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 sha256:50a8be3223a2c431cab257a24dffcbf1df7787661e5774f0d967e211ce4131fb
|
| 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 sha256:21d5900cae423d1f228b451cd12dc7f7970c142fbf8da9c7519bbb1ef288f0e7
|
| 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:dd94f6b777b796543d6b08ccffb107204bb49c671918395111d6a0e89726d827
|
| 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:cc06e27611684543a7657574de34d6fd09d217709b4ed5eff58386b883da8b17
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -1261,3 +1261,44 @@
|
|
| 1261 |
{"current_steps": 6190, "total_steps": 6713, "loss": 0.2054, "lr": 7.379985143648815e-07, "epoch": 6.455920709441836, "percentage": 92.21, "elapsed_time": "1 day, 0:42:51", "remaining_time": "2:05:17"}
|
| 1262 |
{"current_steps": 6195, "total_steps": 6713, "loss": 0.196, "lr": 7.240669679660017e-07, "epoch": 6.46113719353156, "percentage": 92.28, "elapsed_time": "1 day, 0:44:46", "remaining_time": "2:04:09"}
|
| 1263 |
{"current_steps": 6200, "total_steps": 6713, "loss": 0.1998, "lr": 7.102657494218879e-07, "epoch": 6.466353677621283, "percentage": 92.36, "elapsed_time": "1 day, 0:46:30", "remaining_time": "2:02:59"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1261 |
{"current_steps": 6190, "total_steps": 6713, "loss": 0.2054, "lr": 7.379985143648815e-07, "epoch": 6.455920709441836, "percentage": 92.21, "elapsed_time": "1 day, 0:42:51", "remaining_time": "2:05:17"}
|
| 1262 |
{"current_steps": 6195, "total_steps": 6713, "loss": 0.196, "lr": 7.240669679660017e-07, "epoch": 6.46113719353156, "percentage": 92.28, "elapsed_time": "1 day, 0:44:46", "remaining_time": "2:04:09"}
|
| 1263 |
{"current_steps": 6200, "total_steps": 6713, "loss": 0.1998, "lr": 7.102657494218879e-07, "epoch": 6.466353677621283, "percentage": 92.36, "elapsed_time": "1 day, 0:46:30", "remaining_time": "2:02:59"}
|
| 1264 |
+
{"current_steps": 6205, "total_steps": 6713, "loss": 0.1939, "lr": 6.965949520449311e-07, "epoch": 6.471570161711007, "percentage": 92.43, "elapsed_time": "1 day, 0:49:34", "remaining_time": "2:01:57"}
|
| 1265 |
+
{"current_steps": 6210, "total_steps": 6713, "loss": 0.1958, "lr": 6.830546682657035e-07, "epoch": 6.47678664580073, "percentage": 92.51, "elapsed_time": "1 day, 0:51:16", "remaining_time": "2:00:47"}
|
| 1266 |
+
{"current_steps": 6215, "total_steps": 6713, "loss": 0.2084, "lr": 6.696449896323698e-07, "epoch": 6.482003129890454, "percentage": 92.58, "elapsed_time": "1 day, 0:52:53", "remaining_time": "1:59:37"}
|
| 1267 |
+
{"current_steps": 6220, "total_steps": 6713, "loss": 0.1999, "lr": 6.563660068100408e-07, "epoch": 6.487219613980177, "percentage": 92.66, "elapsed_time": "1 day, 0:54:30", "remaining_time": "1:58:27"}
|
| 1268 |
+
{"current_steps": 6225, "total_steps": 6713, "loss": 0.1941, "lr": 6.432178095801678e-07, "epoch": 6.492436098069901, "percentage": 92.73, "elapsed_time": "1 day, 0:56:15", "remaining_time": "1:57:17"}
|
| 1269 |
+
{"current_steps": 6230, "total_steps": 6713, "loss": 0.1978, "lr": 6.302004868399514e-07, "epoch": 6.497652582159624, "percentage": 92.81, "elapsed_time": "1 day, 0:57:54", "remaining_time": "1:56:07"}
|
| 1270 |
+
{"current_steps": 6235, "total_steps": 6713, "loss": 0.1894, "lr": 6.173141266017113e-07, "epoch": 6.502869066249348, "percentage": 92.88, "elapsed_time": "1 day, 0:59:37", "remaining_time": "1:54:58"}
|
| 1271 |
+
{"current_steps": 6240, "total_steps": 6713, "loss": 0.1828, "lr": 6.045588159923266e-07, "epoch": 6.5080855503390715, "percentage": 92.95, "elapsed_time": "1 day, 1:01:18", "remaining_time": "1:53:48"}
|
| 1272 |
+
{"current_steps": 6245, "total_steps": 6713, "loss": 0.1936, "lr": 5.919346412526117e-07, "epoch": 6.513302034428795, "percentage": 93.03, "elapsed_time": "1 day, 1:02:56", "remaining_time": "1:52:37"}
|
| 1273 |
+
{"current_steps": 6250, "total_steps": 6713, "loss": 0.1979, "lr": 5.794416877367526e-07, "epoch": 6.518518518518518, "percentage": 93.1, "elapsed_time": "1 day, 1:04:34", "remaining_time": "1:51:27"}
|
| 1274 |
+
{"current_steps": 6255, "total_steps": 6713, "loss": 0.1939, "lr": 5.670800399117316e-07, "epoch": 6.523735002608242, "percentage": 93.18, "elapsed_time": "1 day, 1:06:17", "remaining_time": "1:50:17"}
|
| 1275 |
+
{"current_steps": 6260, "total_steps": 6713, "loss": 0.1933, "lr": 5.548497813567455e-07, "epoch": 6.528951486697966, "percentage": 93.25, "elapsed_time": "1 day, 1:07:57", "remaining_time": "1:49:07"}
|
| 1276 |
+
{"current_steps": 6265, "total_steps": 6713, "loss": 0.187, "lr": 5.427509947626486e-07, "epoch": 6.534167970787689, "percentage": 93.33, "elapsed_time": "1 day, 1:09:35", "remaining_time": "1:47:56"}
|
| 1277 |
+
{"current_steps": 6270, "total_steps": 6713, "loss": 0.1941, "lr": 5.307837619313949e-07, "epoch": 6.539384454877412, "percentage": 93.4, "elapsed_time": "1 day, 1:11:17", "remaining_time": "1:46:46"}
|
| 1278 |
+
{"current_steps": 6275, "total_steps": 6713, "loss": 0.184, "lr": 5.189481637754679e-07, "epoch": 6.544600938967136, "percentage": 93.48, "elapsed_time": "1 day, 1:12:57", "remaining_time": "1:45:36"}
|
| 1279 |
+
{"current_steps": 6280, "total_steps": 6713, "loss": 0.188, "lr": 5.072442803173649e-07, "epoch": 6.54981742305686, "percentage": 93.55, "elapsed_time": "1 day, 1:14:36", "remaining_time": "1:44:25"}
|
| 1280 |
+
{"current_steps": 6285, "total_steps": 6713, "loss": 0.1883, "lr": 4.956721906890228e-07, "epoch": 6.5550339071465835, "percentage": 93.62, "elapsed_time": "1 day, 1:16:14", "remaining_time": "1:43:15"}
|
| 1281 |
+
{"current_steps": 6290, "total_steps": 6713, "loss": 0.1927, "lr": 4.842319731313016e-07, "epoch": 6.560250391236306, "percentage": 93.7, "elapsed_time": "1 day, 1:17:58", "remaining_time": "1:42:05"}
|
| 1282 |
+
{"current_steps": 6295, "total_steps": 6713, "loss": 0.1849, "lr": 4.729237049934621e-07, "epoch": 6.56546687532603, "percentage": 93.77, "elapsed_time": "1 day, 1:19:36", "remaining_time": "1:40:54"}
|
| 1283 |
+
{"current_steps": 6300, "total_steps": 6713, "loss": 0.1938, "lr": 4.6174746273261793e-07, "epoch": 6.570683359415754, "percentage": 93.85, "elapsed_time": "1 day, 1:21:13", "remaining_time": "1:39:43"}
|
| 1284 |
+
{"current_steps": 6305, "total_steps": 6713, "loss": 0.1961, "lr": 4.507033219132395e-07, "epoch": 6.575899843505478, "percentage": 93.92, "elapsed_time": "1 day, 1:22:48", "remaining_time": "1:38:32"}
|
| 1285 |
+
{"current_steps": 6310, "total_steps": 6713, "loss": 0.1878, "lr": 4.3979135720664035e-07, "epoch": 6.5811163275952005, "percentage": 94.0, "elapsed_time": "1 day, 1:24:31", "remaining_time": "1:37:22"}
|
| 1286 |
+
{"current_steps": 6315, "total_steps": 6713, "loss": 0.1851, "lr": 4.2901164239046443e-07, "epoch": 6.586332811684924, "percentage": 94.07, "elapsed_time": "1 day, 1:26:13", "remaining_time": "1:36:11"}
|
| 1287 |
+
{"current_steps": 6320, "total_steps": 6713, "loss": 0.2041, "lr": 4.1836425034819106e-07, "epoch": 6.591549295774648, "percentage": 94.15, "elapsed_time": "1 day, 1:27:54", "remaining_time": "1:35:00"}
|
| 1288 |
+
{"current_steps": 6325, "total_steps": 6713, "loss": 0.1916, "lr": 4.078492530686506e-07, "epoch": 6.596765779864372, "percentage": 94.22, "elapsed_time": "1 day, 1:29:39", "remaining_time": "1:33:50"}
|
| 1289 |
+
{"current_steps": 6330, "total_steps": 6713, "loss": 0.1832, "lr": 3.9746672164551856e-07, "epoch": 6.601982263954095, "percentage": 94.29, "elapsed_time": "1 day, 1:31:17", "remaining_time": "1:32:39"}
|
| 1290 |
+
{"current_steps": 6335, "total_steps": 6713, "loss": 0.1992, "lr": 3.872167262768578e-07, "epoch": 6.607198748043818, "percentage": 94.37, "elapsed_time": "1 day, 1:32:59", "remaining_time": "1:31:28"}
|
| 1291 |
+
{"current_steps": 6340, "total_steps": 6713, "loss": 0.1923, "lr": 3.7709933626461916e-07, "epoch": 6.612415232133542, "percentage": 94.44, "elapsed_time": "1 day, 1:34:42", "remaining_time": "1:30:17"}
|
| 1292 |
+
{"current_steps": 6345, "total_steps": 6713, "loss": 0.1911, "lr": 3.671146200142017e-07, "epoch": 6.617631716223266, "percentage": 94.52, "elapsed_time": "1 day, 1:36:28", "remaining_time": "1:29:06"}
|
| 1293 |
+
{"current_steps": 6350, "total_steps": 6713, "loss": 0.1793, "lr": 3.5726264503396e-07, "epoch": 6.622848200312989, "percentage": 94.59, "elapsed_time": "1 day, 1:38:05", "remaining_time": "1:27:55"}
|
| 1294 |
+
{"current_steps": 6355, "total_steps": 6713, "loss": 0.2011, "lr": 3.475434779347731e-07, "epoch": 6.6280646844027125, "percentage": 94.67, "elapsed_time": "1 day, 1:39:45", "remaining_time": "1:26:44"}
|
| 1295 |
+
{"current_steps": 6360, "total_steps": 6713, "loss": 0.1865, "lr": 3.3795718442957593e-07, "epoch": 6.633281168492436, "percentage": 94.74, "elapsed_time": "1 day, 1:41:30", "remaining_time": "1:25:33"}
|
| 1296 |
+
{"current_steps": 6365, "total_steps": 6713, "loss": 0.1941, "lr": 3.2850382933292903e-07, "epoch": 6.63849765258216, "percentage": 94.82, "elapsed_time": "1 day, 1:43:07", "remaining_time": "1:24:22"}
|
| 1297 |
+
{"current_steps": 6370, "total_steps": 6713, "loss": 0.1882, "lr": 3.1918347656056946e-07, "epoch": 6.643714136671883, "percentage": 94.89, "elapsed_time": "1 day, 1:44:49", "remaining_time": "1:23:10"}
|
| 1298 |
+
{"current_steps": 6375, "total_steps": 6713, "loss": 0.1982, "lr": 3.0999618912898267e-07, "epoch": 6.648930620761607, "percentage": 94.96, "elapsed_time": "1 day, 1:46:33", "remaining_time": "1:21:59"}
|
| 1299 |
+
{"current_steps": 6380, "total_steps": 6713, "loss": 0.1854, "lr": 3.009420291549825e-07, "epoch": 6.65414710485133, "percentage": 95.04, "elapsed_time": "1 day, 1:48:13", "remaining_time": "1:20:48"}
|
| 1300 |
+
{"current_steps": 6385, "total_steps": 6713, "loss": 0.1989, "lr": 2.9202105785527623e-07, "epoch": 6.659363588941054, "percentage": 95.11, "elapsed_time": "1 day, 1:49:54", "remaining_time": "1:19:37"}
|
| 1301 |
+
{"current_steps": 6390, "total_steps": 6713, "loss": 0.1846, "lr": 2.8323333554606923e-07, "epoch": 6.664580073030777, "percentage": 95.19, "elapsed_time": "1 day, 1:51:37", "remaining_time": "1:18:25"}
|
| 1302 |
+
{"current_steps": 6395, "total_steps": 6713, "loss": 0.1826, "lr": 2.745789216426387e-07, "epoch": 6.669796557120501, "percentage": 95.26, "elapsed_time": "1 day, 1:53:18", "remaining_time": "1:17:14"}
|
| 1303 |
+
{"current_steps": 6400, "total_steps": 6713, "loss": 0.1748, "lr": 2.660578746589515e-07, "epoch": 6.675013041210224, "percentage": 95.34, "elapsed_time": "1 day, 1:54:55", "remaining_time": "1:16:02"}
|
| 1304 |
+
{"current_steps": 6405, "total_steps": 6713, "loss": 0.1991, "lr": 2.5767025220724717e-07, "epoch": 6.680229525299948, "percentage": 95.41, "elapsed_time": "1 day, 1:58:02", "remaining_time": "1:14:55"}
|