metadata
license: mit
base_model: HuggingFaceH4/zephyr-7b-beta
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: results
results: []
results
This model is a fine-tuned version of HuggingFaceH4/zephyr-7b-beta on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.1541
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: 0.00025
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.6363 | 0.93 | 250 | 0.6571 |
| 0.4103 | 1.86 | 500 | 0.6122 |
| 0.3511 | 2.79 | 750 | 0.5630 |
| 0.3216 | 3.72 | 1000 | 0.8045 |
| 0.2322 | 4.65 | 1250 | 0.8021 |
| 0.2852 | 5.58 | 1500 | 0.8288 |
| 0.2239 | 6.51 | 1750 | 0.8178 |
| 0.2181 | 7.43 | 2000 | 1.1541 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1