coinplusfire_chinese-alpaca-2-7b_full
This model is a fine-tuned version of hfl/chinese-alpaca-2-7b on an unknown dataset.
It achieves the following results on the evaluation set:
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: 0.0002
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 2
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss |
Epoch |
Step |
Validation Loss |
| 2.3117 |
1.0 |
207 |
1.9098 |
| 1.878 |
2.0 |
414 |
1.7665 |
| 1.7555 |
3.0 |
621 |
1.6904 |
| 1.6743 |
4.0 |
828 |
1.6407 |
| 1.6157 |
5.0 |
1035 |
1.6056 |
| 1.5661 |
6.0 |
1242 |
1.5841 |
| 1.5265 |
7.0 |
1449 |
1.5642 |
| 1.495 |
8.0 |
1656 |
1.5487 |
| 1.4711 |
9.0 |
1863 |
1.5431 |
| 1.4542 |
10.0 |
2070 |
1.5419 |
Framework versions
- PEFT 0.10.0
- Transformers 4.39.3
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
