metadata
library_name: transformers
license: mit
base_model: FacebookAI/roberta-base
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: Robert-sst2-sentiment-full
results: []
Robert-sst2-sentiment-full
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: 0.3073
- Accuracy: 0.9197
- F1: 0.9219
- Precision: 0.9137
- Recall: 0.9302
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: 5e-05
- train_batch_size: 16
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 0.2364 | 1.0 | 4210 | 0.3238 | 0.9002 | 0.8966 | 0.9496 | 0.8491 |
| 0.1411 | 2.0 | 8420 | 0.2857 | 0.9220 | 0.9234 | 0.9234 | 0.9234 |
| 0.1655 | 3.0 | 12630 | 0.3073 | 0.9197 | 0.9219 | 0.9137 | 0.9302 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.0
- Tokenizers 0.19.1