Hugging Face's logo

levancuong17
/
DACN3_LVC

Safetensors
roberta
Generated from Trainer
Model card Files
xet
Community
levancuong17 commited on
Commit
44a1cfe
·
verified ·
1 Parent(s): 08a4e8a

Training complete

Browse files
Files changed (3) hide show
  1. README.md +55 -25
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
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: 2.6146
19
 
20
  ## Model description
21
 
@@ -40,37 +40,67 @@ 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 | 1.1922 |
50
- | 1.3869 | 2.0 | 694 | 1.0903 |
51
- | 0.893 | 3.0 | 1041 | 1.0290 |
52
- | 0.893 | 4.0 | 1388 | 1.0825 |
53
- | 0.5968 | 5.0 | 1735 | 1.2634 |
54
- | 0.4001 | 6.0 | 2082 | 1.4108 |
55
- | 0.4001 | 7.0 | 2429 | 1.5288 |
56
- | 0.2505 | 8.0 | 2776 | 1.6623 |
57
- | 0.1639 | 9.0 | 3123 | 1.8938 |
58
- | 0.1639 | 10.0 | 3470 | 2.0609 |
59
- | 0.1143 | 11.0 | 3817 | 2.2725 |
60
- | 0.0739 | 12.0 | 4164 | 2.4275 |
61
- | 0.0552 | 13.0 | 4511 | 2.4773 |
62
- | 0.0552 | 14.0 | 4858 | 2.5629 |
63
- | 0.0389 | 15.0 | 5205 | 2.6769 |
64
- | 0.029 | 16.0 | 5552 | 2.7282 |
65
- | 0.029 | 17.0 | 5899 | 2.7699 |
66
- | 0.0176 | 18.0 | 6246 | 2.7834 |
67
- | 0.0171 | 19.0 | 6593 | 2.8041 |
68
- | 0.0171 | 20.0 | 6940 | 2.7942 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
 
70
 
71
  ### Framework versions
72
 
73
  - Transformers 4.35.2
74
- - Pytorch 2.5.0+cu121
75
  - Datasets 2.16.1
76
  - Tokenizers 0.15.2
 
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: 3.6795
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: 50
44
 
45
  ### Training results
46
 
47
+ | Training Loss | Epoch | Step | Validation Loss |
48
+ |:-------------:|:-----:|:-----:|:---------------:|
49
+ | No log | 1.0 | 347 | 1.6767 |
50
+ | 0.233 | 2.0 | 694 | 1.7635 |
51
+ | 0.189 | 3.0 | 1041 | 1.9054 |
52
+ | 0.189 | 4.0 | 1388 | 2.2254 |
53
+ | 0.1566 | 5.0 | 1735 | 2.1978 |
54
+ | 0.1968 | 6.0 | 2082 | 2.1144 |
55
+ | 0.1968 | 7.0 | 2429 | 2.2885 |
56
+ | 0.1541 | 8.0 | 2776 | 2.3121 |
57
+ | 0.1055 | 9.0 | 3123 | 2.5475 |
58
+ | 0.1055 | 10.0 | 3470 | 2.7483 |
59
+ | 0.09 | 11.0 | 3817 | 2.7914 |
60
+ | 0.0716 | 12.0 | 4164 | 2.9014 |
61
+ | 0.0469 | 13.0 | 4511 | 3.1734 |
62
+ | 0.0469 | 14.0 | 4858 | 3.0398 |
63
+ | 0.0571 | 15.0 | 5205 | 3.3835 |
64
+ | 0.0646 | 16.0 | 5552 | 3.0768 |
65
+ | 0.0646 | 17.0 | 5899 | 3.2561 |
66
+ | 0.0263 | 18.0 | 6246 | 3.3902 |
67
+ | 0.0395 | 19.0 | 6593 | 3.3001 |
68
+ | 0.0395 | 20.0 | 6940 | 3.3090 |
69
+ | 0.0258 | 21.0 | 7287 | 3.3304 |
70
+ | 0.0284 | 22.0 | 7634 | 3.6674 |
71
+ | 0.0284 | 23.0 | 7981 | 3.4840 |
72
+ | 0.0227 | 24.0 | 8328 | 3.5787 |
73
+ | 0.0262 | 25.0 | 8675 | 3.4169 |
74
+ | 0.0263 | 26.0 | 9022 | 3.4694 |
75
+ | 0.0263 | 27.0 | 9369 | 3.5745 |
76
+ | 0.027 | 28.0 | 9716 | 3.5336 |
77
+ | 0.0175 | 29.0 | 10063 | 3.5374 |
78
+ | 0.0175 | 30.0 | 10410 | 3.5704 |
79
+ | 0.0185 | 31.0 | 10757 | 3.5223 |
80
+ | 0.012 | 32.0 | 11104 | 3.4871 |
81
+ | 0.012 | 33.0 | 11451 | 3.6621 |
82
+ | 0.0117 | 34.0 | 11798 | 3.4769 |
83
+ | 0.0106 | 35.0 | 12145 | 3.6008 |
84
+ | 0.0106 | 36.0 | 12492 | 3.8597 |
85
+ | 0.0104 | 37.0 | 12839 | 3.5269 |
86
+ | 0.0076 | 38.0 | 13186 | 3.6466 |
87
+ | 0.0051 | 39.0 | 13533 | 3.6385 |
88
+ | 0.0051 | 40.0 | 13880 | 3.6788 |
89
+ | 0.0069 | 41.0 | 14227 | 3.6508 |
90
+ | 0.0033 | 42.0 | 14574 | 3.6343 |
91
+ | 0.0033 | 43.0 | 14921 | 3.5916 |
92
+ | 0.0033 | 44.0 | 15268 | 3.5940 |
93
+ | 0.0033 | 45.0 | 15615 | 3.5818 |
94
+ | 0.0033 | 46.0 | 15962 | 3.6118 |
95
+ | 0.0024 | 47.0 | 16309 | 3.5790 |
96
+ | 0.0012 | 48.0 | 16656 | 3.5841 |
97
+ | 0.0028 | 49.0 | 17003 | 3.6151 |
98
+ | 0.0028 | 50.0 | 17350 | 3.6149 |
99
 
100
 
101
  ### Framework versions
102
 
103
  - Transformers 4.35.2
104
+ - Pytorch 2.5.1+cu121
105
  - Datasets 2.16.1
106
  - Tokenizers 0.15.2
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b2ee69c6e6bd1d9987d9d6b716b89f710b8782cf1ea8194244967e68ebb661b6
3
  size 540038764
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d65ede1c2212e749ca73d4fd585f444b7c5fafc70b09921400550f9988af7dee
3
  size 540038764
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:983f5c96777b2295b427b021c9c39dba3174c743372360dec694474917ff3e19
3
  size 4536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2840f310c7fe3c245070b7b1f665708a9d71e21d2b467423bafe993a66649bac
3
  size 4536