metadata
license: bigscience-bloom-rail-1.0
library_name: peft
tags:
- generated_from_trainer
base_model: bigscience/bloom-3b
model-index:
- name: testing_fine_tune_qa
results: []
testing_fine_tune_qa
This model is a fine-tuned version of bigscience/bloom-3b on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.1709
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: 0.0001
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.9148 | 0.4 | 200 | 1.6602 |
| 1.6726 | 0.8 | 400 | 1.3506 |
| 1.0625 | 1.2 | 600 | 1.2383 |
| 0.8001 | 1.6 | 800 | 1.1885 |
| 0.3615 | 2.0 | 1000 | 1.1709 |
Framework versions
- PEFT 0.7.1
- Transformers 4.36.2
- Pytorch 2.1.2+cu121
- Datasets 2.16.0
- Tokenizers 0.15.0