amazon_helpfulness_classification_seqbn_tapt_full_train
This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3077
- Accuracy: 0.8776
- F1 Macro: 0.7027
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: 0.0001
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-06
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.06
- num_epochs: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro |
---|---|---|---|---|---|
0.3264 | 1.0 | 7204 | 0.3133 | 0.8658 | 0.5988 |
0.3255 | 2.0 | 14408 | 0.3263 | 0.8668 | 0.5816 |
0.3123 | 3.0 | 21612 | 0.3075 | 0.873 | 0.6920 |
0.3098 | 4.0 | 28816 | 0.3100 | 0.8728 | 0.6726 |
0.2613 | 5.0 | 36020 | 0.3124 | 0.8734 | 0.6992 |
0.2496 | 6.0 | 43224 | 0.3123 | 0.8758 | 0.7014 |
0.2484 | 7.0 | 50428 | 0.3164 | 0.8728 | 0.6936 |
0.2296 | 8.0 | 57632 | 0.3310 | 0.8722 | 0.6849 |
0.2885 | 9.0 | 64836 | 0.3307 | 0.873 | 0.6911 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2
- Downloads last month
- 0
Unable to determine this model's library. Check the
docs
.