Downloads · 30 days
15
30% of all-time downloads
tiny-mlm-imdb-target-conll2003
muhtasham/tiny-mlm-imdb-target-conll2003
tiny-mlm-imdb-target-conll2003 is a token classification model from muhtasham. Use it when you need labels on individual words, such as names. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
50
Public
Parameters
28.5M
684 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin114 MB · 50%
Parameter types
How the weights are stored.
F3228.5M · 100%
Try a prompt
Model card
From the Hugging Face model README
<!-- 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-imdb-target-conll2003
This model is a fine-tuned version of muhtasham/small-mlm-wikitext on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1138
- Precision: 0.8869
- Recall: 0.9189
- F1: 0.9026
- Accuracy: 0.9777
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 |
|---|---|---|---|---|---|---|---|
| 0.2197 | 1.14 | 500 | 0.0926 | 0.8440 | 0.8756 | 0.8595 | 0.9715 |
| 0.0745 | 2.28 | 1000 | 0.0795 | 0.8817 | 0.8982 | 0.8899 | 0.9766 |
| 0.0425 | 3.42 | 1500 | 0.0829 | 0.8844 | 0.9127 | 0.8983 | 0.9773 |
| 0.0271 | 4.56 | 2000 | 0.0836 | 0.8975 | 0.9148 | 0.9061 | 0.9788 |
| 0.0181 | 5.69 | 2500 | 0.0949 | 0.8922 | 0.9155 | 0.9037 | 0.9782 |
| 0.0129 | 6.83 | 3000 | 0.0922 | 0.8912 | 0.9157 | 0.9033 | 0.9793 |
| 0.0091 | 7.97 | 3500 | 0.0996 | 0.9002 | 0.9169 | 0.9085 | 0.9789 |
| 0.0073 | 9.11 | 4000 | 0.1031 | 0.9035 | 0.9202 | 0.9118 | 0.9800 |
| 0.0057 | 10.25 | 4500 | 0.1152 | 0.9014 | 0.9125 | 0.9069 | 0.9788 |
| 0.005 | 11.39 | 5000 | 0.1138 | 0.8869 | 0.9189 | 0.9026 | 0.9777 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2
- Task
- Token Classification
- Library
- transformers
- Type
- bert
- License
- apache-2.0
- Created
- Jan 16, 2023
- Updated
- Apr 5, 2023