hsohn3/mayo-bert-uncased-wordlevel-block512-ep10

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

• Train Loss: 0.3171
• Epoch: 9

Model description

• base_model: bert-base-uncased
• block_size: 512
• tokenizer: ehr-bert-wordlevel-uncased

Intended uses & limitations

More information needed

Training and evaluation data

• MAYO visit-level texts

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
• training_precision: float32
• mlm_probability: 0.15
• batch_size: 8
• epochs: 10

Training results

Train Loss	Epoch
3.0885	0
2.8340	1
2.7975	2
2.6720	3
2.4868	4
2.1750	5
1.8143	6
1.0948	7
0.4915	8
0.3171	9

Framework versions

• Transformers 4.20.1
• TensorFlow 2.8.2
• Datasets 2.3.2
• Tokenizers 0.12.1