<!-- 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. -->
film20000bert-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: 2.0507
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
- num_epochs: 40
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
No log | 1.0 | 313 | 2.4018 |
2.5523 | 2.0 | 626 | 2.3561 |
2.5523 | 3.0 | 939 | 2.3207 |
2.3635 | 4.0 | 1252 | 2.2873 |
2.236 | 5.0 | 1565 | 2.2714 |
2.236 | 6.0 | 1878 | 2.2388 |
2.14 | 7.0 | 2191 | 2.2375 |
2.0598 | 8.0 | 2504 | 2.2085 |
2.0598 | 9.0 | 2817 | 2.2044 |
1.9831 | 10.0 | 3130 | 2.1849 |
1.9831 | 11.0 | 3443 | 2.1806 |
1.9281 | 12.0 | 3756 | 2.1785 |
1.8663 | 13.0 | 4069 | 2.1622 |
1.8663 | 14.0 | 4382 | 2.1529 |
1.802 | 15.0 | 4695 | 2.1696 |
1.7597 | 16.0 | 5008 | 2.1453 |
1.7597 | 17.0 | 5321 | 2.1361 |
1.7017 | 18.0 | 5634 | 2.1388 |
1.7017 | 19.0 | 5947 | 2.1174 |
1.6644 | 20.0 | 6260 | 2.1047 |
1.6194 | 21.0 | 6573 | 2.1235 |
1.6194 | 22.0 | 6886 | 2.1033 |
1.5795 | 23.0 | 7199 | 2.0899 |
1.5431 | 24.0 | 7512 | 2.0995 |
1.5431 | 25.0 | 7825 | 2.0889 |
1.5081 | 26.0 | 8138 | 2.0946 |
1.5081 | 27.0 | 8451 | 2.0816 |
1.4755 | 28.0 | 8764 | 2.0935 |
1.4379 | 29.0 | 9077 | 2.0709 |
1.4379 | 30.0 | 9390 | 2.0708 |
1.4048 | 31.0 | 9703 | 2.0817 |
1.3761 | 32.0 | 10016 | 2.0695 |
1.3761 | 33.0 | 10329 | 2.0525 |
1.3536 | 34.0 | 10642 | 2.0750 |
1.3536 | 35.0 | 10955 | 2.0721 |
1.3358 | 36.0 | 11268 | 2.0783 |
1.3147 | 37.0 | 11581 | 2.0731 |
1.3147 | 38.0 | 11894 | 2.0577 |
1.2948 | 39.0 | 12207 | 2.0403 |
1.2884 | 40.0 | 12520 | 2.0217 |
Framework versions
- Transformers 4.27.3
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2