Commit
•
55fbc75
1
Parent(s):
6f5611f
End of training
Browse files- README.md +115 -0
- config.json +49 -0
- model.safetensors +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-cased
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
- precision
|
9 |
+
- recall
|
10 |
+
- f1
|
11 |
+
model-index:
|
12 |
+
- name: Frozen11-50epoch-BERT-multilingual-finetuned-CEFR_ner-10000news
|
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 |
+
# Frozen11-50epoch-BERT-multilingual-finetuned-CEFR_ner-10000news
|
20 |
+
|
21 |
+
This model is a fine-tuned version of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) on an unknown dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.3983
|
24 |
+
- Accuracy: 0.2881
|
25 |
+
- Precision: 0.4062
|
26 |
+
- Recall: 0.7266
|
27 |
+
- F1: 0.4014
|
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 | Accuracy | Precision | Recall | F1 |
|
57 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:---------:|:------:|:------:|
|
58 |
+
| 0.7274 | 1.0 | 500 | 0.6491 | 0.2455 | 0.4102 | 0.4821 | 0.2722 |
|
59 |
+
| 0.6213 | 2.0 | 1000 | 0.5746 | 0.2543 | 0.3790 | 0.5244 | 0.2899 |
|
60 |
+
| 0.5375 | 3.0 | 1500 | 0.5073 | 0.2626 | 0.3959 | 0.5531 | 0.3168 |
|
61 |
+
| 0.4721 | 4.0 | 2000 | 0.4612 | 0.2690 | 0.4067 | 0.5837 | 0.3466 |
|
62 |
+
| 0.4231 | 5.0 | 2500 | 0.4297 | 0.2728 | 0.3975 | 0.6080 | 0.3571 |
|
63 |
+
| 0.3828 | 6.0 | 3000 | 0.4104 | 0.2751 | 0.4034 | 0.6224 | 0.3628 |
|
64 |
+
| 0.3494 | 7.0 | 3500 | 0.3973 | 0.2769 | 0.4011 | 0.6354 | 0.3658 |
|
65 |
+
| 0.3223 | 8.0 | 4000 | 0.3764 | 0.2796 | 0.4004 | 0.6546 | 0.3765 |
|
66 |
+
| 0.2991 | 9.0 | 4500 | 0.3693 | 0.2807 | 0.4138 | 0.6578 | 0.3874 |
|
67 |
+
| 0.2797 | 10.0 | 5000 | 0.3661 | 0.2811 | 0.3998 | 0.6726 | 0.3811 |
|
68 |
+
| 0.2623 | 11.0 | 5500 | 0.3571 | 0.2826 | 0.4118 | 0.6765 | 0.3922 |
|
69 |
+
| 0.2476 | 12.0 | 6000 | 0.3514 | 0.2833 | 0.4063 | 0.6877 | 0.3914 |
|
70 |
+
| 0.2337 | 13.0 | 6500 | 0.3586 | 0.2828 | 0.4046 | 0.6849 | 0.3880 |
|
71 |
+
| 0.2198 | 14.0 | 7000 | 0.3480 | 0.2844 | 0.4107 | 0.6904 | 0.3960 |
|
72 |
+
| 0.2096 | 15.0 | 7500 | 0.3495 | 0.2847 | 0.4128 | 0.6893 | 0.3968 |
|
73 |
+
| 0.2007 | 16.0 | 8000 | 0.3456 | 0.2852 | 0.4106 | 0.7003 | 0.3984 |
|
74 |
+
| 0.1894 | 17.0 | 8500 | 0.3543 | 0.2849 | 0.4003 | 0.7058 | 0.3905 |
|
75 |
+
| 0.1816 | 18.0 | 9000 | 0.3532 | 0.2851 | 0.4071 | 0.7066 | 0.3966 |
|
76 |
+
| 0.1742 | 19.0 | 9500 | 0.3500 | 0.2857 | 0.4138 | 0.7069 | 0.4024 |
|
77 |
+
| 0.167 | 20.0 | 10000 | 0.3495 | 0.286 | 0.4150 | 0.7079 | 0.4047 |
|
78 |
+
| 0.159 | 21.0 | 10500 | 0.3599 | 0.2859 | 0.4067 | 0.7093 | 0.3973 |
|
79 |
+
| 0.1548 | 22.0 | 11000 | 0.3564 | 0.2863 | 0.4061 | 0.7139 | 0.3980 |
|
80 |
+
| 0.1492 | 23.0 | 11500 | 0.3587 | 0.2864 | 0.4081 | 0.7132 | 0.3994 |
|
81 |
+
| 0.1433 | 24.0 | 12000 | 0.3607 | 0.2867 | 0.4110 | 0.7148 | 0.4022 |
|
82 |
+
| 0.1379 | 25.0 | 12500 | 0.3593 | 0.2871 | 0.4133 | 0.7147 | 0.4045 |
|
83 |
+
| 0.1336 | 26.0 | 13000 | 0.3689 | 0.2866 | 0.4062 | 0.7164 | 0.3986 |
|
84 |
+
| 0.1296 | 27.0 | 13500 | 0.3656 | 0.2872 | 0.4056 | 0.7207 | 0.3996 |
|
85 |
+
| 0.1264 | 28.0 | 14000 | 0.3695 | 0.2871 | 0.4104 | 0.7177 | 0.4029 |
|
86 |
+
| 0.1223 | 29.0 | 14500 | 0.3700 | 0.2871 | 0.4113 | 0.7185 | 0.4041 |
|
87 |
+
| 0.119 | 30.0 | 15000 | 0.3732 | 0.2872 | 0.4086 | 0.7206 | 0.4016 |
|
88 |
+
| 0.115 | 31.0 | 15500 | 0.3765 | 0.2873 | 0.4096 | 0.7198 | 0.4030 |
|
89 |
+
| 0.1126 | 32.0 | 16000 | 0.3738 | 0.2878 | 0.4095 | 0.7239 | 0.4040 |
|
90 |
+
| 0.11 | 33.0 | 16500 | 0.3825 | 0.2874 | 0.4069 | 0.7224 | 0.4007 |
|
91 |
+
| 0.1071 | 34.0 | 17000 | 0.3857 | 0.2874 | 0.4029 | 0.7243 | 0.3976 |
|
92 |
+
| 0.105 | 35.0 | 17500 | 0.3871 | 0.2874 | 0.4069 | 0.7230 | 0.4008 |
|
93 |
+
| 0.104 | 36.0 | 18000 | 0.3872 | 0.2875 | 0.4046 | 0.7254 | 0.3997 |
|
94 |
+
| 0.1021 | 37.0 | 18500 | 0.3890 | 0.2876 | 0.4063 | 0.7236 | 0.4006 |
|
95 |
+
| 0.0997 | 38.0 | 19000 | 0.3886 | 0.2877 | 0.4067 | 0.7259 | 0.4017 |
|
96 |
+
| 0.0982 | 39.0 | 19500 | 0.3909 | 0.2877 | 0.4084 | 0.7238 | 0.4027 |
|
97 |
+
| 0.0964 | 40.0 | 20000 | 0.3951 | 0.2877 | 0.4076 | 0.7245 | 0.4019 |
|
98 |
+
| 0.0948 | 41.0 | 20500 | 0.3945 | 0.2879 | 0.4064 | 0.7258 | 0.4011 |
|
99 |
+
| 0.0941 | 42.0 | 21000 | 0.3919 | 0.2881 | 0.4096 | 0.7267 | 0.4044 |
|
100 |
+
| 0.0932 | 43.0 | 21500 | 0.3937 | 0.2879 | 0.4066 | 0.7262 | 0.4014 |
|
101 |
+
| 0.0922 | 44.0 | 22000 | 0.3965 | 0.2879 | 0.4091 | 0.7261 | 0.4038 |
|
102 |
+
| 0.0908 | 45.0 | 22500 | 0.3977 | 0.2880 | 0.4061 | 0.7271 | 0.4013 |
|
103 |
+
| 0.09 | 46.0 | 23000 | 0.3977 | 0.2880 | 0.4063 | 0.7263 | 0.4014 |
|
104 |
+
| 0.0906 | 47.0 | 23500 | 0.3978 | 0.2880 | 0.4051 | 0.7274 | 0.4005 |
|
105 |
+
| 0.0893 | 48.0 | 24000 | 0.3981 | 0.2881 | 0.4063 | 0.7269 | 0.4015 |
|
106 |
+
| 0.0887 | 49.0 | 24500 | 0.3982 | 0.2881 | 0.4067 | 0.7262 | 0.4017 |
|
107 |
+
| 0.0883 | 50.0 | 25000 | 0.3983 | 0.2881 | 0.4062 | 0.7266 | 0.4014 |
|
108 |
+
|
109 |
+
|
110 |
+
### Framework versions
|
111 |
+
|
112 |
+
- Transformers 4.41.1
|
113 |
+
- Pytorch 2.2.1
|
114 |
+
- Datasets 2.19.1
|
115 |
+
- Tokenizers 0.19.1
|
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": "LABEL_0",
|
14 |
+
"1": "LABEL_1",
|
15 |
+
"2": "LABEL_2",
|
16 |
+
"3": "LABEL_3",
|
17 |
+
"4": "LABEL_4",
|
18 |
+
"5": "LABEL_5",
|
19 |
+
"6": "LABEL_6"
|
20 |
+
},
|
21 |
+
"initializer_range": 0.02,
|
22 |
+
"intermediate_size": 3072,
|
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 |
+
},
|
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": "4.41.1",
|
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:a3833c339e390d0231d696dccea69242358bfba71e919fe71ecf2f66b098934e
|
3 |
+
size 709096284
|
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 sha256:4e0a18ac206be27384db0c37b73d28dfb7234db3ffd5d5ad052690c1fef319c8
|
3 |
+
size 5176
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|