metadata
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: toy
results: []
toy
This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2244
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: 2e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
No log | 1.0 | 50 | 0.2753 |
No log | 2.0 | 100 | 0.2382 |
No log | 3.0 | 150 | 0.2362 |
No log | 4.0 | 200 | 0.2340 |
No log | 5.0 | 250 | 0.2278 |
No log | 6.0 | 300 | 0.2225 |
No log | 7.0 | 350 | 0.2233 |
No log | 8.0 | 400 | 0.2250 |
No log | 9.0 | 450 | 0.2244 |
0.548 | 10.0 | 500 | 0.2244 |
Framework versions
- Transformers 4.17.0
- Pytorch 1.10.0
- Datasets 1.18.3
- Tokenizers 0.11.6