Hugging Face's logo

nguyenanh2803
/
gg-bert-base-uncased

Text Classification
Transformers
Safetensors
xlm-roberta
Generated from Trainer
Model card Files Community
nguyenanh2803 commited on
Commit
05799a9
·
verified ·
1 Parent(s): 2eae350

End of training

Browse files
Files changed (1) hide show
  1. README.md +64 -36
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
- license: mit
3
- base_model: FacebookAI/roberta-large
4
  tags:
5
  - generated_from_trainer
6
  metrics:
@@ -9,24 +9,22 @@ metrics:
9
  - recall
10
  - f1
11
  model-index:
12
- - name: absa-train-service-roberta-large
13
  results: []
14
  ---
15
 
16
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
  should probably proofread and complete it, then remove this comment. -->
18
 
19
- [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/cunho2803032003/absa-1721959498.2993438/runs/tad25dun)
20
- [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/cunho2803032003/absa-1721959940.7872202/runs/bsprskdy)
21
- # absa-train-service-roberta-large
22
 
23
- This model is a fine-tuned version of [FacebookAI/roberta-large](https://huggingface.co/FacebookAI/roberta-large) on the None dataset.
24
  It achieves the following results on the evaluation set:
25
- - Loss: 0.8683
26
- - Accuracy: 0.7424
27
- - Precision: 0.7345
28
- - Recall: 0.7367
29
- - F1: 0.7302
30
 
31
  ## Model description
32
 
@@ -52,37 +50,67 @@ The following hyperparameters were used during training:
52
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
53
  - lr_scheduler_type: linear
54
  - lr_scheduler_warmup_steps: 500
55
- - num_epochs: 20
56
 
57
  ### Training results
58
 
59
- | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
60
- |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
61
- | 2.2255 | 1.0 | 469 | 2.0677 | 0.3296 | 0.1937 | 0.3250 | 0.2297 |
62
- | 1.8236 | 2.0 | 938 | 1.7061 | 0.504 | 0.5413 | 0.4914 | 0.4567 |
63
- | 1.5384 | 3.0 | 1407 | 1.4381 | 0.552 | 0.5944 | 0.5549 | 0.5196 |
64
- | 1.4301 | 4.0 | 1876 | 1.3316 | 0.5984 | 0.6000 | 0.5990 | 0.5618 |
65
- | 1.3776 | 5.0 | 2345 | 1.1645 | 0.6576 | 0.6817 | 0.6491 | 0.6332 |
66
- | 1.2078 | 6.0 | 2814 | 1.0967 | 0.6448 | 0.7035 | 0.6348 | 0.6110 |
67
- | 1.2535 | 7.0 | 3283 | 1.0565 | 0.7008 | 0.7467 | 0.6967 | 0.7066 |
68
- | 1.2921 | 8.0 | 3752 | 1.0049 | 0.6976 | 0.7013 | 0.6884 | 0.6813 |
69
- | 1.178 | 9.0 | 4221 | 1.0438 | 0.648 | 0.7746 | 0.6423 | 0.6387 |
70
- | 1.2324 | 10.0 | 4690 | 1.0203 | 0.6896 | 0.7096 | 0.6831 | 0.6704 |
71
- | 1.1899 | 11.0 | 5159 | 1.0193 | 0.6864 | 0.7391 | 0.6819 | 0.6834 |
72
- | 1.1515 | 12.0 | 5628 | 0.9722 | 0.6944 | 0.7164 | 0.6924 | 0.6860 |
73
- | 1.1604 | 13.0 | 6097 | 0.9372 | 0.7312 | 0.7543 | 0.7311 | 0.7259 |
74
- | 1.1229 | 14.0 | 6566 | 0.9265 | 0.72 | 0.7278 | 0.7139 | 0.7147 |
75
- | 1.1459 | 15.0 | 7035 | 0.8896 | 0.7376 | 0.7264 | 0.7323 | 0.7183 |
76
- | 1.1281 | 16.0 | 7504 | 0.9074 | 0.7152 | 0.7107 | 0.7087 | 0.7012 |
77
- | 1.1794 | 17.0 | 7973 | 0.8914 | 0.7424 | 0.7293 | 0.7354 | 0.7266 |
78
- | 1.1101 | 18.0 | 8442 | 0.8707 | 0.7216 | 0.7161 | 0.7141 | 0.7059 |
79
- | 1.1215 | 19.0 | 8911 | 0.8656 | 0.7408 | 0.7322 | 0.7348 | 0.7274 |
80
- | 1.0483 | 20.0 | 9380 | 0.8683 | 0.7424 | 0.7345 | 0.7367 | 0.7302 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
81
 
82
 
83
  ### Framework versions
84
 
85
- - Transformers 4.43.2
86
  - Pytorch 2.3.1+cu121
87
  - Datasets 2.20.0
88
  - Tokenizers 0.19.1
 
1
  ---
2
+ license: apache-2.0
3
+ base_model: google-bert/bert-base-uncased
4
  tags:
5
  - generated_from_trainer
6
  metrics:
 
9
  - recall
10
  - f1
11
  model-index:
12
+ - name: gg-bert-base-uncased
13
  results: []
14
  ---
15
 
16
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
  should probably proofread and complete it, then remove this comment. -->
18
 
19
+ # gg-bert-base-uncased
 
 
20
 
21
+ This model is a fine-tuned version of [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) on the None dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 1.3042
24
+ - Accuracy: 0.6256
25
+ - Precision: 0.6423
26
+ - Recall: 0.6176
27
+ - F1: 0.5920
28
 
29
  ## Model description
30
 
 
50
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
  - lr_scheduler_type: linear
52
  - lr_scheduler_warmup_steps: 500
53
+ - num_epochs: 50
54
 
55
  ### Training results
56
 
57
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
58
+ |:-------------:|:-----:|:-----:|:---------------:|:--------:|:---------:|:------:|:------:|
59
+ | 2.2916 | 1.0 | 469 | 2.2523 | 0.1248 | 0.1126 | 0.1316 | 0.0648 |
60
+ | 2.1782 | 2.0 | 938 | 2.1328 | 0.3712 | 0.4166 | 0.3539 | 0.3419 |
61
+ | 2.0827 | 3.0 | 1407 | 2.0233 | 0.4 | 0.5060 | 0.3927 | 0.3492 |
62
+ | 2.0142 | 4.0 | 1876 | 1.9946 | 0.384 | 0.4626 | 0.3980 | 0.3605 |
63
+ | 1.9595 | 5.0 | 2345 | 1.8959 | 0.4384 | 0.4411 | 0.4313 | 0.3944 |
64
+ | 1.8538 | 6.0 | 2814 | 1.8370 | 0.4608 | 0.4965 | 0.4545 | 0.4048 |
65
+ | 1.8433 | 7.0 | 3283 | 1.7877 | 0.4752 | 0.4488 | 0.4721 | 0.4176 |
66
+ | 1.8114 | 8.0 | 3752 | 1.7508 | 0.5008 | 0.5705 | 0.4936 | 0.4510 |
67
+ | 1.7872 | 9.0 | 4221 | 1.7364 | 0.464 | 0.4673 | 0.4558 | 0.4401 |
68
+ | 1.7446 | 10.0 | 4690 | 1.6801 | 0.5216 | 0.5153 | 0.5144 | 0.4871 |
69
+ | 1.7021 | 11.0 | 5159 | 1.6621 | 0.5024 | 0.5106 | 0.5007 | 0.4838 |
70
+ | 1.6819 | 12.0 | 5628 | 1.6299 | 0.5504 | 0.5087 | 0.5453 | 0.4962 |
71
+ | 1.6803 | 13.0 | 6097 | 1.6008 | 0.5408 | 0.5580 | 0.5345 | 0.4990 |
72
+ | 1.6591 | 14.0 | 6566 | 1.5753 | 0.56 | 0.6140 | 0.5528 | 0.5174 |
73
+ | 1.5972 | 15.0 | 7035 | 1.5556 | 0.5632 | 0.5939 | 0.5566 | 0.5177 |
74
+ | 1.5749 | 16.0 | 7504 | 1.5304 | 0.5824 | 0.5990 | 0.5708 | 0.5433 |
75
+ | 1.5793 | 17.0 | 7973 | 1.5174 | 0.5664 | 0.6593 | 0.5555 | 0.5065 |
76
+ | 1.569 | 18.0 | 8442 | 1.4926 | 0.5824 | 0.5748 | 0.5704 | 0.5330 |
77
+ | 1.5885 | 19.0 | 8911 | 1.4857 | 0.5776 | 0.6052 | 0.5705 | 0.5333 |
78
+ | 1.5004 | 20.0 | 9380 | 1.4639 | 0.5952 | 0.5878 | 0.5836 | 0.5496 |
79
+ | 1.5046 | 21.0 | 9849 | 1.4582 | 0.5904 | 0.5969 | 0.5846 | 0.5593 |
80
+ | 1.5247 | 22.0 | 10318 | 1.4497 | 0.584 | 0.6200 | 0.5738 | 0.5464 |
81
+ | 1.5079 | 23.0 | 10787 | 1.4411 | 0.5792 | 0.6211 | 0.5729 | 0.5379 |
82
+ | 1.4594 | 24.0 | 11256 | 1.4245 | 0.6032 | 0.5973 | 0.5983 | 0.5763 |
83
+ | 1.4362 | 25.0 | 11725 | 1.4046 | 0.6112 | 0.5904 | 0.6025 | 0.5829 |
84
+ | 1.4554 | 26.0 | 12194 | 1.3992 | 0.6 | 0.5959 | 0.5895 | 0.5661 |
85
+ | 1.4484 | 27.0 | 12663 | 1.3923 | 0.6064 | 0.6297 | 0.5998 | 0.5658 |
86
+ | 1.4666 | 28.0 | 13132 | 1.3787 | 0.6096 | 0.6321 | 0.5971 | 0.5732 |
87
+ | 1.4433 | 29.0 | 13601 | 1.3715 | 0.6112 | 0.6291 | 0.6029 | 0.5732 |
88
+ | 1.4253 | 30.0 | 14070 | 1.3686 | 0.6176 | 0.6069 | 0.6096 | 0.5917 |
89
+ | 1.4928 | 31.0 | 14539 | 1.3635 | 0.6176 | 0.6182 | 0.6103 | 0.5889 |
90
+ | 1.4585 | 32.0 | 15008 | 1.3660 | 0.6016 | 0.6105 | 0.5950 | 0.5655 |
91
+ | 1.3631 | 33.0 | 15477 | 1.3523 | 0.6224 | 0.6451 | 0.6153 | 0.5863 |
92
+ | 1.402 | 34.0 | 15946 | 1.3421 | 0.6192 | 0.6245 | 0.6117 | 0.5797 |
93
+ | 1.416 | 35.0 | 16415 | 1.3425 | 0.6192 | 0.6046 | 0.6139 | 0.5936 |
94
+ | 1.4122 | 36.0 | 16884 | 1.3347 | 0.6192 | 0.6026 | 0.6119 | 0.5916 |
95
+ | 1.361 | 37.0 | 17353 | 1.3325 | 0.6128 | 0.5946 | 0.6045 | 0.5787 |
96
+ | 1.4179 | 38.0 | 17822 | 1.3251 | 0.6128 | 0.6098 | 0.6018 | 0.5783 |
97
+ | 1.3549 | 39.0 | 18291 | 1.3191 | 0.624 | 0.6149 | 0.6150 | 0.5883 |
98
+ | 1.4217 | 40.0 | 18760 | 1.3188 | 0.6272 | 0.6471 | 0.6194 | 0.5935 |
99
+ | 1.3848 | 41.0 | 19229 | 1.3137 | 0.6336 | 0.6261 | 0.6250 | 0.6019 |
100
+ | 1.3956 | 42.0 | 19698 | 1.3141 | 0.632 | 0.6512 | 0.6243 | 0.6008 |
101
+ | 1.3965 | 43.0 | 20167 | 1.3116 | 0.6336 | 0.6523 | 0.6246 | 0.6016 |
102
+ | 1.3523 | 44.0 | 20636 | 1.3076 | 0.6288 | 0.6214 | 0.6204 | 0.5964 |
103
+ | 1.3642 | 45.0 | 21105 | 1.3093 | 0.6256 | 0.6341 | 0.6176 | 0.5921 |
104
+ | 1.3796 | 46.0 | 21574 | 1.3066 | 0.624 | 0.6388 | 0.6159 | 0.5869 |
105
+ | 1.3494 | 47.0 | 22043 | 1.3068 | 0.6272 | 0.6469 | 0.6198 | 0.5958 |
106
+ | 1.3697 | 48.0 | 22512 | 1.3051 | 0.6304 | 0.6369 | 0.6222 | 0.5975 |
107
+ | 1.3977 | 49.0 | 22981 | 1.3044 | 0.6288 | 0.6459 | 0.6208 | 0.5957 |
108
+ | 1.3568 | 50.0 | 23450 | 1.3042 | 0.6256 | 0.6423 | 0.6176 | 0.5920 |
109
 
110
 
111
  ### Framework versions
112
 
113
+ - Transformers 4.43.3
114
  - Pytorch 2.3.1+cu121
115
  - Datasets 2.20.0
116
  - Tokenizers 0.19.1