<!-- 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-no_kd_weight_copy-data-smsa-model-xlmr_base_trained
This model is a fine-tuned version of haryoaw/scenario-normal-finetune-clf-data-smsa-model-xlm-roberta-base on the smsa dataset. It achieves the following results on the evaluation set:
- Loss: 0.5242
- Accuracy: 0.9143
- F1: 0.8839
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 6969
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
---|---|---|---|---|---|
No log | 0.29 | 100 | 0.2670 | 0.9032 | 0.8747 |
No log | 0.58 | 200 | 0.2654 | 0.9190 | 0.8830 |
No log | 0.87 | 300 | 0.2685 | 0.9214 | 0.8876 |
No log | 1.16 | 400 | 0.3040 | 0.9167 | 0.8787 |
0.2448 | 1.45 | 500 | 0.2847 | 0.9032 | 0.8568 |
0.2448 | 1.74 | 600 | 0.3752 | 0.9008 | 0.8358 |
0.2448 | 2.03 | 700 | 0.3087 | 0.9183 | 0.8862 |
0.2448 | 2.33 | 800 | 0.3438 | 0.9135 | 0.8812 |
0.2448 | 2.62 | 900 | 0.3114 | 0.9206 | 0.8934 |
0.1462 | 2.91 | 1000 | 0.3708 | 0.9254 | 0.8904 |
0.1462 | 3.2 | 1100 | 0.3469 | 0.9151 | 0.8865 |
0.1462 | 3.49 | 1200 | 0.3034 | 0.9238 | 0.8965 |
0.1462 | 3.78 | 1300 | 0.3154 | 0.9190 | 0.8797 |
0.1462 | 4.07 | 1400 | 0.3910 | 0.9159 | 0.8780 |
0.0986 | 4.36 | 1500 | 0.3831 | 0.9103 | 0.8765 |
0.0986 | 4.65 | 1600 | 0.4052 | 0.9103 | 0.8801 |
0.0986 | 4.94 | 1700 | 0.3837 | 0.9198 | 0.8879 |
0.0986 | 5.23 | 1800 | 0.4070 | 0.9214 | 0.8854 |
0.0986 | 5.52 | 1900 | 0.4152 | 0.9135 | 0.8768 |
0.0736 | 5.81 | 2000 | 0.3980 | 0.9175 | 0.8871 |
0.0736 | 6.1 | 2100 | 0.3915 | 0.9254 | 0.8915 |
0.0736 | 6.4 | 2200 | 0.4206 | 0.9167 | 0.8823 |
0.0736 | 6.69 | 2300 | 0.4657 | 0.9222 | 0.8907 |
0.0736 | 6.98 | 2400 | 0.5060 | 0.9103 | 0.8811 |
0.0511 | 7.27 | 2500 | 0.5469 | 0.9135 | 0.8772 |
0.0511 | 7.56 | 2600 | 0.5588 | 0.9151 | 0.8811 |
0.0511 | 7.85 | 2700 | 0.5242 | 0.9143 | 0.8839 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1
- Datasets 2.14.5
- Tokenizers 0.13.3