Training in progress, step 170000
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 sha256:09da48285c00f35e83db0da95a321030324a605810c023fad8ec151770f2cbd8
|
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 sha256:72a3f29e32136d35d0d484f21fcad2657a916690d11aeaaa36998853c3bb7991
|
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:fe167b89c011e9334490bb755f8c58c01e1caf85f989f94da53733519797dbe1
|
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 sha256:0cc169d7499953d251f984829898af63fd2ea6feb3301fd51c7e59d7e72f37bd
|
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 sha256:94a3bbd343dc19c975e7df34ae10e44f61ac062578533097656a57cc67a369df
|
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 sha256:847b4e7f55e56f03bee946faceffdc669965f86d001d6af9d96c067f56b816a1
|
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 sha256:4db330b47705f38a44d9ca503524acd867a7f5b9c7d09cea471cc2d7ef717581
|
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 sha256:59dff3417cf15ea7d09b90e016664b8ffdb1dc904707cdd6add5a4ecfc696955
|
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,
|
@@ -1986,6 +1986,66 @@
|
|
1986 |
"learning_rate": 0.00011565636799338927,
|
1987 |
"loss": 0.3365,
|
1988 |
"step": 165000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1989 |
}
|
1990 |
],
|
1991 |
"max_steps": 500000,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.8936170212765955,
|
5 |
+
"global_step": 170000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
1986 |
"learning_rate": 0.00011565636799338927,
|
1987 |
"loss": 0.3365,
|
1988 |
"step": 165000
|
1989 |
+
},
|
1990 |
+
{
|
1991 |
+
"epoch": 2.82,
|
1992 |
+
"learning_rate": 0.0001154669489127027,
|
1993 |
+
"loss": 0.3361,
|
1994 |
+
"step": 165500
|
1995 |
+
},
|
1996 |
+
{
|
1997 |
+
"epoch": 2.83,
|
1998 |
+
"learning_rate": 0.00011527717978754894,
|
1999 |
+
"loss": 0.3359,
|
2000 |
+
"step": 166000
|
2001 |
+
},
|
2002 |
+
{
|
2003 |
+
"epoch": 2.83,
|
2004 |
+
"learning_rate": 0.00011508706249087268,
|
2005 |
+
"loss": 0.3362,
|
2006 |
+
"step": 166500
|
2007 |
+
},
|
2008 |
+
{
|
2009 |
+
"epoch": 2.84,
|
2010 |
+
"learning_rate": 0.00011489659889905481,
|
2011 |
+
"loss": 0.3359,
|
2012 |
+
"step": 167000
|
2013 |
+
},
|
2014 |
+
{
|
2015 |
+
"epoch": 2.85,
|
2016 |
+
"learning_rate": 0.00011470617285038384,
|
2017 |
+
"loss": 0.3358,
|
2018 |
+
"step": 167500
|
2019 |
+
},
|
2020 |
+
{
|
2021 |
+
"epoch": 2.86,
|
2022 |
+
"learning_rate": 0.0001145154056345707,
|
2023 |
+
"loss": 0.3358,
|
2024 |
+
"step": 168000
|
2025 |
+
},
|
2026 |
+
{
|
2027 |
+
"epoch": 2.87,
|
2028 |
+
"learning_rate": 0.00011432391580851883,
|
2029 |
+
"loss": 0.3357,
|
2030 |
+
"step": 168500
|
2031 |
+
},
|
2032 |
+
{
|
2033 |
+
"epoch": 2.88,
|
2034 |
+
"learning_rate": 0.00011413208721927504,
|
2035 |
+
"loss": 0.3357,
|
2036 |
+
"step": 169000
|
2037 |
+
},
|
2038 |
+
{
|
2039 |
+
"epoch": 2.89,
|
2040 |
+
"learning_rate": 0.00011394030642596453,
|
2041 |
+
"loss": 0.3357,
|
2042 |
+
"step": 169500
|
2043 |
+
},
|
2044 |
+
{
|
2045 |
+
"epoch": 2.89,
|
2046 |
+
"learning_rate": 0.00011374780666152555,
|
2047 |
+
"loss": 0.3353,
|
2048 |
+
"step": 170000
|
2049 |
}
|
2050 |
],
|
2051 |
"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 sha256:72a3f29e32136d35d0d484f21fcad2657a916690d11aeaaa36998853c3bb7991
|
3 |
size 201355195
|