End of training
Browse files- README.md +64 -0
- config.json +36 -0
- model.safetensors +3 -0
- runs/Apr30_08-20-39_0958311b762e/events.out.tfevents.1714465240.0958311b762e.1217.0 +3 -0
- runs/Apr30_09-18-48_0958311b762e/events.out.tfevents.1714468729.0958311b762e.16512.0 +3 -0
- runs/Apr30_09-18-48_0958311b762e/events.out.tfevents.1714468740.0958311b762e.16512.1 +3 -0
- runs/Apr30_09-48-45_0958311b762e/events.out.tfevents.1714470526.0958311b762e.16512.2 +3 -0
- runs/Apr30_09-48-45_0958311b762e/events.out.tfevents.1714470536.0958311b762e.16512.3 +3 -0
- runs/Apr30_10-48-15_0958311b762e/events.out.tfevents.1714474096.0958311b762e.16512.4 +3 -0
- runs/Apr30_10-48-15_0958311b762e/events.out.tfevents.1714474105.0958311b762e.16512.5 +3 -0
- runs/Apr30_10-55-49_0958311b762e/events.out.tfevents.1714474550.0958311b762e.16512.6 +3 -0
- runs/Apr30_10-56-17_0958311b762e/events.out.tfevents.1714474578.0958311b762e.16512.7 +3 -0
- runs/Apr30_10-56-17_0958311b762e/events.out.tfevents.1714474587.0958311b762e.16512.8 +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +55 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: bert-base-cased
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- precision
|
8 |
+
- recall
|
9 |
+
- f1
|
10 |
+
model-index:
|
11 |
+
- name: BERT-ukpolitics
|
12 |
+
results: []
|
13 |
+
---
|
14 |
+
|
15 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
16 |
+
should probably proofread and complete it, then remove this comment. -->
|
17 |
+
|
18 |
+
# BERT-ukpolitics
|
19 |
+
|
20 |
+
This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the None dataset.
|
21 |
+
It achieves the following results on the evaluation set:
|
22 |
+
- Loss: 0.0989
|
23 |
+
- Precision: 0.6425
|
24 |
+
- Recall: 0.3322
|
25 |
+
- F1: 0.4379
|
26 |
+
|
27 |
+
## Model description
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Intended uses & limitations
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Training and evaluation data
|
36 |
+
|
37 |
+
More information needed
|
38 |
+
|
39 |
+
## Training procedure
|
40 |
+
|
41 |
+
### Training hyperparameters
|
42 |
+
|
43 |
+
The following hyperparameters were used during training:
|
44 |
+
- learning_rate: 5e-05
|
45 |
+
- train_batch_size: 4
|
46 |
+
- eval_batch_size: 4
|
47 |
+
- seed: 42
|
48 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
49 |
+
- lr_scheduler_type: linear
|
50 |
+
- num_epochs: 1
|
51 |
+
|
52 |
+
### Training results
|
53 |
+
|
54 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 |
|
55 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|
|
56 |
+
| No log | 1.0 | 102 | 0.0989 | 0.6425 | 0.3322 | 0.4379 |
|
57 |
+
|
58 |
+
|
59 |
+
### Framework versions
|
60 |
+
|
61 |
+
- Transformers 4.40.0
|
62 |
+
- Pytorch 2.2.1+cu121
|
63 |
+
- Datasets 2.19.0
|
64 |
+
- Tokenizers 0.19.1
|
config.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-base-cased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"id2label": {
|
13 |
+
"0": "O",
|
14 |
+
"1": "I-S",
|
15 |
+
"2": "B-S"
|
16 |
+
},
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"intermediate_size": 3072,
|
19 |
+
"label2id": {
|
20 |
+
"B-S": 2,
|
21 |
+
"I-S": 1,
|
22 |
+
"O": 0
|
23 |
+
},
|
24 |
+
"layer_norm_eps": 1e-12,
|
25 |
+
"max_position_embeddings": 512,
|
26 |
+
"model_type": "bert",
|
27 |
+
"num_attention_heads": 12,
|
28 |
+
"num_hidden_layers": 12,
|
29 |
+
"pad_token_id": 0,
|
30 |
+
"position_embedding_type": "absolute",
|
31 |
+
"torch_dtype": "float32",
|
32 |
+
"transformers_version": "4.40.0",
|
33 |
+
"type_vocab_size": 2,
|
34 |
+
"use_cache": true,
|
35 |
+
"vocab_size": 28996
|
36 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6d0fd0618e5662166422678a3eec509e3bae9dc9ea477c1099cdb39a254cf096
|
3 |
+
size 430911284
|
runs/Apr30_08-20-39_0958311b762e/events.out.tfevents.1714465240.0958311b762e.1217.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3d749d5249c1c7a321f119ddaf17bd55812786e43bfaa49a11f60f62bcfd6780
|
3 |
+
size 5521
|
runs/Apr30_09-18-48_0958311b762e/events.out.tfevents.1714468729.0958311b762e.16512.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5c81cee9cbfddfc949d9b8da38036b6379b67192e29e9b4af444d2d7aea6c70d
|
3 |
+
size 5521
|
runs/Apr30_09-18-48_0958311b762e/events.out.tfevents.1714468740.0958311b762e.16512.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:909af4c0a336491cef82e25ebc59eb71929c75fff6f37ae613bc2b09fdd591f5
|
3 |
+
size 500
|
runs/Apr30_09-48-45_0958311b762e/events.out.tfevents.1714470526.0958311b762e.16512.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f81d0e14e1734391a6387ffbb161d35c4db2a515b2dfa0851d06871bf7ebccf
|
3 |
+
size 5527
|
runs/Apr30_09-48-45_0958311b762e/events.out.tfevents.1714470536.0958311b762e.16512.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dff06e758aa3405e2584828e2cd43b0ba5248eee9836c06b597d0630bfeeab05
|
3 |
+
size 500
|
runs/Apr30_10-48-15_0958311b762e/events.out.tfevents.1714474096.0958311b762e.16512.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2910665e6b522cad59bdf655c537d6e279cc57be90c33f2eb1fa99cb6e788665
|
3 |
+
size 5527
|
runs/Apr30_10-48-15_0958311b762e/events.out.tfevents.1714474105.0958311b762e.16512.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:49053a882de1d9daed0fca1ec554c5a307b08a86957d434dcd573786498a2518
|
3 |
+
size 500
|
runs/Apr30_10-55-49_0958311b762e/events.out.tfevents.1714474550.0958311b762e.16512.6
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d4ed95264ec5305c6a1365760f09ce9f5a628c97b35af0a36393d470a9cb92b7
|
3 |
+
size 4184
|
runs/Apr30_10-56-17_0958311b762e/events.out.tfevents.1714474578.0958311b762e.16512.7
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9ada94b4038569d5c106d037d5cc0dff02a4aec236d5d3be3448930e348f5d6c
|
3 |
+
size 5538
|
runs/Apr30_10-56-17_0958311b762e/events.out.tfevents.1714474587.0958311b762e.16512.8
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8c10ad51b3feea1ea38d38dccf5c59a655cad79c72f4987b97015c56f94fc505
|
3 |
+
size 500
|
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_lower_case": false,
|
47 |
+
"mask_token": "[MASK]",
|
48 |
+
"model_max_length": 512,
|
49 |
+
"pad_token": "[PAD]",
|
50 |
+
"sep_token": "[SEP]",
|
51 |
+
"strip_accents": null,
|
52 |
+
"tokenize_chinese_chars": true,
|
53 |
+
"tokenizer_class": "BertTokenizer",
|
54 |
+
"unk_token": "[UNK]"
|
55 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ccfa459ef3c1ee1e827db10b44a2d74e37cf512e8f06f2a36f177f768eb12ced
|
3 |
+
size 4984
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|