| | --- |
| | tags: |
| | - generated_from_trainer |
| | datasets: |
| | - esnli |
| | metrics: |
| | - f1 |
| | - accuracy |
| | model-index: |
| | - name: textattack-roberta-base-MNLI-e-snli-classification-nli-base |
| | results: |
| | - task: |
| | name: Text Classification |
| | type: text-classification |
| | dataset: |
| | name: esnli |
| | type: esnli |
| | config: plain_text |
| | split: validation |
| | args: plain_text |
| | metrics: |
| | - name: F1 |
| | type: f1 |
| | value: 0.9106202958294739 |
| | - name: Accuracy |
| | type: accuracy |
| | value: 0.9110953058321479 |
| | --- |
| | |
| | <!-- 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. --> |
| |
|
| | # textattack-roberta-base-MNLI-e-snli-classification-nli-base |
| |
|
| | This model is a fine-tuned version of [textattack/roberta-base-MNLI](https://huggingface.co/textattack/roberta-base-MNLI) on the esnli dataset. |
| | It achieves the following results on the evaluation set: |
| | - Loss: 0.2488 |
| | - F1: 0.9106 |
| | - Accuracy: 0.9111 |
| |
|
| | ## 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: 1e-05 |
| | - train_batch_size: 64 |
| | - eval_batch_size: 64 |
| | - seed: 42 |
| | - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
| | - lr_scheduler_type: linear |
| | - lr_scheduler_warmup_ratio: 0.05 |
| | - num_epochs: 3 |
| | - mixed_precision_training: Native AMP |
| | |
| | ### Training results |
| | |
| | | Training Loss | Epoch | Step | Validation Loss | F1 | Accuracy | |
| | |:-------------:|:-----:|:----:|:---------------:|:------:|:--------:| |
| | | 1.5376 | 0.05 | 400 | 0.4010 | 0.8556 | 0.8556 | |
| | | 0.4352 | 0.09 | 800 | 0.3349 | 0.8795 | 0.8800 | |
| | | 0.4 | 0.14 | 1200 | 0.3180 | 0.8851 | 0.8854 | |
| | | 0.3801 | 0.19 | 1600 | 0.2975 | 0.8918 | 0.8921 | |
| | | 0.3599 | 0.23 | 2000 | 0.2949 | 0.8951 | 0.8955 | |
| | | 0.3612 | 0.28 | 2400 | 0.2802 | 0.8987 | 0.8987 | |
| | | 0.3519 | 0.33 | 2800 | 0.2763 | 0.8977 | 0.8980 | |
| | | 0.349 | 0.37 | 3200 | 0.2766 | 0.9020 | 0.9023 | |
| | | 0.3432 | 0.42 | 3600 | 0.2748 | 0.9000 | 0.9001 | |
| | | 0.3435 | 0.47 | 4000 | 0.2702 | 0.9051 | 0.9051 | |
| | | 0.3352 | 0.51 | 4400 | 0.2728 | 0.9034 | 0.9039 | |
| | | 0.3277 | 0.56 | 4800 | 0.2634 | 0.9039 | 0.9043 | |
| | | 0.3307 | 0.61 | 5200 | 0.2623 | 0.9050 | 0.9057 | |
| | | 0.3247 | 0.65 | 5600 | 0.2685 | 0.9059 | 0.9063 | |
| | | 0.3175 | 0.7 | 6000 | 0.2589 | 0.9081 | 0.9084 | |
| | | 0.3144 | 0.75 | 6400 | 0.2586 | 0.9088 | 0.9093 | |
| | | 0.3102 | 0.79 | 6800 | 0.2547 | 0.9088 | 0.9090 | |
| | | 0.3223 | 0.84 | 7200 | 0.2526 | 0.9093 | 0.9096 | |
| | | 0.3166 | 0.89 | 7600 | 0.2490 | 0.9115 | 0.9118 | |
| | | 0.3124 | 0.93 | 8000 | 0.2503 | 0.9106 | 0.9107 | |
| | | 0.3053 | 0.98 | 8400 | 0.2452 | 0.9099 | 0.9101 | |
| | | 0.2908 | 1.03 | 8800 | 0.2575 | 0.9113 | 0.9119 | |
| | | 0.2853 | 1.07 | 9200 | 0.2464 | 0.9114 | 0.9118 | |
| | | 0.2796 | 1.12 | 9600 | 0.2488 | 0.9106 | 0.9111 | |
| | |
| | |
| | ### Framework versions |
| | |
| | - Transformers 4.27.1 |
| | - Pytorch 1.12.1+cu113 |
| | - Datasets 2.10.1 |
| | - Tokenizers 0.13.2 |
| | |
