Training in progress, step 9200
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:b1122f99e3fb1dd69991499b44f455fea57f40e717fcde33a21664d3f92004b7
|
| 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 sha256:7a8eaf068c58e3112cf54a3a8cfce6b33bbfd15f517616ad0160ae8d868afd7f
|
| 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:eeab04c372de4b5cec4efe5fab6e32a2d71c625b0a7462e33e27568aee2bb755
|
| 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 sha256:71f17007a095747f77dce426b7d760ad5cbfa51eca1f13530bbcfd6e00036ef2
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -1812,3 +1812,43 @@
|
|
| 1812 |
{"current_steps": 8990, "total_steps": 9625, "loss": 0.1531, "lr": 5.297257671298384e-07, "epoch": 6.539105129137869, "percentage": 93.4, "elapsed_time": "12:23:28", "remaining_time": "0:52:30"}
|
| 1813 |
{"current_steps": 8995, "total_steps": 9625, "loss": 0.1595, "lr": 5.214657283089208e-07, "epoch": 6.542742815569298, "percentage": 93.45, "elapsed_time": "12:26:22", "remaining_time": "0:52:16"}
|
| 1814 |
{"current_steps": 9000, "total_steps": 9625, "loss": 0.1599, "lr": 5.132697454488545e-07, "epoch": 6.546380502000727, "percentage": 93.51, "elapsed_time": "12:29:10", "remaining_time": "0:52:01"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1812 |
{"current_steps": 8990, "total_steps": 9625, "loss": 0.1531, "lr": 5.297257671298384e-07, "epoch": 6.539105129137869, "percentage": 93.4, "elapsed_time": "12:23:28", "remaining_time": "0:52:30"}
|
| 1813 |
{"current_steps": 8995, "total_steps": 9625, "loss": 0.1595, "lr": 5.214657283089208e-07, "epoch": 6.542742815569298, "percentage": 93.45, "elapsed_time": "12:26:22", "remaining_time": "0:52:16"}
|
| 1814 |
{"current_steps": 9000, "total_steps": 9625, "loss": 0.1599, "lr": 5.132697454488545e-07, "epoch": 6.546380502000727, "percentage": 93.51, "elapsed_time": "12:29:10", "remaining_time": "0:52:01"}
|
| 1815 |
+
{"current_steps": 9005, "total_steps": 9625, "loss": 0.13, "lr": 5.051378455024635e-07, "epoch": 6.550018188432157, "percentage": 93.56, "elapsed_time": "12:32:51", "remaining_time": "0:51:50"}
|
| 1816 |
+
{"current_steps": 9010, "total_steps": 9625, "loss": 0.145, "lr": 4.970700552118368e-07, "epoch": 6.553655874863587, "percentage": 93.61, "elapsed_time": "12:35:19", "remaining_time": "0:51:33"}
|
| 1817 |
+
{"current_steps": 9015, "total_steps": 9625, "loss": 0.1522, "lr": 4.89066401108238e-07, "epoch": 6.557293561295016, "percentage": 93.66, "elapsed_time": "12:38:13", "remaining_time": "0:51:18"}
|
| 1818 |
+
{"current_steps": 9020, "total_steps": 9625, "loss": 0.1614, "lr": 4.811269095120086e-07, "epoch": 6.560931247726446, "percentage": 93.71, "elapsed_time": "12:41:07", "remaining_time": "0:51:03"}
|
| 1819 |
+
{"current_steps": 9025, "total_steps": 9625, "loss": 0.153, "lr": 4.732516065324921e-07, "epoch": 6.564568934157876, "percentage": 93.77, "elapsed_time": "12:43:48", "remaining_time": "0:50:46"}
|
| 1820 |
+
{"current_steps": 9030, "total_steps": 9625, "loss": 0.147, "lr": 4.6544051806794776e-07, "epoch": 6.568206620589305, "percentage": 93.82, "elapsed_time": "12:46:38", "remaining_time": "0:50:30"}
|
| 1821 |
+
{"current_steps": 9035, "total_steps": 9625, "loss": 0.1576, "lr": 4.5769366980546124e-07, "epoch": 6.571844307020735, "percentage": 93.87, "elapsed_time": "12:49:26", "remaining_time": "0:50:14"}
|
| 1822 |
+
{"current_steps": 9040, "total_steps": 9625, "loss": 0.1859, "lr": 4.500110872208652e-07, "epoch": 6.575481993452165, "percentage": 93.92, "elapsed_time": "12:52:03", "remaining_time": "0:49:57"}
|
| 1823 |
+
{"current_steps": 9045, "total_steps": 9625, "loss": 0.2101, "lr": 4.4239279557864114e-07, "epoch": 6.579119679883594, "percentage": 93.97, "elapsed_time": "12:54:13", "remaining_time": "0:49:38"}
|
| 1824 |
+
{"current_steps": 9050, "total_steps": 9625, "loss": 0.2139, "lr": 4.3483881993185985e-07, "epoch": 6.582757366315024, "percentage": 94.03, "elapsed_time": "12:56:39", "remaining_time": "0:49:20"}
|
| 1825 |
+
{"current_steps": 9055, "total_steps": 9625, "loss": 0.2004, "lr": 4.2734918512207903e-07, "epoch": 6.586395052746453, "percentage": 94.08, "elapsed_time": "12:58:54", "remaining_time": "0:49:01"}
|
| 1826 |
+
{"current_steps": 9060, "total_steps": 9625, "loss": 0.2049, "lr": 4.199239157792701e-07, "epoch": 6.590032739177883, "percentage": 94.13, "elapsed_time": "13:01:14", "remaining_time": "0:48:43"}
|
| 1827 |
+
{"current_steps": 9065, "total_steps": 9625, "loss": 0.2111, "lr": 4.125630363217381e-07, "epoch": 6.593670425609313, "percentage": 94.18, "elapsed_time": "13:03:28", "remaining_time": "0:48:23"}
|
| 1828 |
+
{"current_steps": 9070, "total_steps": 9625, "loss": 0.1945, "lr": 4.052665709560377e-07, "epoch": 6.597308112040742, "percentage": 94.23, "elapsed_time": "13:05:53", "remaining_time": "0:48:05"}
|
| 1829 |
+
{"current_steps": 9075, "total_steps": 9625, "loss": 0.2052, "lr": 3.9803454367689064e-07, "epoch": 6.600945798472171, "percentage": 94.29, "elapsed_time": "13:08:16", "remaining_time": "0:47:46"}
|
| 1830 |
+
{"current_steps": 9080, "total_steps": 9625, "loss": 0.2017, "lr": 3.908669782671237e-07, "epoch": 6.604583484903602, "percentage": 94.34, "elapsed_time": "13:10:34", "remaining_time": "0:47:27"}
|
| 1831 |
+
{"current_steps": 9085, "total_steps": 9625, "loss": 0.215, "lr": 3.8376389829756664e-07, "epoch": 6.608221171335031, "percentage": 94.39, "elapsed_time": "13:12:53", "remaining_time": "0:47:07"}
|
| 1832 |
+
{"current_steps": 9090, "total_steps": 9625, "loss": 0.2008, "lr": 3.7672532712698993e-07, "epoch": 6.61185885776646, "percentage": 94.44, "elapsed_time": "13:15:10", "remaining_time": "0:46:48"}
|
| 1833 |
+
{"current_steps": 9095, "total_steps": 9625, "loss": 0.2049, "lr": 3.6975128790202264e-07, "epoch": 6.615496544197891, "percentage": 94.49, "elapsed_time": "13:17:43", "remaining_time": "0:46:29"}
|
| 1834 |
+
{"current_steps": 9100, "total_steps": 9625, "loss": 0.2048, "lr": 3.628418035570791e-07, "epoch": 6.61913423062932, "percentage": 94.55, "elapsed_time": "13:19:57", "remaining_time": "0:46:09"}
|
| 1835 |
+
{"current_steps": 9105, "total_steps": 9625, "loss": 0.2035, "lr": 3.5599689681428795e-07, "epoch": 6.622771917060749, "percentage": 94.6, "elapsed_time": "13:22:04", "remaining_time": "0:45:48"}
|
| 1836 |
+
{"current_steps": 9110, "total_steps": 9625, "loss": 0.1953, "lr": 3.4921659018340324e-07, "epoch": 6.626409603492179, "percentage": 94.65, "elapsed_time": "13:23:47", "remaining_time": "0:45:26"}
|
| 1837 |
+
{"current_steps": 9115, "total_steps": 9625, "loss": 0.1957, "lr": 3.4250090596174233e-07, "epoch": 6.630047289923609, "percentage": 94.7, "elapsed_time": "13:25:25", "remaining_time": "0:45:03"}
|
| 1838 |
+
{"current_steps": 9120, "total_steps": 9625, "loss": 0.1952, "lr": 3.3584986623410585e-07, "epoch": 6.633684976355038, "percentage": 94.75, "elapsed_time": "13:27:07", "remaining_time": "0:44:41"}
|
| 1839 |
+
{"current_steps": 9125, "total_steps": 9625, "loss": 0.1989, "lr": 3.292634928727179e-07, "epoch": 6.637322662786468, "percentage": 94.81, "elapsed_time": "13:28:42", "remaining_time": "0:44:18"}
|
| 1840 |
+
{"current_steps": 9130, "total_steps": 9625, "loss": 0.2066, "lr": 3.227418075371325e-07, "epoch": 6.640960349217897, "percentage": 94.86, "elapsed_time": "13:30:19", "remaining_time": "0:43:56"}
|
| 1841 |
+
{"current_steps": 9135, "total_steps": 9625, "loss": 0.1982, "lr": 3.162848316741829e-07, "epoch": 6.644598035649327, "percentage": 94.91, "elapsed_time": "13:32:01", "remaining_time": "0:43:33"}
|
| 1842 |
+
{"current_steps": 9140, "total_steps": 9625, "loss": 0.2028, "lr": 3.09892586517897e-07, "epoch": 6.648235722080757, "percentage": 94.96, "elapsed_time": "13:33:42", "remaining_time": "0:43:10"}
|
| 1843 |
+
{"current_steps": 9145, "total_steps": 9625, "loss": 0.1846, "lr": 3.035650930894396e-07, "epoch": 6.651873408512186, "percentage": 95.01, "elapsed_time": "13:35:22", "remaining_time": "0:42:47"}
|
| 1844 |
+
{"current_steps": 9150, "total_steps": 9625, "loss": 0.1882, "lr": 2.9730237219703026e-07, "epoch": 6.655511094943616, "percentage": 95.06, "elapsed_time": "13:37:05", "remaining_time": "0:42:25"}
|
| 1845 |
+
{"current_steps": 9155, "total_steps": 9625, "loss": 0.1875, "lr": 2.9110444443588573e-07, "epoch": 6.659148781375046, "percentage": 95.12, "elapsed_time": "13:38:42", "remaining_time": "0:42:01"}
|
| 1846 |
+
{"current_steps": 9160, "total_steps": 9625, "loss": 0.1983, "lr": 2.8497133018814407e-07, "epoch": 6.662786467806475, "percentage": 95.17, "elapsed_time": "13:40:21", "remaining_time": "0:41:38"}
|
| 1847 |
+
{"current_steps": 9165, "total_steps": 9625, "loss": 0.201, "lr": 2.789030496228051e-07, "epoch": 6.666424154237904, "percentage": 95.22, "elapsed_time": "13:41:59", "remaining_time": "0:41:15"}
|
| 1848 |
+
{"current_steps": 9170, "total_steps": 9625, "loss": 0.1911, "lr": 2.728996226956593e-07, "epoch": 6.670061840669335, "percentage": 95.27, "elapsed_time": "13:43:40", "remaining_time": "0:40:52"}
|
| 1849 |
+
{"current_steps": 9175, "total_steps": 9625, "loss": 0.19, "lr": 2.6696106914922525e-07, "epoch": 6.673699527100764, "percentage": 95.32, "elapsed_time": "13:45:18", "remaining_time": "0:40:28"}
|
| 1850 |
+
{"current_steps": 9180, "total_steps": 9625, "loss": 0.1917, "lr": 2.6108740851267467e-07, "epoch": 6.677337213532193, "percentage": 95.38, "elapsed_time": "13:46:58", "remaining_time": "0:40:05"}
|
| 1851 |
+
{"current_steps": 9185, "total_steps": 9625, "loss": 0.1907, "lr": 2.5527866010178536e-07, "epoch": 6.680974899963623, "percentage": 95.43, "elapsed_time": "13:48:39", "remaining_time": "0:39:41"}
|
| 1852 |
+
{"current_steps": 9190, "total_steps": 9625, "loss": 0.1855, "lr": 2.49534843018866e-07, "epoch": 6.684612586395053, "percentage": 95.48, "elapsed_time": "13:50:16", "remaining_time": "0:39:18"}
|
| 1853 |
+
{"current_steps": 9195, "total_steps": 9625, "loss": 0.1898, "lr": 2.4385597615269376e-07, "epoch": 6.688250272826482, "percentage": 95.53, "elapsed_time": "13:51:55", "remaining_time": "0:38:54"}
|
| 1854 |
+
{"current_steps": 9200, "total_steps": 9625, "loss": 0.1902, "lr": 2.382420781784589e-07, "epoch": 6.691887959257912, "percentage": 95.58, "elapsed_time": "13:53:33", "remaining_time": "0:38:30"}
|