<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
scenario-normal-finetune-clf-data-indolem_sentiment-model-xlm-roberta-large
This model is a fine-tuned version of xlm-roberta-large on the indolem_sentiment dataset. It achieves the following results on the evaluation set:
- Loss: 0.6221
- Accuracy: 0.9123
- F1: 0.8583
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-06
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 30
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
---|---|---|---|---|---|
No log | 0.44 | 200 | 0.4767 | 0.7569 | 0.3310 |
No log | 0.88 | 400 | 0.3503 | 0.8822 | 0.7983 |
0.4797 | 1.32 | 600 | 0.3976 | 0.9098 | 0.8302 |
0.4797 | 1.76 | 800 | 0.3545 | 0.9173 | 0.8584 |
0.3498 | 2.2 | 1000 | 0.3955 | 0.9173 | 0.8596 |
0.3498 | 2.64 | 1200 | 0.3558 | 0.9298 | 0.8803 |
0.3498 | 3.08 | 1400 | 0.4563 | 0.9198 | 0.8621 |
0.2444 | 3.52 | 1600 | 0.4079 | 0.9223 | 0.8714 |
0.2444 | 3.96 | 1800 | 0.4416 | 0.9198 | 0.8609 |
0.1788 | 4.4 | 2000 | 0.5722 | 0.9073 | 0.8452 |
0.1788 | 4.84 | 2200 | 0.6618 | 0.8972 | 0.8392 |
0.1788 | 5.27 | 2400 | 0.4956 | 0.9298 | 0.875 |
0.128 | 5.71 | 2600 | 0.6221 | 0.9123 | 0.8583 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1
- Datasets 2.14.5
- Tokenizers 0.13.3