|
--- |
|
license: bigscience-bloom-rail-1.0 |
|
library_name: peft |
|
tags: |
|
- trl |
|
- sft |
|
- generated_from_trainer |
|
base_model: bigscience/bloomz-560m |
|
model-index: |
|
- name: Model-text-generation |
|
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. --> |
|
|
|
# Model-text-generation |
|
|
|
This model is a fine-tuned version of [bigscience/bloomz-560m](https://huggingface.co./bigscience/bloomz-560m) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 3.6440 |
|
|
|
## 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: 1.41e-05 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 8 |
|
- total_train_batch_size: 64 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- num_epochs: 5 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 3.6532 | 1.0 | 984 | 3.6657 | |
|
| 3.6527 | 2.0 | 1968 | 3.6518 | |
|
| 3.6301 | 3.0 | 2953 | 3.6462 | |
|
| 3.6279 | 4.0 | 3937 | 3.6442 | |
|
| 3.6385 | 5.0 | 4920 | 3.6440 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.7.1 |
|
- Transformers 4.36.2 |
|
- Pytorch 2.0.0 |
|
- Datasets 2.15.0 |
|
- Tokenizers 0.15.0 |
