ACTio-glu-linear-9L
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2028
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: 0.0003
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: constant
- training_steps: 2000
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.2290 | 0.0135 | 200 | 3.0630 |
| 0.9419 | 0.0270 | 400 | 0.9078 |
| 0.4119 | 0.0404 | 600 | 0.4039 |
| 0.3213 | 0.0539 | 800 | 0.3212 |
| 0.2753 | 0.0674 | 1000 | 0.2748 |
| 0.2577 | 0.0809 | 1200 | 0.2531 |
| 0.2275 | 0.0944 | 1400 | 0.2294 |
| 0.2254 | 0.1079 | 1600 | 0.2337 |
| 0.2096 | 0.1213 | 1800 | 0.2087 |
| 0.2011 | 0.1348 | 2000 | 0.2028 |
Framework versions
- Transformers 5.15.0.dev0
- Pytorch 2.6.0+cu124
- Datasets 5.0.1
- Tokenizers 0.22.2
- Downloads last month
- 312