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 sha256:602836472b5e2c722465609242f7a47d056ce7ba46e7a86301fef60ff775ce83
|
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:c26aab368e09302dcf13e7d296cef18de072ca0cd67c5e930b7cbc403c13a86d
|
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:c05bfeb5e98bce683190574682f813e2a522697190e69ee10bf7a068f93b6976
|
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:f01f5f84e3a31f42df04145fae58f6f7b1f4506d8b1fe2fb28025394ec8cb07e
|
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 sha256:10e21d463f6e7cd0c9117ab55e1ffd1516f0bf98cf844492234460cda5925bd4
|
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 sha256:6a2d31392d162b7d4d2268dd187329a9f9784b8b62661a5b232ff40ede5f5e92
|
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 sha256:92e5f3bbd27916276b7daba9adf7aec1e0ea749af3982c865282b426347aa9a4
|
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:edb9d0fd6374cceb9b089b55b43f947afaefabbdd3f8ebab7e2dcb2476738627
|
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": 0.0001156586388892709,
|
1987 |
"loss": 0.3405,
|
1988 |
"step": 165000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1989 |
}
|
1990 |
],
|
1991 |
"max_steps": 500000,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.893609416090076,
|
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": 0.0001156586388892709,
|
1987 |
"loss": 0.3405,
|
1988 |
"step": 165000
|
1989 |
+
},
|
1990 |
+
{
|
1991 |
+
"epoch": 2.82,
|
1992 |
+
"learning_rate": 0.00011546922402047642,
|
1993 |
+
"loss": 0.3403,
|
1994 |
+
"step": 165500
|
1995 |
+
},
|
1996 |
+
{
|
1997 |
+
"epoch": 2.83,
|
1998 |
+
"learning_rate": 0.00011527945908476035,
|
1999 |
+
"loss": 0.3409,
|
2000 |
+
"step": 166000
|
2001 |
+
},
|
2002 |
+
{
|
2003 |
+
"epoch": 2.83,
|
2004 |
+
"learning_rate": 0.000115089345955026,
|
2005 |
+
"loss": 0.3406,
|
2006 |
+
"step": 166500
|
2007 |
+
},
|
2008 |
+
{
|
2009 |
+
"epoch": 2.84,
|
2010 |
+
"learning_rate": 0.00011489926777088424,
|
2011 |
+
"loss": 0.3406,
|
2012 |
+
"step": 167000
|
2013 |
+
},
|
2014 |
+
{
|
2015 |
+
"epoch": 2.85,
|
2016 |
+
"learning_rate": 0.00011470846457254845,
|
2017 |
+
"loss": 0.3403,
|
2018 |
+
"step": 167500
|
2019 |
+
},
|
2020 |
+
{
|
2021 |
+
"epoch": 2.86,
|
2022 |
+
"learning_rate": 0.00011451731881567971,
|
2023 |
+
"loss": 0.3402,
|
2024 |
+
"step": 168000
|
2025 |
+
},
|
2026 |
+
{
|
2027 |
+
"epoch": 2.87,
|
2028 |
+
"learning_rate": 0.00011432583238680949,
|
2029 |
+
"loss": 0.3405,
|
2030 |
+
"step": 168500
|
2031 |
+
},
|
2032 |
+
{
|
2033 |
+
"epoch": 2.88,
|
2034 |
+
"learning_rate": 0.00011413400717583146,
|
2035 |
+
"loss": 0.3401,
|
2036 |
+
"step": 169000
|
2037 |
+
},
|
2038 |
+
{
|
2039 |
+
"epoch": 2.89,
|
2040 |
+
"learning_rate": 0.00011394184507598311,
|
2041 |
+
"loss": 0.3398,
|
2042 |
+
"step": 169500
|
2043 |
+
},
|
2044 |
+
{
|
2045 |
+
"epoch": 2.89,
|
2046 |
+
"learning_rate": 0.00011374934798382673,
|
2047 |
+
"loss": 0.3396,
|
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:c26aab368e09302dcf13e7d296cef18de072ca0cd67c5e930b7cbc403c13a86d
|
3 |
size 201355195
|