metadata
license: apache-2.0
base_model: albert-base-v2
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: ALBERT_trainer_irony
results: []
ALBERT_trainer_irony
This model is a fine-tuned version of albert-base-v2 on the irony dataset. It achieves the following results on the evaluation set:
- Loss: 0.6538
- Accuracy: 0.6327
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: 2e-05
- train_batch_size: 20
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 7
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 144 | 0.7213 | 0.4901 |
| No log | 2.0 | 288 | 0.6935 | 0.5644 |
| No log | 3.0 | 432 | 0.6834 | 0.5906 |
| 0.6892 | 4.0 | 576 | 0.6651 | 0.6031 |
| 0.6892 | 5.0 | 720 | 0.6731 | 0.6063 |
| 0.6892 | 6.0 | 864 | 0.6892 | 0.5958 |
| 0.6185 | 7.0 | 1008 | 0.6750 | 0.6188 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2