|
--- |
|
license: mit |
|
base_model: HuggingFaceH4/zephyr-7b-beta |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: zephyr-convsearch-7b |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# zephyr-convsearch-7b |
|
|
|
This model is a fine-tuned version of [HuggingFaceH4/zephyr-7b-beta](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.4475 |
|
|
|
## 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: 8 |
|
- seed: 42 |
|
- distributed_type: multi-GPU |
|
- num_devices: 2 |
|
- gradient_accumulation_steps: 32 |
|
- total_train_batch_size: 512 |
|
- total_eval_batch_size: 16 |
|
- 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 | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 0.5796 | 0.62 | 34 | 0.5780 | |
|
| 0.5119 | 1.62 | 68 | 0.5122 | |
|
| 0.4799 | 2.63 | 103 | 0.4831 | |
|
| 0.4712 | 3.62 | 137 | 0.4706 | |
|
| 0.4615 | 4.63 | 172 | 0.4631 | |
|
| 0.4584 | 5.62 | 206 | 0.4574 | |
|
| 0.4524 | 6.63 | 241 | 0.4529 | |
|
| 0.4507 | 7.62 | 275 | 0.4502 | |
|
| 0.4478 | 8.63 | 310 | 0.4480 | |
|
| 0.4467 | 9.62 | 344 | 0.4475 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.0 |
|
- Pytorch 2.1.1+cu118 |
|
- Datasets 2.14.6 |
|
- Tokenizers 0.14.1 |
|
|
