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-ruozhiba-1e-5-50
results: []
Yi-6B-ruozhiba-1e-5-50
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: 1.9875
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: 1e-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 |
|---|---|---|---|
| 1.8114 | 4.0 | 220 | 1.8505 |
| 1.6723 | 5.0 | 275 | 1.8372 |
| 1.6532 | 6.0 | 330 | 1.8296 |
| 1.7187 | 7.0 | 385 | 1.8273 |
| 1.6945 | 8.0 | 440 | 1.8345 |
| 1.5494 | 9.0 | 495 | 1.8452 |
| 1.5329 | 10.0 | 550 | 1.8665 |
| 1.4105 | 11.0 | 605 | 1.8877 |
| 1.3862 | 12.0 | 660 | 1.9066 |
| 1.4126 | 13.0 | 715 | 1.9303 |
| 1.388 | 14.0 | 770 | 1.9449 |
| 1.3653 | 15.0 | 825 | 1.9637 |
| 1.361 | 16.0 | 880 | 1.9738 |
| 1.2944 | 17.0 | 935 | 1.9819 |
| 1.3433 | 18.0 | 990 | 1.9856 |
| 1.2058 | 19.0 | 1045 | 1.9871 |
| 1.2904 | 20.0 | 1100 | 1.9875 |
Framework versions
- PEFT 0.7.1
- Transformers 4.36.2
- Pytorch 2.2.2+cu118
- Datasets 2.14.6
- Tokenizers 0.15.2