|
--- |
|
license: mit |
|
base_model: HuggingFaceH4/zephyr-7b-beta |
|
tags: |
|
- trl |
|
- sft |
|
- generated_from_trainer |
|
model-index: |
|
- name: results |
|
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. --> |
|
|
|
# results |
|
|
|
This model is a fine-tuned version of [HuggingFaceH4/zephyr-7b-beta](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.7065 |
|
|
|
## 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: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 0.7779 | 0.35 | 100 | 1.0474 | |
|
| 0.6553 | 0.69 | 200 | 0.8922 | |
|
| 0.6339 | 1.04 | 300 | 0.7221 | |
|
| 0.6018 | 1.39 | 400 | 0.7020 | |
|
| 0.5853 | 1.74 | 500 | 0.6908 | |
|
| 0.445 | 2.08 | 600 | 0.6887 | |
|
| 0.4875 | 2.43 | 700 | 0.6783 | |
|
| 0.4938 | 2.78 | 800 | 0.6883 | |
|
| 0.3598 | 3.12 | 900 | 0.6893 | |
|
| 0.3549 | 3.47 | 1000 | 0.6763 | |
|
| 0.3624 | 3.82 | 1100 | 0.6971 | |
|
| 0.344 | 4.17 | 1200 | 0.7348 | |
|
| 0.3393 | 4.51 | 1300 | 0.7502 | |
|
| 0.3823 | 4.86 | 1400 | 0.6861 | |
|
| 0.3534 | 5.21 | 1500 | 0.6849 | |
|
| 0.3632 | 5.56 | 1600 | 0.6585 | |
|
| 0.3634 | 5.9 | 1700 | 0.6414 | |
|
| 0.3002 | 6.25 | 1800 | 0.6662 | |
|
| 0.3126 | 6.6 | 1900 | 0.6864 | |
|
| 0.3129 | 6.94 | 2000 | 0.6638 | |
|
| 0.259 | 7.29 | 2100 | 0.6967 | |
|
| 0.27 | 7.64 | 2200 | 0.7059 | |
|
| 0.3063 | 7.99 | 2300 | 0.6582 | |
|
| 0.2814 | 8.33 | 2400 | 0.7205 | |
|
| 0.3005 | 8.68 | 2500 | 0.7334 | |
|
| 0.2862 | 9.03 | 2600 | 0.6839 | |
|
| 0.3092 | 9.38 | 2700 | 0.6929 | |
|
| 0.3078 | 9.72 | 2800 | 0.7065 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.2 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.16.1 |
|
- Tokenizers 0.15.1 |
|
|
