quangcodecode
commited on
Commit
•
a1ce33e
1
Parent(s):
4567eea
End of training
Browse files- README.md +74 -0
- added_tokens.json +3 -0
- bpe.codes +0 -0
- config.json +58 -0
- model.safetensors +3 -0
- runs/Dec14_02-44-42_bc0cbd9c575c/events.out.tfevents.1702521901.bc0cbd9c575c.685.0 +3 -0
- runs/Dec14_02-52-20_bc0cbd9c575c/events.out.tfevents.1702522349.bc0cbd9c575c.685.1 +3 -0
- runs/Dec14_02-52-20_bc0cbd9c575c/events.out.tfevents.1702522434.bc0cbd9c575c.685.2 +3 -0
- runs/Dec14_02-58-38_bc0cbd9c575c/events.out.tfevents.1702522726.bc0cbd9c575c.5438.0 +3 -0
- runs/Dec14_02-58-38_bc0cbd9c575c/events.out.tfevents.1702522809.bc0cbd9c575c.5438.1 +3 -0
- runs/Dec14_03-11-09_bc0cbd9c575c/events.out.tfevents.1702523503.bc0cbd9c575c.8703.0 +3 -0
- runs/Dec14_03-11-09_bc0cbd9c575c/events.out.tfevents.1702523584.bc0cbd9c575c.8703.1 +3 -0
- special_tokens_map.json +9 -0
- tokenizer_config.json +54 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: vinai/phobert-base-v2
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
metrics:
|
6 |
+
- precision
|
7 |
+
- recall
|
8 |
+
- f1
|
9 |
+
- accuracy
|
10 |
+
model-index:
|
11 |
+
- name: phobert-base-v2-finetuned-ner-thesis-dseb
|
12 |
+
results: []
|
13 |
+
---
|
14 |
+
|
15 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
16 |
+
should probably proofread and complete it, then remove this comment. -->
|
17 |
+
|
18 |
+
# phobert-base-v2-finetuned-ner-thesis-dseb
|
19 |
+
|
20 |
+
This model is a fine-tuned version of [vinai/phobert-base-v2](https://huggingface.co/vinai/phobert-base-v2) on the None dataset.
|
21 |
+
It achieves the following results on the evaluation set:
|
22 |
+
- Loss: 0.3842
|
23 |
+
- Precision: 0.75
|
24 |
+
- Recall: 0.8329
|
25 |
+
- F1: 0.7893
|
26 |
+
- Accuracy: 0.9491
|
27 |
+
|
28 |
+
## Model description
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Intended uses & limitations
|
33 |
+
|
34 |
+
More information needed
|
35 |
+
|
36 |
+
## Training and evaluation data
|
37 |
+
|
38 |
+
More information needed
|
39 |
+
|
40 |
+
## Training procedure
|
41 |
+
|
42 |
+
### Training hyperparameters
|
43 |
+
|
44 |
+
The following hyperparameters were used during training:
|
45 |
+
- learning_rate: 1e-05
|
46 |
+
- train_batch_size: 32
|
47 |
+
- eval_batch_size: 32
|
48 |
+
- seed: 42
|
49 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
50 |
+
- lr_scheduler_type: linear
|
51 |
+
- num_epochs: 10
|
52 |
+
|
53 |
+
### Training results
|
54 |
+
|
55 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
56 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
57 |
+
| 2.0671 | 1.0 | 23 | 1.4715 | 0.0 | 0.0 | 0.0 | 0.6125 |
|
58 |
+
| 1.3776 | 2.0 | 46 | 0.9706 | 0.9471 | 0.3860 | 0.5485 | 0.7545 |
|
59 |
+
| 0.9833 | 3.0 | 69 | 0.6568 | 0.8144 | 0.7207 | 0.7647 | 0.9034 |
|
60 |
+
| 0.7423 | 4.0 | 92 | 0.4905 | 0.9215 | 0.9045 | 0.9130 | 0.9595 |
|
61 |
+
| 0.5928 | 5.0 | 115 | 0.3919 | 0.9626 | 0.9517 | 0.9572 | 0.9893 |
|
62 |
+
| 0.4955 | 6.0 | 138 | 0.3377 | 0.9658 | 0.9579 | 0.9619 | 0.9913 |
|
63 |
+
| 0.4013 | 7.0 | 161 | 0.3058 | 0.9658 | 0.9579 | 0.9619 | 0.9915 |
|
64 |
+
| 0.3747 | 8.0 | 184 | 0.2874 | 0.9658 | 0.9579 | 0.9619 | 0.9915 |
|
65 |
+
| 0.3618 | 9.0 | 207 | 0.2781 | 0.9658 | 0.9579 | 0.9619 | 0.9915 |
|
66 |
+
| 0.3477 | 10.0 | 230 | 0.2748 | 0.9658 | 0.9579 | 0.9619 | 0.9915 |
|
67 |
+
|
68 |
+
|
69 |
+
### Framework versions
|
70 |
+
|
71 |
+
- Transformers 4.36.0
|
72 |
+
- Pytorch 2.1.0+cu118
|
73 |
+
- Datasets 2.15.0
|
74 |
+
- Tokenizers 0.15.0
|
added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<mask>": 64000
|
3 |
+
}
|
bpe.codes
ADDED
The diff for this file is too large to render.
See raw diff
|
|
config.json
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "vinai/phobert-base-v2",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"id2label": {
|
14 |
+
"0": "O",
|
15 |
+
"1": "B-NAME",
|
16 |
+
"2": "I-NAME",
|
17 |
+
"3": "B-DATE",
|
18 |
+
"4": "I-DATE",
|
19 |
+
"5": "B-UNI",
|
20 |
+
"6": "I-UNI",
|
21 |
+
"7": "B-MAJ",
|
22 |
+
"8": "I-MAJ",
|
23 |
+
"9": "B-MAIL",
|
24 |
+
"10": "I-MAIL",
|
25 |
+
"11": "B-UNI_ABRREV",
|
26 |
+
"12": "I-PHONE"
|
27 |
+
},
|
28 |
+
"initializer_range": 0.02,
|
29 |
+
"intermediate_size": 3072,
|
30 |
+
"label2id": {
|
31 |
+
"B-DATE": 3,
|
32 |
+
"B-MAIL": 9,
|
33 |
+
"B-MAJ": 7,
|
34 |
+
"B-NAME": 1,
|
35 |
+
"B-UNI": 5,
|
36 |
+
"B-UNI_ABBREV": 11,
|
37 |
+
"I-DATE": 4,
|
38 |
+
"I-MAIL": 10,
|
39 |
+
"I-MAJ": 8,
|
40 |
+
"I-NAME": 2,
|
41 |
+
"I-PHONE": 12,
|
42 |
+
"I-UNI": 6,
|
43 |
+
"O": 0
|
44 |
+
},
|
45 |
+
"layer_norm_eps": 1e-05,
|
46 |
+
"max_position_embeddings": 258,
|
47 |
+
"model_type": "roberta",
|
48 |
+
"num_attention_heads": 12,
|
49 |
+
"num_hidden_layers": 12,
|
50 |
+
"pad_token_id": 1,
|
51 |
+
"position_embedding_type": "absolute",
|
52 |
+
"tokenizer_class": "PhobertTokenizer",
|
53 |
+
"torch_dtype": "float32",
|
54 |
+
"transformers_version": "4.36.0",
|
55 |
+
"type_vocab_size": 1,
|
56 |
+
"use_cache": true,
|
57 |
+
"vocab_size": 64001
|
58 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ec2db9950429b5964da50fea79d2b99f3007c48761308373344b3e66c5006443
|
3 |
+
size 537694636
|
runs/Dec14_02-44-42_bc0cbd9c575c/events.out.tfevents.1702521901.bc0cbd9c575c.685.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ab8093aab4b40b1ca50b83d8b34b0cc9aaca8aa4a0bc8bf560c0cdace0ea5a94
|
3 |
+
size 7174
|
runs/Dec14_02-52-20_bc0cbd9c575c/events.out.tfevents.1702522349.bc0cbd9c575c.685.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b5e1ca06eae4bcc5894db0ab24e07a62e6c58f2d2fccb5f7c61b25109cb3a09e
|
3 |
+
size 11753
|
runs/Dec14_02-52-20_bc0cbd9c575c/events.out.tfevents.1702522434.bc0cbd9c575c.685.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4de13822e6ab8b5a7b3dff0758f9f92ccf19a84959ba5fc4f8a418dc03e8a736
|
3 |
+
size 560
|
runs/Dec14_02-58-38_bc0cbd9c575c/events.out.tfevents.1702522726.bc0cbd9c575c.5438.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7f2ab6d99a173c81f80b06d1fbcd24f39beec76b91a3e4ef4b15fa888b512ece
|
3 |
+
size 11753
|
runs/Dec14_02-58-38_bc0cbd9c575c/events.out.tfevents.1702522809.bc0cbd9c575c.5438.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e6c59fcc1b9a4f3cdf5412b48bb07282902fea0edbcf9a6d3a84a74407f054ea
|
3 |
+
size 560
|
runs/Dec14_03-11-09_bc0cbd9c575c/events.out.tfevents.1702523503.bc0cbd9c575c.8703.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e7ce5203df5b5785af656e4825a6867a80c85a0348eac97f1bbe424965b07c9a
|
3 |
+
size 11753
|
runs/Dec14_03-11-09_bc0cbd9c575c/events.out.tfevents.1702523584.bc0cbd9c575c.8703.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:081bb6d542289b8affd82f6ddff829a069c36829346daf1c11916ea4b43311d2
|
3 |
+
size 1032
|
special_tokens_map.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": "<mask>",
|
6 |
+
"pad_token": "<pad>",
|
7 |
+
"sep_token": "</s>",
|
8 |
+
"unk_token": "<unk>"
|
9 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<s>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<pad>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "</s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "<unk>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"64000": {
|
36 |
+
"content": "<mask>",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"bos_token": "<s>",
|
45 |
+
"clean_up_tokenization_spaces": true,
|
46 |
+
"cls_token": "<s>",
|
47 |
+
"eos_token": "</s>",
|
48 |
+
"mask_token": "<mask>",
|
49 |
+
"model_max_length": 1000000000000000019884624838656,
|
50 |
+
"pad_token": "<pad>",
|
51 |
+
"sep_token": "</s>",
|
52 |
+
"tokenizer_class": "PhobertTokenizer",
|
53 |
+
"unk_token": "<unk>"
|
54 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f65e4fca5a4364f9407e7a86ca40d99ecbd33dd376273f6c6c929e0da7dcfa49
|
3 |
+
size 4728
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|