charisgao/fine_tuned_super_clean_raid_reviews

fine_tuned_super_clean_raid

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: 0.0885
• Accuracy: 0.9715

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
0.3162	0.0196	100	0.2046	0.9306
0.2626	0.0393	200	0.2988	0.9129
0.2888	0.0589	300	0.2148	0.9490
0.217	0.0786	400	0.1970	0.9523
0.2201	0.0982	500	0.1533	0.9596
0.2836	0.1178	600	0.1406	0.9563
0.2196	0.1375	700	0.1326	0.9574
0.1669	0.1571	800	0.1549	0.9622
0.1482	0.1767	900	0.1740	0.9629
0.1997	0.1964	1000	0.0885	0.9715
0.1271	0.2160	1100	0.4294	0.9163
0.1754	0.2357	1200	0.1268	0.9567
0.1479	0.2553	1300	0.3952	0.9328

Framework versions

• Transformers 4.46.3
• Pytorch 2.5.1+cu121
• Datasets 3.1.0
• Tokenizers 0.20.3