gustavomedeiros
commited on
Commit
•
929f166
1
Parent(s):
240a640
End of training
Browse files- README.md +9 -9
- pytorch_model.bin +1 -1
- special_tokens_map.json +7 -1
- tokenizer.json +4 -4
- tokenizer_config.json +4 -5
README.md
CHANGED
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the None dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
- Loss: 0.
|
19 |
|
20 |
## Model description
|
21 |
|
@@ -47,16 +47,16 @@ The following hyperparameters were used during training:
|
|
47 |
|
48 |
| Training Loss | Epoch | Step | Validation Loss |
|
49 |
|:-------------:|:-----:|:-----:|:---------------:|
|
50 |
-
| 0.
|
51 |
-
| 0.
|
52 |
-
| 0.
|
53 |
-
| 0.
|
54 |
-
| 0.
|
55 |
|
56 |
|
57 |
### Framework versions
|
58 |
|
59 |
-
- Transformers 4.34.
|
60 |
-
- Pytorch 2.0
|
61 |
-
- Datasets 2.14.
|
62 |
- Tokenizers 0.14.1
|
|
|
15 |
|
16 |
This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the None dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 0.4064
|
19 |
|
20 |
## Model description
|
21 |
|
|
|
47 |
|
48 |
| Training Loss | Epoch | Step | Validation Loss |
|
49 |
|:-------------:|:-----:|:-----:|:---------------:|
|
50 |
+
| 0.6062 | 1.0 | 13521 | 0.6637 |
|
51 |
+
| 0.342 | 2.0 | 27042 | 0.5389 |
|
52 |
+
| 0.3967 | 3.0 | 40563 | 0.4142 |
|
53 |
+
| 0.3748 | 4.0 | 54084 | 0.4064 |
|
54 |
+
| 0.3489 | 5.0 | 67605 | 0.4131 |
|
55 |
|
56 |
|
57 |
### Framework versions
|
58 |
|
59 |
+
- Transformers 4.34.1
|
60 |
+
- Pytorch 2.1.0+cu118
|
61 |
+
- Datasets 2.14.6
|
62 |
- Tokenizers 0.14.1
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 498694958
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2d29103a1bbf372bae5140358b4fe676a958daa766cfb132548a56bb46bbea80
|
3 |
size 498694958
|
special_tokens_map.json
CHANGED
@@ -2,7 +2,13 @@
|
|
2 |
"bos_token": "<s>",
|
3 |
"cls_token": "<s>",
|
4 |
"eos_token": "</s>",
|
5 |
-
"mask_token":
|
|
|
|
|
|
|
|
|
|
|
|
|
6 |
"pad_token": "<pad>",
|
7 |
"sep_token": "</s>",
|
8 |
"unk_token": "<unk>"
|
|
|
2 |
"bos_token": "<s>",
|
3 |
"cls_token": "<s>",
|
4 |
"eos_token": "</s>",
|
5 |
+
"mask_token": {
|
6 |
+
"content": "<mask>",
|
7 |
+
"lstrip": true,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
"pad_token": "<pad>",
|
13 |
"sep_token": "</s>",
|
14 |
"unk_token": "<unk>"
|
tokenizer.json
CHANGED
@@ -21,7 +21,7 @@
|
|
21 |
"single_word": false,
|
22 |
"lstrip": false,
|
23 |
"rstrip": false,
|
24 |
-
"normalized":
|
25 |
"special": true
|
26 |
},
|
27 |
{
|
@@ -30,7 +30,7 @@
|
|
30 |
"single_word": false,
|
31 |
"lstrip": false,
|
32 |
"rstrip": false,
|
33 |
-
"normalized":
|
34 |
"special": true
|
35 |
},
|
36 |
{
|
@@ -39,7 +39,7 @@
|
|
39 |
"single_word": false,
|
40 |
"lstrip": false,
|
41 |
"rstrip": false,
|
42 |
-
"normalized":
|
43 |
"special": true
|
44 |
},
|
45 |
{
|
@@ -48,7 +48,7 @@
|
|
48 |
"single_word": false,
|
49 |
"lstrip": false,
|
50 |
"rstrip": false,
|
51 |
-
"normalized":
|
52 |
"special": true
|
53 |
},
|
54 |
{
|
|
|
21 |
"single_word": false,
|
22 |
"lstrip": false,
|
23 |
"rstrip": false,
|
24 |
+
"normalized": true,
|
25 |
"special": true
|
26 |
},
|
27 |
{
|
|
|
30 |
"single_word": false,
|
31 |
"lstrip": false,
|
32 |
"rstrip": false,
|
33 |
+
"normalized": true,
|
34 |
"special": true
|
35 |
},
|
36 |
{
|
|
|
39 |
"single_word": false,
|
40 |
"lstrip": false,
|
41 |
"rstrip": false,
|
42 |
+
"normalized": true,
|
43 |
"special": true
|
44 |
},
|
45 |
{
|
|
|
48 |
"single_word": false,
|
49 |
"lstrip": false,
|
50 |
"rstrip": false,
|
51 |
+
"normalized": true,
|
52 |
"special": true
|
53 |
},
|
54 |
{
|
tokenizer_config.json
CHANGED
@@ -4,7 +4,7 @@
|
|
4 |
"0": {
|
5 |
"content": "<s>",
|
6 |
"lstrip": false,
|
7 |
-
"normalized":
|
8 |
"rstrip": false,
|
9 |
"single_word": false,
|
10 |
"special": true
|
@@ -12,7 +12,7 @@
|
|
12 |
"1": {
|
13 |
"content": "<pad>",
|
14 |
"lstrip": false,
|
15 |
-
"normalized":
|
16 |
"rstrip": false,
|
17 |
"single_word": false,
|
18 |
"special": true
|
@@ -20,7 +20,7 @@
|
|
20 |
"2": {
|
21 |
"content": "</s>",
|
22 |
"lstrip": false,
|
23 |
-
"normalized":
|
24 |
"rstrip": false,
|
25 |
"single_word": false,
|
26 |
"special": true
|
@@ -28,7 +28,7 @@
|
|
28 |
"3": {
|
29 |
"content": "<unk>",
|
30 |
"lstrip": false,
|
31 |
-
"normalized":
|
32 |
"rstrip": false,
|
33 |
"single_word": false,
|
34 |
"special": true
|
@@ -42,7 +42,6 @@
|
|
42 |
"special": true
|
43 |
}
|
44 |
},
|
45 |
-
"additional_special_tokens": [],
|
46 |
"bos_token": "<s>",
|
47 |
"clean_up_tokenization_spaces": true,
|
48 |
"cls_token": "<s>",
|
|
|
4 |
"0": {
|
5 |
"content": "<s>",
|
6 |
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
"rstrip": false,
|
9 |
"single_word": false,
|
10 |
"special": true
|
|
|
12 |
"1": {
|
13 |
"content": "<pad>",
|
14 |
"lstrip": false,
|
15 |
+
"normalized": true,
|
16 |
"rstrip": false,
|
17 |
"single_word": false,
|
18 |
"special": true
|
|
|
20 |
"2": {
|
21 |
"content": "</s>",
|
22 |
"lstrip": false,
|
23 |
+
"normalized": true,
|
24 |
"rstrip": false,
|
25 |
"single_word": false,
|
26 |
"special": true
|
|
|
28 |
"3": {
|
29 |
"content": "<unk>",
|
30 |
"lstrip": false,
|
31 |
+
"normalized": true,
|
32 |
"rstrip": false,
|
33 |
"single_word": false,
|
34 |
"special": true
|
|
|
42 |
"special": true
|
43 |
}
|
44 |
},
|
|
|
45 |
"bos_token": "<s>",
|
46 |
"clean_up_tokenization_spaces": true,
|
47 |
"cls_token": "<s>",
|