<!-- 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-rotten_tomatoes-from-scratch-target-conll2003
This model is a fine-tuned version of muhtasham/tiny-mlm-rotten_tomatoes-from-scratch on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3273
- Precision: 0.4485
- Recall: 0.6124
- F1: 0.5178
- Accuracy: 0.9043
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 | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
1.0073 | 1.14 | 500 | 0.6977 | 0.2294 | 0.1414 | 0.1749 | 0.8160 |
0.5898 | 2.28 | 1000 | 0.5510 | 0.2488 | 0.2842 | 0.2654 | 0.8478 |
0.5001 | 3.42 | 1500 | 0.4898 | 0.3060 | 0.3724 | 0.3359 | 0.8610 |
0.439 | 4.56 | 2000 | 0.4415 | 0.3554 | 0.4377 | 0.3923 | 0.8757 |
0.3893 | 5.69 | 2500 | 0.4050 | 0.3638 | 0.4864 | 0.4162 | 0.8847 |
0.352 | 6.83 | 3000 | 0.3792 | 0.3903 | 0.5226 | 0.4468 | 0.8913 |
0.3169 | 7.97 | 3500 | 0.3567 | 0.4060 | 0.5613 | 0.4712 | 0.8956 |
0.2884 | 9.11 | 4000 | 0.3452 | 0.4174 | 0.5865 | 0.4877 | 0.8982 |
0.264 | 10.25 | 4500 | 0.3346 | 0.4316 | 0.5899 | 0.4985 | 0.9012 |
0.2502 | 11.39 | 5000 | 0.3273 | 0.4485 | 0.6124 | 0.5178 | 0.9043 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.1+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2