Justice0893
commited on
End of training
Browse files- README.md +115 -0
- config.json +65 -0
- pytorch_model.bin +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 +1,115 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: bert-base-multilingual-uncased
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- precision
|
8 |
+
- recall
|
9 |
+
- f1
|
10 |
+
- accuracy
|
11 |
+
model-index:
|
12 |
+
- name: bert_multi-uncased-finetuned-pos-tr
|
13 |
+
results: []
|
14 |
+
---
|
15 |
+
|
16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
17 |
+
should probably proofread and complete it, then remove this comment. -->
|
18 |
+
|
19 |
+
# bert_multi-uncased-finetuned-pos-tr
|
20 |
+
|
21 |
+
This model is a fine-tuned version of [bert-base-multilingual-uncased](https://huggingface.co/bert-base-multilingual-uncased) on the None dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.3933
|
24 |
+
- Precision: 0.9225
|
25 |
+
- Recall: 0.9275
|
26 |
+
- F1: 0.9250
|
27 |
+
- Accuracy: 0.9564
|
28 |
+
|
29 |
+
## Model description
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Intended uses & limitations
|
34 |
+
|
35 |
+
More information needed
|
36 |
+
|
37 |
+
## Training and evaluation data
|
38 |
+
|
39 |
+
More information needed
|
40 |
+
|
41 |
+
## Training procedure
|
42 |
+
|
43 |
+
### Training hyperparameters
|
44 |
+
|
45 |
+
The following hyperparameters were used during training:
|
46 |
+
- learning_rate: 2e-05
|
47 |
+
- train_batch_size: 16
|
48 |
+
- eval_batch_size: 16
|
49 |
+
- seed: 42
|
50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
+
- lr_scheduler_type: linear
|
52 |
+
- num_epochs: 50
|
53 |
+
|
54 |
+
### Training results
|
55 |
+
|
56 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
57 |
+
|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
58 |
+
| 0.4051 | 1.0 | 836 | 0.1752 | 0.9110 | 0.9098 | 0.9104 | 0.9493 |
|
59 |
+
| 0.1506 | 2.0 | 1672 | 0.1492 | 0.9112 | 0.9207 | 0.9159 | 0.9529 |
|
60 |
+
| 0.1182 | 3.0 | 2508 | 0.1632 | 0.9183 | 0.9229 | 0.9206 | 0.9552 |
|
61 |
+
| 0.0973 | 4.0 | 3344 | 0.1544 | 0.9197 | 0.9216 | 0.9206 | 0.9550 |
|
62 |
+
| 0.0796 | 5.0 | 4180 | 0.1676 | 0.9227 | 0.9221 | 0.9224 | 0.9569 |
|
63 |
+
| 0.0673 | 6.0 | 5016 | 0.1829 | 0.9196 | 0.9206 | 0.9201 | 0.9548 |
|
64 |
+
| 0.052 | 7.0 | 5852 | 0.1850 | 0.9220 | 0.9237 | 0.9228 | 0.9562 |
|
65 |
+
| 0.0448 | 8.0 | 6688 | 0.1980 | 0.9187 | 0.9305 | 0.9246 | 0.9571 |
|
66 |
+
| 0.0394 | 9.0 | 7524 | 0.2298 | 0.9147 | 0.9204 | 0.9176 | 0.9531 |
|
67 |
+
| 0.0298 | 10.0 | 8360 | 0.2288 | 0.9217 | 0.9277 | 0.9247 | 0.9571 |
|
68 |
+
| 0.028 | 11.0 | 9196 | 0.2434 | 0.9173 | 0.9231 | 0.9202 | 0.9545 |
|
69 |
+
| 0.0233 | 12.0 | 10032 | 0.2609 | 0.9174 | 0.9275 | 0.9225 | 0.9558 |
|
70 |
+
| 0.018 | 13.0 | 10868 | 0.2701 | 0.9211 | 0.9249 | 0.9230 | 0.9559 |
|
71 |
+
| 0.0168 | 14.0 | 11704 | 0.2694 | 0.9206 | 0.9261 | 0.9234 | 0.9564 |
|
72 |
+
| 0.0157 | 15.0 | 12540 | 0.2774 | 0.9213 | 0.929 | 0.9251 | 0.9568 |
|
73 |
+
| 0.0148 | 16.0 | 13376 | 0.2923 | 0.9229 | 0.9255 | 0.9242 | 0.9565 |
|
74 |
+
| 0.013 | 17.0 | 14212 | 0.2853 | 0.9229 | 0.9263 | 0.9246 | 0.9574 |
|
75 |
+
| 0.0104 | 18.0 | 15048 | 0.2899 | 0.9224 | 0.9265 | 0.9245 | 0.9569 |
|
76 |
+
| 0.0096 | 19.0 | 15884 | 0.2769 | 0.9239 | 0.9253 | 0.9246 | 0.9571 |
|
77 |
+
| 0.009 | 20.0 | 16720 | 0.3074 | 0.9204 | 0.9267 | 0.9235 | 0.9570 |
|
78 |
+
| 0.0098 | 21.0 | 17556 | 0.2985 | 0.9221 | 0.9287 | 0.9254 | 0.9573 |
|
79 |
+
| 0.0071 | 22.0 | 18392 | 0.3293 | 0.9216 | 0.9277 | 0.9246 | 0.9561 |
|
80 |
+
| 0.0069 | 23.0 | 19228 | 0.3135 | 0.9242 | 0.9285 | 0.9263 | 0.9572 |
|
81 |
+
| 0.007 | 24.0 | 20064 | 0.3098 | 0.9226 | 0.9291 | 0.9258 | 0.9576 |
|
82 |
+
| 0.0072 | 25.0 | 20900 | 0.3352 | 0.9241 | 0.9288 | 0.9265 | 0.9580 |
|
83 |
+
| 0.0048 | 26.0 | 21736 | 0.3384 | 0.9228 | 0.9269 | 0.9249 | 0.9567 |
|
84 |
+
| 0.006 | 27.0 | 22572 | 0.3316 | 0.9232 | 0.9276 | 0.9254 | 0.9575 |
|
85 |
+
| 0.0057 | 28.0 | 23408 | 0.3381 | 0.9238 | 0.9272 | 0.9255 | 0.9578 |
|
86 |
+
| 0.0051 | 29.0 | 24244 | 0.3494 | 0.9211 | 0.9282 | 0.9246 | 0.9568 |
|
87 |
+
| 0.0046 | 30.0 | 25080 | 0.3379 | 0.9237 | 0.9254 | 0.9246 | 0.9570 |
|
88 |
+
| 0.0044 | 31.0 | 25916 | 0.3512 | 0.9232 | 0.9251 | 0.9242 | 0.9565 |
|
89 |
+
| 0.0037 | 32.0 | 26752 | 0.3625 | 0.9227 | 0.9252 | 0.9240 | 0.9563 |
|
90 |
+
| 0.0029 | 33.0 | 27588 | 0.3476 | 0.9220 | 0.9264 | 0.9242 | 0.9574 |
|
91 |
+
| 0.0039 | 34.0 | 28424 | 0.3635 | 0.9238 | 0.9275 | 0.9257 | 0.9575 |
|
92 |
+
| 0.0034 | 35.0 | 29260 | 0.3685 | 0.9205 | 0.9247 | 0.9226 | 0.9554 |
|
93 |
+
| 0.0033 | 36.0 | 30096 | 0.3693 | 0.9219 | 0.9245 | 0.9232 | 0.9555 |
|
94 |
+
| 0.003 | 37.0 | 30932 | 0.3698 | 0.9239 | 0.9257 | 0.9248 | 0.9573 |
|
95 |
+
| 0.0024 | 38.0 | 31768 | 0.3772 | 0.9242 | 0.926 | 0.9251 | 0.9570 |
|
96 |
+
| 0.0029 | 39.0 | 32604 | 0.3798 | 0.9246 | 0.9281 | 0.9263 | 0.9563 |
|
97 |
+
| 0.0024 | 40.0 | 33440 | 0.3804 | 0.9215 | 0.9264 | 0.9239 | 0.9562 |
|
98 |
+
| 0.0017 | 41.0 | 34276 | 0.3804 | 0.9238 | 0.9274 | 0.9256 | 0.9570 |
|
99 |
+
| 0.0025 | 42.0 | 35112 | 0.3808 | 0.9252 | 0.9273 | 0.9263 | 0.9570 |
|
100 |
+
| 0.0025 | 43.0 | 35948 | 0.3794 | 0.9237 | 0.9282 | 0.9259 | 0.9568 |
|
101 |
+
| 0.0029 | 44.0 | 36784 | 0.3784 | 0.9249 | 0.9282 | 0.9265 | 0.9576 |
|
102 |
+
| 0.0019 | 45.0 | 37620 | 0.3895 | 0.9238 | 0.9281 | 0.9259 | 0.9569 |
|
103 |
+
| 0.0019 | 46.0 | 38456 | 0.3859 | 0.9238 | 0.9284 | 0.9261 | 0.9572 |
|
104 |
+
| 0.0017 | 47.0 | 39292 | 0.3906 | 0.9222 | 0.9277 | 0.9249 | 0.9567 |
|
105 |
+
| 0.0016 | 48.0 | 40128 | 0.3933 | 0.9221 | 0.9273 | 0.9247 | 0.9565 |
|
106 |
+
| 0.0016 | 49.0 | 40964 | 0.3924 | 0.9224 | 0.9273 | 0.9248 | 0.9565 |
|
107 |
+
| 0.0017 | 50.0 | 41800 | 0.3933 | 0.9225 | 0.9275 | 0.9250 | 0.9564 |
|
108 |
+
|
109 |
+
|
110 |
+
### Framework versions
|
111 |
+
|
112 |
+
- Transformers 4.34.1
|
113 |
+
- Pytorch 2.2.1+cu118
|
114 |
+
- Datasets 2.14.6
|
115 |
+
- Tokenizers 0.14.1
|
config.json
ADDED
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-base-multilingual-uncased",
|
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": "NOUN",
|
14 |
+
"1": "PROPN",
|
15 |
+
"2": "VERB",
|
16 |
+
"3": "PUNCT",
|
17 |
+
"4": "ADJ",
|
18 |
+
"5": "NUM",
|
19 |
+
"6": "DET",
|
20 |
+
"7": "ADV",
|
21 |
+
"8": "ADP",
|
22 |
+
"9": "PRON",
|
23 |
+
"10": "CCONJ",
|
24 |
+
"11": "AUX",
|
25 |
+
"12": "X",
|
26 |
+
"13": "SCONJ",
|
27 |
+
"14": "INTJ"
|
28 |
+
},
|
29 |
+
"initializer_range": 0.02,
|
30 |
+
"intermediate_size": 3072,
|
31 |
+
"label2id": {
|
32 |
+
"ADJ": 4,
|
33 |
+
"ADP": 8,
|
34 |
+
"ADV": 7,
|
35 |
+
"AUX": 11,
|
36 |
+
"CCONJ": 10,
|
37 |
+
"DET": 6,
|
38 |
+
"INTJ": 14,
|
39 |
+
"NOUN": 0,
|
40 |
+
"NUM": 5,
|
41 |
+
"PRON": 9,
|
42 |
+
"PROPN": 1,
|
43 |
+
"PUNCT": 3,
|
44 |
+
"SCONJ": 13,
|
45 |
+
"VERB": 2,
|
46 |
+
"X": 12
|
47 |
+
},
|
48 |
+
"layer_norm_eps": 1e-12,
|
49 |
+
"max_position_embeddings": 512,
|
50 |
+
"model_type": "bert",
|
51 |
+
"num_attention_heads": 12,
|
52 |
+
"num_hidden_layers": 12,
|
53 |
+
"pad_token_id": 0,
|
54 |
+
"pooler_fc_size": 768,
|
55 |
+
"pooler_num_attention_heads": 12,
|
56 |
+
"pooler_num_fc_layers": 3,
|
57 |
+
"pooler_size_per_head": 128,
|
58 |
+
"pooler_type": "first_token_transform",
|
59 |
+
"position_embedding_type": "absolute",
|
60 |
+
"torch_dtype": "float32",
|
61 |
+
"transformers_version": "4.34.1",
|
62 |
+
"type_vocab_size": 2,
|
63 |
+
"use_cache": true,
|
64 |
+
"vocab_size": 105879
|
65 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3a8a18c15f5468f57592ff1eed980a2b91f0fdb834ca7ebe403b495206b3914b
|
3 |
+
size 667177638
|
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": true,
|
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 sha256:7c29b4b154639e755816f0026ea91cd8c69850d86a4c85fe95f483216f669110
|
3 |
+
size 4536
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|