Training in progress, step 500
Browse files- .gitignore +2 -0
- README.md +77 -0
- config.json +49 -0
- model.safetensors +3 -0
- runs/Dec11_00-37-20_n27/events.out.tfevents.1702251461.n27.196116.0 +3 -0
- runs/Dec11_00-41-30_n27/events.out.tfevents.1702251694.n27.198673.0 +3 -0
- runs/Dec11_00-50-54_n27/events.out.tfevents.1702252258.n27.201587.0 +3 -0
- runs/Dec11_00-56-13_n27/events.out.tfevents.1702252575.n27.208325.0 +3 -0
- runs/Dec11_00-56-13_n27/events.out.tfevents.1702253548.n27.208325.1 +3 -0
- runs/Dec12_17-22-06_n26/events.out.tfevents.1702398138.n26.31130.0 +3 -0
- runs/Dec12_17-22-06_n26/events.out.tfevents.1702398882.n26.31130.1 +3 -0
- runs/Dec12_23-49-17_n26/events.out.tfevents.1702421366.n26.73556.0 +3 -0
- runs/Dec12_23-49-17_n26/events.out.tfevents.1702421584.n26.73556.1 +3 -0
- runs/Dec13_00-09-53_n26/events.out.tfevents.1702422595.n26.74777.0 +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
.gitignore
ADDED
@@ -0,0 +1,2 @@
|
|
|
|
|
|
|
1 |
+
checkpoint*
|
2 |
+
runs*
|
README.md
ADDED
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: bert-base-multilingual-cased
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- wikiann
|
8 |
+
model-index:
|
9 |
+
- name: fine_tuned_BERT_cs_wikann
|
10 |
+
results: []
|
11 |
+
---
|
12 |
+
|
13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
+
should probably proofread and complete it, then remove this comment. -->
|
15 |
+
|
16 |
+
# fine_tuned_BERT_cs_wikann
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) on the wikiann dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.1618
|
21 |
+
- Overall Accuracy: 0.9672
|
22 |
+
- Overall F1: 0.9184
|
23 |
+
- Overall Precision: 0.9155
|
24 |
+
- Overall Recall: 0.9213
|
25 |
+
|
26 |
+
## Model description
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Intended uses & limitations
|
31 |
+
|
32 |
+
More information needed
|
33 |
+
|
34 |
+
## Training and evaluation data
|
35 |
+
|
36 |
+
More information needed
|
37 |
+
|
38 |
+
## Training procedure
|
39 |
+
|
40 |
+
### Training hyperparameters
|
41 |
+
|
42 |
+
The following hyperparameters were used during training:
|
43 |
+
- learning_rate: 5e-05
|
44 |
+
- train_batch_size: 8
|
45 |
+
- eval_batch_size: 8
|
46 |
+
- seed: 42
|
47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
48 |
+
- lr_scheduler_type: linear
|
49 |
+
- num_epochs: 3.0
|
50 |
+
|
51 |
+
### Training results
|
52 |
+
|
53 |
+
| Training Loss | Epoch | Step | Validation Loss | Overall Accuracy | Overall F1 | Overall Precision | Overall Recall |
|
54 |
+
|:-------------:|:-----:|:----:|:---------------:|:----------------:|:----------:|:-----------------:|:--------------:|
|
55 |
+
| 0.3538 | 0.2 | 500 | 0.2330 | 0.9392 | 0.8365 | 0.8271 | 0.8461 |
|
56 |
+
| 0.2331 | 0.4 | 1000 | 0.2291 | 0.9429 | 0.8536 | 0.8442 | 0.8633 |
|
57 |
+
| 0.2093 | 0.6 | 1500 | 0.1936 | 0.9515 | 0.8720 | 0.8777 | 0.8663 |
|
58 |
+
| 0.1976 | 0.8 | 2000 | 0.1728 | 0.9512 | 0.8673 | 0.8634 | 0.8714 |
|
59 |
+
| 0.1911 | 1.0 | 2500 | 0.1811 | 0.9586 | 0.8911 | 0.8797 | 0.9027 |
|
60 |
+
| 0.1245 | 1.2 | 3000 | 0.1771 | 0.9604 | 0.8977 | 0.8933 | 0.9022 |
|
61 |
+
| 0.1219 | 1.4 | 3500 | 0.1731 | 0.9595 | 0.8965 | 0.8893 | 0.9039 |
|
62 |
+
| 0.1102 | 1.6 | 4000 | 0.1721 | 0.9625 | 0.9060 | 0.9041 | 0.9078 |
|
63 |
+
| 0.1203 | 1.8 | 4500 | 0.1538 | 0.9625 | 0.9038 | 0.9095 | 0.8981 |
|
64 |
+
| 0.1105 | 2.0 | 5000 | 0.1562 | 0.9656 | 0.9120 | 0.9065 | 0.9177 |
|
65 |
+
| 0.0601 | 2.2 | 5500 | 0.1700 | 0.9648 | 0.9113 | 0.9006 | 0.9222 |
|
66 |
+
| 0.0579 | 2.4 | 6000 | 0.1569 | 0.9659 | 0.9140 | 0.9105 | 0.9176 |
|
67 |
+
| 0.0571 | 2.6 | 6500 | 0.1595 | 0.9673 | 0.9168 | 0.9154 | 0.9183 |
|
68 |
+
| 0.0504 | 2.8 | 7000 | 0.1664 | 0.9670 | 0.9174 | 0.9120 | 0.9228 |
|
69 |
+
| 0.0588 | 3.0 | 7500 | 0.1618 | 0.9672 | 0.9184 | 0.9155 | 0.9213 |
|
70 |
+
|
71 |
+
|
72 |
+
### Framework versions
|
73 |
+
|
74 |
+
- Transformers 4.36.0.dev0
|
75 |
+
- Pytorch 2.0.1+cu117
|
76 |
+
- Datasets 2.14.5
|
77 |
+
- Tokenizers 0.15.0
|
config.json
ADDED
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-base-multilingual-cased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"directionality": "bidi",
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"id2label": {
|
13 |
+
"0": "O",
|
14 |
+
"1": "B-PER",
|
15 |
+
"2": "I-PER",
|
16 |
+
"3": "B-ORG",
|
17 |
+
"4": "I-ORG",
|
18 |
+
"5": "B-LOC",
|
19 |
+
"6": "I-LOC"
|
20 |
+
},
|
21 |
+
"initializer_range": 0.02,
|
22 |
+
"intermediate_size": 3072,
|
23 |
+
"label2id": {
|
24 |
+
"B-LOC": 5,
|
25 |
+
"B-ORG": 3,
|
26 |
+
"B-PER": 1,
|
27 |
+
"I-LOC": 6,
|
28 |
+
"I-ORG": 4,
|
29 |
+
"I-PER": 2,
|
30 |
+
"O": 0
|
31 |
+
},
|
32 |
+
"layer_norm_eps": 1e-12,
|
33 |
+
"max_position_embeddings": 512,
|
34 |
+
"model_type": "bert",
|
35 |
+
"num_attention_heads": 12,
|
36 |
+
"num_hidden_layers": 12,
|
37 |
+
"pad_token_id": 0,
|
38 |
+
"pooler_fc_size": 768,
|
39 |
+
"pooler_num_attention_heads": 12,
|
40 |
+
"pooler_num_fc_layers": 3,
|
41 |
+
"pooler_size_per_head": 128,
|
42 |
+
"pooler_type": "first_token_transform",
|
43 |
+
"position_embedding_type": "absolute",
|
44 |
+
"torch_dtype": "float32",
|
45 |
+
"transformers_version": "4.36.0.dev0",
|
46 |
+
"type_vocab_size": 2,
|
47 |
+
"use_cache": true,
|
48 |
+
"vocab_size": 119547
|
49 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8e45ad0aee723b99188dcd22128e757706c0397bb807a2c871acb083eb1f3a4c
|
3 |
+
size 709096284
|
runs/Dec11_00-37-20_n27/events.out.tfevents.1702251461.n27.196116.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:166f699da044a547d2c2f032ea073bd024bf988d4354be92463981cb1ab420a7
|
3 |
+
size 40
|
runs/Dec11_00-41-30_n27/events.out.tfevents.1702251694.n27.198673.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1b9b32e4b6b5d7f690d5b88439afeeae16f3724abb44b358d8506899db591ce2
|
3 |
+
size 40
|
runs/Dec11_00-50-54_n27/events.out.tfevents.1702252258.n27.201587.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:35119170fee60d6ba627a9d640b93d53c133f5073c4a2076e026484a38e32d1a
|
3 |
+
size 4762
|
runs/Dec11_00-56-13_n27/events.out.tfevents.1702252575.n27.208325.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:302e398553f1c6072cf69e1c898529578dfb8087a1f3ed416be75ac4b6e9fa41
|
3 |
+
size 15018
|
runs/Dec11_00-56-13_n27/events.out.tfevents.1702253548.n27.208325.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6df7971c08d8ad80216074e3c2ba892a9e56190fddf5bdb6bb669cd9f4e2ccbf
|
3 |
+
size 1048
|
runs/Dec12_17-22-06_n26/events.out.tfevents.1702398138.n26.31130.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:97050da79ca29b27f1b9693b29bf1e9136a05511d8ceeec311b91b1a78b716c0
|
3 |
+
size 14984
|
runs/Dec12_17-22-06_n26/events.out.tfevents.1702398882.n26.31130.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2a7161165534ef44a869d4d7c1a70868c3c5f9829f6c6db4821a21e47470245b
|
3 |
+
size 1048
|
runs/Dec12_23-49-17_n26/events.out.tfevents.1702421366.n26.73556.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b0c61b3174afd3e289839b0deaa16d34cd2dd2431b78543c153532b8a81e5ae3
|
3 |
+
size 5068
|
runs/Dec12_23-49-17_n26/events.out.tfevents.1702421584.n26.73556.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fdfa095b13d5e5ab0d80a18092d82a678c90cea0875decb3e46c6ebf9c842071
|
3 |
+
size 544
|
runs/Dec13_00-09-53_n26/events.out.tfevents.1702422595.n26.74777.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:70ab2630a29a46cfd72da1d4f6f687df7af8005c84b3eb04847b30993eb02d8c
|
3 |
+
size 5378
|
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:eb901db0b6253e9b3fa7efd40bde4f38339b5e781762531d44cabbb5869c1dfa
|
3 |
+
size 4219
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|