metadata
license: other
library_name: peft
tags:
- alignment-handbook
- generated_from_trainer
- trl
- sft
- generated_from_trainer
datasets:
- ruozhiba
base_model: 01-ai/Yi-6B
model-index:
- name: Yi-6B-ruozhiba3
results: []
Yi-6B-ruozhiba3
This model is a fine-tuned version of 01-ai/Yi-6B on the ruozhiba dataset. It achieves the following results on the evaluation set:
- Loss: 3.9909
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
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.644 | 1.0 | 55 | 2.3047 |
| 1.9548 | 2.0 | 110 | 1.9419 |
| 1.788 | 3.0 | 165 | 1.9135 |
| 1.6342 | 4.0 | 220 | 1.9499 |
| 1.3781 | 5.0 | 275 | 2.1321 |
| 1.0617 | 6.0 | 330 | 2.3518 |
| 0.8104 | 7.0 | 385 | 2.6090 |
| 0.5864 | 8.0 | 440 | 2.8890 |
| 0.4159 | 9.0 | 495 | 3.1356 |
| 0.3344 | 10.0 | 550 | 3.3190 |
| 0.2446 | 11.0 | 605 | 3.5470 |
| 0.199 | 12.0 | 660 | 3.6840 |
| 0.1245 | 13.0 | 715 | 3.7653 |
| 0.1208 | 14.0 | 770 | 3.8722 |
| 0.1003 | 15.0 | 825 | 3.9575 |
| 0.0767 | 16.0 | 880 | 3.9671 |
| 0.0913 | 17.0 | 935 | 3.9921 |
| 0.0895 | 18.0 | 990 | 3.9940 |
| 0.0671 | 19.0 | 1045 | 3.9915 |
| 0.0671 | 20.0 | 1100 | 3.9909 |
Framework versions
- PEFT 0.7.1
- Transformers 4.36.2
- Pytorch 2.2.2+cu118
- Datasets 2.14.6
- Tokenizers 0.15.2