Hugging Face's logo

levancuong17
/
DACN3_LVC

Safetensors
roberta
Generated from Trainer
Model card Files
xet
 Community
levancuong17 commited on
Commit
48af16d
·
verified ·
1 Parent(s): ed546e1

Training complete

Browse files
Files changed (8) hide show
  1. README.md +12 -5
  2. added_tokens.json +3 -0
  3. bpe.codes +0 -0
  4. model.safetensors +1 -1
  5. special_tokens_map.json +1 -7
  6. tokenizer_config.json +8 -11
  7. training_args.bin +1 -1
  8. vocab.txt +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: 1.4884
19
 
20
  ## Model description
21
 
@@ -40,15 +40,22 @@ 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: 3
44
 
45
  ### Training results
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:----:|:---------------:|
49
- | No log | 1.0 | 347 | 1.5072 |
50
- | 1.3952 | 2.0 | 694 | 1.5059 |
51
- | 1.2176 | 3.0 | 1041 | 1.4760 |
 
 
 
 
 
 
 
52
 
53
 
54
  ### 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: 1.5842
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: 10
44
 
45
  ### Training results
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:----:|:---------------:|
49
+ | No log | 1.0 | 347 | 1.7157 |
50
+ | 1.7535 | 2.0 | 694 | 1.6597 |
51
+ | 1.6281 | 3.0 | 1041 | 1.5573 |
52
+ | 1.6281 | 4.0 | 1388 | 1.5429 |
53
+ | 1.4586 | 5.0 | 1735 | 1.5283 |
54
+ | 1.3473 | 6.0 | 2082 | 1.5098 |
55
+ | 1.3473 | 7.0 | 2429 | 1.4875 |
56
+ | 1.2424 | 8.0 | 2776 | 1.5099 |
57
+ | 1.1512 | 9.0 | 3123 | 1.5074 |
58
+ | 1.1512 | 10.0 | 3470 | 1.5196 |
59
 
60
 
61
  ### Framework versions
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
 
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f0d2321114d2c2d5fdaec1a0915816cf9b53840ded1914c440d1f1e93124eb53
3
  size 540038764
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:371877713c814d0aa69ca5e172018bd32eac7d71f38a0c4f8d3e88fc189bd43a
3
  size 540038764
special_tokens_map.json CHANGED
@@ -2,13 +2,7 @@
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>"
 
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>"
tokenizer_config.json CHANGED
@@ -1,10 +1,9 @@
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
@@ -12,7 +11,7 @@
12
  "1": {
13
  "content": "<pad>",
14
  "lstrip": false,
15
- "normalized": true,
16
  "rstrip": false,
17
  "single_word": false,
18
  "special": true
@@ -20,7 +19,7 @@
20
  "2": {
21
  "content": "</s>",
22
  "lstrip": false,
23
- "normalized": true,
24
  "rstrip": false,
25
  "single_word": false,
26
  "special": true
@@ -28,14 +27,14 @@
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,
@@ -46,12 +45,10 @@
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
  }
 
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
  "1": {
12
  "content": "<pad>",
13
  "lstrip": false,
14
+ "normalized": false,
15
  "rstrip": false,
16
  "single_word": false,
17
  "special": true
 
19
  "2": {
20
  "content": "</s>",
21
  "lstrip": false,
22
+ "normalized": false,
23
  "rstrip": false,
24
  "single_word": false,
25
  "special": true
 
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
  "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
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5035b37b1596882c9d2b0369a24b27e57e3b2d497f1a5805cda3a4e04e52047c
3
  size 4536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03e9354ab7d3e547e7cf388f1dae8420a2fc03e8f1babd52044e171808d78c33
3
  size 4536
vocab.txt ADDED
The diff for this file is too large to render. See raw diff