Training in progress, step 6400
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:d0e385b45214a70f3d73da0619a7f6e5b68605446320bad09fa20eeb697599a1
|
| 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 sha256:0d286b4fac44d7cf2ea9d6cebf8827c93e6e7a66f42ed606b8445639d7cf387d
|
| 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:de3135b52d98acacd883cf31b5c51f94d1aa52840a4a7e364195b23127190d80
|
| 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 sha256:914167a2757137ac9d22a5da65e44597b9313d6a051264eaeacbe3e79a7f778f
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -1239,3 +1239,43 @@
|
|
| 1239 |
{"current_steps": 6195, "total_steps": 6713, "loss": 0.1718, "lr": 7.240669679660017e-07, "epoch": 6.46113719353156, "percentage": 92.28, "elapsed_time": "1 day, 9:11:15", "remaining_time": "2:46:30"}
|
| 1240 |
{"current_steps": 6200, "total_steps": 6713, "loss": 0.1663, "lr": 7.102657494218879e-07, "epoch": 6.466353677621283, "percentage": 92.36, "elapsed_time": "1 day, 9:13:44", "remaining_time": "2:44:57"}
|
| 1241 |
{"current_steps": 6205, "total_steps": 6713, "loss": 0.1723, "lr": 6.965949520449311e-07, "epoch": 6.471570161711007, "percentage": 92.43, "elapsed_time": "1 day, 9:17:40", "remaining_time": "2:43:32"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1239 |
{"current_steps": 6195, "total_steps": 6713, "loss": 0.1718, "lr": 7.240669679660017e-07, "epoch": 6.46113719353156, "percentage": 92.28, "elapsed_time": "1 day, 9:11:15", "remaining_time": "2:46:30"}
|
| 1240 |
{"current_steps": 6200, "total_steps": 6713, "loss": 0.1663, "lr": 7.102657494218879e-07, "epoch": 6.466353677621283, "percentage": 92.36, "elapsed_time": "1 day, 9:13:44", "remaining_time": "2:44:57"}
|
| 1241 |
{"current_steps": 6205, "total_steps": 6713, "loss": 0.1723, "lr": 6.965949520449311e-07, "epoch": 6.471570161711007, "percentage": 92.43, "elapsed_time": "1 day, 9:17:40", "remaining_time": "2:43:32"}
|
| 1242 |
+
{"current_steps": 6210, "total_steps": 6713, "loss": 0.1661, "lr": 6.830546682657035e-07, "epoch": 6.47678664580073, "percentage": 92.51, "elapsed_time": "1 day, 9:20:36", "remaining_time": "2:42:02"}
|
| 1243 |
+
{"current_steps": 6215, "total_steps": 6713, "loss": 0.1581, "lr": 6.696449896323698e-07, "epoch": 6.482003129890454, "percentage": 92.58, "elapsed_time": "1 day, 9:23:26", "remaining_time": "2:40:31"}
|
| 1244 |
+
{"current_steps": 6220, "total_steps": 6713, "loss": 0.1679, "lr": 6.563660068100408e-07, "epoch": 6.487219613980177, "percentage": 92.66, "elapsed_time": "1 day, 9:26:06", "remaining_time": "2:39:00"}
|
| 1245 |
+
{"current_steps": 6225, "total_steps": 6713, "loss": 0.1594, "lr": 6.432178095801678e-07, "epoch": 6.492436098069901, "percentage": 92.73, "elapsed_time": "1 day, 9:28:51", "remaining_time": "2:37:28"}
|
| 1246 |
+
{"current_steps": 6230, "total_steps": 6713, "loss": 0.1724, "lr": 6.302004868399514e-07, "epoch": 6.497652582159624, "percentage": 92.81, "elapsed_time": "1 day, 9:31:39", "remaining_time": "2:35:57"}
|
| 1247 |
+
{"current_steps": 6235, "total_steps": 6713, "loss": 0.1638, "lr": 6.173141266017113e-07, "epoch": 6.502869066249348, "percentage": 92.88, "elapsed_time": "1 day, 9:34:30", "remaining_time": "2:34:26"}
|
| 1248 |
+
{"current_steps": 6240, "total_steps": 6713, "loss": 0.1707, "lr": 6.045588159923266e-07, "epoch": 6.5080855503390715, "percentage": 92.95, "elapsed_time": "1 day, 9:37:22", "remaining_time": "2:32:55"}
|
| 1249 |
+
{"current_steps": 6245, "total_steps": 6713, "loss": 0.1684, "lr": 5.919346412526117e-07, "epoch": 6.513302034428795, "percentage": 93.03, "elapsed_time": "1 day, 9:40:07", "remaining_time": "2:31:23"}
|
| 1250 |
+
{"current_steps": 6250, "total_steps": 6713, "loss": 0.1658, "lr": 5.794416877367526e-07, "epoch": 6.518518518518518, "percentage": 93.1, "elapsed_time": "1 day, 9:42:30", "remaining_time": "2:29:49"}
|
| 1251 |
+
{"current_steps": 6255, "total_steps": 6713, "loss": 0.179, "lr": 5.670800399117316e-07, "epoch": 6.523735002608242, "percentage": 93.18, "elapsed_time": "1 day, 9:45:12", "remaining_time": "2:28:17"}
|
| 1252 |
+
{"current_steps": 6260, "total_steps": 6713, "loss": 0.1659, "lr": 5.548497813567455e-07, "epoch": 6.528951486697966, "percentage": 93.25, "elapsed_time": "1 day, 9:48:05", "remaining_time": "2:26:45"}
|
| 1253 |
+
{"current_steps": 6265, "total_steps": 6713, "loss": 0.1668, "lr": 5.427509947626486e-07, "epoch": 6.534167970787689, "percentage": 93.33, "elapsed_time": "1 day, 9:50:57", "remaining_time": "2:25:13"}
|
| 1254 |
+
{"current_steps": 6270, "total_steps": 6713, "loss": 0.1666, "lr": 5.307837619313949e-07, "epoch": 6.539384454877412, "percentage": 93.4, "elapsed_time": "1 day, 9:53:36", "remaining_time": "2:23:40"}
|
| 1255 |
+
{"current_steps": 6275, "total_steps": 6713, "loss": 0.1611, "lr": 5.189481637754679e-07, "epoch": 6.544600938967136, "percentage": 93.48, "elapsed_time": "1 day, 9:56:22", "remaining_time": "2:22:08"}
|
| 1256 |
+
{"current_steps": 6280, "total_steps": 6713, "loss": 0.1699, "lr": 5.072442803173649e-07, "epoch": 6.54981742305686, "percentage": 93.55, "elapsed_time": "1 day, 9:59:00", "remaining_time": "2:20:35"}
|
| 1257 |
+
{"current_steps": 6285, "total_steps": 6713, "loss": 0.1683, "lr": 4.956721906890228e-07, "epoch": 6.5550339071465835, "percentage": 93.62, "elapsed_time": "1 day, 10:01:48", "remaining_time": "2:19:02"}
|
| 1258 |
+
{"current_steps": 6290, "total_steps": 6713, "loss": 0.167, "lr": 4.842319731313016e-07, "epoch": 6.560250391236306, "percentage": 93.7, "elapsed_time": "1 day, 10:04:15", "remaining_time": "2:17:28"}
|
| 1259 |
+
{"current_steps": 6295, "total_steps": 6713, "loss": 0.1682, "lr": 4.729237049934621e-07, "epoch": 6.56546687532603, "percentage": 93.77, "elapsed_time": "1 day, 10:07:08", "remaining_time": "2:15:56"}
|
| 1260 |
+
{"current_steps": 6300, "total_steps": 6713, "loss": 0.1708, "lr": 4.6174746273261793e-07, "epoch": 6.570683359415754, "percentage": 93.85, "elapsed_time": "1 day, 10:09:51", "remaining_time": "2:14:22"}
|
| 1261 |
+
{"current_steps": 6305, "total_steps": 6713, "loss": 0.1722, "lr": 4.507033219132395e-07, "epoch": 6.575899843505478, "percentage": 93.92, "elapsed_time": "1 day, 10:12:37", "remaining_time": "2:12:49"}
|
| 1262 |
+
{"current_steps": 6310, "total_steps": 6713, "loss": 0.1627, "lr": 4.3979135720664035e-07, "epoch": 6.5811163275952005, "percentage": 94.0, "elapsed_time": "1 day, 10:15:10", "remaining_time": "2:11:15"}
|
| 1263 |
+
{"current_steps": 6315, "total_steps": 6713, "loss": 0.173, "lr": 4.2901164239046443e-07, "epoch": 6.586332811684924, "percentage": 94.07, "elapsed_time": "1 day, 10:17:48", "remaining_time": "2:09:41"}
|
| 1264 |
+
{"current_steps": 6320, "total_steps": 6713, "loss": 0.1704, "lr": 4.1836425034819106e-07, "epoch": 6.591549295774648, "percentage": 94.15, "elapsed_time": "1 day, 10:20:40", "remaining_time": "2:08:08"}
|
| 1265 |
+
{"current_steps": 6325, "total_steps": 6713, "loss": 0.168, "lr": 4.078492530686506e-07, "epoch": 6.596765779864372, "percentage": 94.22, "elapsed_time": "1 day, 10:23:26", "remaining_time": "2:06:34"}
|
| 1266 |
+
{"current_steps": 6330, "total_steps": 6713, "loss": 0.1719, "lr": 3.9746672164551856e-07, "epoch": 6.601982263954095, "percentage": 94.29, "elapsed_time": "1 day, 10:26:16", "remaining_time": "2:05:01"}
|
| 1267 |
+
{"current_steps": 6335, "total_steps": 6713, "loss": 0.1717, "lr": 3.872167262768578e-07, "epoch": 6.607198748043818, "percentage": 94.37, "elapsed_time": "1 day, 10:28:47", "remaining_time": "2:03:26"}
|
| 1268 |
+
{"current_steps": 6340, "total_steps": 6713, "loss": 0.1641, "lr": 3.7709933626461916e-07, "epoch": 6.612415232133542, "percentage": 94.44, "elapsed_time": "1 day, 10:31:30", "remaining_time": "2:01:52"}
|
| 1269 |
+
{"current_steps": 6345, "total_steps": 6713, "loss": 0.1563, "lr": 3.671146200142017e-07, "epoch": 6.617631716223266, "percentage": 94.52, "elapsed_time": "1 day, 10:34:20", "remaining_time": "2:00:18"}
|
| 1270 |
+
{"current_steps": 6350, "total_steps": 6713, "loss": 0.1659, "lr": 3.5726264503396e-07, "epoch": 6.622848200312989, "percentage": 94.59, "elapsed_time": "1 day, 10:36:53", "remaining_time": "1:58:43"}
|
| 1271 |
+
{"current_steps": 6355, "total_steps": 6713, "loss": 0.1688, "lr": 3.475434779347731e-07, "epoch": 6.6280646844027125, "percentage": 94.67, "elapsed_time": "1 day, 10:39:43", "remaining_time": "1:57:09"}
|
| 1272 |
+
{"current_steps": 6360, "total_steps": 6713, "loss": 0.1688, "lr": 3.3795718442957593e-07, "epoch": 6.633281168492436, "percentage": 94.74, "elapsed_time": "1 day, 10:42:28", "remaining_time": "1:55:35"}
|
| 1273 |
+
{"current_steps": 6365, "total_steps": 6713, "loss": 0.166, "lr": 3.2850382933292903e-07, "epoch": 6.63849765258216, "percentage": 94.82, "elapsed_time": "1 day, 10:45:15", "remaining_time": "1:54:00"}
|
| 1274 |
+
{"current_steps": 6370, "total_steps": 6713, "loss": 0.1707, "lr": 3.1918347656056946e-07, "epoch": 6.643714136671883, "percentage": 94.89, "elapsed_time": "1 day, 10:47:59", "remaining_time": "1:52:25"}
|
| 1275 |
+
{"current_steps": 6375, "total_steps": 6713, "loss": 0.1719, "lr": 3.0999618912898267e-07, "epoch": 6.648930620761607, "percentage": 94.96, "elapsed_time": "1 day, 10:50:39", "remaining_time": "1:50:50"}
|
| 1276 |
+
{"current_steps": 6380, "total_steps": 6713, "loss": 0.1618, "lr": 3.009420291549825e-07, "epoch": 6.65414710485133, "percentage": 95.04, "elapsed_time": "1 day, 10:53:28", "remaining_time": "1:49:16"}
|
| 1277 |
+
{"current_steps": 6385, "total_steps": 6713, "loss": 0.1683, "lr": 2.9202105785527623e-07, "epoch": 6.659363588941054, "percentage": 95.11, "elapsed_time": "1 day, 10:56:07", "remaining_time": "1:47:40"}
|
| 1278 |
+
{"current_steps": 6390, "total_steps": 6713, "loss": 0.1691, "lr": 2.8323333554606923e-07, "epoch": 6.664580073030777, "percentage": 95.19, "elapsed_time": "1 day, 10:58:55", "remaining_time": "1:46:05"}
|
| 1279 |
+
{"current_steps": 6395, "total_steps": 6713, "loss": 0.1633, "lr": 2.745789216426387e-07, "epoch": 6.669796557120501, "percentage": 95.26, "elapsed_time": "1 day, 11:01:44", "remaining_time": "1:44:30"}
|
| 1280 |
+
{"current_steps": 6400, "total_steps": 6713, "loss": 0.1677, "lr": 2.660578746589515e-07, "epoch": 6.675013041210224, "percentage": 95.34, "elapsed_time": "1 day, 11:04:29", "remaining_time": "1:42:55"}
|
| 1281 |
+
{"current_steps": 6405, "total_steps": 6713, "loss": 0.1833, "lr": 2.5767025220724717e-07, "epoch": 6.680229525299948, "percentage": 95.41, "elapsed_time": "1 day, 11:08:17", "remaining_time": "1:41:22"}
|