metadata
license: mit
base_model: FacebookAI/roberta-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: roberta_base_amazon
results: []
roberta_base_amazon
This model is a fine-tuned version of FacebookAI/roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6847
- Accuracy: 0.8057
- F1 Macro: 0.7452
- F1 Micro: 0.8057
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 |
|---|---|---|---|---|---|---|
| 2.0556 | 0.26 | 50 | 1.7788 | 0.6166 | 0.4632 | 0.6166 |
| 1.2395 | 0.53 | 100 | 1.1504 | 0.7141 | 0.6033 | 0.7141 |
| 0.9724 | 0.79 | 150 | 0.9645 | 0.7385 | 0.6450 | 0.7385 |
| 0.8878 | 1.05 | 200 | 0.8704 | 0.7734 | 0.7001 | 0.7734 |
| 0.7261 | 1.32 | 250 | 0.8159 | 0.7767 | 0.7188 | 0.7767 |
| 0.8083 | 1.58 | 300 | 0.7718 | 0.7879 | 0.7241 | 0.7879 |
| 0.7209 | 1.84 | 350 | 0.7307 | 0.7997 | 0.7414 | 0.7997 |
| 0.6535 | 2.11 | 400 | 0.7205 | 0.8043 | 0.7452 | 0.8043 |
| 0.6283 | 2.37 | 450 | 0.7047 | 0.8090 | 0.7498 | 0.8090 |
| 0.5214 | 2.63 | 500 | 0.6879 | 0.8109 | 0.7541 | 0.8109 |
| 0.5808 | 2.89 | 550 | 0.6847 | 0.8057 | 0.7452 | 0.8057 |
Framework versions
- Transformers 4.39.0.dev0
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2