Training in progress, step 5800
Browse files
model-00001-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4902257696
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7374e2fd543c6b66f2361df2b2ff041d13a94e0619155f5a15ad38a199c04929
|
| 3 |
size 4902257696
|
model-00002-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4915960368
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:11a9df8e76b7ae488d4da5b35f56e60e415f932e5302d82f7156fb34a3d0d9d6
|
| 3 |
size 4915960368
|
model-00003-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4983068496
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:879a836aa31dea79152575b78e81df44cddd2740da33f10b54f2fc5fb3c8165f
|
| 3 |
size 4983068496
|
model-00004-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1580230264
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cf242c4189e66795916ddc3395a13be9a0db80cb3f05dfe5d0c3360e4c624208
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -1118,3 +1118,43 @@
|
|
| 1118 |
{"current_steps": 5590, "total_steps": 9625, "loss": 0.0979, "lr": 1.7864228450365525e-05, "epoch": 4.065478355765733, "percentage": 58.08, "elapsed_time": "1 day, 12:59:17", "remaining_time": "1 day, 2:41:56"}
|
| 1119 |
{"current_steps": 5595, "total_steps": 9625, "loss": 0.0985, "lr": 1.7828170699955093e-05, "epoch": 4.069116042197162, "percentage": 58.13, "elapsed_time": "1 day, 13:01:04", "remaining_time": "1 day, 2:39:48"}
|
| 1120 |
{"current_steps": 5600, "total_steps": 9625, "loss": 0.0975, "lr": 1.779212009169461e-05, "epoch": 4.072753728628593, "percentage": 58.18, "elapsed_time": "1 day, 13:02:44", "remaining_time": "1 day, 2:37:35"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1118 |
{"current_steps": 5590, "total_steps": 9625, "loss": 0.0979, "lr": 1.7864228450365525e-05, "epoch": 4.065478355765733, "percentage": 58.08, "elapsed_time": "1 day, 12:59:17", "remaining_time": "1 day, 2:41:56"}
|
| 1119 |
{"current_steps": 5595, "total_steps": 9625, "loss": 0.0985, "lr": 1.7828170699955093e-05, "epoch": 4.069116042197162, "percentage": 58.13, "elapsed_time": "1 day, 13:01:04", "remaining_time": "1 day, 2:39:48"}
|
| 1120 |
{"current_steps": 5600, "total_steps": 9625, "loss": 0.0975, "lr": 1.779212009169461e-05, "epoch": 4.072753728628593, "percentage": 58.18, "elapsed_time": "1 day, 13:02:44", "remaining_time": "1 day, 2:37:35"}
|
| 1121 |
+
{"current_steps": 5605, "total_steps": 9625, "loss": 0.0993, "lr": 1.7756076744137982e-05, "epoch": 4.076391415060022, "percentage": 58.23, "elapsed_time": "1 day, 13:05:35", "remaining_time": "1 day, 2:36:13"}
|
| 1122 |
+
{"current_steps": 5610, "total_steps": 9625, "loss": 0.1307, "lr": 1.772004077581525e-05, "epoch": 4.080029101491451, "percentage": 58.29, "elapsed_time": "1 day, 13:07:21", "remaining_time": "1 day, 2:34:05"}
|
| 1123 |
+
{"current_steps": 5615, "total_steps": 9625, "loss": 0.0832, "lr": 1.7684012305232166e-05, "epoch": 4.083666787922881, "percentage": 58.34, "elapsed_time": "1 day, 13:08:54", "remaining_time": "1 day, 2:31:47"}
|
| 1124 |
+
{"current_steps": 5620, "total_steps": 9625, "loss": 0.1131, "lr": 1.764799145086985e-05, "epoch": 4.087304474354311, "percentage": 58.39, "elapsed_time": "1 day, 13:10:25", "remaining_time": "1 day, 2:29:28"}
|
| 1125 |
+
{"current_steps": 5625, "total_steps": 9625, "loss": 0.1139, "lr": 1.7611978331184346e-05, "epoch": 4.09094216078574, "percentage": 58.44, "elapsed_time": "1 day, 13:12:15", "remaining_time": "1 day, 2:27:22"}
|
| 1126 |
+
{"current_steps": 5630, "total_steps": 9625, "loss": 0.0891, "lr": 1.7575973064606298e-05, "epoch": 4.09457984721717, "percentage": 58.49, "elapsed_time": "1 day, 13:13:56", "remaining_time": "1 day, 2:25:10"}
|
| 1127 |
+
{"current_steps": 5635, "total_steps": 9625, "loss": 0.2052, "lr": 1.753997576954049e-05, "epoch": 4.098217533648599, "percentage": 58.55, "elapsed_time": "1 day, 13:15:59", "remaining_time": "1 day, 2:23:14"}
|
| 1128 |
+
{"current_steps": 5640, "total_steps": 9625, "loss": 0.1897, "lr": 1.7503986564365512e-05, "epoch": 4.101855220080029, "percentage": 58.6, "elapsed_time": "1 day, 13:17:53", "remaining_time": "1 day, 2:21:12"}
|
| 1129 |
+
{"current_steps": 5645, "total_steps": 9625, "loss": 0.1005, "lr": 1.7468005567433348e-05, "epoch": 4.105492906511459, "percentage": 58.65, "elapsed_time": "1 day, 13:19:44", "remaining_time": "1 day, 2:19:07"}
|
| 1130 |
+
{"current_steps": 5650, "total_steps": 9625, "loss": 0.1701, "lr": 1.743203289706898e-05, "epoch": 4.109130592942888, "percentage": 58.7, "elapsed_time": "1 day, 13:21:47", "remaining_time": "1 day, 2:17:11"}
|
| 1131 |
+
{"current_steps": 5655, "total_steps": 9625, "loss": 0.109, "lr": 1.7396068671570025e-05, "epoch": 4.112768279374318, "percentage": 58.75, "elapsed_time": "1 day, 13:23:44", "remaining_time": "1 day, 2:15:10"}
|
| 1132 |
+
{"current_steps": 5660, "total_steps": 9625, "loss": 0.0887, "lr": 1.7360113009206305e-05, "epoch": 4.116405965805748, "percentage": 58.81, "elapsed_time": "1 day, 13:25:36", "remaining_time": "1 day, 2:13:06"}
|
| 1133 |
+
{"current_steps": 5665, "total_steps": 9625, "loss": 0.095, "lr": 1.7324166028219495e-05, "epoch": 4.120043652237177, "percentage": 58.86, "elapsed_time": "1 day, 13:27:15", "remaining_time": "1 day, 2:10:54"}
|
| 1134 |
+
{"current_steps": 5670, "total_steps": 9625, "loss": 0.0858, "lr": 1.7288227846822726e-05, "epoch": 4.123681338668606, "percentage": 58.91, "elapsed_time": "1 day, 13:28:56", "remaining_time": "1 day, 2:08:42"}
|
| 1135 |
+
{"current_steps": 5675, "total_steps": 9625, "loss": 0.0866, "lr": 1.725229858320018e-05, "epoch": 4.127319025100037, "percentage": 58.96, "elapsed_time": "1 day, 13:30:43", "remaining_time": "1 day, 2:06:34"}
|
| 1136 |
+
{"current_steps": 5680, "total_steps": 9625, "loss": 0.0819, "lr": 1.721637835550672e-05, "epoch": 4.130956711531466, "percentage": 59.01, "elapsed_time": "1 day, 13:32:12", "remaining_time": "1 day, 2:04:15"}
|
| 1137 |
+
{"current_steps": 5685, "total_steps": 9625, "loss": 0.0836, "lr": 1.7180467281867495e-05, "epoch": 4.134594397962895, "percentage": 59.06, "elapsed_time": "1 day, 13:33:42", "remaining_time": "1 day, 2:01:56"}
|
| 1138 |
+
{"current_steps": 5690, "total_steps": 9625, "loss": 0.0746, "lr": 1.7144565480377547e-05, "epoch": 4.138232084394325, "percentage": 59.12, "elapsed_time": "1 day, 13:35:17", "remaining_time": "1 day, 1:59:40"}
|
| 1139 |
+
{"current_steps": 5695, "total_steps": 9625, "loss": 0.1302, "lr": 1.7108673069101423e-05, "epoch": 4.141869770825755, "percentage": 59.17, "elapsed_time": "1 day, 13:37:15", "remaining_time": "1 day, 1:57:41"}
|
| 1140 |
+
{"current_steps": 5700, "total_steps": 9625, "loss": 0.0684, "lr": 1.7072790166072786e-05, "epoch": 4.145507457257184, "percentage": 59.22, "elapsed_time": "1 day, 13:38:44", "remaining_time": "1 day, 1:55:21"}
|
| 1141 |
+
{"current_steps": 5705, "total_steps": 9625, "loss": 0.0766, "lr": 1.7036916889294053e-05, "epoch": 4.149145143688614, "percentage": 59.27, "elapsed_time": "1 day, 13:40:20", "remaining_time": "1 day, 1:53:07"}
|
| 1142 |
+
{"current_steps": 5710, "total_steps": 9625, "loss": 0.0783, "lr": 1.7001053356735956e-05, "epoch": 4.152782830120044, "percentage": 59.32, "elapsed_time": "1 day, 13:41:56", "remaining_time": "1 day, 1:50:52"}
|
| 1143 |
+
{"current_steps": 5715, "total_steps": 9625, "loss": 0.0968, "lr": 1.696519968633721e-05, "epoch": 4.156420516551473, "percentage": 59.38, "elapsed_time": "1 day, 13:44:00", "remaining_time": "1 day, 1:48:57"}
|
| 1144 |
+
{"current_steps": 5720, "total_steps": 9625, "loss": 0.1087, "lr": 1.692935599600408e-05, "epoch": 4.160058202982903, "percentage": 59.43, "elapsed_time": "1 day, 13:45:51", "remaining_time": "1 day, 1:46:53"}
|
| 1145 |
+
{"current_steps": 5725, "total_steps": 9625, "loss": 0.1158, "lr": 1.6893522403610004e-05, "epoch": 4.163695889414332, "percentage": 59.48, "elapsed_time": "1 day, 13:47:39", "remaining_time": "1 day, 1:44:46"}
|
| 1146 |
+
{"current_steps": 5730, "total_steps": 9625, "loss": 0.092, "lr": 1.6857699026995235e-05, "epoch": 4.167333575845762, "percentage": 59.53, "elapsed_time": "1 day, 13:49:16", "remaining_time": "1 day, 1:42:33"}
|
| 1147 |
+
{"current_steps": 5735, "total_steps": 9625, "loss": 0.1067, "lr": 1.6821885983966416e-05, "epoch": 4.170971262277192, "percentage": 59.58, "elapsed_time": "1 day, 13:51:03", "remaining_time": "1 day, 1:40:26"}
|
| 1148 |
+
{"current_steps": 5740, "total_steps": 9625, "loss": 0.122, "lr": 1.6786083392296217e-05, "epoch": 4.174608948708621, "percentage": 59.64, "elapsed_time": "1 day, 13:52:51", "remaining_time": "1 day, 1:38:20"}
|
| 1149 |
+
{"current_steps": 5745, "total_steps": 9625, "loss": 0.0905, "lr": 1.6750291369722922e-05, "epoch": 4.178246635140051, "percentage": 59.69, "elapsed_time": "1 day, 13:54:28", "remaining_time": "1 day, 1:36:06"}
|
| 1150 |
+
{"current_steps": 5750, "total_steps": 9625, "loss": 0.112, "lr": 1.671451003395008e-05, "epoch": 4.181884321571481, "percentage": 59.74, "elapsed_time": "1 day, 13:56:03", "remaining_time": "1 day, 1:33:51"}
|
| 1151 |
+
{"current_steps": 5755, "total_steps": 9625, "loss": 0.0946, "lr": 1.6678739502646092e-05, "epoch": 4.18552200800291, "percentage": 59.79, "elapsed_time": "1 day, 13:57:47", "remaining_time": "1 day, 1:31:43"}
|
| 1152 |
+
{"current_steps": 5760, "total_steps": 9625, "loss": 0.0869, "lr": 1.6642979893443796e-05, "epoch": 4.189159694434339, "percentage": 59.84, "elapsed_time": "1 day, 13:59:51", "remaining_time": "1 day, 1:29:48"}
|
| 1153 |
+
{"current_steps": 5765, "total_steps": 9625, "loss": 0.079, "lr": 1.6607231323940155e-05, "epoch": 4.19279738086577, "percentage": 59.9, "elapsed_time": "1 day, 14:01:33", "remaining_time": "1 day, 1:27:38"}
|
| 1154 |
+
{"current_steps": 5770, "total_steps": 9625, "loss": 0.0767, "lr": 1.65714939116958e-05, "epoch": 4.196435067297199, "percentage": 59.95, "elapsed_time": "1 day, 14:03:36", "remaining_time": "1 day, 1:25:42"}
|
| 1155 |
+
{"current_steps": 5775, "total_steps": 9625, "loss": 0.0835, "lr": 1.6535767774234695e-05, "epoch": 4.200072753728628, "percentage": 60.0, "elapsed_time": "1 day, 14:05:14", "remaining_time": "1 day, 1:23:29"}
|
| 1156 |
+
{"current_steps": 5780, "total_steps": 9625, "loss": 0.1033, "lr": 1.6500053029043702e-05, "epoch": 4.203710440160058, "percentage": 60.05, "elapsed_time": "1 day, 14:07:41", "remaining_time": "1 day, 1:21:49"}
|
| 1157 |
+
{"current_steps": 5785, "total_steps": 9625, "loss": 0.0866, "lr": 1.646434979357222e-05, "epoch": 4.207348126591488, "percentage": 60.1, "elapsed_time": "1 day, 14:09:14", "remaining_time": "1 day, 1:19:33"}
|
| 1158 |
+
{"current_steps": 5790, "total_steps": 9625, "loss": 0.0985, "lr": 1.642865818523183e-05, "epoch": 4.210985813022917, "percentage": 60.16, "elapsed_time": "1 day, 14:10:47", "remaining_time": "1 day, 1:17:18"}
|
| 1159 |
+
{"current_steps": 5795, "total_steps": 9625, "loss": 0.0711, "lr": 1.639297832139583e-05, "epoch": 4.214623499454347, "percentage": 60.21, "elapsed_time": "1 day, 14:12:25", "remaining_time": "1 day, 1:15:05"}
|
| 1160 |
+
{"current_steps": 5800, "total_steps": 9625, "loss": 0.0929, "lr": 1.6357310319398937e-05, "epoch": 4.218261185885777, "percentage": 60.26, "elapsed_time": "1 day, 14:14:12", "remaining_time": "1 day, 1:12:59"}
|