End of training
Browse files- README.md +4 -2
- all_results.json +11 -11
- eval_results.json +6 -6
- p_object.json +0 -0
- prediction_reference.json +0 -0
- train_results.json +6 -6
- trainer_state.json +585 -57
README.md
CHANGED
|
@@ -1,6 +1,8 @@
|
|
| 1 |
---
|
| 2 |
base_model: microsoft/dit-base-finetuned-rvlcdip
|
| 3 |
tags:
|
|
|
|
|
|
|
| 4 |
- generated_from_trainer
|
| 5 |
metrics:
|
| 6 |
- f1
|
|
@@ -16,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [microsoft/dit-base-finetuned-rvlcdip](https://huggingface.co/microsoft/dit-base-finetuned-rvlcdip) on an unknown dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
-
- Loss: 0.
|
| 20 |
-
- F1: 0.
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
|
|
| 1 |
---
|
| 2 |
base_model: microsoft/dit-base-finetuned-rvlcdip
|
| 3 |
tags:
|
| 4 |
+
- image-classification
|
| 5 |
+
- vision
|
| 6 |
- generated_from_trainer
|
| 7 |
metrics:
|
| 8 |
- f1
|
|
|
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [microsoft/dit-base-finetuned-rvlcdip](https://huggingface.co/microsoft/dit-base-finetuned-rvlcdip) on an unknown dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.0404
|
| 22 |
+
- F1: 0.6134
|
| 23 |
|
| 24 |
## Model description
|
| 25 |
|
all_results.json
CHANGED
|
@@ -1,13 +1,13 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch": 0.
|
| 3 |
-
"eval_f1": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime":
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second": 2.
|
| 8 |
-
"total_flos": 1.
|
| 9 |
-
"train_loss": 0.
|
| 10 |
-
"train_runtime":
|
| 11 |
-
"train_samples_per_second":
|
| 12 |
-
"train_steps_per_second": 0.
|
| 13 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 0.6942691239585963,
|
| 3 |
+
"eval_f1": 0.6133951445650848,
|
| 4 |
+
"eval_loss": 0.04044894501566887,
|
| 5 |
+
"eval_runtime": 1162.523,
|
| 6 |
+
"eval_samples_per_second": 177.426,
|
| 7 |
+
"eval_steps_per_second": 2.772,
|
| 8 |
+
"total_flos": 1.3639932886745088e+19,
|
| 9 |
+
"train_loss": 0.019194319985129618,
|
| 10 |
+
"train_runtime": 18605.0451,
|
| 11 |
+
"train_samples_per_second": 34.399,
|
| 12 |
+
"train_steps_per_second": 0.537
|
| 13 |
}
|
eval_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch": 0.
|
| 3 |
-
"eval_f1": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime":
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second": 2.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 0.6942691239585963,
|
| 3 |
+
"eval_f1": 0.6133951445650848,
|
| 4 |
+
"eval_loss": 0.04044894501566887,
|
| 5 |
+
"eval_runtime": 1162.523,
|
| 6 |
+
"eval_samples_per_second": 177.426,
|
| 7 |
+
"eval_steps_per_second": 2.772
|
| 8 |
}
|
p_object.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
prediction_reference.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch": 0.
|
| 3 |
-
"total_flos": 1.
|
| 4 |
-
"train_loss": 0.
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 0.6942691239585963,
|
| 3 |
+
"total_flos": 1.3639932886745088e+19,
|
| 4 |
+
"train_loss": 0.019194319985129618,
|
| 5 |
+
"train_runtime": 18605.0451,
|
| 6 |
+
"train_samples_per_second": 34.399,
|
| 7 |
+
"train_steps_per_second": 0.537
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "./step_test_microsoft_dit/checkpoint-
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 50,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -1770,144 +1770,672 @@
|
|
| 1770 |
},
|
| 1771 |
{
|
| 1772 |
"epoch": 0.5074476142388286,
|
| 1773 |
-
"grad_norm": 0.
|
| 1774 |
"learning_rate": 2.3970000000000003e-05,
|
| 1775 |
-
"loss": 0.
|
| 1776 |
"step": 2010
|
| 1777 |
},
|
| 1778 |
{
|
| 1779 |
"epoch": 0.5099722292350417,
|
| 1780 |
-
"grad_norm":
|
| 1781 |
"learning_rate": 2.394e-05,
|
| 1782 |
-
"loss": 0.
|
| 1783 |
"step": 2020
|
| 1784 |
},
|
| 1785 |
{
|
| 1786 |
"epoch": 0.5124968442312547,
|
| 1787 |
-
"grad_norm":
|
| 1788 |
"learning_rate": 2.3910000000000003e-05,
|
| 1789 |
-
"loss": 0.
|
| 1790 |
"step": 2030
|
| 1791 |
},
|
| 1792 |
{
|
| 1793 |
"epoch": 0.5150214592274678,
|
| 1794 |
-
"grad_norm":
|
| 1795 |
"learning_rate": 2.3880000000000002e-05,
|
| 1796 |
-
"loss": 0.
|
| 1797 |
"step": 2040
|
| 1798 |
},
|
| 1799 |
{
|
| 1800 |
"epoch": 0.5175460742236809,
|
| 1801 |
-
"grad_norm":
|
| 1802 |
"learning_rate": 2.385e-05,
|
| 1803 |
-
"loss": 0.
|
| 1804 |
"step": 2050
|
| 1805 |
},
|
| 1806 |
{
|
| 1807 |
"epoch": 0.5175460742236809,
|
| 1808 |
-
"eval_f1": 0.
|
| 1809 |
-
"eval_loss": 0.
|
| 1810 |
-
"eval_runtime":
|
| 1811 |
-
"eval_samples_per_second": 178.
|
| 1812 |
-
"eval_steps_per_second": 2.
|
| 1813 |
"step": 2050
|
| 1814 |
},
|
| 1815 |
{
|
| 1816 |
"epoch": 0.520070689219894,
|
| 1817 |
-
"grad_norm": 0.
|
| 1818 |
"learning_rate": 2.3820000000000002e-05,
|
| 1819 |
-
"loss": 0.
|
| 1820 |
"step": 2060
|
| 1821 |
},
|
| 1822 |
{
|
| 1823 |
"epoch": 0.522595304216107,
|
| 1824 |
-
"grad_norm":
|
| 1825 |
"learning_rate": 2.379e-05,
|
| 1826 |
-
"loss": 0.
|
| 1827 |
"step": 2070
|
| 1828 |
},
|
| 1829 |
{
|
| 1830 |
"epoch": 0.5251199192123202,
|
| 1831 |
-
"grad_norm": 0.
|
| 1832 |
"learning_rate": 2.3760000000000003e-05,
|
| 1833 |
-
"loss": 0.
|
| 1834 |
"step": 2080
|
| 1835 |
},
|
| 1836 |
{
|
| 1837 |
"epoch": 0.5276445342085332,
|
| 1838 |
-
"grad_norm":
|
| 1839 |
"learning_rate": 2.373e-05,
|
| 1840 |
-
"loss": 0.
|
| 1841 |
"step": 2090
|
| 1842 |
},
|
| 1843 |
{
|
| 1844 |
"epoch": 0.5301691492047462,
|
| 1845 |
-
"grad_norm": 0.
|
| 1846 |
"learning_rate": 2.37e-05,
|
| 1847 |
-
"loss": 0.
|
| 1848 |
"step": 2100
|
| 1849 |
},
|
| 1850 |
{
|
| 1851 |
"epoch": 0.5301691492047462,
|
| 1852 |
-
"eval_f1": 0.
|
| 1853 |
-
"eval_loss": 0.
|
| 1854 |
-
"eval_runtime":
|
| 1855 |
-
"eval_samples_per_second": 178.
|
| 1856 |
-
"eval_steps_per_second": 2.
|
| 1857 |
"step": 2100
|
| 1858 |
},
|
| 1859 |
{
|
| 1860 |
"epoch": 0.5326937642009594,
|
| 1861 |
-
"grad_norm":
|
| 1862 |
"learning_rate": 2.3670000000000002e-05,
|
| 1863 |
-
"loss": 0.
|
| 1864 |
"step": 2110
|
| 1865 |
},
|
| 1866 |
{
|
| 1867 |
"epoch": 0.5352183791971724,
|
| 1868 |
-
"grad_norm":
|
| 1869 |
"learning_rate": 2.364e-05,
|
| 1870 |
-
"loss": 0.
|
| 1871 |
"step": 2120
|
| 1872 |
},
|
| 1873 |
{
|
| 1874 |
"epoch": 0.5377429941933856,
|
| 1875 |
-
"grad_norm":
|
| 1876 |
"learning_rate": 2.3610000000000003e-05,
|
| 1877 |
-
"loss": 0.
|
| 1878 |
"step": 2130
|
| 1879 |
},
|
| 1880 |
{
|
| 1881 |
"epoch": 0.5402676091895986,
|
| 1882 |
-
"grad_norm": 0.
|
| 1883 |
"learning_rate": 2.358e-05,
|
| 1884 |
-
"loss": 0.
|
| 1885 |
"step": 2140
|
| 1886 |
},
|
| 1887 |
{
|
| 1888 |
"epoch": 0.5427922241858116,
|
| 1889 |
-
"grad_norm": 0.
|
| 1890 |
"learning_rate": 2.3550000000000003e-05,
|
| 1891 |
-
"loss": 0.
|
| 1892 |
"step": 2150
|
| 1893 |
},
|
| 1894 |
{
|
| 1895 |
"epoch": 0.5427922241858116,
|
| 1896 |
-
"eval_f1": 0.
|
| 1897 |
-
"eval_loss": 0.
|
| 1898 |
-
"eval_runtime":
|
| 1899 |
-
"eval_samples_per_second":
|
| 1900 |
-
"eval_steps_per_second": 2.
|
| 1901 |
"step": 2150
|
| 1902 |
},
|
| 1903 |
{
|
| 1904 |
-
"epoch": 0.
|
| 1905 |
-
"
|
| 1906 |
-
"
|
| 1907 |
-
"
|
| 1908 |
-
"
|
| 1909 |
-
|
| 1910 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1911 |
}
|
| 1912 |
],
|
| 1913 |
"logging_steps": 10,
|
|
@@ -1936,7 +2464,7 @@
|
|
| 1936 |
"attributes": {}
|
| 1937 |
}
|
| 1938 |
},
|
| 1939 |
-
"total_flos": 1.
|
| 1940 |
"train_batch_size": 64,
|
| 1941 |
"trial_name": null,
|
| 1942 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.6133951445650848,
|
| 3 |
+
"best_model_checkpoint": "./step_test_microsoft_dit/checkpoint-2500",
|
| 4 |
+
"epoch": 0.6942691239585963,
|
| 5 |
"eval_steps": 50,
|
| 6 |
+
"global_step": 2750,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 1770 |
},
|
| 1771 |
{
|
| 1772 |
"epoch": 0.5074476142388286,
|
| 1773 |
+
"grad_norm": 0.7863900065422058,
|
| 1774 |
"learning_rate": 2.3970000000000003e-05,
|
| 1775 |
+
"loss": 0.061,
|
| 1776 |
"step": 2010
|
| 1777 |
},
|
| 1778 |
{
|
| 1779 |
"epoch": 0.5099722292350417,
|
| 1780 |
+
"grad_norm": 1.0800750255584717,
|
| 1781 |
"learning_rate": 2.394e-05,
|
| 1782 |
+
"loss": 0.0781,
|
| 1783 |
"step": 2020
|
| 1784 |
},
|
| 1785 |
{
|
| 1786 |
"epoch": 0.5124968442312547,
|
| 1787 |
+
"grad_norm": 1.0992929935455322,
|
| 1788 |
"learning_rate": 2.3910000000000003e-05,
|
| 1789 |
+
"loss": 0.0694,
|
| 1790 |
"step": 2030
|
| 1791 |
},
|
| 1792 |
{
|
| 1793 |
"epoch": 0.5150214592274678,
|
| 1794 |
+
"grad_norm": 0.703554093837738,
|
| 1795 |
"learning_rate": 2.3880000000000002e-05,
|
| 1796 |
+
"loss": 0.0881,
|
| 1797 |
"step": 2040
|
| 1798 |
},
|
| 1799 |
{
|
| 1800 |
"epoch": 0.5175460742236809,
|
| 1801 |
+
"grad_norm": 1.214089274406433,
|
| 1802 |
"learning_rate": 2.385e-05,
|
| 1803 |
+
"loss": 0.0736,
|
| 1804 |
"step": 2050
|
| 1805 |
},
|
| 1806 |
{
|
| 1807 |
"epoch": 0.5175460742236809,
|
| 1808 |
+
"eval_f1": 0.612187690432663,
|
| 1809 |
+
"eval_loss": 0.05384594947099686,
|
| 1810 |
+
"eval_runtime": 1155.7771,
|
| 1811 |
+
"eval_samples_per_second": 178.462,
|
| 1812 |
+
"eval_steps_per_second": 2.789,
|
| 1813 |
"step": 2050
|
| 1814 |
},
|
| 1815 |
{
|
| 1816 |
"epoch": 0.520070689219894,
|
| 1817 |
+
"grad_norm": 0.8359307050704956,
|
| 1818 |
"learning_rate": 2.3820000000000002e-05,
|
| 1819 |
+
"loss": 0.0759,
|
| 1820 |
"step": 2060
|
| 1821 |
},
|
| 1822 |
{
|
| 1823 |
"epoch": 0.522595304216107,
|
| 1824 |
+
"grad_norm": 1.6299511194229126,
|
| 1825 |
"learning_rate": 2.379e-05,
|
| 1826 |
+
"loss": 0.076,
|
| 1827 |
"step": 2070
|
| 1828 |
},
|
| 1829 |
{
|
| 1830 |
"epoch": 0.5251199192123202,
|
| 1831 |
+
"grad_norm": 0.6880617737770081,
|
| 1832 |
"learning_rate": 2.3760000000000003e-05,
|
| 1833 |
+
"loss": 0.0745,
|
| 1834 |
"step": 2080
|
| 1835 |
},
|
| 1836 |
{
|
| 1837 |
"epoch": 0.5276445342085332,
|
| 1838 |
+
"grad_norm": 0.7822777032852173,
|
| 1839 |
"learning_rate": 2.373e-05,
|
| 1840 |
+
"loss": 0.0697,
|
| 1841 |
"step": 2090
|
| 1842 |
},
|
| 1843 |
{
|
| 1844 |
"epoch": 0.5301691492047462,
|
| 1845 |
+
"grad_norm": 0.7941886782646179,
|
| 1846 |
"learning_rate": 2.37e-05,
|
| 1847 |
+
"loss": 0.0685,
|
| 1848 |
"step": 2100
|
| 1849 |
},
|
| 1850 |
{
|
| 1851 |
"epoch": 0.5301691492047462,
|
| 1852 |
+
"eval_f1": 0.6104315862855695,
|
| 1853 |
+
"eval_loss": 0.04854836314916611,
|
| 1854 |
+
"eval_runtime": 1154.0649,
|
| 1855 |
+
"eval_samples_per_second": 178.727,
|
| 1856 |
+
"eval_steps_per_second": 2.793,
|
| 1857 |
"step": 2100
|
| 1858 |
},
|
| 1859 |
{
|
| 1860 |
"epoch": 0.5326937642009594,
|
| 1861 |
+
"grad_norm": 0.948130190372467,
|
| 1862 |
"learning_rate": 2.3670000000000002e-05,
|
| 1863 |
+
"loss": 0.0706,
|
| 1864 |
"step": 2110
|
| 1865 |
},
|
| 1866 |
{
|
| 1867 |
"epoch": 0.5352183791971724,
|
| 1868 |
+
"grad_norm": 0.959032416343689,
|
| 1869 |
"learning_rate": 2.364e-05,
|
| 1870 |
+
"loss": 0.0684,
|
| 1871 |
"step": 2120
|
| 1872 |
},
|
| 1873 |
{
|
| 1874 |
"epoch": 0.5377429941933856,
|
| 1875 |
+
"grad_norm": 1.1859666109085083,
|
| 1876 |
"learning_rate": 2.3610000000000003e-05,
|
| 1877 |
+
"loss": 0.0757,
|
| 1878 |
"step": 2130
|
| 1879 |
},
|
| 1880 |
{
|
| 1881 |
"epoch": 0.5402676091895986,
|
| 1882 |
+
"grad_norm": 0.9001142978668213,
|
| 1883 |
"learning_rate": 2.358e-05,
|
| 1884 |
+
"loss": 0.079,
|
| 1885 |
"step": 2140
|
| 1886 |
},
|
| 1887 |
{
|
| 1888 |
"epoch": 0.5427922241858116,
|
| 1889 |
+
"grad_norm": 0.47399717569351196,
|
| 1890 |
"learning_rate": 2.3550000000000003e-05,
|
| 1891 |
+
"loss": 0.0726,
|
| 1892 |
"step": 2150
|
| 1893 |
},
|
| 1894 |
{
|
| 1895 |
"epoch": 0.5427922241858116,
|
| 1896 |
+
"eval_f1": 0.611992731677771,
|
| 1897 |
+
"eval_loss": 0.05662121623754501,
|
| 1898 |
+
"eval_runtime": 1151.3771,
|
| 1899 |
+
"eval_samples_per_second": 179.144,
|
| 1900 |
+
"eval_steps_per_second": 2.799,
|
| 1901 |
"step": 2150
|
| 1902 |
},
|
| 1903 |
{
|
| 1904 |
+
"epoch": 0.5453168391820248,
|
| 1905 |
+
"grad_norm": 0.6292353272438049,
|
| 1906 |
+
"learning_rate": 2.3520000000000002e-05,
|
| 1907 |
+
"loss": 0.0677,
|
| 1908 |
+
"step": 2160
|
| 1909 |
+
},
|
| 1910 |
+
{
|
| 1911 |
+
"epoch": 0.5478414541782378,
|
| 1912 |
+
"grad_norm": 0.7090362906455994,
|
| 1913 |
+
"learning_rate": 2.349e-05,
|
| 1914 |
+
"loss": 0.0703,
|
| 1915 |
+
"step": 2170
|
| 1916 |
+
},
|
| 1917 |
+
{
|
| 1918 |
+
"epoch": 0.5503660691744509,
|
| 1919 |
+
"grad_norm": 0.6082953810691833,
|
| 1920 |
+
"learning_rate": 2.3460000000000002e-05,
|
| 1921 |
+
"loss": 0.0672,
|
| 1922 |
+
"step": 2180
|
| 1923 |
+
},
|
| 1924 |
+
{
|
| 1925 |
+
"epoch": 0.552890684170664,
|
| 1926 |
+
"grad_norm": 0.5937643051147461,
|
| 1927 |
+
"learning_rate": 2.343e-05,
|
| 1928 |
+
"loss": 0.0686,
|
| 1929 |
+
"step": 2190
|
| 1930 |
+
},
|
| 1931 |
+
{
|
| 1932 |
+
"epoch": 0.555415299166877,
|
| 1933 |
+
"grad_norm": 0.7394770979881287,
|
| 1934 |
+
"learning_rate": 2.3400000000000003e-05,
|
| 1935 |
+
"loss": 0.0731,
|
| 1936 |
+
"step": 2200
|
| 1937 |
+
},
|
| 1938 |
+
{
|
| 1939 |
+
"epoch": 0.555415299166877,
|
| 1940 |
+
"eval_f1": 0.6111780293905084,
|
| 1941 |
+
"eval_loss": 0.05852247402071953,
|
| 1942 |
+
"eval_runtime": 1153.1003,
|
| 1943 |
+
"eval_samples_per_second": 178.876,
|
| 1944 |
+
"eval_steps_per_second": 2.795,
|
| 1945 |
+
"step": 2200
|
| 1946 |
+
},
|
| 1947 |
+
{
|
| 1948 |
+
"epoch": 0.5579399141630901,
|
| 1949 |
+
"grad_norm": 0.7641323804855347,
|
| 1950 |
+
"learning_rate": 2.337e-05,
|
| 1951 |
+
"loss": 0.0732,
|
| 1952 |
+
"step": 2210
|
| 1953 |
+
},
|
| 1954 |
+
{
|
| 1955 |
+
"epoch": 0.5604645291593032,
|
| 1956 |
+
"grad_norm": 0.8567935824394226,
|
| 1957 |
+
"learning_rate": 2.334e-05,
|
| 1958 |
+
"loss": 0.0599,
|
| 1959 |
+
"step": 2220
|
| 1960 |
+
},
|
| 1961 |
+
{
|
| 1962 |
+
"epoch": 0.5629891441555163,
|
| 1963 |
+
"grad_norm": 0.9106941819190979,
|
| 1964 |
+
"learning_rate": 2.3310000000000002e-05,
|
| 1965 |
+
"loss": 0.0593,
|
| 1966 |
+
"step": 2230
|
| 1967 |
+
},
|
| 1968 |
+
{
|
| 1969 |
+
"epoch": 0.5655137591517294,
|
| 1970 |
+
"grad_norm": 1.5944632291793823,
|
| 1971 |
+
"learning_rate": 2.328e-05,
|
| 1972 |
+
"loss": 0.0669,
|
| 1973 |
+
"step": 2240
|
| 1974 |
+
},
|
| 1975 |
+
{
|
| 1976 |
+
"epoch": 0.5680383741479424,
|
| 1977 |
+
"grad_norm": 0.9120457768440247,
|
| 1978 |
+
"learning_rate": 2.3250000000000003e-05,
|
| 1979 |
+
"loss": 0.0722,
|
| 1980 |
+
"step": 2250
|
| 1981 |
+
},
|
| 1982 |
+
{
|
| 1983 |
+
"epoch": 0.5680383741479424,
|
| 1984 |
+
"eval_f1": 0.6139676730710583,
|
| 1985 |
+
"eval_loss": 0.05887339636683464,
|
| 1986 |
+
"eval_runtime": 1155.9087,
|
| 1987 |
+
"eval_samples_per_second": 178.441,
|
| 1988 |
+
"eval_steps_per_second": 2.788,
|
| 1989 |
+
"step": 2250
|
| 1990 |
+
},
|
| 1991 |
+
{
|
| 1992 |
+
"epoch": 0.5705629891441555,
|
| 1993 |
+
"grad_norm": 0.8505953550338745,
|
| 1994 |
+
"learning_rate": 2.322e-05,
|
| 1995 |
+
"loss": 0.0863,
|
| 1996 |
+
"step": 2260
|
| 1997 |
+
},
|
| 1998 |
+
{
|
| 1999 |
+
"epoch": 0.5730876041403686,
|
| 2000 |
+
"grad_norm": 0.9573137164115906,
|
| 2001 |
+
"learning_rate": 2.319e-05,
|
| 2002 |
+
"loss": 0.0712,
|
| 2003 |
+
"step": 2270
|
| 2004 |
+
},
|
| 2005 |
+
{
|
| 2006 |
+
"epoch": 0.5756122191365817,
|
| 2007 |
+
"grad_norm": 1.230735182762146,
|
| 2008 |
+
"learning_rate": 2.3160000000000002e-05,
|
| 2009 |
+
"loss": 0.0677,
|
| 2010 |
+
"step": 2280
|
| 2011 |
+
},
|
| 2012 |
+
{
|
| 2013 |
+
"epoch": 0.5781368341327947,
|
| 2014 |
+
"grad_norm": 1.203621745109558,
|
| 2015 |
+
"learning_rate": 2.313e-05,
|
| 2016 |
+
"loss": 0.0634,
|
| 2017 |
+
"step": 2290
|
| 2018 |
+
},
|
| 2019 |
+
{
|
| 2020 |
+
"epoch": 0.5806614491290079,
|
| 2021 |
+
"grad_norm": 1.3590195178985596,
|
| 2022 |
+
"learning_rate": 2.3100000000000002e-05,
|
| 2023 |
+
"loss": 0.0819,
|
| 2024 |
+
"step": 2300
|
| 2025 |
+
},
|
| 2026 |
+
{
|
| 2027 |
+
"epoch": 0.5806614491290079,
|
| 2028 |
+
"eval_f1": 0.6121980676328502,
|
| 2029 |
+
"eval_loss": 0.050494007766246796,
|
| 2030 |
+
"eval_runtime": 1153.6589,
|
| 2031 |
+
"eval_samples_per_second": 178.789,
|
| 2032 |
+
"eval_steps_per_second": 2.794,
|
| 2033 |
+
"step": 2300
|
| 2034 |
+
},
|
| 2035 |
+
{
|
| 2036 |
+
"epoch": 0.5831860641252209,
|
| 2037 |
+
"grad_norm": 0.8538402318954468,
|
| 2038 |
+
"learning_rate": 2.307e-05,
|
| 2039 |
+
"loss": 0.0674,
|
| 2040 |
+
"step": 2310
|
| 2041 |
+
},
|
| 2042 |
+
{
|
| 2043 |
+
"epoch": 0.5857106791214339,
|
| 2044 |
+
"grad_norm": 1.1863012313842773,
|
| 2045 |
+
"learning_rate": 2.304e-05,
|
| 2046 |
+
"loss": 0.0665,
|
| 2047 |
+
"step": 2320
|
| 2048 |
+
},
|
| 2049 |
+
{
|
| 2050 |
+
"epoch": 0.5882352941176471,
|
| 2051 |
+
"grad_norm": 1.0120714902877808,
|
| 2052 |
+
"learning_rate": 2.301e-05,
|
| 2053 |
+
"loss": 0.0675,
|
| 2054 |
+
"step": 2330
|
| 2055 |
+
},
|
| 2056 |
+
{
|
| 2057 |
+
"epoch": 0.5907599091138601,
|
| 2058 |
+
"grad_norm": 0.8394482135772705,
|
| 2059 |
+
"learning_rate": 2.298e-05,
|
| 2060 |
+
"loss": 0.0812,
|
| 2061 |
+
"step": 2340
|
| 2062 |
+
},
|
| 2063 |
+
{
|
| 2064 |
+
"epoch": 0.5932845241100733,
|
| 2065 |
+
"grad_norm": 0.8855767250061035,
|
| 2066 |
+
"learning_rate": 2.2950000000000002e-05,
|
| 2067 |
+
"loss": 0.0694,
|
| 2068 |
+
"step": 2350
|
| 2069 |
+
},
|
| 2070 |
+
{
|
| 2071 |
+
"epoch": 0.5932845241100733,
|
| 2072 |
+
"eval_f1": 0.6101251634597422,
|
| 2073 |
+
"eval_loss": 0.053731031715869904,
|
| 2074 |
+
"eval_runtime": 1147.8424,
|
| 2075 |
+
"eval_samples_per_second": 179.695,
|
| 2076 |
+
"eval_steps_per_second": 2.808,
|
| 2077 |
+
"step": 2350
|
| 2078 |
+
},
|
| 2079 |
+
{
|
| 2080 |
+
"epoch": 0.5958091391062863,
|
| 2081 |
+
"grad_norm": 1.241045594215393,
|
| 2082 |
+
"learning_rate": 2.292e-05,
|
| 2083 |
+
"loss": 0.0646,
|
| 2084 |
+
"step": 2360
|
| 2085 |
+
},
|
| 2086 |
+
{
|
| 2087 |
+
"epoch": 0.5983337541024993,
|
| 2088 |
+
"grad_norm": 2.065401315689087,
|
| 2089 |
+
"learning_rate": 2.289e-05,
|
| 2090 |
+
"loss": 0.0792,
|
| 2091 |
+
"step": 2370
|
| 2092 |
+
},
|
| 2093 |
+
{
|
| 2094 |
+
"epoch": 0.6008583690987125,
|
| 2095 |
+
"grad_norm": 1.0024877786636353,
|
| 2096 |
+
"learning_rate": 2.286e-05,
|
| 2097 |
+
"loss": 0.0751,
|
| 2098 |
+
"step": 2380
|
| 2099 |
+
},
|
| 2100 |
+
{
|
| 2101 |
+
"epoch": 0.6033829840949255,
|
| 2102 |
+
"grad_norm": 0.4943256080150604,
|
| 2103 |
+
"learning_rate": 2.283e-05,
|
| 2104 |
+
"loss": 0.076,
|
| 2105 |
+
"step": 2390
|
| 2106 |
+
},
|
| 2107 |
+
{
|
| 2108 |
+
"epoch": 0.6059075990911386,
|
| 2109 |
+
"grad_norm": 1.0907814502716064,
|
| 2110 |
+
"learning_rate": 2.2800000000000002e-05,
|
| 2111 |
+
"loss": 0.0705,
|
| 2112 |
+
"step": 2400
|
| 2113 |
+
},
|
| 2114 |
+
{
|
| 2115 |
+
"epoch": 0.6059075990911386,
|
| 2116 |
+
"eval_f1": 0.6130196664177247,
|
| 2117 |
+
"eval_loss": 0.06461644172668457,
|
| 2118 |
+
"eval_runtime": 1149.8253,
|
| 2119 |
+
"eval_samples_per_second": 179.386,
|
| 2120 |
+
"eval_steps_per_second": 2.803,
|
| 2121 |
+
"step": 2400
|
| 2122 |
+
},
|
| 2123 |
+
{
|
| 2124 |
+
"epoch": 0.6084322140873517,
|
| 2125 |
+
"grad_norm": 1.1304162740707397,
|
| 2126 |
+
"learning_rate": 2.277e-05,
|
| 2127 |
+
"loss": 0.0548,
|
| 2128 |
+
"step": 2410
|
| 2129 |
+
},
|
| 2130 |
+
{
|
| 2131 |
+
"epoch": 0.6109568290835647,
|
| 2132 |
+
"grad_norm": 1.3394097089767456,
|
| 2133 |
+
"learning_rate": 2.274e-05,
|
| 2134 |
+
"loss": 0.0607,
|
| 2135 |
+
"step": 2420
|
| 2136 |
+
},
|
| 2137 |
+
{
|
| 2138 |
+
"epoch": 0.6134814440797778,
|
| 2139 |
+
"grad_norm": 0.5467960834503174,
|
| 2140 |
+
"learning_rate": 2.271e-05,
|
| 2141 |
+
"loss": 0.0701,
|
| 2142 |
+
"step": 2430
|
| 2143 |
+
},
|
| 2144 |
+
{
|
| 2145 |
+
"epoch": 0.6160060590759909,
|
| 2146 |
+
"grad_norm": 0.5510517954826355,
|
| 2147 |
+
"learning_rate": 2.268e-05,
|
| 2148 |
+
"loss": 0.0725,
|
| 2149 |
+
"step": 2440
|
| 2150 |
+
},
|
| 2151 |
+
{
|
| 2152 |
+
"epoch": 0.618530674072204,
|
| 2153 |
+
"grad_norm": 0.7682734131813049,
|
| 2154 |
+
"learning_rate": 2.265e-05,
|
| 2155 |
+
"loss": 0.0702,
|
| 2156 |
+
"step": 2450
|
| 2157 |
+
},
|
| 2158 |
+
{
|
| 2159 |
+
"epoch": 0.618530674072204,
|
| 2160 |
+
"eval_f1": 0.6124447065762312,
|
| 2161 |
+
"eval_loss": 0.046234920620918274,
|
| 2162 |
+
"eval_runtime": 1146.4615,
|
| 2163 |
+
"eval_samples_per_second": 179.912,
|
| 2164 |
+
"eval_steps_per_second": 2.811,
|
| 2165 |
+
"step": 2450
|
| 2166 |
+
},
|
| 2167 |
+
{
|
| 2168 |
+
"epoch": 0.6210552890684171,
|
| 2169 |
+
"grad_norm": 0.7578818798065186,
|
| 2170 |
+
"learning_rate": 2.262e-05,
|
| 2171 |
+
"loss": 0.0703,
|
| 2172 |
+
"step": 2460
|
| 2173 |
+
},
|
| 2174 |
+
{
|
| 2175 |
+
"epoch": 0.6235799040646302,
|
| 2176 |
+
"grad_norm": 0.7244108319282532,
|
| 2177 |
+
"learning_rate": 2.2590000000000002e-05,
|
| 2178 |
+
"loss": 0.0635,
|
| 2179 |
+
"step": 2470
|
| 2180 |
+
},
|
| 2181 |
+
{
|
| 2182 |
+
"epoch": 0.6261045190608432,
|
| 2183 |
+
"grad_norm": 1.1047908067703247,
|
| 2184 |
+
"learning_rate": 2.256e-05,
|
| 2185 |
+
"loss": 0.0614,
|
| 2186 |
+
"step": 2480
|
| 2187 |
+
},
|
| 2188 |
+
{
|
| 2189 |
+
"epoch": 0.6286291340570563,
|
| 2190 |
+
"grad_norm": 1.0824987888336182,
|
| 2191 |
+
"learning_rate": 2.253e-05,
|
| 2192 |
+
"loss": 0.081,
|
| 2193 |
+
"step": 2490
|
| 2194 |
+
},
|
| 2195 |
+
{
|
| 2196 |
+
"epoch": 0.6311537490532694,
|
| 2197 |
+
"grad_norm": 1.9344598054885864,
|
| 2198 |
+
"learning_rate": 2.25e-05,
|
| 2199 |
+
"loss": 0.0709,
|
| 2200 |
+
"step": 2500
|
| 2201 |
+
},
|
| 2202 |
+
{
|
| 2203 |
+
"epoch": 0.6311537490532694,
|
| 2204 |
+
"eval_f1": 0.6133951445650848,
|
| 2205 |
+
"eval_loss": 0.04044894501566887,
|
| 2206 |
+
"eval_runtime": 1148.0724,
|
| 2207 |
+
"eval_samples_per_second": 179.659,
|
| 2208 |
+
"eval_steps_per_second": 2.807,
|
| 2209 |
+
"step": 2500
|
| 2210 |
+
},
|
| 2211 |
+
{
|
| 2212 |
+
"epoch": 0.6336783640494824,
|
| 2213 |
+
"grad_norm": 1.2797091007232666,
|
| 2214 |
+
"learning_rate": 2.247e-05,
|
| 2215 |
+
"loss": 0.072,
|
| 2216 |
+
"step": 2510
|
| 2217 |
+
},
|
| 2218 |
+
{
|
| 2219 |
+
"epoch": 0.6362029790456956,
|
| 2220 |
+
"grad_norm": 0.7228933572769165,
|
| 2221 |
+
"learning_rate": 2.2440000000000002e-05,
|
| 2222 |
+
"loss": 0.071,
|
| 2223 |
+
"step": 2520
|
| 2224 |
+
},
|
| 2225 |
+
{
|
| 2226 |
+
"epoch": 0.6387275940419086,
|
| 2227 |
+
"grad_norm": 0.9655591249465942,
|
| 2228 |
+
"learning_rate": 2.241e-05,
|
| 2229 |
+
"loss": 0.0611,
|
| 2230 |
+
"step": 2530
|
| 2231 |
+
},
|
| 2232 |
+
{
|
| 2233 |
+
"epoch": 0.6412522090381216,
|
| 2234 |
+
"grad_norm": 0.9924450516700745,
|
| 2235 |
+
"learning_rate": 2.238e-05,
|
| 2236 |
+
"loss": 0.0676,
|
| 2237 |
+
"step": 2540
|
| 2238 |
+
},
|
| 2239 |
+
{
|
| 2240 |
+
"epoch": 0.6437768240343348,
|
| 2241 |
+
"grad_norm": 1.12591552734375,
|
| 2242 |
+
"learning_rate": 2.235e-05,
|
| 2243 |
+
"loss": 0.0804,
|
| 2244 |
+
"step": 2550
|
| 2245 |
+
},
|
| 2246 |
+
{
|
| 2247 |
+
"epoch": 0.6437768240343348,
|
| 2248 |
+
"eval_f1": 0.612305676335696,
|
| 2249 |
+
"eval_loss": 0.04778852313756943,
|
| 2250 |
+
"eval_runtime": 1160.4576,
|
| 2251 |
+
"eval_samples_per_second": 177.742,
|
| 2252 |
+
"eval_steps_per_second": 2.777,
|
| 2253 |
+
"step": 2550
|
| 2254 |
+
},
|
| 2255 |
+
{
|
| 2256 |
+
"epoch": 0.6463014390305478,
|
| 2257 |
+
"grad_norm": 0.7478006482124329,
|
| 2258 |
+
"learning_rate": 2.232e-05,
|
| 2259 |
+
"loss": 0.0638,
|
| 2260 |
+
"step": 2560
|
| 2261 |
+
},
|
| 2262 |
+
{
|
| 2263 |
+
"epoch": 0.648826054026761,
|
| 2264 |
+
"grad_norm": 0.7661213874816895,
|
| 2265 |
+
"learning_rate": 2.2290000000000002e-05,
|
| 2266 |
+
"loss": 0.0632,
|
| 2267 |
+
"step": 2570
|
| 2268 |
+
},
|
| 2269 |
+
{
|
| 2270 |
+
"epoch": 0.651350669022974,
|
| 2271 |
+
"grad_norm": 0.9824168086051941,
|
| 2272 |
+
"learning_rate": 2.226e-05,
|
| 2273 |
+
"loss": 0.0602,
|
| 2274 |
+
"step": 2580
|
| 2275 |
+
},
|
| 2276 |
+
{
|
| 2277 |
+
"epoch": 0.653875284019187,
|
| 2278 |
+
"grad_norm": 1.1700901985168457,
|
| 2279 |
+
"learning_rate": 2.223e-05,
|
| 2280 |
+
"loss": 0.0714,
|
| 2281 |
+
"step": 2590
|
| 2282 |
+
},
|
| 2283 |
+
{
|
| 2284 |
+
"epoch": 0.6563998990154002,
|
| 2285 |
+
"grad_norm": 0.8846214413642883,
|
| 2286 |
+
"learning_rate": 2.22e-05,
|
| 2287 |
+
"loss": 0.0666,
|
| 2288 |
+
"step": 2600
|
| 2289 |
+
},
|
| 2290 |
+
{
|
| 2291 |
+
"epoch": 0.6563998990154002,
|
| 2292 |
+
"eval_f1": 0.6104417670682731,
|
| 2293 |
+
"eval_loss": 0.04546576738357544,
|
| 2294 |
+
"eval_runtime": 1160.1326,
|
| 2295 |
+
"eval_samples_per_second": 177.792,
|
| 2296 |
+
"eval_steps_per_second": 2.778,
|
| 2297 |
+
"step": 2600
|
| 2298 |
+
},
|
| 2299 |
+
{
|
| 2300 |
+
"epoch": 0.6589245140116132,
|
| 2301 |
+
"grad_norm": 0.7641239166259766,
|
| 2302 |
+
"learning_rate": 2.217e-05,
|
| 2303 |
+
"loss": 0.058,
|
| 2304 |
+
"step": 2610
|
| 2305 |
+
},
|
| 2306 |
+
{
|
| 2307 |
+
"epoch": 0.6614491290078263,
|
| 2308 |
+
"grad_norm": 0.5828648209571838,
|
| 2309 |
+
"learning_rate": 2.214e-05,
|
| 2310 |
+
"loss": 0.0686,
|
| 2311 |
+
"step": 2620
|
| 2312 |
+
},
|
| 2313 |
+
{
|
| 2314 |
+
"epoch": 0.6639737440040394,
|
| 2315 |
+
"grad_norm": 0.6906914710998535,
|
| 2316 |
+
"learning_rate": 2.211e-05,
|
| 2317 |
+
"loss": 0.0764,
|
| 2318 |
+
"step": 2630
|
| 2319 |
+
},
|
| 2320 |
+
{
|
| 2321 |
+
"epoch": 0.6664983590002524,
|
| 2322 |
+
"grad_norm": 1.3137489557266235,
|
| 2323 |
+
"learning_rate": 2.208e-05,
|
| 2324 |
+
"loss": 0.0768,
|
| 2325 |
+
"step": 2640
|
| 2326 |
+
},
|
| 2327 |
+
{
|
| 2328 |
+
"epoch": 0.6690229739964655,
|
| 2329 |
+
"grad_norm": 0.863865077495575,
|
| 2330 |
+
"learning_rate": 2.205e-05,
|
| 2331 |
+
"loss": 0.0749,
|
| 2332 |
+
"step": 2650
|
| 2333 |
+
},
|
| 2334 |
+
{
|
| 2335 |
+
"epoch": 0.6690229739964655,
|
| 2336 |
+
"eval_f1": 0.6131900703964431,
|
| 2337 |
+
"eval_loss": 0.04790908098220825,
|
| 2338 |
+
"eval_runtime": 1162.4462,
|
| 2339 |
+
"eval_samples_per_second": 177.438,
|
| 2340 |
+
"eval_steps_per_second": 2.773,
|
| 2341 |
+
"step": 2650
|
| 2342 |
+
},
|
| 2343 |
+
{
|
| 2344 |
+
"epoch": 0.6715475889926786,
|
| 2345 |
+
"grad_norm": 0.9182652235031128,
|
| 2346 |
+
"learning_rate": 2.202e-05,
|
| 2347 |
+
"loss": 0.0625,
|
| 2348 |
+
"step": 2660
|
| 2349 |
+
},
|
| 2350 |
+
{
|
| 2351 |
+
"epoch": 0.6740722039888917,
|
| 2352 |
+
"grad_norm": 1.4961283206939697,
|
| 2353 |
+
"learning_rate": 2.199e-05,
|
| 2354 |
+
"loss": 0.0726,
|
| 2355 |
+
"step": 2670
|
| 2356 |
+
},
|
| 2357 |
+
{
|
| 2358 |
+
"epoch": 0.6765968189851048,
|
| 2359 |
+
"grad_norm": 0.7803681492805481,
|
| 2360 |
+
"learning_rate": 2.196e-05,
|
| 2361 |
+
"loss": 0.0669,
|
| 2362 |
+
"step": 2680
|
| 2363 |
+
},
|
| 2364 |
+
{
|
| 2365 |
+
"epoch": 0.6791214339813179,
|
| 2366 |
+
"grad_norm": 1.0371824502944946,
|
| 2367 |
+
"learning_rate": 2.193e-05,
|
| 2368 |
+
"loss": 0.0566,
|
| 2369 |
+
"step": 2690
|
| 2370 |
+
},
|
| 2371 |
+
{
|
| 2372 |
+
"epoch": 0.6816460489775309,
|
| 2373 |
+
"grad_norm": 1.1832714080810547,
|
| 2374 |
+
"learning_rate": 2.19e-05,
|
| 2375 |
+
"loss": 0.067,
|
| 2376 |
+
"step": 2700
|
| 2377 |
+
},
|
| 2378 |
+
{
|
| 2379 |
+
"epoch": 0.6816460489775309,
|
| 2380 |
+
"eval_f1": 0.6132461161079312,
|
| 2381 |
+
"eval_loss": 0.055793602019548416,
|
| 2382 |
+
"eval_runtime": 1161.8914,
|
| 2383 |
+
"eval_samples_per_second": 177.523,
|
| 2384 |
+
"eval_steps_per_second": 2.774,
|
| 2385 |
+
"step": 2700
|
| 2386 |
+
},
|
| 2387 |
+
{
|
| 2388 |
+
"epoch": 0.684170663973744,
|
| 2389 |
+
"grad_norm": 0.7899573445320129,
|
| 2390 |
+
"learning_rate": 2.187e-05,
|
| 2391 |
+
"loss": 0.0763,
|
| 2392 |
+
"step": 2710
|
| 2393 |
+
},
|
| 2394 |
+
{
|
| 2395 |
+
"epoch": 0.6866952789699571,
|
| 2396 |
+
"grad_norm": 1.4638808965682983,
|
| 2397 |
+
"learning_rate": 2.184e-05,
|
| 2398 |
+
"loss": 0.0768,
|
| 2399 |
+
"step": 2720
|
| 2400 |
+
},
|
| 2401 |
+
{
|
| 2402 |
+
"epoch": 0.6892198939661701,
|
| 2403 |
+
"grad_norm": 0.7547538876533508,
|
| 2404 |
+
"learning_rate": 2.181e-05,
|
| 2405 |
+
"loss": 0.0761,
|
| 2406 |
+
"step": 2730
|
| 2407 |
+
},
|
| 2408 |
+
{
|
| 2409 |
+
"epoch": 0.6917445089623833,
|
| 2410 |
+
"grad_norm": 0.5143932700157166,
|
| 2411 |
+
"learning_rate": 2.178e-05,
|
| 2412 |
+
"loss": 0.0808,
|
| 2413 |
+
"step": 2740
|
| 2414 |
+
},
|
| 2415 |
+
{
|
| 2416 |
+
"epoch": 0.6942691239585963,
|
| 2417 |
+
"grad_norm": 1.011730432510376,
|
| 2418 |
+
"learning_rate": 2.175e-05,
|
| 2419 |
+
"loss": 0.068,
|
| 2420 |
+
"step": 2750
|
| 2421 |
+
},
|
| 2422 |
+
{
|
| 2423 |
+
"epoch": 0.6942691239585963,
|
| 2424 |
+
"eval_f1": 0.6108202443280978,
|
| 2425 |
+
"eval_loss": 0.053855251520872116,
|
| 2426 |
+
"eval_runtime": 1160.3338,
|
| 2427 |
+
"eval_samples_per_second": 177.761,
|
| 2428 |
+
"eval_steps_per_second": 2.778,
|
| 2429 |
+
"step": 2750
|
| 2430 |
+
},
|
| 2431 |
+
{
|
| 2432 |
+
"epoch": 0.6942691239585963,
|
| 2433 |
+
"step": 2750,
|
| 2434 |
+
"total_flos": 1.3639932886745088e+19,
|
| 2435 |
+
"train_loss": 0.019194319985129618,
|
| 2436 |
+
"train_runtime": 18605.0451,
|
| 2437 |
+
"train_samples_per_second": 34.399,
|
| 2438 |
+
"train_steps_per_second": 0.537
|
| 2439 |
}
|
| 2440 |
],
|
| 2441 |
"logging_steps": 10,
|
|
|
|
| 2464 |
"attributes": {}
|
| 2465 |
}
|
| 2466 |
},
|
| 2467 |
+
"total_flos": 1.3639932886745088e+19,
|
| 2468 |
"train_batch_size": 64,
|
| 2469 |
"trial_name": null,
|
| 2470 |
"trial_params": null
|