updated model from notebook
Browse files- README.md +8 -8
- config.json +12 -11
- pytorch_model.bin +2 -2
- tokenizer.json +0 -0
- tokenizer_config.json +1 -1
- vocab.txt +0 -0
README.md
CHANGED
@@ -16,11 +16,11 @@ should probably proofread and complete it, then remove this comment. -->
|
|
16 |
|
17 |
This model was trained from scratch on an unkown dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
-
- Loss: 0.
|
20 |
-
- Precision: 0.
|
21 |
-
- Recall: 0.
|
22 |
-
- F1: 0.
|
23 |
-
- Accuracy: 0.
|
24 |
|
25 |
## Model description
|
26 |
|
@@ -51,9 +51,9 @@ The following hyperparameters were used during training:
|
|
51 |
|
52 |
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
53 |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
54 |
-
| 0.
|
55 |
-
| 0.
|
56 |
-
| 0.
|
57 |
|
58 |
|
59 |
### Framework versions
|
|
|
16 |
|
17 |
This model was trained from scratch on an unkown dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 0.0388
|
20 |
+
- Precision: 0.9360
|
21 |
+
- Recall: 0.9458
|
22 |
+
- F1: 0.9409
|
23 |
+
- Accuracy: 0.9902
|
24 |
|
25 |
## Model description
|
26 |
|
|
|
51 |
|
52 |
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
53 |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
54 |
+
| 0.1653 | 1.0 | 878 | 0.0465 | 0.9267 | 0.9300 | 0.9283 | 0.9883 |
|
55 |
+
| 0.0322 | 2.0 | 1756 | 0.0404 | 0.9360 | 0.9431 | 0.9396 | 0.9897 |
|
56 |
+
| 0.0185 | 3.0 | 2634 | 0.0388 | 0.9360 | 0.9458 | 0.9409 | 0.9902 |
|
57 |
|
58 |
|
59 |
### Framework versions
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "distilbert-base-
|
3 |
"activation": "gelu",
|
4 |
"architectures": [
|
5 |
"DistilBertForTokenClassification"
|
@@ -9,15 +9,15 @@
|
|
9 |
"dropout": 0.1,
|
10 |
"hidden_dim": 3072,
|
11 |
"id2label": {
|
12 |
-
"0": "
|
13 |
-
"1": "
|
14 |
-
"2": "
|
15 |
-
"3": "
|
16 |
-
"4": "
|
17 |
-
"5": "
|
18 |
-
"6": "
|
19 |
-
"7": "
|
20 |
-
"8": "
|
21 |
},
|
22 |
"initializer_range": 0.02,
|
23 |
"label2id": {
|
@@ -35,11 +35,12 @@
|
|
35 |
"model_type": "distilbert",
|
36 |
"n_heads": 12,
|
37 |
"n_layers": 6,
|
|
|
38 |
"pad_token_id": 0,
|
39 |
"qa_dropout": 0.1,
|
40 |
"seq_classif_dropout": 0.2,
|
41 |
"sinusoidal_pos_embds": false,
|
42 |
"tie_weights_": true,
|
43 |
"transformers_version": "4.6.1",
|
44 |
-
"vocab_size":
|
45 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "distilbert-base-multilingual-cased",
|
3 |
"activation": "gelu",
|
4 |
"architectures": [
|
5 |
"DistilBertForTokenClassification"
|
|
|
9 |
"dropout": 0.1,
|
10 |
"hidden_dim": 3072,
|
11 |
"id2label": {
|
12 |
+
"0": "LABEL_0",
|
13 |
+
"1": "LABEL_1",
|
14 |
+
"2": "LABEL_2",
|
15 |
+
"3": "LABEL_3",
|
16 |
+
"4": "LABEL_4",
|
17 |
+
"5": "LABEL_5",
|
18 |
+
"6": "LABEL_6",
|
19 |
+
"7": "LABEL_7",
|
20 |
+
"8": "LABEL_8"
|
21 |
},
|
22 |
"initializer_range": 0.02,
|
23 |
"label2id": {
|
|
|
35 |
"model_type": "distilbert",
|
36 |
"n_heads": 12,
|
37 |
"n_layers": 6,
|
38 |
+
"output_past": true,
|
39 |
"pad_token_id": 0,
|
40 |
"qa_dropout": 0.1,
|
41 |
"seq_classif_dropout": 0.2,
|
42 |
"sinusoidal_pos_embds": false,
|
43 |
"tie_weights_": true,
|
44 |
"transformers_version": "4.6.1",
|
45 |
+
"vocab_size": 119547
|
46 |
}
|
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 sha256:36de80edacc15d43b97c4284f99a5c39d304e498676d7cfcbb52cf0a7f48a045
|
3 |
+
size 539006405
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"do_lower_case":
|
|
|
1 |
+
{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "distilbert-base-multilingual-cased"}
|
vocab.txt
CHANGED
The diff for this file is too large to render.
See raw diff
|
|