yuridrcosta
commited on
Commit
•
a63ea78
1
Parent(s):
5d3f660
End of training
Browse files- README.md +90 -0
- config.json +60 -0
- model.safetensors +3 -0
- runs/Jun23_22-27-47_80923a5b03ab/events.out.tfevents.1719181730.80923a5b03ab.954.0 +3 -0
- runs/Jun23_22-32-28_80923a5b03ab/events.out.tfevents.1719181957.80923a5b03ab.954.1 +3 -0
- runs/Jun23_22-40-10_80923a5b03ab/events.out.tfevents.1719182420.80923a5b03ab.954.2 +3 -0
- runs/Jun23_22-40-10_80923a5b03ab/events.out.tfevents.1719183488.80923a5b03ab.954.3 +3 -0
- special_tokens_map.json +13 -0
- tokenizer.json +0 -0
- tokenizer_config.json +56 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,90 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: google-bert/bert-base-uncased
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- precision
|
8 |
+
- recall
|
9 |
+
- f1
|
10 |
+
- accuracy
|
11 |
+
model-index:
|
12 |
+
- name: bert-base-uncased-finetuned-ner
|
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-base-uncased-finetuned-ner
|
20 |
+
|
21 |
+
This model is a fine-tuned version of [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) on an unknown dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.7238
|
24 |
+
- Precision: 0.3864
|
25 |
+
- Recall: 0.2742
|
26 |
+
- F1: 0.3208
|
27 |
+
- Accuracy: 0.9134
|
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: 5e-05
|
47 |
+
- train_batch_size: 32
|
48 |
+
- eval_batch_size: 32
|
49 |
+
- seed: 42
|
50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
+
- lr_scheduler_type: linear
|
52 |
+
- num_epochs: 25
|
53 |
+
|
54 |
+
### Training results
|
55 |
+
|
56 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
57 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
58 |
+
| No log | 1.0 | 16 | 0.6017 | 0.4286 | 0.2258 | 0.2958 | 0.9187 |
|
59 |
+
| No log | 2.0 | 32 | 0.6134 | 0.3311 | 0.2688 | 0.2967 | 0.9075 |
|
60 |
+
| No log | 3.0 | 48 | 0.5969 | 0.3525 | 0.2634 | 0.3015 | 0.9096 |
|
61 |
+
| No log | 4.0 | 64 | 0.6446 | 0.3208 | 0.2742 | 0.2957 | 0.9071 |
|
62 |
+
| No log | 5.0 | 80 | 0.6219 | 0.4182 | 0.2473 | 0.3108 | 0.9176 |
|
63 |
+
| No log | 6.0 | 96 | 0.6519 | 0.3401 | 0.2688 | 0.3003 | 0.9103 |
|
64 |
+
| No log | 7.0 | 112 | 0.6576 | 0.3551 | 0.2634 | 0.3025 | 0.9120 |
|
65 |
+
| No log | 8.0 | 128 | 0.6534 | 0.3676 | 0.2688 | 0.3106 | 0.9106 |
|
66 |
+
| No log | 9.0 | 144 | 0.6522 | 0.3732 | 0.2849 | 0.3232 | 0.9124 |
|
67 |
+
| No log | 10.0 | 160 | 0.6879 | 0.3503 | 0.2957 | 0.3207 | 0.9078 |
|
68 |
+
| No log | 11.0 | 176 | 0.6825 | 0.3696 | 0.2742 | 0.3148 | 0.9124 |
|
69 |
+
| No log | 12.0 | 192 | 0.7115 | 0.3732 | 0.2849 | 0.3232 | 0.9120 |
|
70 |
+
| No log | 13.0 | 208 | 0.7013 | 0.3984 | 0.2742 | 0.3248 | 0.9138 |
|
71 |
+
| No log | 14.0 | 224 | 0.7016 | 0.3732 | 0.2849 | 0.3232 | 0.9117 |
|
72 |
+
| No log | 15.0 | 240 | 0.7313 | 0.3643 | 0.2742 | 0.3129 | 0.9110 |
|
73 |
+
| No log | 16.0 | 256 | 0.7267 | 0.3442 | 0.2849 | 0.3118 | 0.9082 |
|
74 |
+
| No log | 17.0 | 272 | 0.7159 | 0.3624 | 0.2903 | 0.3224 | 0.9096 |
|
75 |
+
| No log | 18.0 | 288 | 0.6946 | 0.3542 | 0.2742 | 0.3091 | 0.9099 |
|
76 |
+
| No log | 19.0 | 304 | 0.7017 | 0.3852 | 0.2796 | 0.3240 | 0.9127 |
|
77 |
+
| No log | 20.0 | 320 | 0.7229 | 0.3467 | 0.2796 | 0.3095 | 0.9089 |
|
78 |
+
| No log | 21.0 | 336 | 0.7188 | 0.3817 | 0.2688 | 0.3155 | 0.9124 |
|
79 |
+
| No log | 22.0 | 352 | 0.7269 | 0.3669 | 0.2742 | 0.3138 | 0.9110 |
|
80 |
+
| No log | 23.0 | 368 | 0.7248 | 0.3714 | 0.2796 | 0.3190 | 0.9113 |
|
81 |
+
| No log | 24.0 | 384 | 0.7235 | 0.3835 | 0.2742 | 0.3197 | 0.9131 |
|
82 |
+
| No log | 25.0 | 400 | 0.7238 | 0.3864 | 0.2742 | 0.3208 | 0.9134 |
|
83 |
+
|
84 |
+
|
85 |
+
### Framework versions
|
86 |
+
|
87 |
+
- Transformers 4.41.2
|
88 |
+
- Pytorch 2.3.0+cu121
|
89 |
+
- Datasets 2.20.0
|
90 |
+
- Tokenizers 0.19.1
|
config.json
ADDED
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google-bert/bert-base-uncased",
|
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": "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 |
+
"7": "LABEL_7",
|
21 |
+
"8": "LABEL_8",
|
22 |
+
"9": "LABEL_9",
|
23 |
+
"10": "LABEL_10",
|
24 |
+
"11": "LABEL_11",
|
25 |
+
"12": "LABEL_12",
|
26 |
+
"13": "LABEL_13",
|
27 |
+
"14": "LABEL_14"
|
28 |
+
},
|
29 |
+
"initializer_range": 0.02,
|
30 |
+
"intermediate_size": 3072,
|
31 |
+
"label2id": {
|
32 |
+
"LABEL_0": 0,
|
33 |
+
"LABEL_1": 1,
|
34 |
+
"LABEL_10": 10,
|
35 |
+
"LABEL_11": 11,
|
36 |
+
"LABEL_12": 12,
|
37 |
+
"LABEL_13": 13,
|
38 |
+
"LABEL_14": 14,
|
39 |
+
"LABEL_2": 2,
|
40 |
+
"LABEL_3": 3,
|
41 |
+
"LABEL_4": 4,
|
42 |
+
"LABEL_5": 5,
|
43 |
+
"LABEL_6": 6,
|
44 |
+
"LABEL_7": 7,
|
45 |
+
"LABEL_8": 8,
|
46 |
+
"LABEL_9": 9
|
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 |
+
"position_embedding_type": "absolute",
|
55 |
+
"torch_dtype": "float32",
|
56 |
+
"transformers_version": "4.41.2",
|
57 |
+
"type_vocab_size": 2,
|
58 |
+
"use_cache": true,
|
59 |
+
"vocab_size": 30522
|
60 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:58a2fdcbdfcd888fc7820abfa9a6c9faeb5113136e26cb7dbe615faa0a047d25
|
3 |
+
size 435636076
|
runs/Jun23_22-27-47_80923a5b03ab/events.out.tfevents.1719181730.80923a5b03ab.954.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:492ca74f5dd7767732be52997c24f46173835b824a4217452db960a3ad83760c
|
3 |
+
size 10499
|
runs/Jun23_22-32-28_80923a5b03ab/events.out.tfevents.1719181957.80923a5b03ab.954.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e439a318763d290eb150e76449b297b5ce0a6589f61c378078fe713303484381
|
3 |
+
size 15219
|
runs/Jun23_22-40-10_80923a5b03ab/events.out.tfevents.1719182420.80923a5b03ab.954.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bccd927956ddc080785cbc4ec56b05046297fe65ea7f50e0fb4826be9f2c6596
|
3 |
+
size 17579
|
runs/Jun23_22-40-10_80923a5b03ab/events.out.tfevents.1719183488.80923a5b03ab.954.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d9692efbc9268e0d4d1780c1e3dfbccc68e087e956c6dcb92900094d6ab2fd5e
|
3 |
+
size 560
|
special_tokens_map.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": {
|
5 |
+
"content": "[PAD]",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false
|
10 |
+
},
|
11 |
+
"sep_token": "[SEP]",
|
12 |
+
"unk_token": "[UNK]"
|
13 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": true,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "[PAD]",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"100": {
|
13 |
+
"content": "[UNK]",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"101": {
|
21 |
+
"content": "[CLS]",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"102": {
|
29 |
+
"content": "[SEP]",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": false,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
+
},
|
36 |
+
"103": {
|
37 |
+
"content": "[MASK]",
|
38 |
+
"lstrip": false,
|
39 |
+
"normalized": false,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": true
|
43 |
+
}
|
44 |
+
},
|
45 |
+
"clean_up_tokenization_spaces": true,
|
46 |
+
"cls_token": "[CLS]",
|
47 |
+
"do_lower_case": true,
|
48 |
+
"mask_token": "[MASK]",
|
49 |
+
"model_max_length": 512,
|
50 |
+
"pad_token": "[PAD]",
|
51 |
+
"sep_token": "[SEP]",
|
52 |
+
"strip_accents": null,
|
53 |
+
"tokenize_chinese_chars": true,
|
54 |
+
"tokenizer_class": "BertTokenizer",
|
55 |
+
"unk_token": "[UNK]"
|
56 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e35eda349b96be6a00ded64eb078cafebfa044bdf88704b8a98f6acd4df933a2
|
3 |
+
size 5112
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|