metadata
library_name: transformers
license: mit
base_model: microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract
tags:
- generated_from_trainer
model-index:
- name: mistral-7b-instruct-v0.3-mimic4-adapt-l2r
results: []
mistral-7b-instruct-v0.3-mimic4-adapt-l2r
This model is a fine-tuned version of microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract on the None dataset. It achieves the following results on the evaluation set:
- Ndcg: 0.9470
- Loss: 2071.8673
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: 0.0001
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- optimizer: Use 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: 2
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Ndcg | Validation Loss |
|---|---|---|---|---|
| No log | 1.0 | 9 | 0.9469 | 2076.8880 |
| 2178.5025 | 1.8 | 16 | 0.9470 | 2071.8673 |
Framework versions
- Transformers 4.49.0
- Pytorch 2.6.0+cu124
- Datasets 3.2.0
- Tokenizers 0.21.1