<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
ColD-Fusion-finetuned-sufficiency-dagstuhl
This model is a fine-tuned version of ibm/ColD-Fusion on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7250
- Accuracy: 0.6825
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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
No log | 1.0 | 16 | 0.6471 | 0.6508 |
No log | 2.0 | 32 | 0.6400 | 0.6508 |
No log | 3.0 | 48 | 0.6722 | 0.6508 |
No log | 4.0 | 64 | 0.7250 | 0.6825 |
No log | 5.0 | 80 | 0.7518 | 0.6508 |
Framework versions
- Transformers 4.27.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2