metadata
library_name: transformers
tags:
- generated_from_trainer
model-index:
- name: copy_transformer
results: []
copy_transformer
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.5053
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: 0.0005
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.1969 | 1.0 | 28 | 2.9179 |
| 2.7683 | 2.0 | 56 | 2.7478 |
| 2.6335 | 3.0 | 84 | 2.6892 |
| 2.5881 | 4.0 | 112 | 2.6336 |
| 2.5281 | 5.0 | 140 | 2.5946 |
| 2.4957 | 6.0 | 168 | 2.5674 |
| 2.4613 | 7.0 | 196 | 2.5412 |
| 2.4172 | 8.0 | 224 | 2.5212 |
| 2.3997 | 9.0 | 252 | 2.5105 |
| 2.361 | 10.0 | 280 | 2.5053 |
Framework versions
- Transformers 4.50.0.dev0
- Pytorch 2.5.1+cxx11.abi
- Datasets 3.4.0
- Tokenizers 0.21.1