<!-- 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-snli-from-scratch-custom-tokenizer-target-conll2003
This model is a fine-tuned version of muhtasham/tiny-mlm-snli-from-scratch-custom-tokenizer on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4949
- Precision: 0.1811
- Recall: 0.2837
- F1: 0.2211
- Accuracy: 0.8401
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 |
---|---|---|---|---|---|---|---|
1.1064 | 1.14 | 500 | 0.8667 | 0.0151 | 0.0165 | 0.0157 | 0.7660 |
0.7755 | 2.28 | 1000 | 0.7543 | 0.0452 | 0.0653 | 0.0534 | 0.7853 |
0.702 | 3.42 | 1500 | 0.6770 | 0.0724 | 0.1080 | 0.0867 | 0.8021 |
0.643 | 4.56 | 2000 | 0.6336 | 0.0973 | 0.1782 | 0.1259 | 0.8063 |
0.6062 | 5.69 | 2500 | 0.5967 | 0.1146 | 0.2020 | 0.1462 | 0.8143 |
0.5808 | 6.83 | 3000 | 0.5672 | 0.1282 | 0.2198 | 0.1619 | 0.8222 |
0.5564 | 7.97 | 3500 | 0.5431 | 0.1404 | 0.2450 | 0.1786 | 0.8270 |
0.5315 | 9.11 | 4000 | 0.5236 | 0.1478 | 0.2622 | 0.1891 | 0.8309 |
0.5137 | 10.25 | 4500 | 0.5095 | 0.1557 | 0.2777 | 0.1995 | 0.8338 |
0.4978 | 11.39 | 5000 | 0.4949 | 0.1811 | 0.2837 | 0.2211 | 0.8401 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.1+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2