metadata
license: mit
base_model: microsoft/MiniLM-L12-H384-uncased
tags:
- generated_from_trainer
model-index:
- name: midjourney-rank
results: []
midjourney-rank
This model is a fine-tuned version of microsoft/MiniLM-L12-H384-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0509
- Mse: 0.0509
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: 32
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Mse |
|---|---|---|---|---|
| 0.061 | 0.34 | 100 | 0.0565 | 0.0565 |
| 0.0544 | 0.67 | 200 | 0.0562 | 0.0562 |
| 0.0585 | 1.01 | 300 | 0.0509 | 0.0509 |
| 0.0508 | 1.34 | 400 | 0.0523 | 0.0523 |
| 0.0508 | 1.68 | 500 | 0.0518 | 0.0518 |
| 0.0465 | 2.01 | 600 | 0.0509 | 0.0509 |
| 0.0449 | 2.35 | 700 | 0.0526 | 0.0526 |
| 0.0398 | 2.68 | 800 | 0.0509 | 0.0509 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1+cu118
- Tokenizers 0.13.3