| --- |
| base_model: bigscience/bloomz-560m |
| library_name: peft |
| license: bigscience-bloom-rail-1.0 |
| tags: |
| - trl |
| - sft |
| - generated_from_trainer |
| model-index: |
| - name: bloom_ts1 |
| 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_ts1 |
| |
| 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: 3.9558 |
| |
| ## 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: 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 |
| - lr_scheduler_warmup_ratio: 0.1 |
| - num_epochs: 5 |
| - mixed_precision_training: Native AMP |
| |
| ### Training results |
| |
| | Training Loss | Epoch | Step | Validation Loss | |
| |:-------------:|:-----:|:----:|:---------------:| |
| | 4.0922 | 1.0 | 25 | 4.5588 | |
| | 4.8287 | 2.0 | 50 | 4.2458 | |
| | 4.991 | 3.0 | 75 | 4.0713 | |
| | 4.8733 | 4.0 | 100 | 3.9800 | |
| | 4.6998 | 5.0 | 125 | 3.9558 | |
| |
| |
| ### Framework versions |
| |
| - PEFT 0.12.0 |
| - Transformers 4.44.2 |
| - Pytorch 2.4.0+cu121 |
| - Datasets 3.0.0 |
| - Tokenizers 0.19.1 |
