metadata
license: mit
base_model: roberta-base
tags:
- generated_from_trainer
model-index:
- name: htk-aes-2
results: []
htk-aes-2
This model is a fine-tuned version of roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.8348
- Qwk: 0.7851
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-06
- 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 | Qwk |
|---|---|---|---|---|
| No log | 1.0 | 303 | 0.9556 | 0.6966 |
| 1.1107 | 2.0 | 606 | 0.8401 | 0.7658 |
| 1.1107 | 3.0 | 909 | 0.8261 | 0.7804 |
| 0.8616 | 4.0 | 1212 | 0.8239 | 0.7896 |
| 0.8084 | 5.0 | 1515 | 0.8348 | 0.7851 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2