adamjweintraut's picture
bart-finetuned-kwsylgen-64-Rerun
2618291 verified
|
raw
history blame
1.64 kB
---
license: apache-2.0
base_model: adamjweintraut/bart-finetuned-lyrlen-64-lines
tags:
- generated_from_trainer
model-index:
- name: bart-finetuned-kwsylgen-64-Rerun
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# bart-finetuned-kwsylgen-64-Rerun
This model is a fine-tuned version of [adamjweintraut/bart-finetuned-lyrlen-64-lines](https://huggingface.co/adamjweintraut/bart-finetuned-lyrlen-64-lines) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4231
## 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-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 0.4862 | 0.18 | 500 | 0.4553 |
| 0.4128 | 0.36 | 1000 | 0.4430 |
| 0.3923 | 0.54 | 1500 | 0.4311 |
| 0.3789 | 0.72 | 2000 | 0.4255 |
| 0.3722 | 0.9 | 2500 | 0.4231 |
### Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2