<!-- 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. -->
film95000bert-base-uncased
This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.7698
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: 14840
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
2.5616 | 0.34 | 500 | 2.3892 |
2.4245 | 0.67 | 1000 | 2.2938 |
2.3509 | 1.01 | 1500 | 2.2346 |
2.2721 | 1.35 | 2000 | 2.1967 |
2.2412 | 1.68 | 2500 | 2.1570 |
2.2005 | 2.02 | 3000 | 2.1281 |
2.1417 | 2.36 | 3500 | 2.0986 |
2.1257 | 2.69 | 4000 | 2.0741 |
2.0993 | 3.03 | 4500 | 2.0584 |
2.053 | 3.37 | 5000 | 2.0294 |
2.0364 | 3.7 | 5500 | 2.0049 |
2.0128 | 4.04 | 6000 | 1.9917 |
1.9605 | 4.38 | 6500 | 1.9668 |
1.9539 | 4.71 | 7000 | 1.9509 |
1.9349 | 5.05 | 7500 | 1.9346 |
1.8981 | 5.39 | 8000 | 1.9124 |
1.8874 | 5.72 | 8500 | 1.8990 |
1.8661 | 6.06 | 9000 | 1.8831 |
1.8295 | 6.4 | 9500 | 1.8648 |
1.8163 | 6.73 | 10000 | 1.8464 |
1.8021 | 7.07 | 10500 | 1.8448 |
1.7733 | 7.41 | 11000 | 1.8305 |
1.778 | 7.74 | 11500 | 1.8108 |
1.7493 | 8.08 | 12000 | 1.8044 |
1.7235 | 8.42 | 12500 | 1.7883 |
1.719 | 8.75 | 13000 | 1.7876 |
1.7029 | 9.09 | 13500 | 1.7784 |
1.6923 | 9.43 | 14000 | 1.7654 |
1.6913 | 9.76 | 14500 | 1.7684 |
Framework versions
- Transformers 4.27.3
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2