metadata
base_model: BaoLocTown/zephyr-7b-beta-vi-math-v2
tags:
- generated_from_trainer
model-index:
- name: sft-zephyr-7b-beta-v3
results: []
sft-zephyr-7b-beta-v3
This model is a fine-tuned version of BaoLocTown/zephyr-7b-beta-vi-math-v2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4453
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: 5e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 2
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.3985 | 0.35 | 500 | 0.4894 |
| 0.3746 | 0.69 | 1000 | 0.4715 |
| 0.3551 | 1.04 | 1500 | 0.4562 |
| 0.3165 | 1.39 | 2000 | 0.4504 |
| 0.3256 | 1.73 | 2500 | 0.4453 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0
- Datasets 2.15.0
- Tokenizers 0.15.0