robbert1010_lrate7.5b32
This model is a fine-tuned version of Tommert25/robbert0410_lrate7.5b32 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5187
- Precisions: 0.8552
- Recall: 0.7999
- F-measure: 0.8232
- Accuracy: 0.9157
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: 7.5e-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 | Precisions | Recall | F-measure | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.0496 | 1.0 | 118 | 0.5283 | 0.8488 | 0.7962 | 0.8132 | 0.9092 |
| 0.0474 | 2.0 | 236 | 0.4726 | 0.7961 | 0.7965 | 0.7931 | 0.9075 |
| 0.026 | 3.0 | 354 | 0.5187 | 0.8552 | 0.7999 | 0.8232 | 0.9157 |
| 0.0145 | 4.0 | 472 | 0.5150 | 0.8372 | 0.7791 | 0.7998 | 0.9116 |
| 0.0088 | 5.0 | 590 | 0.5250 | 0.8372 | 0.7818 | 0.8021 | 0.9141 |
| 0.007 | 6.0 | 708 | 0.5299 | 0.8468 | 0.7849 | 0.8072 | 0.9162 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1