Aleksandar
commited on
Commit
•
cae2b7d
1
Parent(s):
76272a5
add model
Browse files- .gitignore +1 -0
- README.md +77 -0
- config.json +49 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
README.md
ADDED
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- generated_from_trainer
|
4 |
+
datasets:
|
5 |
+
- null
|
6 |
+
metrics:
|
7 |
+
- precision
|
8 |
+
- recall
|
9 |
+
- f1
|
10 |
+
- accuracy
|
11 |
+
model_index:
|
12 |
+
- name: distilbert-srb-ner-setimes
|
13 |
+
results:
|
14 |
+
- task:
|
15 |
+
name: Token Classification
|
16 |
+
type: token-classification
|
17 |
+
metric:
|
18 |
+
name: Accuracy
|
19 |
+
type: accuracy
|
20 |
+
value: 0.962385099177552
|
21 |
+
---
|
22 |
+
|
23 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
24 |
+
should probably proofread and complete it, then remove this comment. -->
|
25 |
+
|
26 |
+
# distilbert-srb-ner-setimes
|
27 |
+
|
28 |
+
This model was trained from scratch on the None dataset.
|
29 |
+
It achieves the following results on the evaluation set:
|
30 |
+
- Loss: 0.1354
|
31 |
+
- Precision: 0.8
|
32 |
+
- Recall: 0.8319
|
33 |
+
- F1: 0.8156
|
34 |
+
- Accuracy: 0.9624
|
35 |
+
|
36 |
+
## Model description
|
37 |
+
|
38 |
+
More information needed
|
39 |
+
|
40 |
+
## Intended uses & limitations
|
41 |
+
|
42 |
+
More information needed
|
43 |
+
|
44 |
+
## Training and evaluation data
|
45 |
+
|
46 |
+
More information needed
|
47 |
+
|
48 |
+
## Training procedure
|
49 |
+
|
50 |
+
### Training hyperparameters
|
51 |
+
|
52 |
+
The following hyperparameters were used during training:
|
53 |
+
- learning_rate: 2e-05
|
54 |
+
- train_batch_size: 16
|
55 |
+
- eval_batch_size: 8
|
56 |
+
- seed: 42
|
57 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
58 |
+
- lr_scheduler_type: linear
|
59 |
+
- num_epochs: 5
|
60 |
+
|
61 |
+
### Training results
|
62 |
+
|
63 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
64 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
65 |
+
| No log | 1.0 | 207 | 0.2206 | 0.7029 | 0.7267 | 0.7146 | 0.9384 |
|
66 |
+
| No log | 2.0 | 414 | 0.1582 | 0.7449 | 0.7813 | 0.7627 | 0.9532 |
|
67 |
+
| 0.2358 | 3.0 | 621 | 0.1449 | 0.7756 | 0.8171 | 0.7958 | 0.9579 |
|
68 |
+
| 0.2358 | 4.0 | 828 | 0.1382 | 0.7903 | 0.8329 | 0.8110 | 0.9609 |
|
69 |
+
| 0.0895 | 5.0 | 1035 | 0.1354 | 0.8 | 0.8319 | 0.8156 | 0.9624 |
|
70 |
+
|
71 |
+
|
72 |
+
### Framework versions
|
73 |
+
|
74 |
+
- Transformers 4.9.2
|
75 |
+
- Pytorch 1.9.0
|
76 |
+
- Datasets 1.11.0
|
77 |
+
- Tokenizers 0.10.1
|
config.json
ADDED
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Aleksandar/distilbert-srb-base-cased-oscar",
|
3 |
+
"activation": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"DistilBertForTokenClassification"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"dim": 768,
|
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 |
+
"9": "LABEL_9"
|
22 |
+
},
|
23 |
+
"initializer_range": 0.02,
|
24 |
+
"label2id": {
|
25 |
+
"LABEL_0": 0,
|
26 |
+
"LABEL_1": 1,
|
27 |
+
"LABEL_2": 2,
|
28 |
+
"LABEL_3": 3,
|
29 |
+
"LABEL_4": 4,
|
30 |
+
"LABEL_5": 5,
|
31 |
+
"LABEL_6": 6,
|
32 |
+
"LABEL_7": 7,
|
33 |
+
"LABEL_8": 8,
|
34 |
+
"LABEL_9": 9
|
35 |
+
},
|
36 |
+
"max_position_embeddings": 512,
|
37 |
+
"model_type": "distilbert",
|
38 |
+
"n_heads": 12,
|
39 |
+
"n_layers": 6,
|
40 |
+
"output_past": true,
|
41 |
+
"pad_token_id": 0,
|
42 |
+
"qa_dropout": 0.1,
|
43 |
+
"seq_classif_dropout": 0.2,
|
44 |
+
"sinusoidal_pos_embds": false,
|
45 |
+
"tie_weights_": true,
|
46 |
+
"torch_dtype": "float32",
|
47 |
+
"transformers_version": "4.9.2",
|
48 |
+
"vocab_size": 50257
|
49 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:89f96d2c75a31f0230ac8177426f328ee78256c17f95ea933459ec4e136aa9b0
|
3 |
+
size 326147573
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
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": "Aleksandar/distilbert-srb-base-cased-oscar", "tokenizer_class": "DistilBertTokenizer"}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c3b4043154c0af293032a1d5318a9a9e25b29ce6ef48005e4346e383bfe901a8
|
3 |
+
size 2735
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|