<!-- 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. -->
SA-roberta-e12-w1-1.5-b16-mt4-w0.01
This model is a fine-tuned version of Amalq/autotrain-smm4h_large_roberta_clean-874027878 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5163
- Accuracy: 0.946
- F1: 0.9523
- Precision: 0.9489
- Recall: 0.9557
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: 2e-05
- 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
- num_epochs: 12
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
---|---|---|---|---|---|---|---|
No log | 1.0 | 285 | 0.2656 | 0.886 | 0.9059 | 0.8472 | 0.9734 |
0.2593 | 2.0 | 570 | 0.1967 | 0.938 | 0.9453 | 0.9404 | 0.9504 |
0.2593 | 3.0 | 855 | 0.2726 | 0.925 | 0.9353 | 0.9109 | 0.9610 |
0.1239 | 4.0 | 1140 | 0.3039 | 0.942 | 0.9481 | 0.9567 | 0.9397 |
0.1239 | 5.0 | 1425 | 0.3721 | 0.935 | 0.9421 | 0.9463 | 0.9379 |
0.053 | 6.0 | 1710 | 0.4110 | 0.939 | 0.9458 | 0.9483 | 0.9433 |
0.053 | 7.0 | 1995 | 0.4106 | 0.941 | 0.9481 | 0.9407 | 0.9557 |
0.0183 | 8.0 | 2280 | 0.4839 | 0.94 | 0.9470 | 0.9437 | 0.9504 |
0.0004 | 9.0 | 2565 | 0.4994 | 0.945 | 0.9516 | 0.9442 | 0.9592 |
0.0004 | 10.0 | 2850 | 0.5032 | 0.943 | 0.9496 | 0.9471 | 0.9521 |
0.0026 | 11.0 | 3135 | 0.5092 | 0.946 | 0.9523 | 0.9489 | 0.9557 |
0.0026 | 12.0 | 3420 | 0.5163 | 0.946 | 0.9523 | 0.9489 | 0.9557 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3