--- license: mit tags: - generated_from_trainer datasets: - rotten_tomatoes metrics: - accuracy model-index: - name: rtm_roBERTa_5E results: - task: name: Text Classification type: text-classification dataset: name: rotten_tomatoes type: rotten_tomatoes config: default split: train args: default metrics: - name: Accuracy type: accuracy value: 0.8666666666666667 --- # rtm_roBERTa_5E This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the rotten_tomatoes dataset. It achieves the following results on the evaluation set: - Loss: 0.6545 - Accuracy: 0.8667 ## 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: 16 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 5 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:--------:| | 0.6955 | 0.09 | 50 | 0.6752 | 0.7867 | | 0.5362 | 0.19 | 100 | 0.4314 | 0.8333 | | 0.4065 | 0.28 | 150 | 0.4476 | 0.8533 | | 0.3563 | 0.37 | 200 | 0.3454 | 0.8467 | | 0.3729 | 0.47 | 250 | 0.3421 | 0.86 | | 0.3355 | 0.56 | 300 | 0.3253 | 0.8467 | | 0.338 | 0.66 | 350 | 0.3859 | 0.8733 | | 0.2875 | 0.75 | 400 | 0.3537 | 0.8533 | | 0.3477 | 0.84 | 450 | 0.3636 | 0.8467 | | 0.3259 | 0.94 | 500 | 0.3115 | 0.88 | | 0.3204 | 1.03 | 550 | 0.4295 | 0.8333 | | 0.2673 | 1.12 | 600 | 0.3369 | 0.88 | | 0.2479 | 1.22 | 650 | 0.3620 | 0.8667 | | 0.2821 | 1.31 | 700 | 0.3582 | 0.8733 | | 0.2355 | 1.4 | 750 | 0.3130 | 0.8867 | | 0.2357 | 1.5 | 800 | 0.3229 | 0.86 | | 0.2725 | 1.59 | 850 | 0.3035 | 0.88 | | 0.2425 | 1.69 | 900 | 0.3146 | 0.8533 | | 0.1977 | 1.78 | 950 | 0.4079 | 0.86 | | 0.2557 | 1.87 | 1000 | 0.4132 | 0.8733 | | 0.2395 | 1.97 | 1050 | 0.3336 | 0.86 | | 0.1951 | 2.06 | 1100 | 0.5068 | 0.84 | | 0.1631 | 2.15 | 1150 | 0.5209 | 0.8867 | | 0.2192 | 2.25 | 1200 | 0.4766 | 0.8733 | | 0.1725 | 2.34 | 1250 | 0.3962 | 0.8667 | | 0.2215 | 2.43 | 1300 | 0.4133 | 0.8867 | | 0.1602 | 2.53 | 1350 | 0.5564 | 0.8533 | | 0.1986 | 2.62 | 1400 | 0.5826 | 0.86 | | 0.1972 | 2.72 | 1450 | 0.5412 | 0.8667 | | 0.2299 | 2.81 | 1500 | 0.4636 | 0.8733 | | 0.2028 | 2.9 | 1550 | 0.5096 | 0.8667 | | 0.2591 | 3.0 | 1600 | 0.3790 | 0.8467 | | 0.1197 | 3.09 | 1650 | 0.5704 | 0.8467 | | 0.174 | 3.18 | 1700 | 0.5904 | 0.8467 | | 0.1499 | 3.28 | 1750 | 0.6066 | 0.86 | | 0.1687 | 3.37 | 1800 | 0.6353 | 0.8533 | | 0.1463 | 3.46 | 1850 | 0.6434 | 0.8467 | | 0.1373 | 3.56 | 1900 | 0.6507 | 0.8533 | | 0.1339 | 3.65 | 1950 | 0.6014 | 0.86 | | 0.1488 | 3.75 | 2000 | 0.7245 | 0.84 | | 0.1725 | 3.84 | 2050 | 0.6214 | 0.86 | | 0.1443 | 3.93 | 2100 | 0.6446 | 0.8533 | | 0.1619 | 4.03 | 2150 | 0.6223 | 0.8533 | | 0.1153 | 4.12 | 2200 | 0.6579 | 0.8333 | | 0.1159 | 4.21 | 2250 | 0.6760 | 0.8667 | | 0.0948 | 4.31 | 2300 | 0.7172 | 0.8467 | | 0.1373 | 4.4 | 2350 | 0.7346 | 0.8467 | | 0.1463 | 4.49 | 2400 | 0.6453 | 0.8533 | | 0.0758 | 4.59 | 2450 | 0.6579 | 0.86 | | 0.16 | 4.68 | 2500 | 0.6556 | 0.8667 | | 0.112 | 4.78 | 2550 | 0.6490 | 0.88 | | 0.1151 | 4.87 | 2600 | 0.6525 | 0.8667 | | 0.2152 | 4.96 | 2650 | 0.6545 | 0.8667 | ### Framework versions - Transformers 4.24.0 - Pytorch 1.13.0 - Datasets 2.7.1 - Tokenizers 0.13.2