metadata
license: mit
base_model: HuggingFaceH4/zephyr-7b-beta
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: NXAIR_M
results: []
NXAIR_M
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: 0.4843
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 |
|---|---|---|---|
| 0.8314 | 0.77 | 250 | 0.5800 |
| 0.5538 | 1.55 | 500 | 0.3466 |
| 0.4055 | 2.32 | 750 | 0.3881 |
| 0.2974 | 3.1 | 1000 | 0.4570 |
| 0.3618 | 3.87 | 1250 | 0.4268 |
| 0.31 | 4.64 | 1500 | 0.4043 |
| 0.2542 | 5.42 | 1750 | 0.4843 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1