bert-small-mlm-finetuned-imdb
This model is a fine-tuned version of google/bert_uncased_L-4_H-512_A-8 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.3337
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: 3e-05
- train_batch_size: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- num_epochs: 200
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
2.6923 | 0.64 | 500 | 2.4796 |
2.602 | 1.28 | 1000 | 2.4423 |
2.5672 | 1.92 | 1500 | 2.4226 |
2.5252 | 2.56 | 2000 | 2.4148 |
2.5107 | 3.2 | 2500 | 2.3978 |
2.4948 | 3.84 | 3000 | 2.3839 |
2.463 | 4.48 | 3500 | 2.3739 |
2.4584 | 5.12 | 4000 | 2.3726 |
2.4367 | 5.75 | 4500 | 2.3515 |
2.4308 | 6.39 | 5000 | 2.3565 |
2.411 | 7.03 | 5500 | 2.3540 |
2.4026 | 7.67 | 6000 | 2.3491 |
2.3956 | 8.31 | 6500 | 2.3297 |
2.3864 | 8.95 | 7000 | 2.3338 |
2.3799 | 9.59 | 7500 | 2.3310 |
2.3575 | 10.23 | 8000 | 2.3337 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.12.1+cu113
- Datasets 2.7.1
- Tokenizers 0.13.2
- Downloads last month
- 7
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.