xlm-roberta-base-english-sentweet-sentiment
This model is a fine-tuned version of xlm-roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5227
- Accuracy: 0.8090
- Precision: 0.8294
- Recall: 0.8176
- F1: 0.8082
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: 5e-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: 6
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 81 | 0.5108 | 0.7708 | 0.7955 | 0.7804 | 0.7692 |
| No log | 2.0 | 162 | 0.5028 | 0.7882 | 0.8054 | 0.7961 | 0.7875 |
| No log | 3.0 | 243 | 0.4881 | 0.7847 | 0.8102 | 0.7943 | 0.7832 |
| No log | 4.0 | 324 | 0.4914 | 0.8090 | 0.8248 | 0.8166 | 0.8085 |
| No log | 5.0 | 405 | 0.5390 | 0.8090 | 0.8248 | 0.8166 | 0.8085 |
| No log | 6.0 | 486 | 0.5227 | 0.8090 | 0.8294 | 0.8176 | 0.8082 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.13.1+cu117
- Datasets 2.6.1
- Tokenizers 0.11.0