<!-- 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-tiny-mlm-finetuned-emotion
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: 3.5597
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 |
|---|---|---|---|
| 4.1612 | 22.73 | 500 | 3.6903 |
| 3.9137 | 45.45 | 1000 | 3.6206 |
| 3.819 | 68.18 | 1500 | 3.5811 |
| 3.7498 | 90.91 | 2000 | 3.5975 |
| 3.6958 | 113.64 | 2500 | 3.5832 |
| 3.6354 | 136.36 | 3000 | 3.5528 |
| 3.5974 | 159.09 | 3500 | 3.4957 |
| 3.5552 | 181.82 | 4000 | 3.5597 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.12.1+cu113
- Datasets 2.7.1
- Tokenizers 0.13.2
