chembert-lower-cased-chemrxn-ner

This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.5970
• Precision: 0.5465
• Recall: 0.6425
• F1: 0.5906
• Accuracy: 0.8132

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: 7

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	51	0.9649	0.2309	0.0966	0.1362	0.7075
No log	2.0	102	0.6760	0.4830	0.5674	0.5218	0.7779
No log	3.0	153	0.5911	0.5136	0.7103	0.5961	0.7985
No log	4.0	204	0.5908	0.5636	0.5802	0.5718	0.8097
No log	5.0	255	0.5783	0.5336	0.6784	0.5973	0.8077
No log	6.0	306	0.5933	0.5425	0.6464	0.5899	0.8085
No log	7.0	357	0.5970	0.5465	0.6425	0.5906	0.8132

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1