chembert-cased-chemrxn-ner
This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2689
- Precision: 0.8012
- Recall: 0.8261
- F1: 0.8135
- Accuracy: 0.9561
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: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 1.0 | 73 | 0.2740 | 0.8009 | 0.8140 | 0.8074 | 0.9553 |
No log | 2.0 | 146 | 0.2718 | 0.7717 | 0.8218 | 0.7960 | 0.9538 |
No log | 3.0 | 219 | 0.2588 | 0.8151 | 0.8235 | 0.8193 | 0.9573 |
No log | 4.0 | 292 | 0.2611 | 0.7950 | 0.8183 | 0.8065 | 0.9545 |
No log | 5.0 | 365 | 0.2572 | 0.8085 | 0.8253 | 0.8168 | 0.9568 |
No log | 6.0 | 438 | 0.2683 | 0.8029 | 0.8279 | 0.8152 | 0.9556 |
0.0098 | 7.0 | 511 | 0.2672 | 0.8018 | 0.8330 | 0.8171 | 0.9565 |
0.0098 | 8.0 | 584 | 0.2689 | 0.8012 | 0.8261 | 0.8135 | 0.9561 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 13
This model does not have enough activity to be deployed to Inference API (serverless) yet.
Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.