metadata
license: apache-2.0
base_model: distilbert/distilroberta-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: distilroberta_base_scotus
results: []
distilroberta_base_scotus
This model is a fine-tuned version of distilbert/distilroberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.6983
- Accuracy: 0.4914
- F1 Macro: 0.1888
- F1 Micro: 0.4914
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: 32
- eval_batch_size: 32
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- total_train_batch_size: 64
- total_eval_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro | F1 Micro |
|---|---|---|---|---|---|---|
| 2.0217 | 0.63 | 50 | 2.0067 | 0.3879 | 0.0997 | 0.3879 |
| 1.6626 | 1.27 | 100 | 1.8174 | 0.4421 | 0.1288 | 0.4421 |
| 1.7473 | 1.9 | 150 | 1.7735 | 0.4486 | 0.1535 | 0.4486 |
| 1.5993 | 2.53 | 200 | 1.6983 | 0.4914 | 0.1888 | 0.4914 |
Framework versions
- Transformers 4.39.0.dev0
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2