Training in progress, step 165000
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/scaler.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +62 -2
- pytorch_model.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 402588883
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c1da5fdc4111ee2770add0165e4add6ff533bd89c233f6303638103bd1afe8e6
|
3 |
size 402588883
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 201355195
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:be35c470b46dcba434d734403c5f7aee5d3e62c017c0ef749aa3c942c96f0d30
|
3 |
size 201355195
|
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 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2dc925f9b70c7a9f6fcb0d4781cf4f1d803b523baf72253f91371f65ecc10bf5
|
3 |
size 14503
|
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 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a5d657171b91d4078d50d9dfa736a40bc88c72060ab7574ed479a997f38418ea
|
3 |
size 14503
|
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 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e8ad09b727042b4afa0175a9a5fc770490008eeca7f8eee0d4d218203a4f7faa
|
3 |
size 14503
|
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 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a4f50f98851341aa7450213c411727a4c6c324924a80df02b72c0132b11457ca
|
3 |
size 14503
|
last-checkpoint/scaler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 559
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9ef626b588e6c1fed9266747bb97bf1f7b8c8ee6287e260226d50b8a69b8e56b
|
3 |
size 559
|
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 sha256:540efa15d83a059648280798e43e73685800452b921c91e8d769a80ae3759f43
|
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": 2.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -1926,6 +1926,66 @@
|
|
1926 |
"learning_rate": 0.00011753089680060416,
|
1927 |
"loss": 0.3371,
|
1928 |
"step": 160000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1929 |
}
|
1930 |
],
|
1931 |
"max_steps": 500000,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.8085106382978724,
|
5 |
+
"global_step": 165000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
1926 |
"learning_rate": 0.00011753089680060416,
|
1927 |
"loss": 0.3371,
|
1928 |
"step": 160000
|
1929 |
+
},
|
1930 |
+
{
|
1931 |
+
"epoch": 2.73,
|
1932 |
+
"learning_rate": 0.00011734508040738386,
|
1933 |
+
"loss": 0.3371,
|
1934 |
+
"step": 160500
|
1935 |
+
},
|
1936 |
+
{
|
1937 |
+
"epoch": 2.74,
|
1938 |
+
"learning_rate": 0.00011715889543329673,
|
1939 |
+
"loss": 0.3367,
|
1940 |
+
"step": 161000
|
1941 |
+
},
|
1942 |
+
{
|
1943 |
+
"epoch": 2.75,
|
1944 |
+
"learning_rate": 0.00011697234371591335,
|
1945 |
+
"loss": 0.3368,
|
1946 |
+
"step": 161500
|
1947 |
+
},
|
1948 |
+
{
|
1949 |
+
"epoch": 2.76,
|
1950 |
+
"learning_rate": 0.0001167854270964238,
|
1951 |
+
"loss": 0.3368,
|
1952 |
+
"step": 162000
|
1953 |
+
},
|
1954 |
+
{
|
1955 |
+
"epoch": 2.77,
|
1956 |
+
"learning_rate": 0.00011659814741961971,
|
1957 |
+
"loss": 0.3366,
|
1958 |
+
"step": 162500
|
1959 |
+
},
|
1960 |
+
{
|
1961 |
+
"epoch": 2.77,
|
1962 |
+
"learning_rate": 0.00011641050653387583,
|
1963 |
+
"loss": 0.3365,
|
1964 |
+
"step": 163000
|
1965 |
+
},
|
1966 |
+
{
|
1967 |
+
"epoch": 2.78,
|
1968 |
+
"learning_rate": 0.000116222506291132,
|
1969 |
+
"loss": 0.3363,
|
1970 |
+
"step": 163500
|
1971 |
+
},
|
1972 |
+
{
|
1973 |
+
"epoch": 2.79,
|
1974 |
+
"learning_rate": 0.0001160341485468747,
|
1975 |
+
"loss": 0.3364,
|
1976 |
+
"step": 164000
|
1977 |
+
},
|
1978 |
+
{
|
1979 |
+
"epoch": 2.8,
|
1980 |
+
"learning_rate": 0.00011584543516011881,
|
1981 |
+
"loss": 0.3365,
|
1982 |
+
"step": 164500
|
1983 |
+
},
|
1984 |
+
{
|
1985 |
+
"epoch": 2.81,
|
1986 |
+
"learning_rate": 0.00011565636799338927,
|
1987 |
+
"loss": 0.3365,
|
1988 |
+
"step": 165000
|
1989 |
}
|
1990 |
],
|
1991 |
"max_steps": 500000,
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 201355195
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:be35c470b46dcba434d734403c5f7aee5d3e62c017c0ef749aa3c942c96f0d30
|
3 |
size 201355195
|