<!-- 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. -->
bert-mini-mlm-finetuned-imdb
This model is a fine-tuned version of google/bert_uncased_L-4_H-256_A-4 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.6935
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 |
---|---|---|---|
3.2058 | 0.64 | 500 | 2.9411 |
3.1048 | 1.28 | 1000 | 2.9042 |
3.0631 | 1.92 | 1500 | 2.8780 |
3.0197 | 2.56 | 2000 | 2.8667 |
3.0071 | 3.2 | 2500 | 2.8503 |
2.9886 | 3.84 | 3000 | 2.8319 |
2.9577 | 4.48 | 3500 | 2.8127 |
2.9498 | 5.12 | 4000 | 2.8080 |
2.9301 | 5.75 | 4500 | 2.7894 |
2.9229 | 6.39 | 5000 | 2.7912 |
2.9027 | 7.03 | 5500 | 2.7874 |
2.8961 | 7.67 | 6000 | 2.7785 |
2.8869 | 8.31 | 6500 | 2.7619 |
2.8793 | 8.95 | 7000 | 2.7607 |
2.8729 | 9.59 | 7500 | 2.7581 |
2.8523 | 10.23 | 8000 | 2.7593 |
2.8525 | 10.87 | 8500 | 2.7433 |
2.8403 | 11.51 | 9000 | 2.7505 |
2.8318 | 12.15 | 9500 | 2.7444 |
2.8314 | 12.79 | 10000 | 2.7352 |
2.8136 | 13.43 | 10500 | 2.7334 |
2.8161 | 14.07 | 11000 | 2.7280 |
2.7955 | 14.71 | 11500 | 2.7342 |
2.7951 | 15.35 | 12000 | 2.7237 |
2.7878 | 15.98 | 12500 | 2.7171 |
2.7816 | 16.62 | 13000 | 2.7160 |
2.7805 | 17.26 | 13500 | 2.7120 |
2.7776 | 17.9 | 14000 | 2.7078 |
2.7661 | 18.54 | 14500 | 2.7086 |
2.7678 | 19.18 | 15000 | 2.7017 |
2.7613 | 19.82 | 15500 | 2.7015 |
2.7516 | 20.46 | 16000 | 2.6958 |
2.7529 | 21.1 | 16500 | 2.6909 |
2.7422 | 21.74 | 17000 | 2.6966 |
2.738 | 22.38 | 17500 | 2.7034 |
2.7303 | 23.02 | 18000 | 2.6935 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.12.1+cu113
- Datasets 2.7.1
- Tokenizers 0.13.2