<!-- 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. -->
small-mlm-wikitext-from-scratch-target-conll2003
This model is a fine-tuned version of muhtasham/small-mlm-wikitext-from-scratch on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3086
- Precision: 0.5752
- Recall: 0.7120
- F1: 0.6363
- Accuracy: 0.9257
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 |
---|---|---|---|---|---|---|---|
0.5989 | 1.14 | 500 | 0.4372 | 0.3407 | 0.4672 | 0.3941 | 0.8684 |
0.3588 | 2.28 | 1000 | 0.3477 | 0.4385 | 0.5505 | 0.4882 | 0.8945 |
0.2735 | 3.42 | 1500 | 0.3273 | 0.4400 | 0.6358 | 0.5201 | 0.8992 |
0.2173 | 4.56 | 2000 | 0.3083 | 0.5089 | 0.6141 | 0.5566 | 0.9119 |
0.1776 | 5.69 | 2500 | 0.3000 | 0.5235 | 0.6397 | 0.5758 | 0.9157 |
0.1484 | 6.83 | 3000 | 0.2900 | 0.5332 | 0.6624 | 0.5908 | 0.9184 |
0.1207 | 7.97 | 3500 | 0.2929 | 0.5422 | 0.6696 | 0.5992 | 0.9210 |
0.0988 | 9.11 | 4000 | 0.3015 | 0.5755 | 0.6770 | 0.6222 | 0.9242 |
0.0817 | 10.25 | 4500 | 0.3053 | 0.5528 | 0.7009 | 0.6181 | 0.9229 |
0.0704 | 11.39 | 5000 | 0.3086 | 0.5752 | 0.7120 | 0.6363 | 0.9257 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.1+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2