metadata
license: mit
base_model: mhr2004/plm-nsp-100000
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: base-nsp-100000
results: []
base-nsp-100000
This model is a fine-tuned version of mhr2004/plm-nsp-100000 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8933
- Accuracy: 0.4877
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: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.9735 | 1.0 | 183 | 0.8668 | 0.4811 |
| 0.8972 | 2.0 | 366 | 0.8636 | 0.4784 |
| 0.8381 | 3.0 | 549 | 0.8927 | 0.4613 |
| 0.8088 | 4.0 | 732 | 0.9399 | 0.4586 |
| 0.793 | 5.0 | 915 | 0.9159 | 0.4856 |
| 0.767 | 6.0 | 1098 | 0.9487 | 0.4793 |
| 0.7457 | 7.0 | 1281 | 0.9372 | 0.4946 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1