results

This model is a fine-tuned version of bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.2470
• Treatment: 0.9008
• Chronic: 0.9220
• Cancer: 0.8965
• Allergy: 0.8154
• Other: 0.9478
• Weighted Avg: 0.9304

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Treatment	Chronic	Cancer	Allergy	Other	Weighted Avg
0.8208	0.5435	200	0.3363	0.8455	0.8784	0.8229	0.0	0.9217	0.8862
0.2979	1.0870	400	0.3045	0.8706	0.8933	0.8658	0.7921	0.9300	0.9076
0.2343	1.6304	600	0.2495	0.8872	0.9043	0.8791	0.7788	0.9389	0.9184
0.1812	2.1739	800	0.2587	0.8918	0.9174	0.8843	0.8208	0.9443	0.9253
0.1288	2.7174	1000	0.2470	0.9008	0.9220	0.8965	0.8154	0.9478	0.9304

Framework versions

• Transformers 4.41.2
• Pytorch 2.1.2
• Datasets 2.19.2
• Tokenizers 0.19.1