# Load model directly
from transformers import AutoTokenizer, AutoModelForTokenClassification
tokenizer = AutoTokenizer.from_pretrained("ania3000/mmbert-base-oss-morph")
model = AutoModelForTokenClassification.from_pretrained("ania3000/mmbert-base-oss-morph", device_map="auto")Quick Links
trainer_output
This model is a fine-tuned version of jhu-clsp/mmBERT-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4158
- Accuracy: 94.7892
- Sentence accuracy: 54.4954
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: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 25
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Sentence accuracy |
|---|---|---|---|---|---|
| 0.7863 | 1.0 | 546 | 0.3676 | 90.7489 | 37.6147 |
| 0.2408 | 2.0 | 1092 | 0.2598 | 93.2662 | 47.3394 |
| 0.1363 | 3.0 | 1638 | 0.2659 | 93.6060 | 47.7064 |
| 0.0828 | 4.0 | 2184 | 0.2874 | 94.2857 | 51.0092 |
| 0.0525 | 5.0 | 2730 | 0.3354 | 94.1221 | 50.0917 |
| 0.0321 | 6.0 | 3276 | 0.3410 | 94.4242 | 53.5780 |
| 0.0206 | 7.0 | 3822 | 0.3864 | 94.4619 | 51.7431 |
| 0.0161 | 8.0 | 4368 | 0.3735 | 94.8143 | 53.5780 |
| 0.0101 | 9.0 | 4914 | 0.3780 | 94.9654 | 55.4128 |
| 0.0089 | 10.0 | 5460 | 0.3959 | 94.6130 | 53.3945 |
| 0.0055 | 11.0 | 6006 | 0.4154 | 94.8018 | 53.3945 |
| 0.0046 | 12.0 | 6552 | 0.4089 | 94.8899 | 54.6789 |
| 0.0041 | 13.0 | 7098 | 0.4007 | 95.1542 | 55.2294 |
| 0.0028 | 14.0 | 7644 | 0.4057 | 95.0535 | 55.5963 |
| 0.0019 | 15.0 | 8190 | 0.4216 | 95.0157 | 54.3119 |
| 0.0021 | 16.0 | 8736 | 0.4158 | 95.0913 | 56.3303 |
| 0.0027 | 17.0 | 9282 | 0.4158 | 94.7892 | 54.4954 |
Framework versions
- Transformers 4.57.3
- Pytorch 2.11.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2
- Downloads last month
- 12
Model tree for ania3000/mmbert-base-oss-morph
Base model
jhu-clsp/mmBERT-base
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="ania3000/mmbert-base-oss-morph")