add model
Browse files- .gitignore +1 -0
- README.md +74 -0
- config.json +58 -0
- pytorch_model.bin +3 -0
- runs/Dec11_18-11-58_DESKTOP-GRC5L8E/1639246327.399495/events.out.tfevents.1639246327.DESKTOP-GRC5L8E.15736.1 +3 -0
- runs/Dec11_18-11-58_DESKTOP-GRC5L8E/events.out.tfevents.1639246327.DESKTOP-GRC5L8E.15736.0 +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
README.md
ADDED
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
metrics:
|
6 |
+
- precision
|
7 |
+
- recall
|
8 |
+
- f1
|
9 |
+
- accuracy
|
10 |
+
model_index:
|
11 |
+
- name: portuguese-archival-finding-aids
|
12 |
+
results:
|
13 |
+
- task:
|
14 |
+
name: Token Classification
|
15 |
+
type: token-classification
|
16 |
+
metric:
|
17 |
+
name: Accuracy
|
18 |
+
type: accuracy
|
19 |
+
value: 0.9617770479839446
|
20 |
+
---
|
21 |
+
|
22 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
23 |
+
should probably proofread and complete it, then remove this comment. -->
|
24 |
+
|
25 |
+
# portuguese-archival-finding-aids
|
26 |
+
|
27 |
+
This model is a fine-tuned version of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) on an unkown dataset.
|
28 |
+
It achieves the following results on the evaluation set:
|
29 |
+
- Loss: 0.1812
|
30 |
+
- Precision: 0.8624
|
31 |
+
- Recall: 0.9557
|
32 |
+
- F1: 0.9067
|
33 |
+
- Accuracy: 0.9618
|
34 |
+
|
35 |
+
## Model description
|
36 |
+
|
37 |
+
More information needed
|
38 |
+
|
39 |
+
## Intended uses & limitations
|
40 |
+
|
41 |
+
More information needed
|
42 |
+
|
43 |
+
## Training and evaluation data
|
44 |
+
|
45 |
+
More information needed
|
46 |
+
|
47 |
+
## Training procedure
|
48 |
+
|
49 |
+
### Training hyperparameters
|
50 |
+
|
51 |
+
The following hyperparameters were used during training:
|
52 |
+
- learning_rate: 2e-05
|
53 |
+
- train_batch_size: 16
|
54 |
+
- eval_batch_size: 16
|
55 |
+
- seed: 42
|
56 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
57 |
+
- lr_scheduler_type: linear
|
58 |
+
- num_epochs: 3
|
59 |
+
|
60 |
+
### Training results
|
61 |
+
|
62 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
63 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
64 |
+
| No log | 1.0 | 192 | 0.1565 | 0.8511 | 0.9327 | 0.8900 | 0.9563 |
|
65 |
+
| 0.1849 | 2.0 | 384 | 0.1594 | 0.8634 | 0.9543 | 0.9065 | 0.9619 |
|
66 |
+
| 0.0454 | 3.0 | 576 | 0.1812 | 0.8624 | 0.9557 | 0.9067 | 0.9618 |
|
67 |
+
|
68 |
+
|
69 |
+
### Framework versions
|
70 |
+
|
71 |
+
- Transformers 4.10.0.dev0
|
72 |
+
- Pytorch 1.9.0+cu111
|
73 |
+
- Datasets 1.10.2
|
74 |
+
- Tokenizers 0.10.3
|
config.json
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"gradient_checkpointing": false,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"id2label": {
|
14 |
+
"0": "LABEL_0",
|
15 |
+
"1": "LABEL_1",
|
16 |
+
"2": "LABEL_2",
|
17 |
+
"3": "LABEL_3",
|
18 |
+
"4": "LABEL_4",
|
19 |
+
"5": "LABEL_5",
|
20 |
+
"6": "LABEL_6",
|
21 |
+
"7": "LABEL_7",
|
22 |
+
"8": "LABEL_8",
|
23 |
+
"9": "LABEL_9",
|
24 |
+
"10": "LABEL_10"
|
25 |
+
},
|
26 |
+
"initializer_range": 0.02,
|
27 |
+
"intermediate_size": 3072,
|
28 |
+
"label2id": {
|
29 |
+
"LABEL_0": 0,
|
30 |
+
"LABEL_1": 1,
|
31 |
+
"LABEL_10": 10,
|
32 |
+
"LABEL_2": 2,
|
33 |
+
"LABEL_3": 3,
|
34 |
+
"LABEL_4": 4,
|
35 |
+
"LABEL_5": 5,
|
36 |
+
"LABEL_6": 6,
|
37 |
+
"LABEL_7": 7,
|
38 |
+
"LABEL_8": 8,
|
39 |
+
"LABEL_9": 9
|
40 |
+
},
|
41 |
+
"layer_norm_eps": 1e-12,
|
42 |
+
"max_position_embeddings": 512,
|
43 |
+
"model_type": "bert",
|
44 |
+
"num_attention_heads": 12,
|
45 |
+
"num_hidden_layers": 12,
|
46 |
+
"pad_token_id": 0,
|
47 |
+
"pooler_fc_size": 768,
|
48 |
+
"pooler_num_attention_heads": 12,
|
49 |
+
"pooler_num_fc_layers": 3,
|
50 |
+
"pooler_size_per_head": 128,
|
51 |
+
"pooler_type": "first_token_transform",
|
52 |
+
"position_embedding_type": "absolute",
|
53 |
+
"torch_dtype": "float32",
|
54 |
+
"transformers_version": "4.10.0.dev0",
|
55 |
+
"type_vocab_size": 2,
|
56 |
+
"use_cache": true,
|
57 |
+
"vocab_size": 119547
|
58 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4f7d5c70b0d90d5a76ceb6b988b8400020be36c31d664e49229f89d89d82bead
|
3 |
+
size 709168625
|
runs/Dec11_18-11-58_DESKTOP-GRC5L8E/1639246327.399495/events.out.tfevents.1639246327.DESKTOP-GRC5L8E.15736.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d1c0e1c7d5fc6390b19d9ecf59a919b64f05240510bf7c85f7237ffafebe189a
|
3 |
+
size 4395
|
runs/Dec11_18-11-58_DESKTOP-GRC5L8E/events.out.tfevents.1639246327.DESKTOP-GRC5L8E.15736.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d7a0608407250626d95c94b7e848f2fe6d12004899880bf520ab5a2b42af1e3e
|
3 |
+
size 5911
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-base-multilingual-cased", "tokenizer_class": "BertTokenizer"}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:37b692d9495b713f0dc13e2653505ac14057a03549de04b9908bc31f2693c9dc
|
3 |
+
size 2799
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|