metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: distilroberta-base-mic
results: []
distilroberta-base-mic
This model is a fine-tuned version of distilroberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6948
- Accuracy: 0.7124
- F1: 0.7122
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: 5.8525604794432464e-05
- train_batch_size: 400
- eval_batch_size: 400
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 7
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| No log | 1.0 | 22 | 0.5543 | 0.7124 | 0.7056 |
| No log | 2.0 | 44 | 0.5304 | 0.7209 | 0.7191 |
| No log | 3.0 | 66 | 0.5412 | 0.7331 | 0.7314 |
| No log | 4.0 | 88 | 0.5614 | 0.7190 | 0.7175 |
| No log | 5.0 | 110 | 0.6271 | 0.7133 | 0.7120 |
| No log | 6.0 | 132 | 0.6746 | 0.7030 | 0.7024 |
| No log | 7.0 | 154 | 0.6948 | 0.7124 | 0.7122 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.11.0+cu113
- Datasets 2.1.0
- Tokenizers 0.12.1