|
--- |
|
license: mit |
|
library_name: peft |
|
tags: |
|
- trl |
|
- sft |
|
- generated_from_trainer |
|
base_model: HuggingFaceH4/zephyr-7b-beta |
|
model-index: |
|
- name: zephyr_instruct_generation |
|
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_instruct_generation |
|
|
|
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: 0.5753 |
|
|
|
## 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: 0.0001 |
|
- 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_steps: 0.03 |
|
- training_steps: 150 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 2.8455 | 0.4 | 10 | 2.2310 | |
|
| 1.8394 | 0.8 | 20 | 1.3360 | |
|
| 1.0736 | 1.2 | 30 | 0.9132 | |
|
| 0.8515 | 1.6 | 40 | 0.7353 | |
|
| 0.7499 | 2.0 | 50 | 0.6281 | |
|
| 0.5876 | 2.4 | 60 | 0.5897 | |
|
| 0.6041 | 2.8 | 70 | 0.5737 | |
|
| 0.5057 | 3.2 | 80 | 0.5581 | |
|
| 0.512 | 3.6 | 90 | 0.5704 | |
|
| 0.5419 | 4.0 | 100 | 0.5537 | |
|
| 0.4451 | 4.4 | 110 | 0.5777 | |
|
| 0.4467 | 4.8 | 120 | 0.5541 | |
|
| 0.4351 | 5.2 | 130 | 0.5612 | |
|
| 0.3963 | 5.6 | 140 | 0.5898 | |
|
| 0.4264 | 6.0 | 150 | 0.5753 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.7.1 |
|
- Transformers 4.36.2 |
|
- Pytorch 2.1.2+cu121 |
|
- Datasets 2.16.0 |
|
- Tokenizers 0.15.0 |
