4500 checkpoint
Browse files- optimizer.pt +1 -1
- pytorch_model-00001-of-00002.bin +1 -1
- pytorch_model-00002-of-00002.bin +1 -1
- rng_state.pth +1 -1
- scheduler.pt +1 -1
- trainer_state.json +15 -3
optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 21210715097
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:199c3170fd3a41772a9babb0927700ffddd6d1c8ac5b7aaec62f8e6d0110efb0
|
3 |
size 21210715097
|
pytorch_model-00001-of-00002.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 9996970517
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3e22aada20aea4b7a32f71bdf574f6a942a6fd2f64107e76eee64bc0c51124e1
|
3 |
size 9996970517
|
pytorch_model-00002-of-00002.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 742637631
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4b835b661b4b00d3aca1275c295567e4a1beca1a2f2d5b628e35eb278d35ace6
|
3 |
size 742637631
|
rng_state.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:f6430e5ad1d877b2cd1749d223eec11a131930ad358c4a7dfa9f4e6830aa494e
|
3 |
size 14503
|
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:ed56d7b3709a7b50b7e2ab3a6a14bdf4c03d66f131c7f3dfccdf9e4a98638acb
|
3 |
size 623
|
trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -48,11 +48,23 @@
|
|
48 |
"learning_rate": 4.110410736071574e-06,
|
49 |
"loss": 2.977,
|
50 |
"step": 3500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
51 |
}
|
52 |
],
|
53 |
"max_steps": 19672,
|
54 |
"num_train_epochs": 4,
|
55 |
-
"total_flos": 2.
|
56 |
"trial_name": null,
|
57 |
"trial_params": null
|
58 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.9148293843198243,
|
5 |
+
"global_step": 4500,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
48 |
"learning_rate": 4.110410736071574e-06,
|
49 |
"loss": 2.977,
|
50 |
"step": 3500
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.81,
|
54 |
+
"learning_rate": 3.983326555510371e-06,
|
55 |
+
"loss": 2.9616,
|
56 |
+
"step": 4000
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.91,
|
60 |
+
"learning_rate": 3.856242374949167e-06,
|
61 |
+
"loss": 2.9615,
|
62 |
+
"step": 4500
|
63 |
}
|
64 |
],
|
65 |
"max_steps": 19672,
|
66 |
"num_train_epochs": 4,
|
67 |
+
"total_flos": 2.7840504397824e+18,
|
68 |
"trial_name": null,
|
69 |
"trial_params": null
|
70 |
}
|