README.md

metadata

library_name: transformers
license: mit
base_model: EleutherAI/gpt-neo-1.3B
tags:
  - generated_from_trainer
datasets:
  - Ben10x/MedMentions-MTI881-NER
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: gpt-medmentions
    results:
      - task:
          name: Token Classification
          type: token-classification
        dataset:
          name: Ben10x/MedMentions-MTI881-NER
          type: Ben10x/MedMentions-MTI881-NER
        metrics:
          - name: Precision
            type: precision
            value: 0.4453316069630269
          - name: Recall
            type: recall
            value: 0.5247499576199356
          - name: F1
            type: f1
            value: 0.48178988326848243
          - name: Accuracy
            type: accuracy
            value: 0.8454107464662687

gpt-medmentions

This model is a fine-tuned version of EleutherAI/gpt-neo-1.3B on the Ben10x/MedMentions-MTI881-NER dataset. It achieves the following results on the evaluation set:

• Loss: 0.5111
• Precision: 0.4453
• Recall: 0.5247
• F1: 0.4818
• Accuracy: 0.8454

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: 4
• eval_batch_size: 8
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 5.0
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.5307	1.0	5850	0.5369	0.4129	0.4711	0.4401	0.8341
0.3585	2.0	11700	0.5111	0.4453	0.5247	0.4818	0.8454
0.1758	3.0	17550	0.6349	0.4718	0.4900	0.4807	0.8497
0.0751	4.0	23400	0.9264	0.4628	0.5208	0.4901	0.8497
0.0387	5.0	29250	1.0903	0.4758	0.5181	0.4960	0.8518

Framework versions

• Transformers 4.50.3
• Pytorch 2.6.0+cu124
• Datasets 3.5.0
• Tokenizers 0.21.1