Your Name
commited on
Commit
•
bab456a
1
Parent(s):
c5964e6
add model
Browse files- .gitignore +1 -0
- README.md +76 -0
- config.json +49 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- runs/Aug18_03-31-20_06dc742a3f46/1629257513.6828794/events.out.tfevents.1629257513.06dc742a3f46.75.1 +3 -0
- runs/Aug18_03-31-20_06dc742a3f46/events.out.tfevents.1629257513.06dc742a3f46.75.0 +3 -0
- runs/Aug18_03-31-20_06dc742a3f46/events.out.tfevents.1629257961.06dc742a3f46.75.2 +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
README.md
ADDED
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
datasets:
|
6 |
+
- null
|
7 |
+
metrics:
|
8 |
+
- precision
|
9 |
+
- recall
|
10 |
+
- f1
|
11 |
+
- accuracy
|
12 |
+
model_index:
|
13 |
+
- name: roberta-base-finetuned-ner
|
14 |
+
results:
|
15 |
+
- task:
|
16 |
+
name: Token Classification
|
17 |
+
type: token-classification
|
18 |
+
metric:
|
19 |
+
name: Accuracy
|
20 |
+
type: accuracy
|
21 |
+
value: 0.9914674251177673
|
22 |
+
---
|
23 |
+
|
24 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
25 |
+
should probably proofread and complete it, then remove this comment. -->
|
26 |
+
|
27 |
+
# roberta-base-finetuned-ner
|
28 |
+
|
29 |
+
This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the None dataset.
|
30 |
+
It achieves the following results on the evaluation set:
|
31 |
+
- Loss: 0.0381
|
32 |
+
- Precision: 0.9469
|
33 |
+
- Recall: 0.9530
|
34 |
+
- F1: 0.9500
|
35 |
+
- Accuracy: 0.9915
|
36 |
+
|
37 |
+
## Model description
|
38 |
+
|
39 |
+
More information needed
|
40 |
+
|
41 |
+
## Intended uses & limitations
|
42 |
+
|
43 |
+
More information needed
|
44 |
+
|
45 |
+
## Training and evaluation data
|
46 |
+
|
47 |
+
More information needed
|
48 |
+
|
49 |
+
## Training procedure
|
50 |
+
|
51 |
+
### Training hyperparameters
|
52 |
+
|
53 |
+
The following hyperparameters were used during training:
|
54 |
+
- learning_rate: 2e-05
|
55 |
+
- train_batch_size: 16
|
56 |
+
- eval_batch_size: 16
|
57 |
+
- seed: 42
|
58 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
59 |
+
- lr_scheduler_type: linear
|
60 |
+
- num_epochs: 3
|
61 |
+
|
62 |
+
### Training results
|
63 |
+
|
64 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
65 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
66 |
+
| 0.1328 | 1.0 | 753 | 0.0492 | 0.9143 | 0.9308 | 0.9225 | 0.9884 |
|
67 |
+
| 0.0301 | 2.0 | 1506 | 0.0378 | 0.9421 | 0.9474 | 0.9448 | 0.9910 |
|
68 |
+
| 0.0185 | 3.0 | 2259 | 0.0381 | 0.9469 | 0.9530 | 0.9500 | 0.9915 |
|
69 |
+
|
70 |
+
|
71 |
+
### Framework versions
|
72 |
+
|
73 |
+
- Transformers 4.9.2
|
74 |
+
- Pytorch 1.9.0+cu102
|
75 |
+
- Datasets 1.11.0
|
76 |
+
- Tokenizers 0.10.3
|
config.json
ADDED
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "roberta-base",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"gradient_checkpointing": false,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"id2label": {
|
14 |
+
"0": "LABEL_0",
|
15 |
+
"1": "LABEL_1",
|
16 |
+
"2": "LABEL_2",
|
17 |
+
"3": "LABEL_3",
|
18 |
+
"4": "LABEL_4",
|
19 |
+
"5": "LABEL_5",
|
20 |
+
"6": "LABEL_6",
|
21 |
+
"7": "LABEL_7",
|
22 |
+
"8": "LABEL_8"
|
23 |
+
},
|
24 |
+
"initializer_range": 0.02,
|
25 |
+
"intermediate_size": 3072,
|
26 |
+
"label2id": {
|
27 |
+
"LABEL_0": 0,
|
28 |
+
"LABEL_1": 1,
|
29 |
+
"LABEL_2": 2,
|
30 |
+
"LABEL_3": 3,
|
31 |
+
"LABEL_4": 4,
|
32 |
+
"LABEL_5": 5,
|
33 |
+
"LABEL_6": 6,
|
34 |
+
"LABEL_7": 7,
|
35 |
+
"LABEL_8": 8
|
36 |
+
},
|
37 |
+
"layer_norm_eps": 1e-05,
|
38 |
+
"max_position_embeddings": 514,
|
39 |
+
"model_type": "roberta",
|
40 |
+
"num_attention_heads": 12,
|
41 |
+
"num_hidden_layers": 12,
|
42 |
+
"pad_token_id": 1,
|
43 |
+
"position_embedding_type": "absolute",
|
44 |
+
"torch_dtype": "float32",
|
45 |
+
"transformers_version": "4.9.2",
|
46 |
+
"type_vocab_size": 1,
|
47 |
+
"use_cache": true,
|
48 |
+
"vocab_size": 50265
|
49 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b296faa3bcfaa20a4c49af551e12468ff671d8db91750f86957ee1d5dc10ef9c
|
3 |
+
size 496332529
|
runs/Aug18_03-31-20_06dc742a3f46/1629257513.6828794/events.out.tfevents.1629257513.06dc742a3f46.75.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b5046c30e9261a5858a1723a7bba38df71fc9b2eb8116fbe1c64e777758d68ba
|
3 |
+
size 4187
|
runs/Aug18_03-31-20_06dc742a3f46/events.out.tfevents.1629257513.06dc742a3f46.75.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:050c4b6c474b6d77dc0081722519ef4d9bab83cbfd0d4736a661af19ef6ee744
|
3 |
+
size 5740
|
runs/Aug18_03-31-20_06dc742a3f46/events.out.tfevents.1629257961.06dc742a3f46.75.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:85213b7f3bf8a897202127f86cff825579215bf593310e99a29c8ac90477bbae
|
3 |
+
size 512
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": true, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "roberta-base", "tokenizer_class": "RobertaTokenizer"}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4f5b8b4c5ef34e933157268e5f0eb3202e3b52a32991d9d6b20edf63b55464d1
|
3 |
+
size 2671
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|