Training in progress, step 8200
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:c9ff29f01d66754a7c0b40fe6cf643ebb562aa3805aadb35ae2f275d7e7cc7aa
|
| 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 sha256:388fd5ef868aacc98ffff465190c2fb1025c09dc9996fce95fad4d868a8096e5
|
| 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 sha256:8aa679502b30435f63541a099f77dc655666608ddfe02c7f3e2ce6b6480c9086
|
| 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:f2133b06dd91ea338aaf0b0fe9cee68a31dc47ee71ea41510cd6e4c85f494062
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -1631,3 +1631,44 @@
|
|
| 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"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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"}
|
| 1634 |
+
{"current_steps": 8005, "total_steps": 9128, "loss": 0.1623, "lr": 1.8193660068570284e-06, "epoch": 6.1396240889911775, "percentage": 87.7, "elapsed_time": "3:03:13", "remaining_time": "0:25:42"}
|
| 1635 |
+
{"current_steps": 8010, "total_steps": 9128, "loss": 0.1657, "lr": 1.803462716645399e-06, "epoch": 6.143459915611814, "percentage": 87.75, "elapsed_time": "3:06:15", "remaining_time": "0:25:59"}
|
| 1636 |
+
{"current_steps": 8015, "total_steps": 9128, "loss": 0.1659, "lr": 1.7876259557772547e-06, "epoch": 6.147295742232451, "percentage": 87.81, "elapsed_time": "3:09:14", "remaining_time": "0:26:16"}
|
| 1637 |
+
{"current_steps": 8020, "total_steps": 9128, "loss": 0.167, "lr": 1.7718557821542303e-06, "epoch": 6.151131568853088, "percentage": 87.86, "elapsed_time": "3:12:10", "remaining_time": "0:26:33"}
|
| 1638 |
+
{"current_steps": 8025, "total_steps": 9128, "loss": 0.1577, "lr": 1.7561522534345132e-06, "epoch": 6.154967395473725, "percentage": 87.92, "elapsed_time": "3:14:59", "remaining_time": "0:26:47"}
|
| 1639 |
+
{"current_steps": 8030, "total_steps": 9128, "loss": 0.1493, "lr": 1.7405154270326208e-06, "epoch": 6.158803222094361, "percentage": 87.97, "elapsed_time": "3:17:25", "remaining_time": "0:26:59"}
|
| 1640 |
+
{"current_steps": 8035, "total_steps": 9128, "loss": 0.1455, "lr": 1.7249453601192013e-06, "epoch": 6.162639048714998, "percentage": 88.03, "elapsed_time": "3:19:54", "remaining_time": "0:27:11"}
|
| 1641 |
+
{"current_steps": 8040, "total_steps": 9128, "loss": 0.1593, "lr": 1.7094421096208136e-06, "epoch": 6.166474875335635, "percentage": 88.08, "elapsed_time": "3:22:41", "remaining_time": "0:27:25"}
|
| 1642 |
+
{"current_steps": 8045, "total_steps": 9128, "loss": 0.1621, "lr": 1.6940057322197367e-06, "epoch": 6.1703107019562715, "percentage": 88.14, "elapsed_time": "3:25:34", "remaining_time": "0:27:40"}
|
| 1643 |
+
{"current_steps": 8050, "total_steps": 9128, "loss": 0.1581, "lr": 1.6786362843537386e-06, "epoch": 6.174146528576908, "percentage": 88.19, "elapsed_time": "3:28:34", "remaining_time": "0:27:55"}
|
| 1644 |
+
{"current_steps": 8055, "total_steps": 9128, "loss": 0.1604, "lr": 1.6633338222158891e-06, "epoch": 6.177982355197545, "percentage": 88.24, "elapsed_time": "3:31:30", "remaining_time": "0:28:10"}
|
| 1645 |
+
{"current_steps": 8060, "total_steps": 9128, "loss": 0.1628, "lr": 1.64809840175435e-06, "epoch": 6.181818181818182, "percentage": 88.3, "elapsed_time": "3:34:30", "remaining_time": "0:28:25"}
|
| 1646 |
+
{"current_steps": 8065, "total_steps": 9128, "loss": 0.1659, "lr": 1.6329300786721635e-06, "epoch": 6.185654008438819, "percentage": 88.35, "elapsed_time": "3:37:18", "remaining_time": "0:28:38"}
|
| 1647 |
+
{"current_steps": 8070, "total_steps": 9128, "loss": 0.1213, "lr": 1.6178289084270571e-06, "epoch": 6.189489835059455, "percentage": 88.41, "elapsed_time": "3:39:26", "remaining_time": "0:28:46"}
|
| 1648 |
+
{"current_steps": 8075, "total_steps": 9128, "loss": 0.1606, "lr": 1.602794946231232e-06, "epoch": 6.193325661680092, "percentage": 88.46, "elapsed_time": "3:42:10", "remaining_time": "0:28:58"}
|
| 1649 |
+
{"current_steps": 8080, "total_steps": 9128, "loss": 0.1554, "lr": 1.587828247051173e-06, "epoch": 6.197161488300729, "percentage": 88.52, "elapsed_time": "3:45:00", "remaining_time": "0:29:11"}
|
| 1650 |
+
{"current_steps": 8085, "total_steps": 9128, "loss": 0.1628, "lr": 1.5729288656074393e-06, "epoch": 6.2009973149213655, "percentage": 88.57, "elapsed_time": "3:47:51", "remaining_time": "0:29:23"}
|
| 1651 |
+
{"current_steps": 8090, "total_steps": 9128, "loss": 0.1511, "lr": 1.5580968563744603e-06, "epoch": 6.204833141542002, "percentage": 88.63, "elapsed_time": "3:50:37", "remaining_time": "0:29:35"}
|
| 1652 |
+
{"current_steps": 8095, "total_steps": 9128, "loss": 0.158, "lr": 1.543332273580349e-06, "epoch": 6.208668968162639, "percentage": 88.68, "elapsed_time": "3:53:28", "remaining_time": "0:29:47"}
|
| 1653 |
+
{"current_steps": 8100, "total_steps": 9128, "loss": 0.1573, "lr": 1.528635171206696e-06, "epoch": 6.212504794783276, "percentage": 88.74, "elapsed_time": "3:56:26", "remaining_time": "0:30:00"}
|
| 1654 |
+
{"current_steps": 8105, "total_steps": 9128, "loss": 0.1553, "lr": 1.5140056029883642e-06, "epoch": 6.216340621403913, "percentage": 88.79, "elapsed_time": "3:58:02", "remaining_time": "0:30:02"}
|
| 1655 |
+
{"current_steps": 8110, "total_steps": 9128, "loss": 0.1396, "lr": 1.4994436224133235e-06, "epoch": 6.220176448024549, "percentage": 88.85, "elapsed_time": "3:59:17", "remaining_time": "0:30:02"}
|
| 1656 |
+
{"current_steps": 8115, "total_steps": 9128, "loss": 0.1342, "lr": 1.4849492827224054e-06, "epoch": 6.224012274645186, "percentage": 88.9, "elapsed_time": "4:00:33", "remaining_time": "0:30:01"}
|
| 1657 |
+
{"current_steps": 8120, "total_steps": 9128, "loss": 0.1316, "lr": 1.4705226369091485e-06, "epoch": 6.227848101265823, "percentage": 88.96, "elapsed_time": "4:01:47", "remaining_time": "0:30:00"}
|
| 1658 |
+
{"current_steps": 8125, "total_steps": 9128, "loss": 0.1361, "lr": 1.4561637377196047e-06, "epoch": 6.2316839278864595, "percentage": 89.01, "elapsed_time": "4:03:05", "remaining_time": "0:30:00"}
|
| 1659 |
+
{"current_steps": 8130, "total_steps": 9128, "loss": 0.134, "lr": 1.4418726376521087e-06, "epoch": 6.235519754507096, "percentage": 89.07, "elapsed_time": "4:04:20", "remaining_time": "0:29:59"}
|
| 1660 |
+
{"current_steps": 8135, "total_steps": 9128, "loss": 0.1242, "lr": 1.4276493889571285e-06, "epoch": 6.239355581127733, "percentage": 89.12, "elapsed_time": "4:05:36", "remaining_time": "0:29:58"}
|
| 1661 |
+
{"current_steps": 8140, "total_steps": 9128, "loss": 0.1375, "lr": 1.4134940436370514e-06, "epoch": 6.24319140774837, "percentage": 89.18, "elapsed_time": "4:06:51", "remaining_time": "0:29:57"}
|
| 1662 |
+
{"current_steps": 8145, "total_steps": 9128, "loss": 0.125, "lr": 1.3994066534460005e-06, "epoch": 6.247027234369007, "percentage": 89.23, "elapsed_time": "4:08:04", "remaining_time": "0:29:56"}
|
| 1663 |
+
{"current_steps": 8150, "total_steps": 9128, "loss": 0.1325, "lr": 1.3853872698896486e-06, "epoch": 6.250863060989643, "percentage": 89.29, "elapsed_time": "4:09:21", "remaining_time": "0:29:55"}
|
| 1664 |
+
{"current_steps": 8155, "total_steps": 9128, "loss": 0.1226, "lr": 1.371435944225017e-06, "epoch": 6.25469888761028, "percentage": 89.34, "elapsed_time": "4:10:38", "remaining_time": "0:29:54"}
|
| 1665 |
+
{"current_steps": 8160, "total_steps": 9128, "loss": 0.1282, "lr": 1.3575527274603006e-06, "epoch": 6.258534714230917, "percentage": 89.4, "elapsed_time": "4:11:55", "remaining_time": "0:29:53"}
|
| 1666 |
+
{"current_steps": 8165, "total_steps": 9128, "loss": 0.1197, "lr": 1.3437376703546855e-06, "epoch": 6.2623705408515535, "percentage": 89.45, "elapsed_time": "4:13:11", "remaining_time": "0:29:51"}
|
| 1667 |
+
{"current_steps": 8170, "total_steps": 9128, "loss": 0.118, "lr": 1.3299908234181412e-06, "epoch": 6.26620636747219, "percentage": 89.5, "elapsed_time": "4:14:24", "remaining_time": "0:29:49"}
|
| 1668 |
+
{"current_steps": 8175, "total_steps": 9128, "loss": 0.1136, "lr": 1.3163122369112591e-06, "epoch": 6.270042194092827, "percentage": 89.56, "elapsed_time": "4:15:40", "remaining_time": "0:29:48"}
|
| 1669 |
+
{"current_steps": 8180, "total_steps": 9128, "loss": 0.1291, "lr": 1.3027019608450652e-06, "epoch": 6.273878020713464, "percentage": 89.61, "elapsed_time": "4:16:58", "remaining_time": "0:29:46"}
|
| 1670 |
+
{"current_steps": 8185, "total_steps": 9128, "loss": 0.1252, "lr": 1.289160044980815e-06, "epoch": 6.2777138473341, "percentage": 89.67, "elapsed_time": "4:18:15", "remaining_time": "0:29:45"}
|
| 1671 |
+
{"current_steps": 8190, "total_steps": 9128, "loss": 0.1305, "lr": 1.275686538829848e-06, "epoch": 6.281549673954737, "percentage": 89.72, "elapsed_time": "4:19:33", "remaining_time": "0:29:43"}
|
| 1672 |
+
{"current_steps": 8195, "total_steps": 9128, "loss": 0.1227, "lr": 1.2622814916533765e-06, "epoch": 6.285385500575374, "percentage": 89.78, "elapsed_time": "4:20:50", "remaining_time": "0:29:41"}
|
| 1673 |
+
{"current_steps": 8200, "total_steps": 9128, "loss": 0.1211, "lr": 1.248944952462312e-06, "epoch": 6.289221327196011, "percentage": 89.83, "elapsed_time": "4:22:06", "remaining_time": "0:29:39"}
|
| 1674 |
+
{"current_steps": 8205, "total_steps": 9128, "loss": 0.1247, "lr": 1.2356769700171035e-06, "epoch": 6.2930571538166475, "percentage": 89.89, "elapsed_time": "4:24:42", "remaining_time": "0:29:46"}
|