Commit
•
fb55c64
1
Parent(s):
b4411f5
End of training
Browse files- all_results.json +13 -0
- config.json +1 -1
- eval_results.json +9 -0
- pytorch_model.bin +2 -2
- train_results.json +7 -0
- trainer_state.json +0 -0
all_results.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.39,
|
3 |
+
"eval_accuracy": 0.838442284952852,
|
4 |
+
"eval_loss": 0.7085304260253906,
|
5 |
+
"eval_runtime": 9.8682,
|
6 |
+
"eval_samples_per_second": 506.676,
|
7 |
+
"eval_steps_per_second": 1.013,
|
8 |
+
"perplexity": 2.031004353305193,
|
9 |
+
"train_loss": 0.18125205249023438,
|
10 |
+
"train_runtime": 269324.8897,
|
11 |
+
"train_samples_per_second": 3802.099,
|
12 |
+
"train_steps_per_second": 3.713
|
13 |
+
}
|
config.json
CHANGED
@@ -19,7 +19,7 @@
|
|
19 |
"num_hidden_layers": 12,
|
20 |
"pad_token_id": 0,
|
21 |
"position_embedding_type": "absolute",
|
22 |
-
"torch_dtype": "
|
23 |
"transformers_version": "4.20.1",
|
24 |
"type_vocab_size": 1,
|
25 |
"use_cache": true,
|
|
|
19 |
"num_hidden_layers": 12,
|
20 |
"pad_token_id": 0,
|
21 |
"position_embedding_type": "absolute",
|
22 |
+
"torch_dtype": "bfloat16",
|
23 |
"transformers_version": "4.20.1",
|
24 |
"type_vocab_size": 1,
|
25 |
"use_cache": true,
|
eval_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.39,
|
3 |
+
"eval_accuracy": 0.838442284952852,
|
4 |
+
"eval_loss": 0.7085304260253906,
|
5 |
+
"eval_runtime": 9.8682,
|
6 |
+
"eval_samples_per_second": 506.676,
|
7 |
+
"eval_steps_per_second": 1.013,
|
8 |
+
"perplexity": 2.031004353305193
|
9 |
+
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:50b540d5baa5e506eadd065b45c5f621480792a3a73b38c7b1de7abd0cdde37b
|
3 |
+
size 221375275
|
train_results.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.39,
|
3 |
+
"train_loss": 0.18125205249023438,
|
4 |
+
"train_runtime": 269324.8897,
|
5 |
+
"train_samples_per_second": 3802.099,
|
6 |
+
"train_steps_per_second": 3.713
|
7 |
+
}
|
trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|