outputs
This model is a fine-tuned version of tiiuae/falcon-7b on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.7625
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: 2
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
1.2971 | 1.0 | 17 | 1.0151 |
1.0235 | 2.0 | 34 | 0.8409 |
0.7755 | 3.0 | 51 | 0.7797 |
0.7146 | 4.0 | 68 | 0.7590 |
0.333 | 5.0 | 85 | 0.7625 |
Framework versions
- PEFT 0.10.1.dev0
- Transformers 4.40.0.dev0
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 2
Model tree for thangtedao/outputs
Base model
tiiuae/falcon-7b