Hugging Face's logo

levancuong17
/
results

TensorBoard
Safetensors
roberta
Generated from Trainer
Model card Files Metrics Community
levancuong17 commited on
Commit
24d15c4
·
verified ·
1 Parent(s): 0d28b05

Training complete

Browse files
Files changed (8) hide show
  1. README.md +5 -22
  2. merges.txt +0 -0
  3. model.safetensors +1 -1
  4. special_tokens_map.json +7 -1
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +11 -8
  7. training_args.bin +1 -1
  8. vocab.json +0 -0
README.md CHANGED
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [vinai/phobert-base](https://huggingface.co/vinai/phobert-base) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 2.7735
19
 
20
  ## Model description
21
 
@@ -40,32 +40,15 @@ The following hyperparameters were used during training:
40
  - seed: 42
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: linear
43
- - num_epochs: 20
44
 
45
  ### Training results
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:----:|:---------------:|
49
- | No log | 1.0 | 347 | 1.2051 |
50
- | 1.3864 | 2.0 | 694 | 1.1012 |
51
- | 0.8986 | 3.0 | 1041 | 1.0558 |
52
- | 0.8986 | 4.0 | 1388 | 1.1254 |
53
- | 0.6019 | 5.0 | 1735 | 1.4252 |
54
- | 0.3972 | 6.0 | 2082 | 1.5207 |
55
- | 0.3972 | 7.0 | 2429 | 1.6013 |
56
- | 0.2536 | 8.0 | 2776 | 1.8216 |
57
- | 0.1597 | 9.0 | 3123 | 2.0175 |
58
- | 0.1597 | 10.0 | 3470 | 2.0884 |
59
- | 0.1262 | 11.0 | 3817 | 2.3397 |
60
- | 0.0789 | 12.0 | 4164 | 2.4385 |
61
- | 0.0545 | 13.0 | 4511 | 2.5664 |
62
- | 0.0545 | 14.0 | 4858 | 2.6797 |
63
- | 0.0312 | 15.0 | 5205 | 2.7723 |
64
- | 0.032 | 16.0 | 5552 | 2.8236 |
65
- | 0.032 | 17.0 | 5899 | 2.7557 |
66
- | 0.0237 | 18.0 | 6246 | 2.8256 |
67
- | 0.0157 | 19.0 | 6593 | 2.8168 |
68
- | 0.0157 | 20.0 | 6940 | 2.8602 |
69
 
70
 
71
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [vinai/phobert-base](https://huggingface.co/vinai/phobert-base) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 1.5672
19
 
20
  ## Model description
21
 
 
40
  - seed: 42
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: linear
43
+ - num_epochs: 3
44
 
45
  ### Training results
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:----:|:---------------:|
49
+ | No log | 1.0 | 347 | 1.6831 |
50
+ | 1.73 | 2.0 | 694 | 1.5771 |
51
+ | 1.579 | 3.0 | 1041 | 1.5432 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
52
 
53
 
54
  ### Framework versions
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b9fd1ae500ef8a785c6af1b4a0bd79cfedeaeebe29a717b88ef188ae56c76945
3
  size 540038764
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5c73d8ae78b018520f1b3486cca36391c1da668efd922b29c10cf3609728520
3
  size 540038764
special_tokens_map.json CHANGED
@@ -2,7 +2,13 @@
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>"
 
2
  "bos_token": "<s>",
3
  "cls_token": "<s>",
4
  "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
  "pad_token": "<pad>",
13
  "sep_token": "</s>",
14
  "unk_token": "<unk>"
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,9 +1,10 @@
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
@@ -11,7 +12,7 @@
11
  "1": {
12
  "content": "<pad>",
13
  "lstrip": false,
14
- "normalized": false,
15
  "rstrip": false,
16
  "single_word": false,
17
  "special": true
@@ -19,7 +20,7 @@
19
  "2": {
20
  "content": "</s>",
21
  "lstrip": false,
22
- "normalized": false,
23
  "rstrip": false,
24
  "single_word": false,
25
  "special": true
@@ -27,14 +28,14 @@
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,
@@ -45,10 +46,12 @@
45
  "clean_up_tokenization_spaces": true,
46
  "cls_token": "<s>",
47
  "eos_token": "</s>",
 
48
  "mask_token": "<mask>",
49
- "model_max_length": 256,
50
  "pad_token": "<pad>",
51
  "sep_token": "</s>",
52
- "tokenizer_class": "PhobertTokenizer",
 
53
  "unk_token": "<unk>"
54
  }
 
1
  {
2
+ "add_prefix_space": false,
3
  "added_tokens_decoder": {
4
  "0": {
5
  "content": "<s>",
6
  "lstrip": false,
7
+ "normalized": true,
8
  "rstrip": false,
9
  "single_word": false,
10
  "special": true
 
12
  "1": {
13
  "content": "<pad>",
14
  "lstrip": false,
15
+ "normalized": true,
16
  "rstrip": false,
17
  "single_word": false,
18
  "special": true
 
20
  "2": {
21
  "content": "</s>",
22
  "lstrip": false,
23
+ "normalized": true,
24
  "rstrip": false,
25
  "single_word": false,
26
  "special": true
 
28
  "3": {
29
  "content": "<unk>",
30
  "lstrip": false,
31
+ "normalized": true,
32
  "rstrip": false,
33
  "single_word": false,
34
  "special": true
35
  },
36
+ "50264": {
37
  "content": "<mask>",
38
+ "lstrip": true,
39
  "normalized": false,
40
  "rstrip": false,
41
  "single_word": false,
 
46
  "clean_up_tokenization_spaces": true,
47
  "cls_token": "<s>",
48
  "eos_token": "</s>",
49
+ "errors": "replace",
50
  "mask_token": "<mask>",
51
+ "model_max_length": 512,
52
  "pad_token": "<pad>",
53
  "sep_token": "</s>",
54
+ "tokenizer_class": "RobertaTokenizer",
55
+ "trim_offsets": true,
56
  "unk_token": "<unk>"
57
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:96881f394cfa44b064512fb5838114d0d9a17143da019e5ba08fb43d581b8bdb
3
  size 4536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:537fabe3c89dfe34e9ac617891ebd37ab6965e8a1462b1be57f16c8dab26607f
3
  size 4536
vocab.json ADDED
The diff for this file is too large to render. See raw diff