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 sha256:036aa766680514ebd6de901bdce97db53f0d37ca399d80b47ef766eb1bfc07af
|
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:b8a22485edc13dba34e8db83180d2c2081cf07a4481b12bb65b2efc00098593e
|
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 sha256:3906b7bf9b2299d26cf2c3bb194cd599ad2ab76018d03dc2b0848a7b379518c6
|
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 sha256:5c35974bf9bd4c8745f9376e1b44780a74da197e9bc52f8e04c7df7d58bd88ab
|
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 sha256:84410c327199006a774462587e14b56cd0625ce7dea9dc2d950e65b384e19400
|
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:f2084089a60ac88585fd1ad4a3050aa7d4e52c87b4c2533fca1237f1fd63e24d
|
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:e11d7a4429ee3329729eddce2fc923bf2e9c12b836aecdb35beb8451fcb77a64
|
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 sha256:65cadebf6576eff943bbe91b7eec7f11ed6ac3d8a79550cd75c237196b314951
|
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": 0.00011753163932360551,
|
1927 |
"loss": 0.3408,
|
1928 |
"step": 160000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1929 |
}
|
1930 |
],
|
1931 |
"max_steps": 500000,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.8085037574148304,
|
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": 0.00011753163932360551,
|
1927 |
"loss": 0.3408,
|
1928 |
"step": 160000
|
1929 |
+
},
|
1930 |
+
{
|
1931 |
+
"epoch": 2.73,
|
1932 |
+
"learning_rate": 0.00011734582440839364,
|
1933 |
+
"loss": 0.3411,
|
1934 |
+
"step": 160500
|
1935 |
+
},
|
1936 |
+
{
|
1937 |
+
"epoch": 2.74,
|
1938 |
+
"learning_rate": 0.00011715964090497195,
|
1939 |
+
"loss": 0.3406,
|
1940 |
+
"step": 161000
|
1941 |
+
},
|
1942 |
+
{
|
1943 |
+
"epoch": 2.75,
|
1944 |
+
"learning_rate": 0.00011697309065089649,
|
1945 |
+
"loss": 0.3412,
|
1946 |
+
"step": 161500
|
1947 |
+
},
|
1948 |
+
{
|
1949 |
+
"epoch": 2.76,
|
1950 |
+
"learning_rate": 0.00011678654968062415,
|
1951 |
+
"loss": 0.3411,
|
1952 |
+
"step": 162000
|
1953 |
+
},
|
1954 |
+
{
|
1955 |
+
"epoch": 2.77,
|
1956 |
+
"learning_rate": 0.00011659964709277792,
|
1957 |
+
"loss": 0.3414,
|
1958 |
+
"step": 162500
|
1959 |
+
},
|
1960 |
+
{
|
1961 |
+
"epoch": 2.77,
|
1962 |
+
"learning_rate": 0.00011641200908936181,
|
1963 |
+
"loss": 0.3414,
|
1964 |
+
"step": 163000
|
1965 |
+
},
|
1966 |
+
{
|
1967 |
+
"epoch": 2.78,
|
1968 |
+
"learning_rate": 0.00011622401171411614,
|
1969 |
+
"loss": 0.3412,
|
1970 |
+
"step": 163500
|
1971 |
+
},
|
1972 |
+
{
|
1973 |
+
"epoch": 2.79,
|
1974 |
+
"learning_rate": 0.00011603565682249906,
|
1975 |
+
"loss": 0.3411,
|
1976 |
+
"step": 164000
|
1977 |
+
},
|
1978 |
+
{
|
1979 |
+
"epoch": 2.8,
|
1980 |
+
"learning_rate": 0.00011584732404830404,
|
1981 |
+
"loss": 0.3408,
|
1982 |
+
"step": 164500
|
1983 |
+
},
|
1984 |
+
{
|
1985 |
+
"epoch": 2.81,
|
1986 |
+
"learning_rate": 0.0001156586388892709,
|
1987 |
+
"loss": 0.3405,
|
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:b8a22485edc13dba34e8db83180d2c2081cf07a4481b12bb65b2efc00098593e
|
3 |
size 201355195
|