mikhail-panzo
commited on
Commit
•
9de99a3
1
Parent(s):
361bb40
Training in progress, step 12000, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 577789320
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:56a801f7874b64e033e7d65093ff6a670b591b9e352bb55a9efedb82bb7bd081
|
3 |
size 577789320
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1155772233
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d15e5170813dcff285d169be8481933a4cb0c9a73034315f866ed759fa591047
|
3 |
size 1155772233
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:23d7f02c1a1a9aea0c08b9ee9ea167031247ef6b9121df34e7f784a8ef6bb970
|
3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b2891075898e42caf114b73a9c8652d14f8fed0b39122b829f8ae7578e63f2a0
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 0.3699803650379181,
|
3 |
"best_model_checkpoint": "mikhail-panzo/zlm_b32_le5_s12000/checkpoint-11500",
|
4 |
-
"epoch":
|
5 |
"eval_steps": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -1801,6 +1801,84 @@
|
|
1801 |
"eval_samples_per_second": 28.557,
|
1802 |
"eval_steps_per_second": 3.573,
|
1803 |
"step": 11500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1804 |
}
|
1805 |
],
|
1806 |
"logging_steps": 50,
|
@@ -1815,12 +1893,12 @@
|
|
1815 |
"should_evaluate": false,
|
1816 |
"should_log": false,
|
1817 |
"should_save": true,
|
1818 |
-
"should_training_stop":
|
1819 |
},
|
1820 |
"attributes": {}
|
1821 |
}
|
1822 |
},
|
1823 |
-
"total_flos": 5.
|
1824 |
"train_batch_size": 16,
|
1825 |
"trial_name": null,
|
1826 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": 0.3699803650379181,
|
3 |
"best_model_checkpoint": "mikhail-panzo/zlm_b32_le5_s12000/checkpoint-11500",
|
4 |
+
"epoch": 5.026178010471204,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 12000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
1801 |
"eval_samples_per_second": 28.557,
|
1802 |
"eval_steps_per_second": 3.573,
|
1803 |
"step": 11500
|
1804 |
+
},
|
1805 |
+
{
|
1806 |
+
"epoch": 4.837696335078534,
|
1807 |
+
"grad_norm": 1.7664463520050049,
|
1808 |
+
"learning_rate": 4.5500000000000004e-07,
|
1809 |
+
"loss": 0.4102,
|
1810 |
+
"step": 11550
|
1811 |
+
},
|
1812 |
+
{
|
1813 |
+
"epoch": 4.858638743455497,
|
1814 |
+
"grad_norm": 2.0069000720977783,
|
1815 |
+
"learning_rate": 4.0500000000000004e-07,
|
1816 |
+
"loss": 0.4026,
|
1817 |
+
"step": 11600
|
1818 |
+
},
|
1819 |
+
{
|
1820 |
+
"epoch": 4.879581151832461,
|
1821 |
+
"grad_norm": 1.475438117980957,
|
1822 |
+
"learning_rate": 3.55e-07,
|
1823 |
+
"loss": 0.4132,
|
1824 |
+
"step": 11650
|
1825 |
+
},
|
1826 |
+
{
|
1827 |
+
"epoch": 4.900523560209424,
|
1828 |
+
"grad_norm": 1.6426637172698975,
|
1829 |
+
"learning_rate": 3.0500000000000004e-07,
|
1830 |
+
"loss": 0.4082,
|
1831 |
+
"step": 11700
|
1832 |
+
},
|
1833 |
+
{
|
1834 |
+
"epoch": 4.9214659685863875,
|
1835 |
+
"grad_norm": 1.6717259883880615,
|
1836 |
+
"learning_rate": 2.55e-07,
|
1837 |
+
"loss": 0.4115,
|
1838 |
+
"step": 11750
|
1839 |
+
},
|
1840 |
+
{
|
1841 |
+
"epoch": 4.942408376963351,
|
1842 |
+
"grad_norm": 1.9856605529785156,
|
1843 |
+
"learning_rate": 2.0500000000000002e-07,
|
1844 |
+
"loss": 0.4064,
|
1845 |
+
"step": 11800
|
1846 |
+
},
|
1847 |
+
{
|
1848 |
+
"epoch": 4.963350785340314,
|
1849 |
+
"grad_norm": 2.535362958908081,
|
1850 |
+
"learning_rate": 1.5500000000000002e-07,
|
1851 |
+
"loss": 0.4126,
|
1852 |
+
"step": 11850
|
1853 |
+
},
|
1854 |
+
{
|
1855 |
+
"epoch": 4.984293193717278,
|
1856 |
+
"grad_norm": 1.6207140684127808,
|
1857 |
+
"learning_rate": 1.0500000000000001e-07,
|
1858 |
+
"loss": 0.4139,
|
1859 |
+
"step": 11900
|
1860 |
+
},
|
1861 |
+
{
|
1862 |
+
"epoch": 5.005235602094241,
|
1863 |
+
"grad_norm": 1.4156582355499268,
|
1864 |
+
"learning_rate": 5.5e-08,
|
1865 |
+
"loss": 0.409,
|
1866 |
+
"step": 11950
|
1867 |
+
},
|
1868 |
+
{
|
1869 |
+
"epoch": 5.026178010471204,
|
1870 |
+
"grad_norm": 3.40710186958313,
|
1871 |
+
"learning_rate": 5e-09,
|
1872 |
+
"loss": 0.4088,
|
1873 |
+
"step": 12000
|
1874 |
+
},
|
1875 |
+
{
|
1876 |
+
"epoch": 5.026178010471204,
|
1877 |
+
"eval_loss": 0.3706651031970978,
|
1878 |
+
"eval_runtime": 299.1328,
|
1879 |
+
"eval_samples_per_second": 28.379,
|
1880 |
+
"eval_steps_per_second": 3.55,
|
1881 |
+
"step": 12000
|
1882 |
}
|
1883 |
],
|
1884 |
"logging_steps": 50,
|
|
|
1893 |
"should_evaluate": false,
|
1894 |
"should_log": false,
|
1895 |
"should_save": true,
|
1896 |
+
"should_training_stop": true
|
1897 |
},
|
1898 |
"attributes": {}
|
1899 |
}
|
1900 |
},
|
1901 |
+
"total_flos": 5.37491824204009e+16,
|
1902 |
"train_batch_size": 16,
|
1903 |
"trial_name": null,
|
1904 |
"trial_params": null
|