<!-- 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-tweet_eval-from-scratch-custom-tokenizer-target-conll2003
This model is a fine-tuned version of muhtasham/tiny-mlm-tweet_eval-from-scratch-custom-tokenizer on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4153
- Precision: 0.2618
- Recall: 0.4002
- F1: 0.3166
- Accuracy: 0.8656
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 |
---|---|---|---|---|---|---|---|
1.0571 | 1.14 | 500 | 0.7799 | 0.0549 | 0.0559 | 0.0554 | 0.7879 |
0.6857 | 2.28 | 1000 | 0.6491 | 0.1028 | 0.1508 | 0.1222 | 0.8120 |
0.6016 | 3.42 | 1500 | 0.5834 | 0.1427 | 0.2189 | 0.1728 | 0.8256 |
0.5481 | 4.56 | 2000 | 0.5410 | 0.1707 | 0.2654 | 0.2078 | 0.8366 |
0.5078 | 5.69 | 2500 | 0.5046 | 0.1888 | 0.3080 | 0.2341 | 0.8467 |
0.474 | 6.83 | 3000 | 0.4732 | 0.2181 | 0.3477 | 0.2681 | 0.8552 |
0.4435 | 7.97 | 3500 | 0.4505 | 0.2310 | 0.3814 | 0.2877 | 0.8593 |
0.4168 | 9.11 | 4000 | 0.4369 | 0.2343 | 0.3851 | 0.2913 | 0.8611 |
0.3965 | 10.25 | 4500 | 0.4222 | 0.2431 | 0.4000 | 0.3024 | 0.8636 |
0.3829 | 11.39 | 5000 | 0.4153 | 0.2618 | 0.4002 | 0.3166 | 0.8656 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.1+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2