.CON - Story Generation Models
Collection
6 items
•
Updated
PointCon-falcon-40b-2
This model is a fine-tuned version of tiiuae/falcon-40b on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.8131
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: 1
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.9879 | 0.26 | 30 | 1.9850 |
| 1.9725 | 0.53 | 60 | 1.9057 |
| 1.8858 | 0.79 | 90 | 1.8573 |
| 1.8604 | 1.05 | 120 | 1.8330 |
| 1.7798 | 1.32 | 150 | 1.8250 |
| 1.7554 | 1.58 | 180 | 1.8169 |
| 1.7917 | 1.84 | 210 | 1.8127 |
| 1.7538 | 2.11 | 240 | 1.8102 |
| 1.6949 | 2.37 | 270 | 1.8133 |
| 1.7112 | 2.63 | 300 | 1.8128 |
| 1.7024 | 2.89 | 330 | 1.8131 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for Acadys/PointCon-Falcon40B
Base model
tiiuae/falcon-40b