|
--- |
|
license: bigscience-bloom-rail-1.0 |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: bloom-560m-finetuned-the-stack-prolog |
|
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-560m-finetuned-the-stack-prolog |
|
|
|
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: 0.2433 |
|
|
|
## 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: 2 |
|
- 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: 2 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 1.2334 | 0.2 | 200 | 0.9993 | |
|
| 0.9174 | 0.4 | 400 | 0.7460 | |
|
| 0.7892 | 0.6 | 600 | 0.6046 | |
|
| 0.6805 | 0.8 | 800 | 0.4964 | |
|
| 0.5898 | 0.99 | 1000 | 0.4283 | |
|
| 0.411 | 1.19 | 1200 | 0.3721 | |
|
| 0.3705 | 1.39 | 1400 | 0.3182 | |
|
| 0.3516 | 1.59 | 1600 | 0.2795 | |
|
| 0.3298 | 1.79 | 1800 | 0.2528 | |
|
| 0.2721 | 1.99 | 2000 | 0.2433 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.24.0 |
|
- Pytorch 1.13.0+cu117 |
|
- Datasets 2.5.1 |
|
- Tokenizers 0.13.0 |
|
|
