|
--- |
|
license: bigscience-bloom-rail-1.0 |
|
base_model: alonzogarbanzo/Bloom-1b7-dialogsum-Cont-IT-Step4 |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: Bloom-1b7-creative-writing-Cont-IT-Step5 |
|
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. --> |
|
|
|
# Bloom-1b7-creative-writing-Cont-IT-Step5 |
|
|
|
This model is a fine-tuned version of [alonzogarbanzo/Bloom-1b7-dialogsum-Cont-IT-Step4](https://huggingface.co./alonzogarbanzo/Bloom-1b7-dialogsum-Cont-IT-Step4) on an unknown dataset. |
|
|
|
## 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: 8 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 4 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 10 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
Final results: {'loss': 0.0439, 'grad_norm': 1.5330853462219238, 'learning_rate': 3.1914893617021275e-07, 'epoch': 9.89} |
|
|
|
Average results: {'train_runtime': 1120.6953, 'train_samples_per_second': 1.695, 'train_steps_per_second': 0.419, 'train_loss': 0.8163050188663158, 'epoch': 9.89} |
|
|
|
### Framework versions |
|
|
|
- Transformers 4.38.1 |
|
- Pytorch 2.2.0+cu121 |
|
- Datasets 2.17.0 |
|
- Tokenizers 0.15.2 |
|
|
