<!-- 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. -->
results
This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7398
- F1: 0.3764
- Recall: 0.4257
- Precision: 0.5363
- Accuracy: 0.7155
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=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 1
Training results
Training Loss | Epoch | Step | Validation Loss | F1 | Recall | Precision | Accuracy |
---|---|---|---|---|---|---|---|
1.4981 | 0.03 | 10 | 1.4740 | 0.1556 | 0.2 | 0.1274 | 0.6368 |
1.473 | 0.05 | 20 | 1.4299 | 0.1556 | 0.2 | 0.1274 | 0.6368 |
1.4055 | 0.08 | 30 | 1.3260 | 0.1556 | 0.2 | 0.1274 | 0.6368 |
1.2743 | 0.11 | 40 | 1.1795 | 0.1556 | 0.2 | 0.1274 | 0.6368 |
1.2937 | 0.13 | 50 | 1.1463 | 0.1556 | 0.2 | 0.1274 | 0.6368 |
1.193 | 0.16 | 60 | 1.1367 | 0.1556 | 0.2 | 0.1274 | 0.6368 |
1.1709 | 0.18 | 70 | 1.0957 | 0.1556 | 0.2 | 0.1274 | 0.6368 |
1.0956 | 0.21 | 80 | 1.0457 | 0.1556 | 0.2 | 0.1274 | 0.6368 |
1.0756 | 0.24 | 90 | 0.9852 | 0.1556 | 0.2 | 0.1274 | 0.6368 |
0.862 | 0.26 | 100 | 1.0718 | 0.1556 | 0.2 | 0.1274 | 0.6368 |
0.9677 | 0.29 | 110 | 0.8931 | 0.1556 | 0.2 | 0.1274 | 0.6368 |
0.7597 | 0.32 | 120 | 0.8502 | 0.2195 | 0.2499 | 0.2034 | 0.6561 |
0.7797 | 0.34 | 130 | 0.8028 | 0.2818 | 0.3758 | 0.3547 | 0.6888 |
0.8114 | 0.37 | 140 | 0.9480 | 0.2918 | 0.3313 | 0.3515 | 0.6907 |
0.8693 | 0.4 | 150 | 0.7799 | 0.3703 | 0.4000 | 0.5420 | 0.7081 |
0.9561 | 0.42 | 160 | 0.7844 | 0.3825 | 0.4261 | 0.3493 | 0.7199 |
0.6979 | 0.45 | 170 | 0.7656 | 0.3882 | 0.4404 | 0.4166 | 0.7165 |
0.8083 | 0.47 | 180 | 0.8847 | 0.3596 | 0.3688 | 0.5985 | 0.7051 |
0.8009 | 0.5 | 190 | 0.7665 | 0.3244 | 0.3916 | 0.3801 | 0.7021 |
0.6833 | 0.53 | 200 | 0.8408 | 0.4270 | 0.4631 | 0.4603 | 0.6724 |
0.749 | 0.55 | 210 | 0.7344 | 0.3889 | 0.4745 | 0.4888 | 0.7120 |
0.7106 | 0.58 | 220 | 0.7037 | 0.4511 | 0.4965 | 0.4562 | 0.7343 |
0.7631 | 0.61 | 230 | 0.7118 | 0.4331 | 0.4626 | 0.4472 | 0.7378 |
0.7672 | 0.63 | 240 | 0.6925 | 0.5035 | 0.4976 | 0.5470 | 0.7412 |
0.7662 | 0.66 | 250 | 0.7188 | 0.4425 | 0.4812 | 0.4662 | 0.7308 |
0.726 | 0.69 | 260 | 0.7120 | 0.4052 | 0.4616 | 0.4508 | 0.7353 |
0.9073 | 0.71 | 270 | 0.7969 | 0.3495 | 0.3862 | 0.3547 | 0.7036 |
0.6709 | 0.74 | 280 | 0.7429 | 0.3800 | 0.4279 | 0.4814 | 0.7145 |
0.9403 | 0.77 | 290 | 0.8199 | 0.3926 | 0.3870 | 0.5164 | 0.6992 |
0.9277 | 0.79 | 300 | 0.7304 | 0.3599 | 0.4349 | 0.3786 | 0.7086 |
0.9503 | 0.82 | 310 | 0.7764 | 0.4613 | 0.5283 | 0.4263 | 0.6828 |
0.6553 | 0.84 | 320 | 0.7386 | 0.4051 | 0.4593 | 0.5329 | 0.7081 |
0.7655 | 0.87 | 330 | 0.7527 | 0.5087 | 0.5252 | 0.5375 | 0.7204 |
0.6663 | 0.9 | 340 | 0.7248 | 0.4618 | 0.4841 | 0.5283 | 0.7353 |
0.915 | 0.92 | 350 | 0.8947 | 0.4279 | 0.4875 | 0.3979 | 0.6596 |
0.8718 | 0.95 | 360 | 0.7893 | 0.3796 | 0.3938 | 0.5016 | 0.7110 |
0.8338 | 0.98 | 370 | 0.7293 | 0.4124 | 0.4277 | 0.4147 | 0.7130 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.9.0
- Tokenizers 0.13.2