<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
distilbert-base-uncased-sentiment-finetuned-memes
This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.1824
- Accuracy: 0.8270
- Precision: 0.8270
- Recall: 0.8270
- F1: 0.8270
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
---|---|---|---|---|---|---|---|
0.5224 | 1.0 | 4293 | 0.5321 | 0.7720 | 0.8084 | 0.7720 | 0.7721 |
0.4386 | 2.0 | 8586 | 0.4930 | 0.7961 | 0.7980 | 0.7961 | 0.7967 |
0.3722 | 3.0 | 12879 | 0.7652 | 0.7925 | 0.7955 | 0.7925 | 0.7932 |
0.3248 | 4.0 | 17172 | 0.9827 | 0.8045 | 0.8047 | 0.8045 | 0.8023 |
0.308 | 5.0 | 21465 | 0.9518 | 0.8244 | 0.8260 | 0.8244 | 0.8249 |
0.2906 | 6.0 | 25758 | 1.0971 | 0.8155 | 0.8166 | 0.8155 | 0.8159 |
0.2036 | 7.0 | 30051 | 1.1457 | 0.8260 | 0.8271 | 0.8260 | 0.8264 |
0.1747 | 8.0 | 34344 | 1.1824 | 0.8270 | 0.8270 | 0.8270 | 0.8270 |
Framework versions
- Transformers 4.22.1
- Pytorch 1.12.1+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1