|
--- |
|
license: bigscience-bloom-rail-1.0 |
|
base_model: bigscience/bloomz-7b1-mt |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: BLOOM_VI |
|
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_VI |
|
|
|
This model is a fine-tuned version of [bigscience/bloomz-7b1-mt](https://huggingface.co/bigscience/bloomz-7b1-mt) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.2309 |
|
|
|
## 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: 0.0003 |
|
- train_batch_size: 4 |
|
- eval_batch_size: 4 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 32 |
|
- total_train_batch_size: 128 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 100 |
|
- num_epochs: 3 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 1.3278 | 0.51 | 200 | 1.3118 | |
|
| 1.2775 | 1.03 | 400 | 1.2715 | |
|
| 1.2464 | 1.54 | 600 | 1.2517 | |
|
| 1.2231 | 2.05 | 800 | 1.2390 | |
|
| 1.2162 | 2.56 | 1000 | 1.2309 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.0.dev0 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.14.5 |
|
- Tokenizers 0.14.1 |
|
|
