Training in progress, step 7000
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:f7a46a7360648b302ad0496bf93b6d3883c74942d028f41e2f50657143073314
|
| 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 sha256:1bb33d70743fcb25214de545b3a46fb9e6288d529b974bd563cb20cbff66a685
|
| 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:b8dac38a9b4adcb43291642a70a5ef6eb103ddcbf339b577cce72743807483c0
|
| 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:e63b56d38c9ba30bc8ae30cd09cbfcc7e90f6cc5f31636110e5ace74deae0df8
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -1369,3 +1369,35 @@
|
|
| 1369 |
{"current_steps": 6845, "total_steps": 9128, "loss": 0.1334, "lr": 7.156295353832161e-06, "epoch": 5.2493287303413885, "percentage": 74.99, "elapsed_time": "1 day, 19:05:35", "remaining_time": "14:22:21"}
|
| 1370 |
{"current_steps": 6850, "total_steps": 9128, "loss": 0.1363, "lr": 7.127004349938234e-06, "epoch": 5.253164556962025, "percentage": 75.04, "elapsed_time": "1 day, 19:06:53", "remaining_time": "14:20:17"}
|
| 1371 |
{"current_steps": 6855, "total_steps": 9128, "loss": 0.1355, "lr": 7.0977604116994795e-06, "epoch": 5.257000383582662, "percentage": 75.1, "elapsed_time": "1 day, 19:08:12", "remaining_time": "14:18:12"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1369 |
{"current_steps": 6845, "total_steps": 9128, "loss": 0.1334, "lr": 7.156295353832161e-06, "epoch": 5.2493287303413885, "percentage": 74.99, "elapsed_time": "1 day, 19:05:35", "remaining_time": "14:22:21"}
|
| 1370 |
{"current_steps": 6850, "total_steps": 9128, "loss": 0.1363, "lr": 7.127004349938234e-06, "epoch": 5.253164556962025, "percentage": 75.04, "elapsed_time": "1 day, 19:06:53", "remaining_time": "14:20:17"}
|
| 1371 |
{"current_steps": 6855, "total_steps": 9128, "loss": 0.1355, "lr": 7.0977604116994795e-06, "epoch": 5.257000383582662, "percentage": 75.1, "elapsed_time": "1 day, 19:08:12", "remaining_time": "14:18:12"}
|
| 1372 |
+
{"current_steps": 6860, "total_steps": 9128, "loss": 0.131, "lr": 7.068563646036244e-06, "epoch": 5.260836210203299, "percentage": 75.15, "elapsed_time": "1 day, 19:09:28", "remaining_time": "14:16:06"}
|
| 1373 |
+
{"current_steps": 6865, "total_steps": 9128, "loss": 0.1214, "lr": 7.039414159696418e-06, "epoch": 5.264672036823936, "percentage": 75.21, "elapsed_time": "1 day, 19:10:42", "remaining_time": "14:14:00"}
|
| 1374 |
+
{"current_steps": 6870, "total_steps": 9128, "loss": 0.1263, "lr": 7.010312059254998e-06, "epoch": 5.268507863444572, "percentage": 75.26, "elapsed_time": "1 day, 19:11:56", "remaining_time": "14:11:54"}
|
| 1375 |
+
{"current_steps": 6875, "total_steps": 9128, "loss": 0.1296, "lr": 6.981257451113741e-06, "epoch": 5.272343690065209, "percentage": 75.32, "elapsed_time": "1 day, 19:13:13", "remaining_time": "14:09:49"}
|
| 1376 |
+
{"current_steps": 6880, "total_steps": 9128, "loss": 0.1308, "lr": 6.952250441500794e-06, "epoch": 5.276179516685846, "percentage": 75.37, "elapsed_time": "1 day, 19:14:27", "remaining_time": "14:07:43"}
|
| 1377 |
+
{"current_steps": 6885, "total_steps": 9128, "loss": 0.1365, "lr": 6.923291136470225e-06, "epoch": 5.2800153433064825, "percentage": 75.43, "elapsed_time": "1 day, 19:15:46", "remaining_time": "14:05:39"}
|
| 1378 |
+
{"current_steps": 6890, "total_steps": 9128, "loss": 0.133, "lr": 6.894379641901734e-06, "epoch": 5.283851169927119, "percentage": 75.48, "elapsed_time": "1 day, 19:16:59", "remaining_time": "14:03:33"}
|
| 1379 |
+
{"current_steps": 6895, "total_steps": 9128, "loss": 0.1323, "lr": 6.865516063500199e-06, "epoch": 5.287686996547756, "percentage": 75.54, "elapsed_time": "1 day, 19:18:16", "remaining_time": "14:01:28"}
|
| 1380 |
+
{"current_steps": 6900, "total_steps": 9128, "loss": 0.1301, "lr": 6.836700506795289e-06, "epoch": 5.291522823168393, "percentage": 75.59, "elapsed_time": "1 day, 19:19:34", "remaining_time": "13:59:23"}
|
| 1381 |
+
{"current_steps": 6905, "total_steps": 9128, "loss": 0.1334, "lr": 6.807933077141147e-06, "epoch": 5.29535864978903, "percentage": 75.65, "elapsed_time": "1 day, 19:20:55", "remaining_time": "13:57:20"}
|
| 1382 |
+
{"current_steps": 6910, "total_steps": 9128, "loss": 0.1318, "lr": 6.779213879715902e-06, "epoch": 5.299194476409666, "percentage": 75.7, "elapsed_time": "1 day, 19:22:10", "remaining_time": "13:55:15"}
|
| 1383 |
+
{"current_steps": 6915, "total_steps": 9128, "loss": 0.1189, "lr": 6.750543019521372e-06, "epoch": 5.303030303030303, "percentage": 75.76, "elapsed_time": "1 day, 19:23:23", "remaining_time": "13:53:09"}
|
| 1384 |
+
{"current_steps": 6920, "total_steps": 9128, "loss": 0.1263, "lr": 6.721920601382652e-06, "epoch": 5.30686612965094, "percentage": 75.81, "elapsed_time": "1 day, 19:24:38", "remaining_time": "13:51:04"}
|
| 1385 |
+
{"current_steps": 6925, "total_steps": 9128, "loss": 0.1289, "lr": 6.693346729947687e-06, "epoch": 5.3107019562715765, "percentage": 75.87, "elapsed_time": "1 day, 19:25:53", "remaining_time": "13:48:59"}
|
| 1386 |
+
{"current_steps": 6930, "total_steps": 9128, "loss": 0.1277, "lr": 6.664821509686976e-06, "epoch": 5.314537782892213, "percentage": 75.92, "elapsed_time": "1 day, 19:27:07", "remaining_time": "13:46:54"}
|
| 1387 |
+
{"current_steps": 6935, "total_steps": 9128, "loss": 0.138, "lr": 6.636345044893116e-06, "epoch": 5.31837360951285, "percentage": 75.98, "elapsed_time": "1 day, 19:28:27", "remaining_time": "13:44:51"}
|
| 1388 |
+
{"current_steps": 6940, "total_steps": 9128, "loss": 0.124, "lr": 6.607917439680427e-06, "epoch": 5.322209436133487, "percentage": 76.03, "elapsed_time": "1 day, 19:29:43", "remaining_time": "13:42:46"}
|
| 1389 |
+
{"current_steps": 6945, "total_steps": 9128, "loss": 0.1282, "lr": 6.579538797984635e-06, "epoch": 5.326045262754123, "percentage": 76.08, "elapsed_time": "1 day, 19:30:57", "remaining_time": "13:40:41"}
|
| 1390 |
+
{"current_steps": 6950, "total_steps": 9128, "loss": 0.1262, "lr": 6.551209223562427e-06, "epoch": 5.32988108937476, "percentage": 76.14, "elapsed_time": "1 day, 19:32:11", "remaining_time": "13:38:36"}
|
| 1391 |
+
{"current_steps": 6955, "total_steps": 9128, "loss": 0.1287, "lr": 6.52292881999107e-06, "epoch": 5.333716915995397, "percentage": 76.19, "elapsed_time": "1 day, 19:33:27", "remaining_time": "13:36:32"}
|
| 1392 |
+
{"current_steps": 6960, "total_steps": 9128, "loss": 0.1247, "lr": 6.494697690668094e-06, "epoch": 5.337552742616034, "percentage": 76.25, "elapsed_time": "1 day, 19:34:42", "remaining_time": "13:34:28"}
|
| 1393 |
+
{"current_steps": 6965, "total_steps": 9128, "loss": 0.1246, "lr": 6.466515938810856e-06, "epoch": 5.3413885692366705, "percentage": 76.3, "elapsed_time": "1 day, 19:35:55", "remaining_time": "13:32:22"}
|
| 1394 |
+
{"current_steps": 6970, "total_steps": 9128, "loss": 0.1176, "lr": 6.4383836674561766e-06, "epoch": 5.345224395857307, "percentage": 76.36, "elapsed_time": "1 day, 19:37:10", "remaining_time": "13:30:18"}
|
| 1395 |
+
{"current_steps": 6975, "total_steps": 9128, "loss": 0.127, "lr": 6.410300979459976e-06, "epoch": 5.349060222477944, "percentage": 76.41, "elapsed_time": "1 day, 19:38:27", "remaining_time": "13:28:15"}
|
| 1396 |
+
{"current_steps": 6980, "total_steps": 9128, "loss": 0.127, "lr": 6.382267977496886e-06, "epoch": 5.352896049098581, "percentage": 76.47, "elapsed_time": "1 day, 19:39:41", "remaining_time": "13:26:10"}
|
| 1397 |
+
{"current_steps": 6985, "total_steps": 9128, "loss": 0.1251, "lr": 6.3542847640598815e-06, "epoch": 5.356731875719218, "percentage": 76.52, "elapsed_time": "1 day, 19:40:57", "remaining_time": "13:24:06"}
|
| 1398 |
+
{"current_steps": 6990, "total_steps": 9128, "loss": 0.1239, "lr": 6.326351441459908e-06, "epoch": 5.360567702339854, "percentage": 76.58, "elapsed_time": "1 day, 19:42:11", "remaining_time": "13:22:02"}
|
| 1399 |
+
{"current_steps": 6995, "total_steps": 9128, "loss": 0.1307, "lr": 6.298468111825478e-06, "epoch": 5.364403528960491, "percentage": 76.63, "elapsed_time": "1 day, 19:43:27", "remaining_time": "13:19:58"}
|
| 1400 |
+
{"current_steps": 7000, "total_steps": 9128, "loss": 0.1216, "lr": 6.270634877102357e-06, "epoch": 5.368239355581128, "percentage": 76.69, "elapsed_time": "1 day, 19:44:41", "remaining_time": "13:17:54"}
|
| 1401 |
+
{"current_steps": 7005, "total_steps": 9128, "loss": 0.1314, "lr": 6.242851839053132e-06, "epoch": 5.3720751822017645, "percentage": 76.74, "elapsed_time": "1 day, 19:47:20", "remaining_time": "13:16:15"}
|
| 1402 |
+
{"current_steps": 7010, "total_steps": 9128, "loss": 0.1332, "lr": 6.2151190992568745e-06, "epoch": 5.375911008822401, "percentage": 76.8, "elapsed_time": "1 day, 19:48:39", "remaining_time": "13:14:13"}
|
| 1403 |
+
{"current_steps": 7015, "total_steps": 9128, "loss": 0.1341, "lr": 6.187436759108749e-06, "epoch": 5.379746835443038, "percentage": 76.85, "elapsed_time": "1 day, 19:49:57", "remaining_time": "13:12:10"}
|