metadata
base_model: allenai/biomed_roberta_base
tags:
- generated_from_trainer
model-index:
- name: clinical_transcripts_roberta
results: []
clinical_transcripts_roberta
This model is a fine-tuned version of allenai/biomed_roberta_base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.0798
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: 0.0005
- 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_ratio: 0.1
- lr_scheduler_warmup_steps: 100
- training_steps: 2000
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.405 | 0.51 | 100 | 1.2925 |
| 1.3155 | 1.01 | 200 | 1.2096 |
| 1.276 | 1.52 | 300 | 1.1683 |
| 1.2876 | 2.02 | 400 | 1.1698 |
| 1.2189 | 2.53 | 500 | 1.1662 |
| 1.1993 | 3.03 | 600 | 1.1183 |
| 1.1656 | 3.54 | 700 | 1.1337 |
| 1.1486 | 4.04 | 800 | 1.1396 |
| 1.14 | 4.55 | 900 | 1.1034 |
| 1.1411 | 5.05 | 1000 | 1.1279 |
| 1.1132 | 5.56 | 1100 | 1.0999 |
| 1.1039 | 6.06 | 1200 | 1.0912 |
| 1.0986 | 6.57 | 1300 | 1.0948 |
| 1.077 | 7.07 | 1400 | 1.0866 |
| 1.0649 | 7.58 | 1500 | 1.0695 |
| 1.0564 | 8.08 | 1600 | 1.0676 |
| 1.028 | 8.59 | 1700 | 1.0567 |
| 1.0917 | 9.09 | 1800 | 1.0642 |
| 1.0456 | 9.6 | 1900 | 1.0386 |
| 1.0353 | 10.1 | 2000 | 1.0798 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.0