fine_tuned_main_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: 0.0284
• Accuracy: 0.9931

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
0.3359	0.1018	100	0.1977	0.9703
0.17	0.2037	200	0.3161	0.9542
0.1525	0.3055	300	0.0936	0.9828
0.0874	0.4073	400	0.0900	0.9863
0.097	0.5092	500	0.0992	0.9863
0.0874	0.6110	600	0.1275	0.9851
0.0763	0.7128	700	0.1173	0.9840
0.1067	0.8147	800	0.0585	0.9874
0.0646	0.9165	900	0.0358	0.9943
0.0338	1.0183	1000	0.0413	0.9943
0.0463	1.1202	1100	0.0311	0.9943
0.0683	1.2220	1200	0.0473	0.9920
0.0315	1.3238	1300	0.0374	0.9931
0.0251	1.4257	1400	0.0335	0.9954
0.0238	1.5275	1500	0.0481	0.9931
0.0105	1.6293	1600	0.0555	0.9931
0.063	1.7312	1700	0.0343	0.9931
0.0389	1.8330	1800	0.0355	0.9931
0.0463	1.9348	1900	0.0584	0.9897
0.0075	2.0367	2000	0.0284	0.9931
0.0036	2.1385	2100	0.1225	0.9760
0.0062	2.2403	2200	0.0333	0.9943
0.0136	2.3422	2300	0.0379	0.9920

Framework versions

• Transformers 4.46.2
• Pytorch 2.5.1+cu121
• Datasets 3.1.0
• Tokenizers 0.20.3