|
--- |
|
license: bigscience-bloom-rail-1.0 |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: bloom-560m-finetuned-aeslc |
|
results: [] |
|
widget: |
|
- text: "<s>Given the following email subject, generate a body for it:\nService Agreement\n\nBody:" |
|
|
|
inference: |
|
parameters: |
|
eos_token_id: 2 |
|
max_length: 500 |
|
|
|
--- |
|
|
|
<!-- 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-560m-finetuned-aeslc |
|
|
|
This model is a fine-tuned version of [bigscience/bloom-560m](https://huggingface.co/bigscience/bloom-560m) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 3.4199 |
|
|
|
## 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 |
|
- 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: 6 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 2.994 | 0.62 | 200 | 3.0855 | |
|
| 2.4454 | 1.23 | 400 | 3.0508 | |
|
| 2.3019 | 1.85 | 600 | 2.9731 | |
|
| 1.7647 | 2.46 | 800 | 3.1036 | |
|
| 1.636 | 3.08 | 1000 | 3.4199 | |
|
| 1.2469 | 3.69 | 1200 | 3.5381 | |
|
| 0.8443 | 4.31 | 1400 | 4.0697 | |
|
| 0.8214 | 4.92 | 1600 | 4.0181 | |
|
| 0.5355 | 5.54 | 1800 | 4.7636 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.22.2 |
|
- Pytorch 1.12.1+cu113 |
|
- Datasets 2.5.1 |
|
- Tokenizers 0.12.1 |
|
|
