<!-- 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-tweet_eval-from-scratch-custom-tokenizer-target-rotten_tomatoes
This model is a fine-tuned version of muhtasham/tiny-mlm-tweet_eval-from-scratch-custom-tokenizer on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.8231
- Accuracy: 0.7411
- F1: 0.7411
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 | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.6934 | 1.87 | 500 | 0.6934 | 0.5 | 0.3333 |
| 0.6926 | 3.75 | 1000 | 0.6889 | 0.5347 | 0.4338 |
| 0.5447 | 5.62 | 1500 | 0.5816 | 0.7298 | 0.7285 |
| 0.3766 | 7.49 | 2000 | 0.5989 | 0.7364 | 0.7363 |
| 0.3119 | 9.36 | 2500 | 0.6346 | 0.7467 | 0.7466 |
| 0.265 | 11.24 | 3000 | 0.6979 | 0.7430 | 0.7429 |
| 0.2287 | 13.11 | 3500 | 0.7540 | 0.7420 | 0.7416 |
| 0.1984 | 14.98 | 4000 | 0.8231 | 0.7411 | 0.7411 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.1+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2
