update model card README.md
Browse files
README.md
CHANGED
@@ -13,12 +13,12 @@ should probably proofread and complete it, then remove this comment. -->
|
|
13 |
|
14 |
This model is a fine-tuned version of [cardiffnlp/twitter-roberta-base-sentiment](https://huggingface.co/cardiffnlp/twitter-roberta-base-sentiment) on an unknown dataset.
|
15 |
It achieves the following results on the evaluation set:
|
16 |
-
- Loss: 0.
|
17 |
-
- Accuracy@en: 0.
|
18 |
-
- F1@en: 0.
|
19 |
-
- Precision@en: 0.
|
20 |
-
- Recall@en: 0.
|
21 |
-
- Loss@en: 0.
|
22 |
|
23 |
## Model description
|
24 |
|
@@ -43,25 +43,14 @@ The following hyperparameters were used during training:
|
|
43 |
- seed: 42
|
44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
- lr_scheduler_type: linear
|
46 |
-
- num_epochs:
|
47 |
|
48 |
### Training results
|
49 |
|
50 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy@en | F1@en | Precision@en | Recall@en | Loss@en |
|
51 |
|:-------------:|:-----:|:----:|:---------------:|:-----------:|:------:|:------------:|:---------:|:-------:|
|
52 |
-
| 0.
|
53 |
-
| 0.
|
54 |
-
| 0.1342 | 3.0 | 1125 | 0.4022 | 0.9233 | 0.9209 | 0.9194 | 0.9225 | 0.4022 |
|
55 |
-
| 0.0982 | 4.0 | 1500 | 0.4177 | 0.9433 | 0.9418 | 0.9389 | 0.9458 | 0.4177 |
|
56 |
-
| 0.0237 | 5.0 | 1875 | 0.5359 | 0.94 | 0.9386 | 0.9351 | 0.9443 | 0.5359 |
|
57 |
-
| 0.0243 | 6.0 | 2250 | 0.5797 | 0.9233 | 0.9212 | 0.9185 | 0.9251 | 0.5797 |
|
58 |
-
| 0.0377 | 7.0 | 2625 | 0.5550 | 0.94 | 0.9387 | 0.9350 | 0.9456 | 0.5550 |
|
59 |
-
| 0.0001 | 8.0 | 3000 | 0.5920 | 0.9367 | 0.9353 | 0.9316 | 0.9428 | 0.5920 |
|
60 |
-
| 0.0119 | 9.0 | 3375 | 0.5539 | 0.94 | 0.9387 | 0.9350 | 0.9456 | 0.5539 |
|
61 |
-
| 0.0215 | 10.0 | 3750 | 0.5690 | 0.9433 | 0.9420 | 0.9384 | 0.9484 | 0.5690 |
|
62 |
-
| 0.0146 | 11.0 | 4125 | 0.5687 | 0.9433 | 0.9420 | 0.9384 | 0.9484 | 0.5687 |
|
63 |
-
| 0.0001 | 12.0 | 4500 | 0.5718 | 0.94 | 0.9386 | 0.9351 | 0.9443 | 0.5718 |
|
64 |
-
| 0.0091 | 13.0 | 4875 | 0.5869 | 0.9367 | 0.9349 | 0.9321 | 0.9389 | 0.5869 |
|
65 |
|
66 |
|
67 |
### Framework versions
|
|
|
13 |
|
14 |
This model is a fine-tuned version of [cardiffnlp/twitter-roberta-base-sentiment](https://huggingface.co/cardiffnlp/twitter-roberta-base-sentiment) on an unknown dataset.
|
15 |
It achieves the following results on the evaluation set:
|
16 |
+
- Loss: 0.3372
|
17 |
+
- Accuracy@en: 0.89
|
18 |
+
- F1@en: 0.8859
|
19 |
+
- Precision@en: 0.8864
|
20 |
+
- Recall@en: 0.8854
|
21 |
+
- Loss@en: 0.3372
|
22 |
|
23 |
## Model description
|
24 |
|
|
|
43 |
- seed: 42
|
44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
- lr_scheduler_type: linear
|
46 |
+
- num_epochs: 2
|
47 |
|
48 |
### Training results
|
49 |
|
50 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy@en | F1@en | Precision@en | Recall@en | Loss@en |
|
51 |
|:-------------:|:-----:|:----:|:---------------:|:-----------:|:------:|:------------:|:---------:|:-------:|
|
52 |
+
| 0.389 | 1.0 | 375 | 0.3372 | 0.89 | 0.8859 | 0.8864 | 0.8854 | 0.3372 |
|
53 |
+
| 0.2437 | 2.0 | 750 | 0.3435 | 0.9 | 0.8967 | 0.8957 | 0.8977 | 0.3435 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
54 |
|
55 |
|
56 |
### Framework versions
|