Training in progress, step 8000
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 sha256:67d60c03a1e73c15929f5b7ae1800af9b30c7f139390c1ad17e19171d7981bf4
|
| 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 sha256:2fc577bfd3b682b97335e35bea3b71c499ea716bedd9a2c997bfa2dcc7a16867
|
| 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 sha256:7a64d5ddfb9abad8f55cf71848d5ff0c37b519d15b0e292450007b5864ab7d62
|
| 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 sha256:1df618dcc9e40a7185bca069b87d6be57d5ca1ac38d21dd5b4ec4353309143b6
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -1609,3 +1609,25 @@
|
|
| 1609 |
{"current_steps": 7880, "total_steps": 9128, "loss": 0.1582, "lr": 2.2383959773471765e-06, "epoch": 6.043728423475259, "percentage": 86.33, "elapsed_time": "1:50:45", "remaining_time": "0:17:32"}
|
| 1610 |
{"current_steps": 7885, "total_steps": 9128, "loss": 0.167, "lr": 2.220848979259682e-06, "epoch": 6.0475642500958955, "percentage": 86.38, "elapsed_time": "1:53:32", "remaining_time": "0:17:53"}
|
| 1611 |
{"current_steps": 7890, "total_steps": 9128, "loss": 0.1583, "lr": 2.2033669844871897e-06, "epoch": 6.051400076716533, "percentage": 86.44, "elapsed_time": "1:56:21", "remaining_time": "0:18:15"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1609 |
{"current_steps": 7880, "total_steps": 9128, "loss": 0.1582, "lr": 2.2383959773471765e-06, "epoch": 6.043728423475259, "percentage": 86.33, "elapsed_time": "1:50:45", "remaining_time": "0:17:32"}
|
| 1610 |
{"current_steps": 7885, "total_steps": 9128, "loss": 0.167, "lr": 2.220848979259682e-06, "epoch": 6.0475642500958955, "percentage": 86.38, "elapsed_time": "1:53:32", "remaining_time": "0:17:53"}
|
| 1611 |
{"current_steps": 7890, "total_steps": 9128, "loss": 0.1583, "lr": 2.2033669844871897e-06, "epoch": 6.051400076716533, "percentage": 86.44, "elapsed_time": "1:56:21", "remaining_time": "0:18:15"}
|
| 1612 |
+
{"current_steps": 7895, "total_steps": 9128, "loss": 0.1571, "lr": 2.1859500569465818e-06, "epoch": 6.055235903337169, "percentage": 86.49, "elapsed_time": "1:59:11", "remaining_time": "0:18:36"}
|
| 1613 |
+
{"current_steps": 7900, "total_steps": 9128, "loss": 0.1636, "lr": 2.1685982603168144e-06, "epoch": 6.059071729957806, "percentage": 86.55, "elapsed_time": "2:01:53", "remaining_time": "0:18:56"}
|
| 1614 |
+
{"current_steps": 7905, "total_steps": 9128, "loss": 0.1586, "lr": 2.1513116580387304e-06, "epoch": 6.062907556578443, "percentage": 86.6, "elapsed_time": "2:04:43", "remaining_time": "0:19:17"}
|
| 1615 |
+
{"current_steps": 7910, "total_steps": 9128, "loss": 0.1613, "lr": 2.1340903133148205e-06, "epoch": 6.066743383199079, "percentage": 86.66, "elapsed_time": "2:07:41", "remaining_time": "0:19:39"}
|
| 1616 |
+
{"current_steps": 7915, "total_steps": 9128, "loss": 0.1726, "lr": 2.116934289108967e-06, "epoch": 6.070579209819716, "percentage": 86.71, "elapsed_time": "2:10:31", "remaining_time": "0:20:00"}
|
| 1617 |
+
{"current_steps": 7920, "total_steps": 9128, "loss": 0.1791, "lr": 2.0998436481462315e-06, "epoch": 6.074415036440353, "percentage": 86.77, "elapsed_time": "2:13:10", "remaining_time": "0:20:18"}
|
| 1618 |
+
{"current_steps": 7925, "total_steps": 9128, "loss": 0.1333, "lr": 2.0828184529126473e-06, "epoch": 6.0782508630609895, "percentage": 86.82, "elapsed_time": "2:15:51", "remaining_time": "0:20:37"}
|
| 1619 |
+
{"current_steps": 7930, "total_steps": 9128, "loss": 0.1587, "lr": 2.065858765654931e-06, "epoch": 6.082086689681627, "percentage": 86.88, "elapsed_time": "2:18:41", "remaining_time": "0:20:57"}
|
| 1620 |
+
{"current_steps": 7935, "total_steps": 9128, "loss": 0.1576, "lr": 2.048964648380325e-06, "epoch": 6.085922516302263, "percentage": 86.93, "elapsed_time": "2:21:36", "remaining_time": "0:21:17"}
|
| 1621 |
+
{"current_steps": 7940, "total_steps": 9128, "loss": 0.1636, "lr": 2.0321361628563263e-06, "epoch": 6.0897583429229, "percentage": 86.99, "elapsed_time": "2:24:22", "remaining_time": "0:21:36"}
|
| 1622 |
+
{"current_steps": 7945, "total_steps": 9128, "loss": 0.1618, "lr": 2.015373370610456e-06, "epoch": 6.093594169543537, "percentage": 87.04, "elapsed_time": "2:27:23", "remaining_time": "0:21:56"}
|
| 1623 |
+
{"current_steps": 7950, "total_steps": 9128, "loss": 0.1545, "lr": 1.9986763329300783e-06, "epoch": 6.097429996164173, "percentage": 87.09, "elapsed_time": "2:30:24", "remaining_time": "0:22:17"}
|
| 1624 |
+
{"current_steps": 7955, "total_steps": 9128, "loss": 0.1408, "lr": 1.982045110862134e-06, "epoch": 6.10126582278481, "percentage": 87.15, "elapsed_time": "2:33:26", "remaining_time": "0:22:37"}
|
| 1625 |
+
{"current_steps": 7960, "total_steps": 9128, "loss": 0.1445, "lr": 1.965479765212921e-06, "epoch": 6.105101649405447, "percentage": 87.2, "elapsed_time": "2:36:20", "remaining_time": "0:22:56"}
|
| 1626 |
+
{"current_steps": 7965, "total_steps": 9128, "loss": 0.1548, "lr": 1.9489803565479094e-06, "epoch": 6.1089374760260835, "percentage": 87.26, "elapsed_time": "2:39:21", "remaining_time": "0:23:16"}
|
| 1627 |
+
{"current_steps": 7970, "total_steps": 9128, "loss": 0.1432, "lr": 1.9325469451914714e-06, "epoch": 6.112773302646721, "percentage": 87.31, "elapsed_time": "2:41:27", "remaining_time": "0:23:27"}
|
| 1628 |
+
{"current_steps": 7975, "total_steps": 9128, "loss": 0.1647, "lr": 1.9161795912266945e-06, "epoch": 6.116609129267357, "percentage": 87.37, "elapsed_time": "2:44:17", "remaining_time": "0:23:45"}
|
| 1629 |
+
{"current_steps": 7980, "total_steps": 9128, "loss": 0.1761, "lr": 1.899878354495146e-06, "epoch": 6.120444955887994, "percentage": 87.42, "elapsed_time": "2:47:16", "remaining_time": "0:24:03"}
|
| 1630 |
+
{"current_steps": 7985, "total_steps": 9128, "loss": 0.1693, "lr": 1.8836432945966487e-06, "epoch": 6.124280782508631, "percentage": 87.48, "elapsed_time": "2:50:08", "remaining_time": "0:24:21"}
|
| 1631 |
+
{"current_steps": 7990, "total_steps": 9128, "loss": 0.16, "lr": 1.8674744708890969e-06, "epoch": 6.128116609129267, "percentage": 87.53, "elapsed_time": "2:53:01", "remaining_time": "0:24:38"}
|
| 1632 |
+
{"current_steps": 7995, "total_steps": 9128, "loss": 0.1627, "lr": 1.851371942488196e-06, "epoch": 6.131952435749904, "percentage": 87.59, "elapsed_time": "2:56:04", "remaining_time": "0:24:57"}
|
| 1633 |
+
{"current_steps": 8000, "total_steps": 9128, "loss": 0.1676, "lr": 1.8353357682672613e-06, "epoch": 6.135788262370541, "percentage": 87.64, "elapsed_time": "2:59:01", "remaining_time": "0:25:14"}
|