Commit
•
c8bf4b1
1
Parent(s):
ad4db4a
add model
Browse files- .gitignore +1 -0
- README.md +67 -0
- config.json +46 -0
- pytorch_model.bin +3 -0
- runs/Jul26_11-24-51_fa721952f957/1627298796.8540747/events.out.tfevents.1627298796.fa721952f957.61.1 +3 -0
- runs/Jul26_11-24-51_fa721952f957/events.out.tfevents.1627298796.fa721952f957.61.0 +3 -0
- runs/Jul26_11-24-51_fa721952f957/events.out.tfevents.1627311253.fa721952f957.61.2 +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 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
datasets:
|
6 |
+
- conll2003
|
7 |
+
model_index:
|
8 |
+
- name: distilbert-base-uncased-finetuned-ner
|
9 |
+
results:
|
10 |
+
- task:
|
11 |
+
name: Token Classification
|
12 |
+
type: token-classification
|
13 |
+
dataset:
|
14 |
+
name: conll2003
|
15 |
+
type: conll2003
|
16 |
+
args: conll2003
|
17 |
+
---
|
18 |
+
|
19 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
20 |
+
should probably proofread and complete it, then remove this comment. -->
|
21 |
+
|
22 |
+
# distilbert-base-uncased-finetuned-ner
|
23 |
+
|
24 |
+
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the conll2003 dataset.
|
25 |
+
It achieves the following results on the evaluation set:
|
26 |
+
- Loss: 0.0623
|
27 |
+
|
28 |
+
## Model description
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Intended uses & limitations
|
33 |
+
|
34 |
+
More information needed
|
35 |
+
|
36 |
+
## Training and evaluation data
|
37 |
+
|
38 |
+
More information needed
|
39 |
+
|
40 |
+
## Training procedure
|
41 |
+
|
42 |
+
### Training hyperparameters
|
43 |
+
|
44 |
+
The following hyperparameters were used during training:
|
45 |
+
- learning_rate: 2e-05
|
46 |
+
- train_batch_size: 16
|
47 |
+
- eval_batch_size: 16
|
48 |
+
- seed: 42
|
49 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
50 |
+
- lr_scheduler_type: linear
|
51 |
+
- num_epochs: 3
|
52 |
+
|
53 |
+
### Training results
|
54 |
+
|
55 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
56 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
57 |
+
| 0.2377 | 1.0 | 878 | 0.0711 |
|
58 |
+
| 0.0514 | 2.0 | 1756 | 0.0637 |
|
59 |
+
| 0.031 | 3.0 | 2634 | 0.0623 |
|
60 |
+
|
61 |
+
|
62 |
+
### Framework versions
|
63 |
+
|
64 |
+
- Transformers 4.9.0
|
65 |
+
- Pytorch 1.9.0+cu102
|
66 |
+
- Datasets 1.10.2
|
67 |
+
- Tokenizers 0.10.3
|
config.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert-base-uncased",
|
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 |
+
},
|
22 |
+
"initializer_range": 0.02,
|
23 |
+
"label2id": {
|
24 |
+
"LABEL_0": 0,
|
25 |
+
"LABEL_1": 1,
|
26 |
+
"LABEL_2": 2,
|
27 |
+
"LABEL_3": 3,
|
28 |
+
"LABEL_4": 4,
|
29 |
+
"LABEL_5": 5,
|
30 |
+
"LABEL_6": 6,
|
31 |
+
"LABEL_7": 7,
|
32 |
+
"LABEL_8": 8
|
33 |
+
},
|
34 |
+
"max_position_embeddings": 512,
|
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 |
+
"torch_dtype": "float32",
|
44 |
+
"transformers_version": "4.9.0",
|
45 |
+
"vocab_size": 30522
|
46 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7772de0a33135c23a927175b269112dc1ff986bbf1abdeec8ad1bdb0b14fab2f
|
3 |
+
size 265517173
|
runs/Jul26_11-24-51_fa721952f957/1627298796.8540747/events.out.tfevents.1627298796.fa721952f957.61.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:179cfc4fce0d59d5457280a80fb0a33a1ec0c0048e8f3a87301237c79a89f5a5
|
3 |
+
size 4198
|
runs/Jul26_11-24-51_fa721952f957/events.out.tfevents.1627298796.fa721952f957.61.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a6d253708c849856cc08ddd5be65d6e91bdf5ab2a5a797762ee346ca76742412
|
3 |
+
size 5180
|
runs/Jul26_11-24-51_fa721952f957/events.out.tfevents.1627311253.fa721952f957.61.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8171f12280e138adc06db8b080840734c9db2093737d3e6ff3353b2b66514fcc
|
3 |
+
size 311
|
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": true, "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-uncased", "tokenizer_class": "DistilBertTokenizer"}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cae3f2b133bbcd910ddb294260e495cf0a7c3302bae1f710ff0703c0c2485696
|
3 |
+
size 2671
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|