Training in progress, step 6200
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 sha256:311428ed999ee3d795fe1e401e74336a9b9880fdfe5fb97d8c30a8b052df45cd
|
| 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 sha256:51a4c4e3612d2dc95784929510f9489ec700cfbf02b8873b0d393987134d9cce
|
| 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 sha256:6c7d291d4d2e0a4ce4df71be242d529baf1e73ab862dfba23b88eb25b904e999
|
| 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 sha256:2c01da7b7bda5e548b2d4dc23c0c6bc95b6d5b1c9a7dabd5715ebb2fd7588ba8
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -1198,3 +1198,43 @@
|
|
| 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"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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"}
|
| 1201 |
+
{"current_steps": 6005, "total_steps": 9625, "loss": 0.0863, "lr": 1.4906577595175428e-05, "epoch": 4.367406329574391, "percentage": 62.39, "elapsed_time": "1 day, 15:27:02", "remaining_time": "23:46:55"}
|
| 1202 |
+
{"current_steps": 6010, "total_steps": 9625, "loss": 0.1078, "lr": 1.4871513174816445e-05, "epoch": 4.37104401600582, "percentage": 62.44, "elapsed_time": "1 day, 15:28:58", "remaining_time": "23:44:55"}
|
| 1203 |
+
{"current_steps": 6015, "total_steps": 9625, "loss": 0.1761, "lr": 1.483646561969726e-05, "epoch": 4.3746817024372495, "percentage": 62.49, "elapsed_time": "1 day, 15:31:56", "remaining_time": "23:43:33"}
|
| 1204 |
+
{"current_steps": 6020, "total_steps": 9625, "loss": 0.1887, "lr": 1.4801435045073197e-05, "epoch": 4.37831938886868, "percentage": 62.55, "elapsed_time": "1 day, 15:34:55", "remaining_time": "23:42:11"}
|
| 1205 |
+
{"current_steps": 6025, "total_steps": 9625, "loss": 0.1772, "lr": 1.4766421566143726e-05, "epoch": 4.381957075300109, "percentage": 62.6, "elapsed_time": "1 day, 15:37:33", "remaining_time": "23:40:36"}
|
| 1206 |
+
{"current_steps": 6030, "total_steps": 9625, "loss": 0.1716, "lr": 1.4731425298052133e-05, "epoch": 4.3855947617315385, "percentage": 62.65, "elapsed_time": "1 day, 15:40:37", "remaining_time": "23:39:17"}
|
| 1207 |
+
{"current_steps": 6035, "total_steps": 9625, "loss": 0.1768, "lr": 1.469644635588507e-05, "epoch": 4.389232448162969, "percentage": 62.7, "elapsed_time": "1 day, 15:43:41", "remaining_time": "23:37:57"}
|
| 1208 |
+
{"current_steps": 6040, "total_steps": 9625, "loss": 0.1819, "lr": 1.4661484854672234e-05, "epoch": 4.392870134594398, "percentage": 62.75, "elapsed_time": "1 day, 15:46:44", "remaining_time": "23:36:37"}
|
| 1209 |
+
{"current_steps": 6045, "total_steps": 9625, "loss": 0.1854, "lr": 1.4626540909385954e-05, "epoch": 4.3965078210258275, "percentage": 62.81, "elapsed_time": "1 day, 15:49:45", "remaining_time": "23:35:16"}
|
| 1210 |
+
{"current_steps": 6050, "total_steps": 9625, "loss": 0.1753, "lr": 1.4591614634940836e-05, "epoch": 4.400145507457257, "percentage": 62.86, "elapsed_time": "1 day, 15:52:41", "remaining_time": "23:33:51"}
|
| 1211 |
+
{"current_steps": 6055, "total_steps": 9625, "loss": 0.173, "lr": 1.4556706146193374e-05, "epoch": 4.403783193888687, "percentage": 62.91, "elapsed_time": "1 day, 15:55:22", "remaining_time": "23:32:18"}
|
| 1212 |
+
{"current_steps": 6060, "total_steps": 9625, "loss": 0.1536, "lr": 1.4521815557941547e-05, "epoch": 4.4074208803201165, "percentage": 62.96, "elapsed_time": "1 day, 15:58:07", "remaining_time": "23:30:46"}
|
| 1213 |
+
{"current_steps": 6065, "total_steps": 9625, "loss": 0.175, "lr": 1.4486942984924519e-05, "epoch": 4.411058566751546, "percentage": 63.01, "elapsed_time": "1 day, 16:00:52", "remaining_time": "23:29:14"}
|
| 1214 |
+
{"current_steps": 6070, "total_steps": 9625, "loss": 0.1647, "lr": 1.4452088541822156e-05, "epoch": 4.414696253182976, "percentage": 63.06, "elapsed_time": "1 day, 16:03:37", "remaining_time": "23:27:43"}
|
| 1215 |
+
{"current_steps": 6075, "total_steps": 9625, "loss": 0.1717, "lr": 1.4417252343254739e-05, "epoch": 4.4183339396144055, "percentage": 63.12, "elapsed_time": "1 day, 16:06:27", "remaining_time": "23:26:14"}
|
| 1216 |
+
{"current_steps": 6080, "total_steps": 9625, "loss": 0.1647, "lr": 1.4382434503782538e-05, "epoch": 4.421971626045835, "percentage": 63.17, "elapsed_time": "1 day, 16:09:22", "remaining_time": "23:24:48"}
|
| 1217 |
+
{"current_steps": 6085, "total_steps": 9625, "loss": 0.1668, "lr": 1.4347635137905445e-05, "epoch": 4.425609312477264, "percentage": 63.22, "elapsed_time": "1 day, 16:12:00", "remaining_time": "23:23:12"}
|
| 1218 |
+
{"current_steps": 6090, "total_steps": 9625, "loss": 0.1749, "lr": 1.4312854360062615e-05, "epoch": 4.429246998908694, "percentage": 63.27, "elapsed_time": "1 day, 16:14:43", "remaining_time": "23:21:39"}
|
| 1219 |
+
{"current_steps": 6095, "total_steps": 9625, "loss": 0.167, "lr": 1.427809228463205e-05, "epoch": 4.432884685340124, "percentage": 63.32, "elapsed_time": "1 day, 16:17:32", "remaining_time": "23:20:09"}
|
| 1220 |
+
{"current_steps": 6100, "total_steps": 9625, "loss": 0.1746, "lr": 1.4243349025930286e-05, "epoch": 4.436522371771553, "percentage": 63.38, "elapsed_time": "1 day, 16:20:31", "remaining_time": "23:18:44"}
|
| 1221 |
+
{"current_steps": 6105, "total_steps": 9625, "loss": 0.184, "lr": 1.4208624698211937e-05, "epoch": 4.4401600582029825, "percentage": 63.43, "elapsed_time": "1 day, 16:23:19", "remaining_time": "23:17:13"}
|
| 1222 |
+
{"current_steps": 6110, "total_steps": 9625, "loss": 0.1577, "lr": 1.41739194156694e-05, "epoch": 4.443797744634413, "percentage": 63.48, "elapsed_time": "1 day, 16:25:42", "remaining_time": "23:15:28"}
|
| 1223 |
+
{"current_steps": 6115, "total_steps": 9625, "loss": 0.1577, "lr": 1.4139233292432411e-05, "epoch": 4.447435431065842, "percentage": 63.53, "elapsed_time": "1 day, 16:28:35", "remaining_time": "23:14:00"}
|
| 1224 |
+
{"current_steps": 6120, "total_steps": 9625, "loss": 0.1669, "lr": 1.4104566442567712e-05, "epoch": 4.4510731174972715, "percentage": 63.58, "elapsed_time": "1 day, 16:31:30", "remaining_time": "23:12:33"}
|
| 1225 |
+
{"current_steps": 6125, "total_steps": 9625, "loss": 0.1656, "lr": 1.406991898007868e-05, "epoch": 4.454710803928702, "percentage": 63.64, "elapsed_time": "1 day, 16:34:17", "remaining_time": "23:11:01"}
|
| 1226 |
+
{"current_steps": 6130, "total_steps": 9625, "loss": 0.1722, "lr": 1.4035291018904896e-05, "epoch": 4.458348490360131, "percentage": 63.69, "elapsed_time": "1 day, 16:37:10", "remaining_time": "23:09:32"}
|
| 1227 |
+
{"current_steps": 6135, "total_steps": 9625, "loss": 0.1645, "lr": 1.400068267292186e-05, "epoch": 4.4619861767915605, "percentage": 63.74, "elapsed_time": "1 day, 16:40:13", "remaining_time": "23:08:09"}
|
| 1228 |
+
{"current_steps": 6140, "total_steps": 9625, "loss": 0.1577, "lr": 1.396609405594052e-05, "epoch": 4.46562386322299, "percentage": 63.79, "elapsed_time": "1 day, 16:43:13", "remaining_time": "23:06:45"}
|
| 1229 |
+
{"current_steps": 6145, "total_steps": 9625, "loss": 0.1471, "lr": 1.3931525281706972e-05, "epoch": 4.46926154965442, "percentage": 63.84, "elapsed_time": "1 day, 16:46:16", "remaining_time": "23:05:21"}
|
| 1230 |
+
{"current_steps": 6150, "total_steps": 9625, "loss": 0.1458, "lr": 1.3896976463902054e-05, "epoch": 4.4728992360858495, "percentage": 63.9, "elapsed_time": "1 day, 16:49:06", "remaining_time": "23:03:51"}
|
| 1231 |
+
{"current_steps": 6155, "total_steps": 9625, "loss": 0.1727, "lr": 1.3862447716140973e-05, "epoch": 4.476536922517279, "percentage": 63.95, "elapsed_time": "1 day, 16:51:55", "remaining_time": "23:02:19"}
|
| 1232 |
+
{"current_steps": 6160, "total_steps": 9625, "loss": 0.1598, "lr": 1.3827939151972937e-05, "epoch": 4.480174608948708, "percentage": 64.0, "elapsed_time": "1 day, 16:54:16", "remaining_time": "23:00:31"}
|
| 1233 |
+
{"current_steps": 6165, "total_steps": 9625, "loss": 0.1737, "lr": 1.3793450884880767e-05, "epoch": 4.4838122953801385, "percentage": 64.05, "elapsed_time": "1 day, 16:57:04", "remaining_time": "22:58:59"}
|
| 1234 |
+
{"current_steps": 6170, "total_steps": 9625, "loss": 0.1787, "lr": 1.3758983028280568e-05, "epoch": 4.487449981811568, "percentage": 64.1, "elapsed_time": "1 day, 17:00:02", "remaining_time": "22:57:32"}
|
| 1235 |
+
{"current_steps": 6175, "total_steps": 9625, "loss": 0.1766, "lr": 1.3724535695521289e-05, "epoch": 4.491087668242997, "percentage": 64.16, "elapsed_time": "1 day, 17:02:55", "remaining_time": "22:56:02"}
|
| 1236 |
+
{"current_steps": 6180, "total_steps": 9625, "loss": 0.1672, "lr": 1.36901089998844e-05, "epoch": 4.4947253546744275, "percentage": 64.21, "elapsed_time": "1 day, 17:05:51", "remaining_time": "22:54:34"}
|
| 1237 |
+
{"current_steps": 6185, "total_steps": 9625, "loss": 0.1763, "lr": 1.3655703054583512e-05, "epoch": 4.498363041105857, "percentage": 64.26, "elapsed_time": "1 day, 17:08:50", "remaining_time": "22:53:07"}
|
| 1238 |
+
{"current_steps": 6190, "total_steps": 9625, "loss": 0.1678, "lr": 1.3621317972763981e-05, "epoch": 4.502000727537286, "percentage": 64.31, "elapsed_time": "1 day, 17:11:51", "remaining_time": "22:51:42"}
|
| 1239 |
+
{"current_steps": 6195, "total_steps": 9625, "loss": 0.1718, "lr": 1.3586953867502576e-05, "epoch": 4.505638413968716, "percentage": 64.36, "elapsed_time": "1 day, 17:14:49", "remaining_time": "22:50:14"}
|
| 1240 |
+
{"current_steps": 6200, "total_steps": 9625, "loss": 0.172, "lr": 1.3552610851807062e-05, "epoch": 4.509276100400146, "percentage": 64.42, "elapsed_time": "1 day, 17:17:52", "remaining_time": "22:48:49"}
|