metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: distilbert-base-uncased-finetuned-ft1500_reg1
results: []
distilbert-base-uncased-finetuned-ft1500_reg1
This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6165
- Mse: 0.6165
- Mae: 0.6069
- R2: 0.4197
- Accuracy: 0.5007
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: 4
- eval_batch_size: 4
- 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 | Mae | R2 | Accuracy |
---|---|---|---|---|---|---|---|
0.7297 | 1.0 | 3000 | 0.9128 | 0.9128 | 0.7501 | 0.1408 | 0.4113 |
0.4692 | 2.0 | 6000 | 0.5875 | 0.5875 | 0.5946 | 0.4470 | 0.514 |
0.3361 | 3.0 | 9000 | 0.6165 | 0.6165 | 0.6069 | 0.4197 | 0.5007 |
Framework versions
- Transformers 4.21.0
- Pytorch 1.12.0+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1