Downloads · 30 days
36
31% of all-time downloads
small-mlm-conll2003-from-scratch-custom-tokenizer-target-conll2003
muhtasham/small-mlm-conll2003-from-scratch-custom-tokenizer-target-conll2003
small-mlm-conll2003-from-scratch-custom-tokenizer-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.
should probably proofread and complete it, then remove this comment. --
All-time downloads
116
Public
Repo size
1.1 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin104 MB · 99%
At a glance
- Task
- Token Classification
- Library
- transformers
- Model type
- bert
- Access
- Public
- Created
- Jan 20, 2023
- Updated
- Jan 20, 2023
- SHA
- da87a769
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. -->
small-mlm-conll2003-from-scratch-custom-tokenizer-target-conll2003
This model is a fine-tuned version of muhtasham/small-mlm-conll2003-from-scratch-custom-tokenizer on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3448
- Precision: 0.5713
- Recall: 0.6853
- F1: 0.6231
- Accuracy: 0.9188
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 |
|---|---|---|---|---|---|---|---|
| 0.5039 | 1.14 | 500 | 0.4083 | 0.4419 | 0.4899 | 0.4647 | 0.8780 |
| 0.3033 | 2.28 | 1000 | 0.3461 | 0.4899 | 0.5717 | 0.5276 | 0.8962 |
| 0.2307 | 3.42 | 1500 | 0.3217 | 0.4619 | 0.6373 | 0.5356 | 0.9006 |
| 0.182 | 4.56 | 2000 | 0.3198 | 0.4844 | 0.6530 | 0.5562 | 0.9045 |
| 0.1502 | 5.69 | 2500 | 0.3146 | 0.5239 | 0.6528 | 0.5813 | 0.9104 |
| 0.1265 | 6.83 | 3000 | 0.3216 | 0.4999 | 0.6755 | 0.5746 | 0.9071 |
| 0.1042 | 7.97 | 3500 | 0.3151 | 0.5320 | 0.6666 | 0.5918 | 0.9138 |
| 0.0873 | 9.11 | 4000 | 0.3378 | 0.5443 | 0.6839 | 0.6062 | 0.9139 |
| 0.0723 | 10.25 | 4500 | 0.3487 | 0.5488 | 0.6781 | 0.6066 | 0.9140 |
| 0.0636 | 11.39 | 5000 | 0.3448 | 0.5713 | 0.6853 | 0.6231 | 0.9188 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.1+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2
- Task
- Token Classification
- Library
- transformers
- Type
- bert
- Created
- Jan 20, 2023
- Updated
- Jan 20, 2023