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
results: []
Yi-6B-ruozhiba
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: 4.2495
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 | 2.2811 |
| 1.9483 | 2.0 | 110 | 1.9384 |
| 1.7791 | 3.0 | 165 | 1.9109 |
| 1.6053 | 4.0 | 220 | 1.9560 |
| 1.3206 | 5.0 | 275 | 2.1674 |
| 0.9722 | 6.0 | 330 | 2.4236 |
| 0.7026 | 7.0 | 385 | 2.6935 |
| 0.4776 | 8.0 | 440 | 3.0005 |
| 0.3163 | 9.0 | 495 | 3.2703 |
| 0.2355 | 10.0 | 550 | 3.4524 |
| 0.1489 | 11.0 | 605 | 3.6805 |
| 0.1179 | 12.0 | 660 | 3.7960 |
| 0.0712 | 13.0 | 715 | 3.9715 |
| 0.0782 | 14.0 | 770 | 4.0284 |
| 0.0691 | 15.0 | 825 | 4.1576 |
| 0.0486 | 16.0 | 880 | 4.1690 |
| 0.0639 | 17.0 | 935 | 4.2094 |
| 0.0589 | 18.0 | 990 | 4.2436 |
| 0.042 | 19.0 | 1045 | 4.2491 |
| 0.0405 | 20.0 | 1100 | 4.2495 |
Framework versions
- PEFT 0.7.1
- Transformers 4.36.2
- Pytorch 2.2.2+cu118
- Datasets 2.14.6
- Tokenizers 0.15.2