metadata
license: mit
base_model: HuggingFaceH4/zephyr-7b-beta
tags:
- generated_from_trainer
model-index:
- name: zephyr-7b-ikat
results: []
zephyr-7b-ikat
This model is a fine-tuned version of HuggingFaceH4/zephyr-7b-beta on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5166
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: 2e-05
- train_batch_size: 8
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- gradient_accumulation_steps: 16
- total_train_batch_size: 256
- total_eval_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.7437 | 0.62 | 17 | 0.6867 |
| 0.6372 | 1.63 | 35 | 0.6215 |
| 0.6078 | 2.64 | 53 | 0.5859 |
| 0.5724 | 3.62 | 70 | 0.5625 |
| 0.5613 | 4.63 | 88 | 0.5448 |
| 0.5427 | 5.64 | 106 | 0.5337 |
| 0.5388 | 6.62 | 123 | 0.5274 |
| 0.5284 | 7.63 | 141 | 0.5229 |
| 0.5285 | 8.64 | 159 | 0.5188 |
| 0.5222 | 9.61 | 176 | 0.5165 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.1+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1