Training in progress, step 6000
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 sha256:65d2f5d83e3579d3f809ea673e00bfc5ea2d84ad2709550f8cbd0b11a1fc7c26
|
| 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 sha256:4f9e32a11735c267bf8bbc25498ca5ee6bd36d6653cd9dda08a54675b26f0982
|
| 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 sha256:60fbb35e471ecf4d79f65dbe936980ce50f57fe9bb2d87896267000f30240f8a
|
| 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 sha256:154f634d203008172391eb14c988eb8ec5623fc06766cdf5619be779af99a011
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -1158,3 +1158,43 @@
|
|
| 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"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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"}
|
| 1161 |
+
{"current_steps": 5805, "total_steps": 9625, "loss": 0.085, "lr": 1.632165429653683e-05, "epoch": 4.221898872317206, "percentage": 60.31, "elapsed_time": "1 day, 14:16:53", "remaining_time": "1 day, 1:11:28"}
|
| 1162 |
+
{"current_steps": 5810, "total_steps": 9625, "loss": 0.0769, "lr": 1.628601037006582e-05, "epoch": 4.225536558748636, "percentage": 60.36, "elapsed_time": "1 day, 14:18:31", "remaining_time": "1 day, 1:09:16"}
|
| 1163 |
+
{"current_steps": 5815, "total_steps": 9625, "loss": 0.0857, "lr": 1.6250378657202414e-05, "epoch": 4.229174245180065, "percentage": 60.42, "elapsed_time": "1 day, 14:20:10", "remaining_time": "1 day, 1:07:04"}
|
| 1164 |
+
{"current_steps": 5820, "total_steps": 9625, "loss": 0.0891, "lr": 1.6214759275122953e-05, "epoch": 4.232811931611495, "percentage": 60.47, "elapsed_time": "1 day, 14:21:46", "remaining_time": "1 day, 1:04:51"}
|
| 1165 |
+
{"current_steps": 5825, "total_steps": 9625, "loss": 0.1036, "lr": 1.6179152340963268e-05, "epoch": 4.236449618042925, "percentage": 60.52, "elapsed_time": "1 day, 14:23:33", "remaining_time": "1 day, 1:02:45"}
|
| 1166 |
+
{"current_steps": 5830, "total_steps": 9625, "loss": 0.085, "lr": 1.6143557971818205e-05, "epoch": 4.240087304474354, "percentage": 60.57, "elapsed_time": "1 day, 14:25:12", "remaining_time": "1 day, 1:00:33"}
|
| 1167 |
+
{"current_steps": 5835, "total_steps": 9625, "loss": 0.1041, "lr": 1.610797628474132e-05, "epoch": 4.243724990905784, "percentage": 60.62, "elapsed_time": "1 day, 14:26:42", "remaining_time": "1 day, 0:58:16"}
|
| 1168 |
+
{"current_steps": 5840, "total_steps": 9625, "loss": 0.1077, "lr": 1.6072407396744447e-05, "epoch": 4.247362677337214, "percentage": 60.68, "elapsed_time": "1 day, 14:28:42", "remaining_time": "1 day, 0:56:18"}
|
| 1169 |
+
{"current_steps": 5845, "total_steps": 9625, "loss": 0.0878, "lr": 1.6036851424797338e-05, "epoch": 4.251000363768643, "percentage": 60.73, "elapsed_time": "1 day, 14:30:20", "remaining_time": "1 day, 0:54:06"}
|
| 1170 |
+
{"current_steps": 5850, "total_steps": 9625, "loss": 0.0737, "lr": 1.6001308485827284e-05, "epoch": 4.2546380502000725, "percentage": 60.78, "elapsed_time": "1 day, 14:31:55", "remaining_time": "1 day, 0:51:52"}
|
| 1171 |
+
{"current_steps": 5855, "total_steps": 9625, "loss": 0.0848, "lr": 1.5965778696718672e-05, "epoch": 4.258275736631503, "percentage": 60.83, "elapsed_time": "1 day, 14:33:28", "remaining_time": "1 day, 0:49:37"}
|
| 1172 |
+
{"current_steps": 5860, "total_steps": 9625, "loss": 0.1129, "lr": 1.5930262174312704e-05, "epoch": 4.261913423062932, "percentage": 60.88, "elapsed_time": "1 day, 14:35:33", "remaining_time": "1 day, 0:47:43"}
|
| 1173 |
+
{"current_steps": 5865, "total_steps": 9625, "loss": 0.0717, "lr": 1.5894759035406902e-05, "epoch": 4.2655511094943614, "percentage": 60.94, "elapsed_time": "1 day, 14:37:03", "remaining_time": "1 day, 0:45:26"}
|
| 1174 |
+
{"current_steps": 5870, "total_steps": 9625, "loss": 0.0858, "lr": 1.5859269396754814e-05, "epoch": 4.269188795925791, "percentage": 60.99, "elapsed_time": "1 day, 14:39:07", "remaining_time": "1 day, 0:43:31"}
|
| 1175 |
+
{"current_steps": 5875, "total_steps": 9625, "loss": 0.0815, "lr": 1.5823793375065566e-05, "epoch": 4.272826482357221, "percentage": 61.04, "elapsed_time": "1 day, 14:40:49", "remaining_time": "1 day, 0:41:22"}
|
| 1176 |
+
{"current_steps": 5880, "total_steps": 9625, "loss": 0.0696, "lr": 1.5788331087003515e-05, "epoch": 4.27646416878865, "percentage": 61.09, "elapsed_time": "1 day, 14:42:29", "remaining_time": "1 day, 0:39:12"}
|
| 1177 |
+
{"current_steps": 5885, "total_steps": 9625, "loss": 0.0907, "lr": 1.575288264918786e-05, "epoch": 4.28010185522008, "percentage": 61.14, "elapsed_time": "1 day, 14:44:11", "remaining_time": "1 day, 0:37:03"}
|
| 1178 |
+
{"current_steps": 5890, "total_steps": 9625, "loss": 0.0762, "lr": 1.5717448178192233e-05, "epoch": 4.28373954165151, "percentage": 61.19, "elapsed_time": "1 day, 14:45:55", "remaining_time": "1 day, 0:34:55"}
|
| 1179 |
+
{"current_steps": 5895, "total_steps": 9625, "loss": 0.1089, "lr": 1.568202779054437e-05, "epoch": 4.287377228082939, "percentage": 61.25, "elapsed_time": "1 day, 14:47:40", "remaining_time": "1 day, 0:32:48"}
|
| 1180 |
+
{"current_steps": 5900, "total_steps": 9625, "loss": 0.104, "lr": 1.5646621602725654e-05, "epoch": 4.291014914514369, "percentage": 61.3, "elapsed_time": "1 day, 14:49:23", "remaining_time": "1 day, 0:30:40"}
|
| 1181 |
+
{"current_steps": 5905, "total_steps": 9625, "loss": 0.0711, "lr": 1.5611229731170793e-05, "epoch": 4.294652600945798, "percentage": 61.35, "elapsed_time": "1 day, 14:50:56", "remaining_time": "1 day, 0:28:26"}
|
| 1182 |
+
{"current_steps": 5910, "total_steps": 9625, "loss": 0.1006, "lr": 1.5575852292267414e-05, "epoch": 4.298290287377228, "percentage": 61.4, "elapsed_time": "1 day, 14:52:30", "remaining_time": "1 day, 0:26:12"}
|
| 1183 |
+
{"current_steps": 5915, "total_steps": 9625, "loss": 0.0806, "lr": 1.5540489402355678e-05, "epoch": 4.301927973808658, "percentage": 61.45, "elapsed_time": "1 day, 14:54:05", "remaining_time": "1 day, 0:23:59"}
|
| 1184 |
+
{"current_steps": 5920, "total_steps": 9625, "loss": 0.0922, "lr": 1.5505141177727913e-05, "epoch": 4.305565660240087, "percentage": 61.51, "elapsed_time": "1 day, 14:55:36", "remaining_time": "1 day, 0:21:43"}
|
| 1185 |
+
{"current_steps": 5925, "total_steps": 9625, "loss": 0.1056, "lr": 1.5469807734628183e-05, "epoch": 4.3092033466715165, "percentage": 61.56, "elapsed_time": "1 day, 14:57:29", "remaining_time": "1 day, 0:19:41"}
|
| 1186 |
+
{"current_steps": 5930, "total_steps": 9625, "loss": 0.1144, "lr": 1.5434489189252e-05, "epoch": 4.312841033102947, "percentage": 61.61, "elapsed_time": "1 day, 14:59:17", "remaining_time": "1 day, 0:17:37"}
|
| 1187 |
+
{"current_steps": 5935, "total_steps": 9625, "loss": 0.088, "lr": 1.539918565774584e-05, "epoch": 4.316478719534376, "percentage": 61.66, "elapsed_time": "1 day, 15:01:20", "remaining_time": "1 day, 0:15:41"}
|
| 1188 |
+
{"current_steps": 5940, "total_steps": 9625, "loss": 0.0905, "lr": 1.5363897256206805e-05, "epoch": 4.3201164059658055, "percentage": 61.71, "elapsed_time": "1 day, 15:03:00", "remaining_time": "1 day, 0:13:31"}
|
| 1189 |
+
{"current_steps": 5945, "total_steps": 9625, "loss": 0.0815, "lr": 1.532862410068227e-05, "epoch": 4.323754092397236, "percentage": 61.77, "elapsed_time": "1 day, 15:04:32", "remaining_time": "1 day, 0:11:17"}
|
| 1190 |
+
{"current_steps": 5950, "total_steps": 9625, "loss": 0.0797, "lr": 1.529336630716945e-05, "epoch": 4.327391778828665, "percentage": 61.82, "elapsed_time": "1 day, 15:06:03", "remaining_time": "1 day, 0:09:02"}
|
| 1191 |
+
{"current_steps": 5955, "total_steps": 9625, "loss": 0.0764, "lr": 1.525812399161506e-05, "epoch": 4.3310294652600945, "percentage": 61.87, "elapsed_time": "1 day, 15:07:33", "remaining_time": "1 day, 0:06:46"}
|
| 1192 |
+
{"current_steps": 5960, "total_steps": 9625, "loss": 0.0927, "lr": 1.5222897269914892e-05, "epoch": 4.334667151691524, "percentage": 61.92, "elapsed_time": "1 day, 15:09:05", "remaining_time": "1 day, 0:04:32"}
|
| 1193 |
+
{"current_steps": 5965, "total_steps": 9625, "loss": 0.077, "lr": 1.5187686257913466e-05, "epoch": 4.338304838122954, "percentage": 61.97, "elapsed_time": "1 day, 15:10:40", "remaining_time": "1 day, 0:02:19"}
|
| 1194 |
+
{"current_steps": 5970, "total_steps": 9625, "loss": 0.0777, "lr": 1.515249107140365e-05, "epoch": 4.3419425245543835, "percentage": 62.03, "elapsed_time": "1 day, 15:12:16", "remaining_time": "1 day, 0:00:07"}
|
| 1195 |
+
{"current_steps": 5975, "total_steps": 9625, "loss": 0.0935, "lr": 1.511731182612626e-05, "epoch": 4.345580210985813, "percentage": 62.08, "elapsed_time": "1 day, 15:13:52", "remaining_time": "23:57:55"}
|
| 1196 |
+
{"current_steps": 5980, "total_steps": 9625, "loss": 0.072, "lr": 1.5082148637769694e-05, "epoch": 4.349217897417242, "percentage": 62.13, "elapsed_time": "1 day, 15:15:56", "remaining_time": "23:56:01"}
|
| 1197 |
+
{"current_steps": 5985, "total_steps": 9625, "loss": 0.0784, "lr": 1.5047001621969537e-05, "epoch": 4.352855583848672, "percentage": 62.18, "elapsed_time": "1 day, 15:17:42", "remaining_time": "23:53:55"}
|
| 1198 |
+
{"current_steps": 5990, "total_steps": 9625, "loss": 0.0758, "lr": 1.5011870894308205e-05, "epoch": 4.356493270280102, "percentage": 62.23, "elapsed_time": "1 day, 15:19:33", "remaining_time": "23:51:52"}
|
| 1199 |
+
{"current_steps": 5995, "total_steps": 9625, "loss": 0.1788, "lr": 1.497675657031453e-05, "epoch": 4.360130956711531, "percentage": 62.29, "elapsed_time": "1 day, 15:22:30", "remaining_time": "23:50:30"}
|
| 1200 |
+
{"current_steps": 6000, "total_steps": 9625, "loss": 0.075, "lr": 1.4941658765463412e-05, "epoch": 4.363768643142961, "percentage": 62.34, "elapsed_time": "1 day, 15:24:05", "remaining_time": "23:48:18"}
|