|
--- |
|
license: bigscience-bloom-rail-1.0 |
|
tags: |
|
- generated_from_trainer |
|
datasets: cmotions/Beatles_lyrics |
|
widget: |
|
- text: Last night I couldn't sleep |
|
example_title: Sleep |
|
- text: It hasn't rained in weeks |
|
example_title: Rain |
|
model-index: |
|
- name: BLOOM-350m-Beatles-Lyrics-finetuned-newlyrics |
|
results: [] |
|
--- |
|
|
|
# BLOOM-350m-Beatles-Lyrics-finetuned-newlyrics |
|
|
|
This model is a fine-tuned version of [bigscience/bloom-350m](https://huggingface.co/bigscience/bloom-350m) on the [Cmotions - Beatles lyrics](https://huggingface.co/datasets/cmotions/Beatles_lyrics) dataset. It will complete an input prompt with Beatles-like text. |
|
|
|
## 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: 1 |
|
- eval_batch_size: 1 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 100 |
|
- num_epochs: 5 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 3.1135 | 1.0 | 138 | 3.4852 | |
|
| 2.0717 | 2.0 | 276 | 3.8820 | |
|
| 1.3296 | 3.0 | 414 | 3.6281 | |
|
| 0.8146 | 4.0 | 552 | 3.8985 | |
|
| 0.477 | 5.0 | 690 | 4.0317 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.20.1 |
|
- Pytorch 1.11.0+cu113 |
|
- Datasets 2.3.2 |
|
- Tokenizers 0.12.1 |
|
|
