Training in progress, step 415000
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 sha256:618cea0b5c1c06ce77ede7b550590749b63b78b7da1cb596a0728d76abb4d1bc
|
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 sha256:056bccb8b4a42302f57ae874e9edc332490f19b934b5ce46745280a90f0c731d
|
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:bee53eb28363d1b61f1fae205b6010f941e2e1637534f85331f1d7756f4c3484
|
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 sha256:965769a497940386e65b96b22573e204c24951b3e101d914927f5b89b9974bd2
|
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 sha256:2cb9d4c70ef3f4bec22a0428ba80b1fc3be727829d87ceebacff1d033435698f
|
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 sha256:4af117147e75dbd72a2a1d9c349ee6e27b94fa9fd3d2720856cd671206834a2c
|
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 sha256:3b877799815111125ba76d99f570ed432b74b7c78e9b626746a6a3762cb07886
|
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 sha256:52597013a4eca13ce461fb3dce5a2029e2a62545110452a45574044ed2bc8fe2
|
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":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -4926,6 +4926,66 @@
|
|
4926 |
"learning_rate": 2.0934546062965312e-05,
|
4927 |
"loss": 0.32,
|
4928 |
"step": 410000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
4929 |
}
|
4930 |
],
|
4931 |
"max_steps": 500000,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 7.063829244006434,
|
5 |
+
"global_step": 415000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
4926 |
"learning_rate": 2.0934546062965312e-05,
|
4927 |
"loss": 0.32,
|
4928 |
"step": 410000
|
4929 |
+
},
|
4930 |
+
{
|
4931 |
+
"epoch": 6.99,
|
4932 |
+
"learning_rate": 2.0816817828791883e-05,
|
4933 |
+
"loss": 0.3197,
|
4934 |
+
"step": 410500
|
4935 |
+
},
|
4936 |
+
{
|
4937 |
+
"epoch": 7.0,
|
4938 |
+
"learning_rate": 2.069990741325806e-05,
|
4939 |
+
"loss": 0.3195,
|
4940 |
+
"step": 411000
|
4941 |
+
},
|
4942 |
+
{
|
4943 |
+
"epoch": 7.0,
|
4944 |
+
"learning_rate": 2.0583347391788827e-05,
|
4945 |
+
"loss": 0.3199,
|
4946 |
+
"step": 411500
|
4947 |
+
},
|
4948 |
+
{
|
4949 |
+
"epoch": 7.01,
|
4950 |
+
"learning_rate": 2.046737378869338e-05,
|
4951 |
+
"loss": 0.3197,
|
4952 |
+
"step": 412000
|
4953 |
+
},
|
4954 |
+
{
|
4955 |
+
"epoch": 7.02,
|
4956 |
+
"learning_rate": 2.0351987748584336e-05,
|
4957 |
+
"loss": 0.3196,
|
4958 |
+
"step": 412500
|
4959 |
+
},
|
4960 |
+
{
|
4961 |
+
"epoch": 7.03,
|
4962 |
+
"learning_rate": 2.0237190410275346e-05,
|
4963 |
+
"loss": 0.3197,
|
4964 |
+
"step": 413000
|
4965 |
+
},
|
4966 |
+
{
|
4967 |
+
"epoch": 7.04,
|
4968 |
+
"learning_rate": 2.0122982906769767e-05,
|
4969 |
+
"loss": 0.3195,
|
4970 |
+
"step": 413500
|
4971 |
+
},
|
4972 |
+
{
|
4973 |
+
"epoch": 7.05,
|
4974 |
+
"learning_rate": 2.000936636524959e-05,
|
4975 |
+
"loss": 0.3195,
|
4976 |
+
"step": 414000
|
4977 |
+
},
|
4978 |
+
{
|
4979 |
+
"epoch": 7.06,
|
4980 |
+
"learning_rate": 1.9896567364338962e-05,
|
4981 |
+
"loss": 0.3197,
|
4982 |
+
"step": 414500
|
4983 |
+
},
|
4984 |
+
{
|
4985 |
+
"epoch": 7.06,
|
4986 |
+
"learning_rate": 1.978413491748704e-05,
|
4987 |
+
"loss": 0.3197,
|
4988 |
+
"step": 415000
|
4989 |
}
|
4990 |
],
|
4991 |
"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 sha256:056bccb8b4a42302f57ae874e9edc332490f19b934b5ce46745280a90f0c731d
|
3 |
size 201355195
|