<!-- 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. -->
correct_twitter_RoBERTa_token_itr0_1e-05_all_01_03_2022-15_36_04
This model is a fine-tuned version of cardiffnlp/twitter-roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2876
- Precision: 0.2345
- Recall: 0.4281
- F1: 0.3030
- Accuracy: 0.8728
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: 1e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 1.0 | 30 | 0.3907 | 0.0433 | 0.0824 | 0.0568 | 0.7626 |
No log | 2.0 | 60 | 0.3046 | 0.2302 | 0.4095 | 0.2947 | 0.8598 |
No log | 3.0 | 90 | 0.2945 | 0.2084 | 0.4095 | 0.2762 | 0.8668 |
No log | 4.0 | 120 | 0.2687 | 0.2847 | 0.4607 | 0.3519 | 0.8761 |
No log | 5.0 | 150 | 0.2643 | 0.2779 | 0.4444 | 0.3420 | 0.8788 |
Framework versions
- Transformers 4.15.0
- Pytorch 1.10.1+cu113
- Datasets 1.18.0
- Tokenizers 0.10.3