<!-- 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. -->
small-mlm-glue-sst2-custom-tokenizer-expand-vocab
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: 3.6691
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- training_steps: 5000
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
5.7845 | 0.4 | 500 | 4.9051 |
5.1318 | 0.8 | 1000 | 4.4760 |
4.6574 | 1.2 | 1500 | 4.2424 |
4.485 | 1.6 | 2000 | 4.1395 |
4.3228 | 2.0 | 2500 | 3.8747 |
4.0944 | 2.4 | 3000 | 3.9020 |
3.9534 | 2.8 | 3500 | 3.7970 |
3.8158 | 3.2 | 4000 | 3.6970 |
3.6654 | 3.6 | 4500 | 3.7170 |
3.6095 | 4.0 | 5000 | 3.6691 |
Framework versions
- Transformers 4.27.0.dev0
- Pytorch 1.13.1+cu116
- Datasets 2.9.1.dev0
- Tokenizers 0.13.2