": 2.670926517571885, "percentage": 53.59, "elapsed_time": "1:24:41", "remaining_time": "1:13:20"}
+{"current_steps": 210, "total_steps": 390, "loss": 0.4708, "lr": 2.0805318802188307e-05, "epoch": 2.68370607028754, "percentage": 53.85, "elapsed_time": "1:25:05", "remaining_time": "1:12:55"}
+{"current_steps": 211, "total_steps": 390, "loss": 0.4494, "lr": 2.0626425981061608e-05, "epoch": 2.696485623003195, "percentage": 54.1, "elapsed_time": "1:25:27", "remaining_time": "1:12:29"}
+{"current_steps": 212, "total_steps": 390, "loss": 0.4563, "lr": 2.0447482977425465e-05, "epoch": 2.70926517571885, "percentage": 54.36, "elapsed_time": "1:25:50", "remaining_time": "1:12:04"}
+{"current_steps": 213, "total_steps": 390, "loss": 0.4495, "lr": 2.0268504126267952e-05, "epoch": 2.722044728434505, "percentage": 54.62, "elapsed_time": "1:26:14", "remaining_time": "1:11:39"}
+{"current_steps": 214, "total_steps": 390, "loss": 0.4681, "lr": 2.008950376544887e-05, "epoch": 2.7348242811501597, "percentage": 54.87, "elapsed_time": "1:26:36", "remaining_time": "1:11:13"}
+{"current_steps": 215, "total_steps": 390, "loss": 0.4579, "lr": 1.9910496234551132e-05, "epoch": 2.747603833865815, "percentage": 55.13, "elapsed_time": "1:27:00", "remaining_time": "1:10:49"}
+{"current_steps": 216, "total_steps": 390, "loss": 0.4631, "lr": 1.9731495873732055e-05, "epoch": 2.7603833865814695, "percentage": 55.38, "elapsed_time": "1:27:23", "remaining_time": "1:10:24"}
+{"current_steps": 217, "total_steps": 390, "loss": 0.4588, "lr": 1.9552517022574542e-05, "epoch": 2.7731629392971247, "percentage": 55.64, "elapsed_time": "1:27:46", "remaining_time": "1:09:59"}
+{"current_steps": 218, "total_steps": 390, "loss": 0.4554, "lr": 1.93735740189384e-05, "epoch": 2.7859424920127793, "percentage": 55.9, "elapsed_time": "1:28:09", "remaining_time": "1:09:33"}
+{"current_steps": 219, "total_steps": 390, "loss": 0.4379, "lr": 1.9194681197811703e-05, "epoch": 2.7987220447284344, "percentage": 56.15, "elapsed_time": "1:28:32", "remaining_time": "1:09:08"}
+{"current_steps": 220, "total_steps": 390, "loss": 0.4536, "lr": 1.901585289016244e-05, "epoch": 2.8115015974440896, "percentage": 56.41, "elapsed_time": "1:28:56", "remaining_time": "1:08:43"}
+{"current_steps": 221, "total_steps": 390, "loss": 0.4546, "lr": 1.8837103421790486e-05, "epoch": 2.8242811501597442, "percentage": 56.67, "elapsed_time": "1:29:20", "remaining_time": "1:08:18"}
+{"current_steps": 222, "total_steps": 390, "loss": 0.4971, "lr": 1.8658447112179952e-05, "epoch": 2.8370607028753994, "percentage": 56.92, "elapsed_time": "1:29:43", "remaining_time": "1:07:54"}
+{"current_steps": 223, "total_steps": 390, "loss": 0.4636, "lr": 1.8479898273352084e-05, "epoch": 2.8498402555910545, "percentage": 57.18, "elapsed_time": "1:30:07", "remaining_time": "1:07:29"}
+{"current_steps": 224, "total_steps": 390, "loss": 0.4454, "lr": 1.83014712087187e-05, "epoch": 2.862619808306709, "percentage": 57.44, "elapsed_time": "1:30:30", "remaining_time": "1:07:04"}
+{"current_steps": 225, "total_steps": 390, "loss": 0.4321, "lr": 1.8123180211936417e-05, "epoch": 2.8753993610223643, "percentage": 57.69, "elapsed_time": "1:30:52", "remaining_time": "1:06:38"}
+{"current_steps": 226, "total_steps": 390, "loss": 0.4737, "lr": 1.794503956576152e-05, "epoch": 2.8881789137380194, "percentage": 57.95, "elapsed_time": "1:31:16", "remaining_time": "1:06:14"}
+{"current_steps": 227, "total_steps": 390, "loss": 0.4699, "lr": 1.776706354090585e-05, "epoch": 2.900958466453674, "percentage": 58.21, "elapsed_time": "1:31:39", "remaining_time": "1:05:49"}
+{"current_steps": 228, "total_steps": 390, "loss": 0.449, "lr": 1.758926639489354e-05, "epoch": 2.913738019169329, "percentage": 58.46, "elapsed_time": "1:32:02", "remaining_time": "1:05:23"}
+{"current_steps": 229, "total_steps": 390, "loss": 0.441, "lr": 1.7411662370918893e-05, "epoch": 2.9265175718849843, "percentage": 58.72, "elapsed_time": "1:32:25", "remaining_time": "1:04:58"}
+{"current_steps": 230, "total_steps": 390, "loss": 0.4747, "lr": 1.7234265696705344e-05, "epoch": 2.939297124600639, "percentage": 58.97, "elapsed_time": "1:32:50", "remaining_time": "1:04:34"}
+{"current_steps": 231, "total_steps": 390, "loss": 0.4598, "lr": 1.7057090583365678e-05, "epoch": 2.952076677316294, "percentage": 59.23, "elapsed_time": "1:33:13", "remaining_time": "1:04:10"}
+{"current_steps": 232, "total_steps": 390, "loss": 0.4641, "lr": 1.6880151224263646e-05, "epoch": 2.9648562300319488, "percentage": 59.49, "elapsed_time": "1:33:36", "remaining_time": "1:03:45"}
+{"current_steps": 233, "total_steps": 390, "loss": 0.4586, "lr": 1.6703461793876876e-05, "epoch": 2.977635782747604, "percentage": 59.74, "elapsed_time": "1:34:00", "remaining_time": "1:03:20"}
+{"current_steps": 234, "total_steps": 390, "loss": 0.4662, "lr": 1.6527036446661396e-05, "epoch": 2.9904153354632586, "percentage": 60.0, "elapsed_time": "1:34:22", "remaining_time": "1:02:55"}
+{"current_steps": 235, "total_steps": 390, "loss": 0.4364, "lr": 1.635088931591775e-05, "epoch": 3.0031948881789137, "percentage": 60.26, "elapsed_time": "1:37:37", "remaining_time": "1:04:23"}
+{"current_steps": 236, "total_steps": 390, "loss": 0.3809, "lr": 1.6175034512658753e-05, "epoch": 3.015974440894569, "percentage": 60.51, "elapsed_time": "1:37:59", "remaining_time": "1:03:56"}
+{"current_steps": 237, "total_steps": 390, "loss": 0.4028, "lr": 1.5999486124479115e-05, "epoch": 3.0287539936102235, "percentage": 60.77, "elapsed_time": "1:38:22", "remaining_time": "1:03:30"}
+{"current_steps": 238, "total_steps": 390, "loss": 0.3926, "lr": 1.5824258214426833e-05, "epoch": 3.0415335463258786, "percentage": 61.03, "elapsed_time": "1:38:46", "remaining_time": "1:03:04"}
+{"current_steps": 239, "total_steps": 390, "loss": 0.3762, "lr": 1.5649364819876655e-05, "epoch": 3.0543130990415337, "percentage": 61.28, "elapsed_time": "1:39:09", "remaining_time": "1:02:38"}
+{"current_steps": 240, "total_steps": 390, "loss": 0.4066, "lr": 1.547481995140556e-05, "epoch": 3.0670926517571884, "percentage": 61.54, "elapsed_time": "1:39:31", "remaining_time": "1:02:12"}
+{"current_steps": 241, "total_steps": 390, "loss": 0.3714, "lr": 1.5300637591670357e-05, "epoch": 3.0798722044728435, "percentage": 61.79, "elapsed_time": "1:39:55", "remaining_time": "1:01:46"}
+{"current_steps": 242, "total_steps": 390, "loss": 0.3806, "lr": 1.5126831694287564e-05, "epoch": 3.0926517571884986, "percentage": 62.05, "elapsed_time": "1:40:15", "remaining_time": "1:01:18"}