charisgao/finetuned_raid_reviews_cleaned

fine_tuned_raid_cleaned

This model is a fine-tuned version of FacebookAI/roberta-large on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1136
• Accuracy: 0.9800

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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.3826	0.0139	100	0.1739	0.9443
0.2556	0.0277	200	0.2700	0.9408
0.3383	0.0416	300	0.1667	0.9529
0.3672	0.0554	400	0.9354	0.7975
0.2223	0.0693	500	0.1584	0.9673
0.2197	0.0832	600	0.6363	0.8793
0.2873	0.0970	700	0.2169	0.9462
0.2201	0.1109	800	0.1366	0.9621
0.1695	0.1248	900	0.2912	0.9554
0.1912	0.1386	1000	0.2287	0.9542
0.131	0.1525	1100	0.1136	0.9800
0.1764	0.1663	1200	0.1770	0.9645
0.1195	0.1802	1300	0.1255	0.9755
0.09	0.1941	1400	0.1285	0.9758

Framework versions

• Transformers 4.46.2
• Pytorch 2.5.0+cu121
• Datasets 3.1.0
• Tokenizers 0.20.3