metadata
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
base_model: MediaTek-Research/Breeze-7B-Instruct-v1_0
model-index:
- name: Experiment-QA-Breeze-7B-Instruct-v1_0
results: []
Experiment-QA-Breeze-7B-Instruct-v1_0
This model is a fine-tuned version of MediaTek-Research/Breeze-7B-Instruct-v1_0 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.7361
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: 0.0002
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 6
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.3943 | 1.0 | 27 | 1.9839 |
| 1.9857 | 2.0 | 54 | 1.8182 |
| 1.8169 | 3.0 | 81 | 1.7600 |
| 1.6758 | 4.0 | 108 | 1.7318 |
| 1.636 | 5.0 | 135 | 1.7330 |
| 1.5205 | 6.0 | 162 | 1.7361 |
Framework versions
- PEFT 0.7.1
- Transformers 4.36.1
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.15.0