Hugging Face's logo

lucaordronneau
/
twitter-roberta-base-sentiment-latest-finetuned-FG-SINGLE_SENTENCE-NEWS

Text Classification
Transformers
PyTorch
TensorBoard
roberta
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
2
lucaordronneau commited on
Commit
8a58a10
•
1 Parent(s): 36a61b8

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +25 -25
README.md CHANGED
@@ -16,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [cardiffnlp/twitter-roberta-base-sentiment-latest](https://huggingface.co/cardiffnlp/twitter-roberta-base-sentiment-latest) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 3.0009
20
- - Accuracy: 0.5817
21
- - F1: 0.5806
22
 
23
  ## Model description
24
 
@@ -38,8 +38,8 @@ More information needed
38
 
39
  The following hyperparameters were used during training:
40
  - learning_rate: 6e-05
41
- - train_batch_size: 64
42
- - eval_batch_size: 64
43
  - seed: 42
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
@@ -49,26 +49,26 @@ The following hyperparameters were used during training:
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
51
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
52
- | No log | 1.0 | 99 | 1.0432 | 0.4494 | 0.3552 |
53
- | No log | 2.0 | 198 | 1.0374 | 0.4700 | 0.4141 |
54
- | No log | 3.0 | 297 | 0.9865 | 0.5202 | 0.5092 |
55
- | No log | 4.0 | 396 | 1.1032 | 0.5483 | 0.5267 |
56
- | No log | 5.0 | 495 | 1.3364 | 0.5490 | 0.5358 |
57
- | 0.8401 | 6.0 | 594 | 1.4154 | 0.5506 | 0.5484 |
58
- | 0.8401 | 7.0 | 693 | 1.6709 | 0.5627 | 0.5621 |
59
- | 0.8401 | 8.0 | 792 | 1.9323 | 0.5452 | 0.5460 |
60
- | 0.8401 | 9.0 | 891 | 1.9337 | 0.5574 | 0.5595 |
61
- | 0.8401 | 10.0 | 990 | 2.0417 | 0.5589 | 0.5535 |
62
- | 0.1967 | 11.0 | 1089 | 2.2161 | 0.5490 | 0.5503 |
63
- | 0.1967 | 12.0 | 1188 | 2.2465 | 0.5627 | 0.5579 |
64
- | 0.1967 | 13.0 | 1287 | 2.4423 | 0.5749 | 0.5718 |
65
- | 0.1967 | 14.0 | 1386 | 2.5506 | 0.5719 | 0.5679 |
66
- | 0.1967 | 15.0 | 1485 | 2.6597 | 0.5802 | 0.5768 |
67
- | 0.0641 | 16.0 | 1584 | 2.8111 | 0.5551 | 0.5552 |
68
- | 0.0641 | 17.0 | 1683 | 2.8681 | 0.5635 | 0.5619 |
69
- | 0.0641 | 18.0 | 1782 | 2.8802 | 0.5817 | 0.5777 |
70
- | 0.0641 | 19.0 | 1881 | 3.0192 | 0.5711 | 0.5699 |
71
- | 0.0641 | 20.0 | 1980 | 3.0009 | 0.5817 | 0.5806 |
72
 
73
 
74
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [cardiffnlp/twitter-roberta-base-sentiment-latest](https://huggingface.co/cardiffnlp/twitter-roberta-base-sentiment-latest) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 3.2822
20
+ - Accuracy: 0.6305
21
+ - F1: 0.6250
22
 
23
  ## Model description
24
 
 
38
 
39
  The following hyperparameters were used during training:
40
  - learning_rate: 6e-05
41
+ - train_batch_size: 32
42
+ - eval_batch_size: 32
43
  - seed: 42
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
 
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
51
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
52
+ | No log | 1.0 | 321 | 0.9646 | 0.5624 | 0.4048 |
53
+ | 0.9537 | 2.0 | 642 | 0.9474 | 0.5644 | 0.4176 |
54
+ | 0.9537 | 3.0 | 963 | 0.9008 | 0.5903 | 0.5240 |
55
+ | 0.858 | 4.0 | 1284 | 0.9939 | 0.5999 | 0.5846 |
56
+ | 0.5908 | 5.0 | 1605 | 1.0947 | 0.6108 | 0.6026 |
57
+ | 0.5908 | 6.0 | 1926 | 1.2507 | 0.5740 | 0.5823 |
58
+ | 0.3676 | 7.0 | 2247 | 1.4717 | 0.6128 | 0.6017 |
59
+ | 0.2246 | 8.0 | 2568 | 1.6726 | 0.5965 | 0.6003 |
60
+ | 0.2246 | 9.0 | 2889 | 1.8041 | 0.6380 | 0.6298 |
61
+ | 0.1468 | 10.0 | 3210 | 1.9796 | 0.6053 | 0.6026 |
62
+ | 0.1161 | 11.0 | 3531 | 2.0988 | 0.6237 | 0.6202 |
63
+ | 0.1161 | 12.0 | 3852 | 2.4171 | 0.5944 | 0.5989 |
64
+ | 0.0916 | 13.0 | 4173 | 2.3326 | 0.6374 | 0.6288 |
65
+ | 0.0916 | 14.0 | 4494 | 2.5472 | 0.6360 | 0.6245 |
66
+ | 0.0661 | 15.0 | 4815 | 2.9127 | 0.6176 | 0.6187 |
67
+ | 0.0454 | 16.0 | 5136 | 2.9133 | 0.6326 | 0.6276 |
68
+ | 0.0454 | 17.0 | 5457 | 3.1299 | 0.6210 | 0.6162 |
69
+ | 0.0337 | 18.0 | 5778 | 3.1828 | 0.6224 | 0.6188 |
70
+ | 0.0223 | 19.0 | 6099 | 3.2655 | 0.6299 | 0.6223 |
71
+ | 0.0223 | 20.0 | 6420 | 3.2822 | 0.6305 | 0.6250 |
72
 
73
 
74
  ### Framework versions