Training in progress, step 500000
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 sha256:84c83cbcfacd10aeb9a969660c792f41ebc155f73939d0019973e15e7c35916c
|
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:ef5e7724e2be440c70a1ce15f2086804fcec75575bff2fcab3069f8c6486071c
|
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 sha256:218592ad1b1e18adfc72618cbc7516e8e91e807da1dc2b546140a936e1a6b626
|
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 sha256:66293004c266e2a9992e5cbc35145ec7fa6299eb91f23be667c80b51cf0929dd
|
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 sha256:58ca7c68b6355890f2bcc439c58f19c35f365d87f576184e59ed5f13c0136aa7
|
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 sha256:234c2144a86f56c68f451b64cc0cc045b7700c4ed3b53ec595877767cfc61c98
|
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 sha256:93bff0c5a183441a60eeb077c6938bb4b3052c87517f6d53963e10eae8a46503
|
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 sha256:8d4adbb1377a13e7ef10c792e4a27ee2630c4970ee2cd10e4a4dde89d18e50eb
|
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": 8.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -5946,6 +5946,66 @@
|
|
5946 |
"learning_rate": 1.0037215513081807e-05,
|
5947 |
"loss": 0.3182,
|
5948 |
"step": 495000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5949 |
}
|
5950 |
],
|
5951 |
"max_steps": 500000,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 8.510633952051473,
|
5 |
+
"global_step": 500000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
5946 |
"learning_rate": 1.0037215513081807e-05,
|
5947 |
"loss": 0.3182,
|
5948 |
"step": 495000
|
5949 |
+
},
|
5950 |
+
{
|
5951 |
+
"epoch": 8.43,
|
5952 |
+
"learning_rate": 1.003039079344833e-05,
|
5953 |
+
"loss": 0.3185,
|
5954 |
+
"step": 495500
|
5955 |
+
},
|
5956 |
+
{
|
5957 |
+
"epoch": 8.44,
|
5958 |
+
"learning_rate": 1.0024256645609842e-05,
|
5959 |
+
"loss": 0.3182,
|
5960 |
+
"step": 496000
|
5961 |
+
},
|
5962 |
+
{
|
5963 |
+
"epoch": 8.45,
|
5964 |
+
"learning_rate": 1.0018813130107917e-05,
|
5965 |
+
"loss": 0.3183,
|
5966 |
+
"step": 496500
|
5967 |
+
},
|
5968 |
+
{
|
5969 |
+
"epoch": 8.46,
|
5970 |
+
"learning_rate": 1.0014069116989727e-05,
|
5971 |
+
"loss": 0.3181,
|
5972 |
+
"step": 497000
|
5973 |
+
},
|
5974 |
+
{
|
5975 |
+
"epoch": 8.47,
|
5976 |
+
"learning_rate": 1.0010005639011795e-05,
|
5977 |
+
"loss": 0.3182,
|
5978 |
+
"step": 497500
|
5979 |
+
},
|
5980 |
+
{
|
5981 |
+
"epoch": 8.48,
|
5982 |
+
"learning_rate": 1.000663293402211e-05,
|
5983 |
+
"loss": 0.3183,
|
5984 |
+
"step": 498000
|
5985 |
+
},
|
5986 |
+
{
|
5987 |
+
"epoch": 8.49,
|
5988 |
+
"learning_rate": 1.0003951035307893e-05,
|
5989 |
+
"loss": 0.3181,
|
5990 |
+
"step": 498500
|
5991 |
+
},
|
5992 |
+
{
|
5993 |
+
"epoch": 8.49,
|
5994 |
+
"learning_rate": 1.0001959969338421e-05,
|
5995 |
+
"loss": 0.3181,
|
5996 |
+
"step": 499000
|
5997 |
+
},
|
5998 |
+
{
|
5999 |
+
"epoch": 8.5,
|
6000 |
+
"learning_rate": 1.0000659755764688e-05,
|
6001 |
+
"loss": 0.3181,
|
6002 |
+
"step": 499500
|
6003 |
+
},
|
6004 |
+
{
|
6005 |
+
"epoch": 8.51,
|
6006 |
+
"learning_rate": 1.000005040741929e-05,
|
6007 |
+
"loss": 0.3182,
|
6008 |
+
"step": 500000
|
6009 |
}
|
6010 |
],
|
6011 |
"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:ef5e7724e2be440c70a1ce15f2086804fcec75575bff2fcab3069f8c6486071c
|
3 |
size 201355195
|