Training in progress, step 8400
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:a0eebff2e694fc223570fd6f6da96dfe6741123791e69c1c7fb0cb3759a207e8
|
| 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:b02d25a9604b57c8d4bf5c21d91a0a712f526c84b28ec6d1e6b8fb692a8bcf4c
|
| 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 sha256:7dad38fef4fb80ef1abf8aa338530c0b85267dc7b110b86da90ca3805c7095fc
|
| 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:f2583d86b29981481a6a5ad6cb3f17b94ce020e6ef080338c81861a90452a9c2
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -1652,3 +1652,43 @@
|
|
| 1652 |
{"current_steps": 8190, "total_steps": 9625, "loss": 0.1804, "lr": 2.6517529344365687e-06, "epoch": 5.956711531465988, "percentage": 85.09, "elapsed_time": "6:51:11", "remaining_time": "1:12:02"}
|
| 1653 |
{"current_steps": 8195, "total_steps": 9625, "loss": 0.1807, "lr": 2.6337345393557614e-06, "epoch": 5.960349217897417, "percentage": 85.14, "elapsed_time": "6:52:50", "remaining_time": "1:12:02"}
|
| 1654 |
{"current_steps": 8200, "total_steps": 9625, "loss": 0.1983, "lr": 2.615773253952969e-06, "epoch": 5.963986904328847, "percentage": 85.19, "elapsed_time": "6:54:32", "remaining_time": "1:12:02"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1652 |
{"current_steps": 8190, "total_steps": 9625, "loss": 0.1804, "lr": 2.6517529344365687e-06, "epoch": 5.956711531465988, "percentage": 85.09, "elapsed_time": "6:51:11", "remaining_time": "1:12:02"}
|
| 1653 |
{"current_steps": 8195, "total_steps": 9625, "loss": 0.1807, "lr": 2.6337345393557614e-06, "epoch": 5.960349217897417, "percentage": 85.14, "elapsed_time": "6:52:50", "remaining_time": "1:12:02"}
|
| 1654 |
{"current_steps": 8200, "total_steps": 9625, "loss": 0.1983, "lr": 2.615773253952969e-06, "epoch": 5.963986904328847, "percentage": 85.19, "elapsed_time": "6:54:32", "remaining_time": "1:12:02"}
|
| 1655 |
+
{"current_steps": 8205, "total_steps": 9625, "loss": 0.195, "lr": 2.5978691372946174e-06, "epoch": 5.967624590760277, "percentage": 85.25, "elapsed_time": "6:57:20", "remaining_time": "1:12:13"}
|
| 1656 |
+
{"current_steps": 8210, "total_steps": 9625, "loss": 0.1831, "lr": 2.5800222482591375e-06, "epoch": 5.971262277191706, "percentage": 85.3, "elapsed_time": "6:58:59", "remaining_time": "1:12:12"}
|
| 1657 |
+
{"current_steps": 8215, "total_steps": 9625, "loss": 0.1797, "lr": 2.5622326455367486e-06, "epoch": 5.974899963623136, "percentage": 85.35, "elapsed_time": "7:00:36", "remaining_time": "1:12:11"}
|
| 1658 |
+
{"current_steps": 8220, "total_steps": 9625, "loss": 0.191, "lr": 2.5445003876292872e-06, "epoch": 5.978537650054565, "percentage": 85.4, "elapsed_time": "7:02:14", "remaining_time": "1:12:10"}
|
| 1659 |
+
{"current_steps": 8225, "total_steps": 9625, "loss": 0.1866, "lr": 2.526825532850019e-06, "epoch": 5.982175336485994, "percentage": 85.45, "elapsed_time": "7:03:53", "remaining_time": "1:12:09"}
|
| 1660 |
+
{"current_steps": 8230, "total_steps": 9625, "loss": 0.1977, "lr": 2.5092081393234315e-06, "epoch": 5.985813022917425, "percentage": 85.51, "elapsed_time": "7:05:31", "remaining_time": "1:12:07"}
|
| 1661 |
+
{"current_steps": 8235, "total_steps": 9625, "loss": 0.1903, "lr": 2.4916482649850495e-06, "epoch": 5.989450709348854, "percentage": 85.56, "elapsed_time": "7:07:15", "remaining_time": "1:12:07"}
|
| 1662 |
+
{"current_steps": 8240, "total_steps": 9625, "loss": 0.1968, "lr": 2.4741459675812384e-06, "epoch": 5.993088395780283, "percentage": 85.61, "elapsed_time": "7:08:52", "remaining_time": "1:12:05"}
|
| 1663 |
+
{"current_steps": 8245, "total_steps": 9625, "loss": 0.1951, "lr": 2.4567013046690156e-06, "epoch": 5.996726082211714, "percentage": 85.66, "elapsed_time": "7:10:32", "remaining_time": "1:12:03"}
|
| 1664 |
+
{"current_steps": 8250, "total_steps": 9625, "loss": 0.1916, "lr": 2.439314333615883e-06, "epoch": 6.000727537286286, "percentage": 85.71, "elapsed_time": "7:12:25", "remaining_time": "1:12:04"}
|
| 1665 |
+
{"current_steps": 8255, "total_steps": 9625, "loss": 0.0952, "lr": 2.421985111599605e-06, "epoch": 6.004365223717715, "percentage": 85.77, "elapsed_time": "7:14:06", "remaining_time": "1:12:02"}
|
| 1666 |
+
{"current_steps": 8260, "total_steps": 9625, "loss": 0.0787, "lr": 2.4047136956080454e-06, "epoch": 6.008002910149145, "percentage": 85.82, "elapsed_time": "7:15:48", "remaining_time": "1:12:01"}
|
| 1667 |
+
{"current_steps": 8265, "total_steps": 9625, "loss": 0.0725, "lr": 2.3875001424389586e-06, "epoch": 6.011640596580575, "percentage": 85.87, "elapsed_time": "7:17:24", "remaining_time": "1:11:58"}
|
| 1668 |
+
{"current_steps": 8270, "total_steps": 9625, "loss": 0.0921, "lr": 2.3703445086998267e-06, "epoch": 6.015278283012004, "percentage": 85.92, "elapsed_time": "7:19:00", "remaining_time": "1:11:55"}
|
| 1669 |
+
{"current_steps": 8275, "total_steps": 9625, "loss": 0.0713, "lr": 2.35324685080766e-06, "epoch": 6.018915969443434, "percentage": 85.97, "elapsed_time": "7:20:42", "remaining_time": "1:11:53"}
|
| 1670 |
+
{"current_steps": 8280, "total_steps": 9625, "loss": 0.0991, "lr": 2.3362072249888e-06, "epoch": 6.022553655874864, "percentage": 86.03, "elapsed_time": "7:22:18", "remaining_time": "1:11:50"}
|
| 1671 |
+
{"current_steps": 8285, "total_steps": 9625, "loss": 0.1093, "lr": 2.3192256872787677e-06, "epoch": 6.026191342306293, "percentage": 86.08, "elapsed_time": "7:24:04", "remaining_time": "1:11:49"}
|
| 1672 |
+
{"current_steps": 8290, "total_steps": 9625, "loss": 0.0822, "lr": 2.3023022935220363e-06, "epoch": 6.029829028737723, "percentage": 86.13, "elapsed_time": "7:25:39", "remaining_time": "1:11:45"}
|
| 1673 |
+
{"current_steps": 8295, "total_steps": 9625, "loss": 0.1059, "lr": 2.28543709937189e-06, "epoch": 6.033466715169152, "percentage": 86.18, "elapsed_time": "7:27:39", "remaining_time": "1:11:46"}
|
| 1674 |
+
{"current_steps": 8300, "total_steps": 9625, "loss": 0.0744, "lr": 2.268630160290213e-06, "epoch": 6.037104401600582, "percentage": 86.23, "elapsed_time": "7:29:45", "remaining_time": "1:11:47"}
|
| 1675 |
+
{"current_steps": 8305, "total_steps": 9625, "loss": 0.0746, "lr": 2.2518815315473108e-06, "epoch": 6.040742088032012, "percentage": 86.29, "elapsed_time": "7:31:45", "remaining_time": "1:11:48"}
|
| 1676 |
+
{"current_steps": 8310, "total_steps": 9625, "loss": 0.0735, "lr": 2.235191268221746e-06, "epoch": 6.044379774463441, "percentage": 86.34, "elapsed_time": "7:33:29", "remaining_time": "1:11:45"}
|
| 1677 |
+
{"current_steps": 8315, "total_steps": 9625, "loss": 0.0906, "lr": 2.2185594252001263e-06, "epoch": 6.0480174608948705, "percentage": 86.39, "elapsed_time": "7:35:21", "remaining_time": "1:11:44"}
|
| 1678 |
+
{"current_steps": 8320, "total_steps": 9625, "loss": 0.0927, "lr": 2.2019860571769545e-06, "epoch": 6.051655147326301, "percentage": 86.44, "elapsed_time": "7:37:01", "remaining_time": "1:11:41"}
|
| 1679 |
+
{"current_steps": 8325, "total_steps": 9625, "loss": 0.074, "lr": 2.1854712186544334e-06, "epoch": 6.05529283375773, "percentage": 86.49, "elapsed_time": "7:38:41", "remaining_time": "1:11:37"}
|
| 1680 |
+
{"current_steps": 8330, "total_steps": 9625, "loss": 0.0685, "lr": 2.1690149639422954e-06, "epoch": 6.0589305201891595, "percentage": 86.55, "elapsed_time": "7:40:17", "remaining_time": "1:11:33"}
|
| 1681 |
+
{"current_steps": 8335, "total_steps": 9625, "loss": 0.073, "lr": 2.1526173471576018e-06, "epoch": 6.06256820662059, "percentage": 86.6, "elapsed_time": "7:41:50", "remaining_time": "1:11:28"}
|
| 1682 |
+
{"current_steps": 8340, "total_steps": 9625, "loss": 0.0848, "lr": 2.1362784222245845e-06, "epoch": 6.066205893052019, "percentage": 86.65, "elapsed_time": "7:43:21", "remaining_time": "1:11:23"}
|
| 1683 |
+
{"current_steps": 8345, "total_steps": 9625, "loss": 0.0822, "lr": 2.119998242874488e-06, "epoch": 6.069843579483448, "percentage": 86.7, "elapsed_time": "7:45:11", "remaining_time": "1:11:21"}
|
| 1684 |
+
{"current_steps": 8350, "total_steps": 9625, "loss": 0.0826, "lr": 2.1037768626453347e-06, "epoch": 6.073481265914878, "percentage": 86.75, "elapsed_time": "7:46:47", "remaining_time": "1:11:16"}
|
| 1685 |
+
{"current_steps": 8355, "total_steps": 9625, "loss": 0.092, "lr": 2.087614334881811e-06, "epoch": 6.077118952346308, "percentage": 86.81, "elapsed_time": "7:48:41", "remaining_time": "1:11:14"}
|
| 1686 |
+
{"current_steps": 8360, "total_steps": 9625, "loss": 0.1083, "lr": 2.0715107127350453e-06, "epoch": 6.080756638777737, "percentage": 86.86, "elapsed_time": "7:50:19", "remaining_time": "1:11:10"}
|
| 1687 |
+
{"current_steps": 8365, "total_steps": 9625, "loss": 0.0702, "lr": 2.055466049162467e-06, "epoch": 6.084394325209167, "percentage": 86.91, "elapsed_time": "7:51:49", "remaining_time": "1:11:04"}
|
| 1688 |
+
{"current_steps": 8370, "total_steps": 9625, "loss": 0.1064, "lr": 2.0394803969276156e-06, "epoch": 6.088032011640596, "percentage": 86.96, "elapsed_time": "7:53:24", "remaining_time": "1:10:58"}
|
| 1689 |
+
{"current_steps": 8375, "total_steps": 9625, "loss": 0.0922, "lr": 2.023553808599954e-06, "epoch": 6.091669698072026, "percentage": 87.01, "elapsed_time": "7:55:12", "remaining_time": "1:10:55"}
|
| 1690 |
+
{"current_steps": 8380, "total_steps": 9625, "loss": 0.0791, "lr": 2.007686336554735e-06, "epoch": 6.095307384503456, "percentage": 87.06, "elapsed_time": "7:56:55", "remaining_time": "1:10:51"}
|
| 1691 |
+
{"current_steps": 8385, "total_steps": 9625, "loss": 0.2422, "lr": 1.991878032972785e-06, "epoch": 6.098945070934885, "percentage": 87.12, "elapsed_time": "7:59:04", "remaining_time": "1:10:50"}
|
| 1692 |
+
{"current_steps": 8390, "total_steps": 9625, "loss": 0.112, "lr": 1.976128949840361e-06, "epoch": 6.102582757366315, "percentage": 87.17, "elapsed_time": "8:00:50", "remaining_time": "1:10:46"}
|
| 1693 |
+
{"current_steps": 8395, "total_steps": 9625, "loss": 0.0902, "lr": 1.9604391389489753e-06, "epoch": 6.106220443797745, "percentage": 87.22, "elapsed_time": "8:02:47", "remaining_time": "1:10:44"}
|
| 1694 |
+
{"current_steps": 8400, "total_steps": 9625, "loss": 0.1715, "lr": 1.9448086518952115e-06, "epoch": 6.109858130229174, "percentage": 87.27, "elapsed_time": "8:05:00", "remaining_time": "1:10:43"}
|