<!-- 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. -->
tiny-mlm-glue-stsb-from-scratch-custom-tokenizer-expand-vocab
This model is a fine-tuned version of google/bert_uncased_L-2_H-128_A-2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 6.5710
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 |
---|---|---|---|
9.575 | 0.7 | 500 | 8.4501 |
7.8603 | 1.39 | 1000 | 7.2557 |
7.0873 | 2.09 | 1500 | 6.8941 |
6.8132 | 2.78 | 2000 | 6.7624 |
6.8004 | 3.48 | 2500 | 6.5626 |
6.7383 | 4.17 | 3000 | 6.6079 |
6.6661 | 4.87 | 3500 | 6.5800 |
6.6778 | 5.56 | 4000 | 6.5710 |
Framework versions
- Transformers 4.27.0.dev0
- Pytorch 1.13.1+cu116
- Datasets 2.9.1.dev0
- Tokenizers 0.13.2