<!-- 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. -->
film20000distilbert-base-uncased
This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.1515
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: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 6240
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
2.7616 | 1.6 | 500 | 2.5693 |
2.527 | 3.19 | 1000 | 2.4370 |
2.3591 | 4.79 | 1500 | 2.3738 |
2.2511 | 6.39 | 2000 | 2.3388 |
2.1606 | 7.99 | 2500 | 2.2899 |
2.0761 | 9.58 | 3000 | 2.2732 |
2.013 | 11.18 | 3500 | 2.2362 |
1.9468 | 12.78 | 4000 | 2.2172 |
1.8953 | 14.38 | 4500 | 2.1972 |
1.8467 | 15.97 | 5000 | 2.1812 |
1.806 | 17.57 | 5500 | 2.1746 |
1.7826 | 19.17 | 6000 | 2.1537 |
Framework versions
- Transformers 4.27.3
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2