Instructions to use lexlms/legal-roberta-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use lexlms/legal-roberta-base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="lexlms/legal-roberta-base")# Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("lexlms/legal-roberta-base") model = AutoModelForMaskedLM.from_pretrained("lexlms/legal-roberta-base") - Notebooks
- Google Colab
- Kaggle
Commit ·
f928948
1
Parent(s): f78ff50
Training in progress, step 350000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state_0.pth +1 -1
- last-checkpoint/rng_state_1.pth +1 -1
- last-checkpoint/rng_state_2.pth +1 -1
- last-checkpoint/rng_state_3.pth +1 -1
- last-checkpoint/rng_state_4.pth +1 -1
- last-checkpoint/rng_state_5.pth +1 -1
- last-checkpoint/rng_state_6.pth +1 -1
- last-checkpoint/rng_state_7.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +311 -3
- last-checkpoint/training_args.bin +1 -1
- pytorch_model.bin +1 -1
- runs/Nov11_11-14-20_t1v-n-088af867-w-0/events.out.tfevents.1668165319.t1v-n-088af867-w-0.346597.0 +2 -2
- runs/Nov17_09-03-22_t1v-n-088af867-w-0/1668675880.4394102/events.out.tfevents.1668675880.t1v-n-088af867-w-0.91101.1 +3 -0
- runs/Nov17_09-03-22_t1v-n-088af867-w-0/events.out.tfevents.1668675880.t1v-n-088af867-w-0.91101.0 +3 -0
- runs/Nov21_18-14-51_t1v-n-088af867-w-0/1669054551.8620195/events.out.tfevents.1669054551.t1v-n-088af867-w-0.42571.1 +3 -0
- runs/Nov21_18-14-51_t1v-n-088af867-w-0/events.out.tfevents.1669054551.t1v-n-088af867-w-0.42571.0 +3 -0
- training_args.bin +1 -1
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 996067161
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e61ee14a21dfb599f1c63f3e0e8686eb244cce7311c2a2b967485c15ff52a3f8
|
| 3 |
size 996067161
|
last-checkpoint/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 498046827
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e1fddf171aaf7fcd5407c99cb8a97835dce9ceccd14ee70ed5b23a17af12fdf3
|
| 3 |
size 498046827
|
last-checkpoint/rng_state_0.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 13611
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:036eb5eec66f4acc5bf94747270222b9c5a69b86c3f623f9e981140d862a7ab4
|
| 3 |
size 13611
|
last-checkpoint/rng_state_1.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 13611
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9fcbaab8f44aa44b57133d3d5819bbf91b8fc92df692100e5583bb214e77939c
|
| 3 |
size 13611
|
last-checkpoint/rng_state_2.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 13611
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:036eb5eec66f4acc5bf94747270222b9c5a69b86c3f623f9e981140d862a7ab4
|
| 3 |
size 13611
|
last-checkpoint/rng_state_3.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 13611
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:74cd3be6cc3a9e9a714d813672381da6434030e8445f48465040931d56dcaba6
|
| 3 |
size 13611
|
last-checkpoint/rng_state_4.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 13611
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:673bcbb9d666bc7c835ef864763b55aa80db016b301aae7e39ae8a0cb0efb86a
|
| 3 |
size 13611
|
last-checkpoint/rng_state_5.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 13611
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:74cd3be6cc3a9e9a714d813672381da6434030e8445f48465040931d56dcaba6
|
| 3 |
size 13611
|
last-checkpoint/rng_state_6.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 13611
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:673bcbb9d666bc7c835ef864763b55aa80db016b301aae7e39ae8a0cb0efb86a
|
| 3 |
size 13611
|
last-checkpoint/rng_state_7.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 13611
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:036eb5eec66f4acc5bf94747270222b9c5a69b86c3f623f9e981140d862a7ab4
|
| 3 |
size 13611
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 623
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f8f220426de5a076dbb6f66f54955d3a3fc0acbab10b1bd60cf9472b552bfdca
|
| 3 |
size 623
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 1.
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -1854,11 +1854,319 @@
|
|
| 1854 |
"eval_samples_per_second": 492.503,
|
| 1855 |
"eval_steps_per_second": 1.97,
|
| 1856 |
"step": 300000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1857 |
}
|
| 1858 |
],
|
| 1859 |
"max_steps": 1000000,
|
| 1860 |
"num_train_epochs": 9223372036854775807,
|
| 1861 |
-
"total_flos": 5.
|
| 1862 |
"trial_name": null,
|
| 1863 |
"trial_params": null
|
| 1864 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.08296,
|
| 5 |
+
"global_step": 350000,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 1854 |
"eval_samples_per_second": 492.503,
|
| 1855 |
"eval_steps_per_second": 1.97,
|
| 1856 |
"step": 300000
|
| 1857 |
+
},
|
| 1858 |
+
{
|
| 1859 |
+
"epoch": 1.03,
|
| 1860 |
+
"learning_rate": 8.37422439088976e-05,
|
| 1861 |
+
"loss": 0.894,
|
| 1862 |
+
"step": 301000
|
| 1863 |
+
},
|
| 1864 |
+
{
|
| 1865 |
+
"epoch": 1.03,
|
| 1866 |
+
"learning_rate": 8.362004023673474e-05,
|
| 1867 |
+
"loss": 0.8804,
|
| 1868 |
+
"step": 302000
|
| 1869 |
+
},
|
| 1870 |
+
{
|
| 1871 |
+
"epoch": 1.04,
|
| 1872 |
+
"learning_rate": 8.349746890119826e-05,
|
| 1873 |
+
"loss": 0.8663,
|
| 1874 |
+
"step": 303000
|
| 1875 |
+
},
|
| 1876 |
+
{
|
| 1877 |
+
"epoch": 1.04,
|
| 1878 |
+
"learning_rate": 8.337453124270863e-05,
|
| 1879 |
+
"loss": 0.8767,
|
| 1880 |
+
"step": 304000
|
| 1881 |
+
},
|
| 1882 |
+
{
|
| 1883 |
+
"epoch": 1.04,
|
| 1884 |
+
"learning_rate": 8.32512286056924e-05,
|
| 1885 |
+
"loss": 0.8697,
|
| 1886 |
+
"step": 305000
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 1.04,
|
| 1890 |
+
"learning_rate": 8.31275623385675e-05,
|
| 1891 |
+
"loss": 0.876,
|
| 1892 |
+
"step": 306000
|
| 1893 |
+
},
|
| 1894 |
+
{
|
| 1895 |
+
"epoch": 1.04,
|
| 1896 |
+
"learning_rate": 8.300353379372834e-05,
|
| 1897 |
+
"loss": 0.8752,
|
| 1898 |
+
"step": 307000
|
| 1899 |
+
},
|
| 1900 |
+
{
|
| 1901 |
+
"epoch": 1.04,
|
| 1902 |
+
"learning_rate": 8.287914432753123e-05,
|
| 1903 |
+
"loss": 0.8711,
|
| 1904 |
+
"step": 308000
|
| 1905 |
+
},
|
| 1906 |
+
{
|
| 1907 |
+
"epoch": 1.04,
|
| 1908 |
+
"learning_rate": 8.275439530027948e-05,
|
| 1909 |
+
"loss": 0.8526,
|
| 1910 |
+
"step": 309000
|
| 1911 |
+
},
|
| 1912 |
+
{
|
| 1913 |
+
"epoch": 1.04,
|
| 1914 |
+
"learning_rate": 8.262928807620843e-05,
|
| 1915 |
+
"loss": 0.8794,
|
| 1916 |
+
"step": 310000
|
| 1917 |
+
},
|
| 1918 |
+
{
|
| 1919 |
+
"epoch": 1.04,
|
| 1920 |
+
"learning_rate": 8.250382402347065e-05,
|
| 1921 |
+
"loss": 0.8671,
|
| 1922 |
+
"step": 311000
|
| 1923 |
+
},
|
| 1924 |
+
{
|
| 1925 |
+
"epoch": 1.04,
|
| 1926 |
+
"learning_rate": 8.237800451412095e-05,
|
| 1927 |
+
"loss": 0.8772,
|
| 1928 |
+
"step": 312000
|
| 1929 |
+
},
|
| 1930 |
+
{
|
| 1931 |
+
"epoch": 1.05,
|
| 1932 |
+
"learning_rate": 8.225183092410128e-05,
|
| 1933 |
+
"loss": 0.8786,
|
| 1934 |
+
"step": 313000
|
| 1935 |
+
},
|
| 1936 |
+
{
|
| 1937 |
+
"epoch": 1.05,
|
| 1938 |
+
"learning_rate": 8.212530463322583e-05,
|
| 1939 |
+
"loss": 0.8704,
|
| 1940 |
+
"step": 314000
|
| 1941 |
+
},
|
| 1942 |
+
{
|
| 1943 |
+
"epoch": 1.05,
|
| 1944 |
+
"learning_rate": 8.199842702516583e-05,
|
| 1945 |
+
"loss": 0.8801,
|
| 1946 |
+
"step": 315000
|
| 1947 |
+
},
|
| 1948 |
+
{
|
| 1949 |
+
"epoch": 1.05,
|
| 1950 |
+
"learning_rate": 8.18711994874345e-05,
|
| 1951 |
+
"loss": 0.8728,
|
| 1952 |
+
"step": 316000
|
| 1953 |
+
},
|
| 1954 |
+
{
|
| 1955 |
+
"epoch": 1.05,
|
| 1956 |
+
"learning_rate": 8.174362341137177e-05,
|
| 1957 |
+
"loss": 0.8628,
|
| 1958 |
+
"step": 317000
|
| 1959 |
+
},
|
| 1960 |
+
{
|
| 1961 |
+
"epoch": 1.05,
|
| 1962 |
+
"learning_rate": 8.161570019212921e-05,
|
| 1963 |
+
"loss": 0.8591,
|
| 1964 |
+
"step": 318000
|
| 1965 |
+
},
|
| 1966 |
+
{
|
| 1967 |
+
"epoch": 1.05,
|
| 1968 |
+
"learning_rate": 8.148743122865463e-05,
|
| 1969 |
+
"loss": 0.8793,
|
| 1970 |
+
"step": 319000
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"epoch": 1.05,
|
| 1974 |
+
"learning_rate": 8.135881792367686e-05,
|
| 1975 |
+
"loss": 0.8958,
|
| 1976 |
+
"step": 320000
|
| 1977 |
+
},
|
| 1978 |
+
{
|
| 1979 |
+
"epoch": 1.05,
|
| 1980 |
+
"learning_rate": 8.12298616836904e-05,
|
| 1981 |
+
"loss": 0.8768,
|
| 1982 |
+
"step": 321000
|
| 1983 |
+
},
|
| 1984 |
+
{
|
| 1985 |
+
"epoch": 1.05,
|
| 1986 |
+
"learning_rate": 8.110056391894005e-05,
|
| 1987 |
+
"loss": 0.8882,
|
| 1988 |
+
"step": 322000
|
| 1989 |
+
},
|
| 1990 |
+
{
|
| 1991 |
+
"epoch": 1.06,
|
| 1992 |
+
"learning_rate": 8.097092604340542e-05,
|
| 1993 |
+
"loss": 0.8954,
|
| 1994 |
+
"step": 323000
|
| 1995 |
+
},
|
| 1996 |
+
{
|
| 1997 |
+
"epoch": 1.06,
|
| 1998 |
+
"learning_rate": 8.084094947478556e-05,
|
| 1999 |
+
"loss": 0.9074,
|
| 2000 |
+
"step": 324000
|
| 2001 |
+
},
|
| 2002 |
+
{
|
| 2003 |
+
"epoch": 1.06,
|
| 2004 |
+
"learning_rate": 8.07106356344834e-05,
|
| 2005 |
+
"loss": 0.894,
|
| 2006 |
+
"step": 325000
|
| 2007 |
+
},
|
| 2008 |
+
{
|
| 2009 |
+
"epoch": 1.06,
|
| 2010 |
+
"learning_rate": 8.057998594759022e-05,
|
| 2011 |
+
"loss": 0.8978,
|
| 2012 |
+
"step": 326000
|
| 2013 |
+
},
|
| 2014 |
+
{
|
| 2015 |
+
"epoch": 1.06,
|
| 2016 |
+
"learning_rate": 8.044900184287007e-05,
|
| 2017 |
+
"loss": 0.9071,
|
| 2018 |
+
"step": 327000
|
| 2019 |
+
},
|
| 2020 |
+
{
|
| 2021 |
+
"epoch": 1.06,
|
| 2022 |
+
"learning_rate": 8.031768475274413e-05,
|
| 2023 |
+
"loss": 0.9107,
|
| 2024 |
+
"step": 328000
|
| 2025 |
+
},
|
| 2026 |
+
{
|
| 2027 |
+
"epoch": 1.06,
|
| 2028 |
+
"learning_rate": 8.018603611327504e-05,
|
| 2029 |
+
"loss": 0.8774,
|
| 2030 |
+
"step": 329000
|
| 2031 |
+
},
|
| 2032 |
+
{
|
| 2033 |
+
"epoch": 1.06,
|
| 2034 |
+
"learning_rate": 8.005405736415126e-05,
|
| 2035 |
+
"loss": 0.8975,
|
| 2036 |
+
"step": 330000
|
| 2037 |
+
},
|
| 2038 |
+
{
|
| 2039 |
+
"epoch": 1.06,
|
| 2040 |
+
"learning_rate": 7.992174994867123e-05,
|
| 2041 |
+
"loss": 0.8813,
|
| 2042 |
+
"step": 331000
|
| 2043 |
+
},
|
| 2044 |
+
{
|
| 2045 |
+
"epoch": 1.06,
|
| 2046 |
+
"learning_rate": 7.978911531372765e-05,
|
| 2047 |
+
"loss": 0.869,
|
| 2048 |
+
"step": 332000
|
| 2049 |
+
},
|
| 2050 |
+
{
|
| 2051 |
+
"epoch": 1.07,
|
| 2052 |
+
"learning_rate": 7.965615490979163e-05,
|
| 2053 |
+
"loss": 0.8809,
|
| 2054 |
+
"step": 333000
|
| 2055 |
+
},
|
| 2056 |
+
{
|
| 2057 |
+
"epoch": 1.07,
|
| 2058 |
+
"learning_rate": 7.952287019089685e-05,
|
| 2059 |
+
"loss": 0.8669,
|
| 2060 |
+
"step": 334000
|
| 2061 |
+
},
|
| 2062 |
+
{
|
| 2063 |
+
"epoch": 1.07,
|
| 2064 |
+
"learning_rate": 7.938926261462366e-05,
|
| 2065 |
+
"loss": 0.8675,
|
| 2066 |
+
"step": 335000
|
| 2067 |
+
},
|
| 2068 |
+
{
|
| 2069 |
+
"epoch": 1.07,
|
| 2070 |
+
"learning_rate": 7.925533364208309e-05,
|
| 2071 |
+
"loss": 0.8748,
|
| 2072 |
+
"step": 336000
|
| 2073 |
+
},
|
| 2074 |
+
{
|
| 2075 |
+
"epoch": 1.07,
|
| 2076 |
+
"learning_rate": 7.912108473790092e-05,
|
| 2077 |
+
"loss": 0.883,
|
| 2078 |
+
"step": 337000
|
| 2079 |
+
},
|
| 2080 |
+
{
|
| 2081 |
+
"epoch": 1.07,
|
| 2082 |
+
"learning_rate": 7.898651737020166e-05,
|
| 2083 |
+
"loss": 0.8941,
|
| 2084 |
+
"step": 338000
|
| 2085 |
+
},
|
| 2086 |
+
{
|
| 2087 |
+
"epoch": 1.07,
|
| 2088 |
+
"learning_rate": 7.88516330105925e-05,
|
| 2089 |
+
"loss": 0.8876,
|
| 2090 |
+
"step": 339000
|
| 2091 |
+
},
|
| 2092 |
+
{
|
| 2093 |
+
"epoch": 1.07,
|
| 2094 |
+
"learning_rate": 7.871643313414718e-05,
|
| 2095 |
+
"loss": 0.8878,
|
| 2096 |
+
"step": 340000
|
| 2097 |
+
},
|
| 2098 |
+
{
|
| 2099 |
+
"epoch": 1.07,
|
| 2100 |
+
"learning_rate": 7.858091921938988e-05,
|
| 2101 |
+
"loss": 0.8908,
|
| 2102 |
+
"step": 341000
|
| 2103 |
+
},
|
| 2104 |
+
{
|
| 2105 |
+
"epoch": 1.07,
|
| 2106 |
+
"learning_rate": 7.844509274827907e-05,
|
| 2107 |
+
"loss": 0.8878,
|
| 2108 |
+
"step": 342000
|
| 2109 |
+
},
|
| 2110 |
+
{
|
| 2111 |
+
"epoch": 1.08,
|
| 2112 |
+
"learning_rate": 7.830895520619128e-05,
|
| 2113 |
+
"loss": 0.8865,
|
| 2114 |
+
"step": 343000
|
| 2115 |
+
},
|
| 2116 |
+
{
|
| 2117 |
+
"epoch": 1.08,
|
| 2118 |
+
"learning_rate": 7.817250808190483e-05,
|
| 2119 |
+
"loss": 0.8842,
|
| 2120 |
+
"step": 344000
|
| 2121 |
+
},
|
| 2122 |
+
{
|
| 2123 |
+
"epoch": 1.08,
|
| 2124 |
+
"learning_rate": 7.803575286758364e-05,
|
| 2125 |
+
"loss": 0.8879,
|
| 2126 |
+
"step": 345000
|
| 2127 |
+
},
|
| 2128 |
+
{
|
| 2129 |
+
"epoch": 1.08,
|
| 2130 |
+
"learning_rate": 7.789869105876083e-05,
|
| 2131 |
+
"loss": 0.8964,
|
| 2132 |
+
"step": 346000
|
| 2133 |
+
},
|
| 2134 |
+
{
|
| 2135 |
+
"epoch": 1.08,
|
| 2136 |
+
"learning_rate": 7.776132415432234e-05,
|
| 2137 |
+
"loss": 0.8836,
|
| 2138 |
+
"step": 347000
|
| 2139 |
+
},
|
| 2140 |
+
{
|
| 2141 |
+
"epoch": 1.08,
|
| 2142 |
+
"learning_rate": 7.762365365649067e-05,
|
| 2143 |
+
"loss": 0.8834,
|
| 2144 |
+
"step": 348000
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 1.08,
|
| 2148 |
+
"learning_rate": 7.748568107080832e-05,
|
| 2149 |
+
"loss": 0.8907,
|
| 2150 |
+
"step": 349000
|
| 2151 |
+
},
|
| 2152 |
+
{
|
| 2153 |
+
"epoch": 1.08,
|
| 2154 |
+
"learning_rate": 7.734740790612136e-05,
|
| 2155 |
+
"loss": 0.8899,
|
| 2156 |
+
"step": 350000
|
| 2157 |
+
},
|
| 2158 |
+
{
|
| 2159 |
+
"epoch": 1.08,
|
| 2160 |
+
"eval_loss": 0.8285813331604004,
|
| 2161 |
+
"eval_runtime": 24.9856,
|
| 2162 |
+
"eval_samples_per_second": 400.23,
|
| 2163 |
+
"eval_steps_per_second": 1.601,
|
| 2164 |
+
"step": 350000
|
| 2165 |
}
|
| 2166 |
],
|
| 2167 |
"max_steps": 1000000,
|
| 2168 |
"num_train_epochs": 9223372036854775807,
|
| 2169 |
+
"total_flos": 5.897119717969625e+18,
|
| 2170 |
"trial_name": null,
|
| 2171 |
"trial_params": null
|
| 2172 |
}
|
last-checkpoint/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3375
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:225de94e6547ae8e2d8e5b9a0e34c719612311b29038a27f9107115c46808f63
|
| 3 |
size 3375
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 498046827
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e1fddf171aaf7fcd5407c99cb8a97835dce9ceccd14ee70ed5b23a17af12fdf3
|
| 3 |
size 498046827
|
runs/Nov11_11-14-20_t1v-n-088af867-w-0/events.out.tfevents.1668165319.t1v-n-088af867-w-0.346597.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5f584155741b1ac1c66f2deec1a86eb4dec91ffb6ede4b340e14a38064332a51
|
| 3 |
+
size 61035
|
runs/Nov17_09-03-22_t1v-n-088af867-w-0/1668675880.4394102/events.out.tfevents.1668675880.t1v-n-088af867-w-0.91101.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:84092474497834ded5ff6a628c5df8f98b1991b6bf66a6e9c229275fb3983810
|
| 3 |
+
size 5419
|
runs/Nov17_09-03-22_t1v-n-088af867-w-0/events.out.tfevents.1668675880.t1v-n-088af867-w-0.91101.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:77d571d78f4fe0979689c970eb58513ff26e9e28f757dd306ffedcec3e98b4b2
|
| 3 |
+
size 3748
|
runs/Nov21_18-14-51_t1v-n-088af867-w-0/1669054551.8620195/events.out.tfevents.1669054551.t1v-n-088af867-w-0.42571.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6eadbd757619674b78bab6f3a98c1ced53a048c7440ccbd25ca0e2ad1b0441cf
|
| 3 |
+
size 5419
|
runs/Nov21_18-14-51_t1v-n-088af867-w-0/events.out.tfevents.1669054551.t1v-n-088af867-w-0.42571.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1b0ad7fd9cf05d0068da00ee4295784721aa3d2aa25d542d74eb8a8ae739909e
|
| 3 |
+
size 12024
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3375
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:225de94e6547ae8e2d8e5b9a0e34c719612311b29038a27f9107115c46808f63
|
| 3 |
size 3375
|