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:dd6ba679180e17b7424b269139ef0276c68203d04d8cbbd7a27707b6fab734a1
|
| 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 sha256:2afdf3fc1b3cdcf06212c68db2da15211305b7f0c2414145a323a2b68a9c2bc2
|
| 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 sha256:2e696b5e09889c5fd6002b9ed5af162216ce73026bc1156b8503a4b151ce62c0
|
| 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:be7730cd8004a6e0649dcddda702eac4bcae1a3cef83daefd9fe4d288906c6fb
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -1612,3 +1612,43 @@
|
|
| 1612 |
{"current_steps": 7990, "total_steps": 9625, "loss": 0.1777, "lr": 3.4186176050614937e-06, "epoch": 5.811204074208804, "percentage": 83.01, "elapsed_time": "5:42:58", "remaining_time": "1:10:11"}
|
| 1613 |
{"current_steps": 7995, "total_steps": 9625, "loss": 0.1824, "lr": 3.398365391027323e-06, "epoch": 5.814841760640233, "percentage": 83.06, "elapsed_time": "5:44:42", "remaining_time": "1:10:16"}
|
| 1614 |
{"current_steps": 8000, "total_steps": 9625, "loss": 0.1692, "lr": 3.3781677721511773e-06, "epoch": 5.818479447071662, "percentage": 83.12, "elapsed_time": "5:46:17", "remaining_time": "1:10:20"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1612 |
{"current_steps": 7990, "total_steps": 9625, "loss": 0.1777, "lr": 3.4186176050614937e-06, "epoch": 5.811204074208804, "percentage": 83.01, "elapsed_time": "5:42:58", "remaining_time": "1:10:11"}
|
| 1613 |
{"current_steps": 7995, "total_steps": 9625, "loss": 0.1824, "lr": 3.398365391027323e-06, "epoch": 5.814841760640233, "percentage": 83.06, "elapsed_time": "5:44:42", "remaining_time": "1:10:16"}
|
| 1614 |
{"current_steps": 8000, "total_steps": 9625, "loss": 0.1692, "lr": 3.3781677721511773e-06, "epoch": 5.818479447071662, "percentage": 83.12, "elapsed_time": "5:46:17", "remaining_time": "1:10:20"}
|
| 1615 |
+
{"current_steps": 8005, "total_steps": 9625, "loss": 0.1862, "lr": 3.3580248148537485e-06, "epoch": 5.822117133503092, "percentage": 83.17, "elapsed_time": "5:49:07", "remaining_time": "1:10:39"}
|
| 1616 |
+
{"current_steps": 8010, "total_steps": 9625, "loss": 0.209, "lr": 3.3379365853759872e-06, "epoch": 5.825754819934522, "percentage": 83.22, "elapsed_time": "5:50:46", "remaining_time": "1:10:43"}
|
| 1617 |
+
{"current_steps": 8015, "total_steps": 9625, "loss": 0.1892, "lr": 3.317903149778854e-06, "epoch": 5.829392506365951, "percentage": 83.27, "elapsed_time": "5:52:25", "remaining_time": "1:10:47"}
|
| 1618 |
+
{"current_steps": 8020, "total_steps": 9625, "loss": 0.1979, "lr": 3.2979245739431275e-06, "epoch": 5.833030192797381, "percentage": 83.32, "elapsed_time": "5:54:03", "remaining_time": "1:10:51"}
|
| 1619 |
+
{"current_steps": 8025, "total_steps": 9625, "loss": 0.1917, "lr": 3.27800092356918e-06, "epoch": 5.836667879228811, "percentage": 83.38, "elapsed_time": "5:55:44", "remaining_time": "1:10:55"}
|
| 1620 |
+
{"current_steps": 8030, "total_steps": 9625, "loss": 0.1927, "lr": 3.2581322641767588e-06, "epoch": 5.84030556566024, "percentage": 83.43, "elapsed_time": "5:57:28", "remaining_time": "1:11:00"}
|
| 1621 |
+
{"current_steps": 8035, "total_steps": 9625, "loss": 0.1902, "lr": 3.23831866110476e-06, "epoch": 5.84394325209167, "percentage": 83.48, "elapsed_time": "5:59:13", "remaining_time": "1:11:05"}
|
| 1622 |
+
{"current_steps": 8040, "total_steps": 9625, "loss": 0.1807, "lr": 3.21856017951103e-06, "epoch": 5.847580938523099, "percentage": 83.53, "elapsed_time": "6:00:56", "remaining_time": "1:11:09"}
|
| 1623 |
+
{"current_steps": 8045, "total_steps": 9625, "loss": 0.1917, "lr": 3.19885688437215e-06, "epoch": 5.851218624954529, "percentage": 83.58, "elapsed_time": "6:02:37", "remaining_time": "1:11:13"}
|
| 1624 |
+
{"current_steps": 8050, "total_steps": 9625, "loss": 0.1842, "lr": 3.179208840483219e-06, "epoch": 5.854856311385959, "percentage": 83.64, "elapsed_time": "6:04:17", "remaining_time": "1:11:16"}
|
| 1625 |
+
{"current_steps": 8055, "total_steps": 9625, "loss": 0.1895, "lr": 3.15961611245764e-06, "epoch": 5.858493997817388, "percentage": 83.69, "elapsed_time": "6:05:53", "remaining_time": "1:11:19"}
|
| 1626 |
+
{"current_steps": 8060, "total_steps": 9625, "loss": 0.2015, "lr": 3.1400787647268947e-06, "epoch": 5.862131684248817, "percentage": 83.74, "elapsed_time": "6:07:39", "remaining_time": "1:11:23"}
|
| 1627 |
+
{"current_steps": 8065, "total_steps": 9625, "loss": 0.1911, "lr": 3.1205968615403615e-06, "epoch": 5.865769370680248, "percentage": 83.79, "elapsed_time": "6:09:19", "remaining_time": "1:11:26"}
|
| 1628 |
+
{"current_steps": 8070, "total_steps": 9625, "loss": 0.2014, "lr": 3.1011704669650842e-06, "epoch": 5.869407057111677, "percentage": 83.84, "elapsed_time": "6:10:55", "remaining_time": "1:11:28"}
|
| 1629 |
+
{"current_steps": 8075, "total_steps": 9625, "loss": 0.1932, "lr": 3.0817996448855482e-06, "epoch": 5.873044743543106, "percentage": 83.9, "elapsed_time": "6:12:30", "remaining_time": "1:11:30"}
|
| 1630 |
+
{"current_steps": 8080, "total_steps": 9625, "loss": 0.2069, "lr": 3.0624844590035096e-06, "epoch": 5.876682429974537, "percentage": 83.95, "elapsed_time": "6:14:10", "remaining_time": "1:11:32"}
|
| 1631 |
+
{"current_steps": 8085, "total_steps": 9625, "loss": 0.2018, "lr": 3.043224972837744e-06, "epoch": 5.880320116405966, "percentage": 84.0, "elapsed_time": "6:15:51", "remaining_time": "1:11:35"}
|
| 1632 |
+
{"current_steps": 8090, "total_steps": 9625, "loss": 0.2002, "lr": 3.024021249723865e-06, "epoch": 5.883957802837395, "percentage": 84.05, "elapsed_time": "6:17:28", "remaining_time": "1:11:37"}
|
| 1633 |
+
{"current_steps": 8095, "total_steps": 9625, "loss": 0.2007, "lr": 3.0048733528141106e-06, "epoch": 5.887595489268825, "percentage": 84.1, "elapsed_time": "6:19:16", "remaining_time": "1:11:41"}
|
| 1634 |
+
{"current_steps": 8100, "total_steps": 9625, "loss": 0.1934, "lr": 2.9857813450771213e-06, "epoch": 5.891233175700255, "percentage": 84.16, "elapsed_time": "6:20:53", "remaining_time": "1:11:42"}
|
| 1635 |
+
{"current_steps": 8105, "total_steps": 9625, "loss": 0.1943, "lr": 2.9667452892977543e-06, "epoch": 5.894870862131684, "percentage": 84.21, "elapsed_time": "6:22:30", "remaining_time": "1:11:44"}
|
| 1636 |
+
{"current_steps": 8110, "total_steps": 9625, "loss": 0.1987, "lr": 2.9477652480768506e-06, "epoch": 5.898508548563114, "percentage": 84.26, "elapsed_time": "6:24:07", "remaining_time": "1:11:45"}
|
| 1637 |
+
{"current_steps": 8115, "total_steps": 9625, "loss": 0.1867, "lr": 2.928841283831072e-06, "epoch": 5.902146234994543, "percentage": 84.31, "elapsed_time": "6:25:46", "remaining_time": "1:11:46"}
|
| 1638 |
+
{"current_steps": 8120, "total_steps": 9625, "loss": 0.1797, "lr": 2.9099734587926477e-06, "epoch": 5.905783921425973, "percentage": 84.36, "elapsed_time": "6:27:34", "remaining_time": "1:11:50"}
|
| 1639 |
+
{"current_steps": 8125, "total_steps": 9625, "loss": 0.1962, "lr": 2.8911618350091887e-06, "epoch": 5.909421607857403, "percentage": 84.42, "elapsed_time": "6:29:14", "remaining_time": "1:11:51"}
|
| 1640 |
+
{"current_steps": 8130, "total_steps": 9625, "loss": 0.1855, "lr": 2.8724064743434988e-06, "epoch": 5.913059294288832, "percentage": 84.47, "elapsed_time": "6:30:57", "remaining_time": "1:11:53"}
|
| 1641 |
+
{"current_steps": 8135, "total_steps": 9625, "loss": 0.2042, "lr": 2.853707438473352e-06, "epoch": 5.916696980720262, "percentage": 84.52, "elapsed_time": "6:32:33", "remaining_time": "1:11:54"}
|
| 1642 |
+
{"current_steps": 8140, "total_steps": 9625, "loss": 0.1913, "lr": 2.8350647888913018e-06, "epoch": 5.920334667151692, "percentage": 84.57, "elapsed_time": "6:34:13", "remaining_time": "1:11:55"}
|
| 1643 |
+
{"current_steps": 8145, "total_steps": 9625, "loss": 0.1943, "lr": 2.8164785869044585e-06, "epoch": 5.923972353583121, "percentage": 84.62, "elapsed_time": "6:35:54", "remaining_time": "1:11:56"}
|
| 1644 |
+
{"current_steps": 8150, "total_steps": 9625, "loss": 0.1933, "lr": 2.7979488936343215e-06, "epoch": 5.92761004001455, "percentage": 84.68, "elapsed_time": "6:37:31", "remaining_time": "1:11:56"}
|
| 1645 |
+
{"current_steps": 8155, "total_steps": 9625, "loss": 0.1964, "lr": 2.77947577001654e-06, "epoch": 5.931247726445981, "percentage": 84.73, "elapsed_time": "6:39:13", "remaining_time": "1:11:57"}
|
| 1646 |
+
{"current_steps": 8160, "total_steps": 9625, "loss": 0.1909, "lr": 2.7610592768007437e-06, "epoch": 5.93488541287741, "percentage": 84.78, "elapsed_time": "6:41:02", "remaining_time": "1:11:59"}
|
| 1647 |
+
{"current_steps": 8165, "total_steps": 9625, "loss": 0.1854, "lr": 2.742699474550332e-06, "epoch": 5.938523099308839, "percentage": 84.83, "elapsed_time": "6:42:48", "remaining_time": "1:12:01"}
|
| 1648 |
+
{"current_steps": 8170, "total_steps": 9625, "loss": 0.1876, "lr": 2.7243964236422614e-06, "epoch": 5.942160785740269, "percentage": 84.88, "elapsed_time": "6:44:29", "remaining_time": "1:12:02"}
|
| 1649 |
+
{"current_steps": 8175, "total_steps": 9625, "loss": 0.1885, "lr": 2.7061501842668782e-06, "epoch": 5.945798472171699, "percentage": 84.94, "elapsed_time": "6:46:12", "remaining_time": "1:12:03"}
|
| 1650 |
+
{"current_steps": 8180, "total_steps": 9625, "loss": 0.1821, "lr": 2.6879608164276793e-06, "epoch": 5.949436158603128, "percentage": 84.99, "elapsed_time": "6:47:53", "remaining_time": "1:12:03"}
|
| 1651 |
+
{"current_steps": 8185, "total_steps": 9625, "loss": 0.1827, "lr": 2.6698283799411527e-06, "epoch": 5.953073845034558, "percentage": 85.04, "elapsed_time": "6:49:34", "remaining_time": "1:12:03"}
|
| 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"}
|