finetuned_roberta-base-on-IEMOCAP_5

This model is a fine-tuned version of cardiffnlp/twitter-roberta-base-emotion on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.5796
• Accuracy: 0.6833

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: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.9167	1.0	108	0.9034	0.6477
0.7123	2.0	216	0.8683	0.6860
0.5267	3.0	324	0.8770	0.6953
0.387	4.0	432	0.9405	0.6965
0.3795	5.0	540	1.0109	0.7070
0.2305	6.0	648	1.0698	0.6977
0.1937	7.0	756	1.1674	0.7093
0.1661	8.0	864	1.2279	0.6907
0.2069	9.0	972	1.2690	0.7105
0.1453	10.0	1080	1.3482	0.6977
0.1251	11.0	1188	1.3402	0.7105
0.1433	12.0	1296	1.3726	0.7023
0.1243	13.0	1404	1.4308	0.7012
0.1295	14.0	1512	1.4511	0.7116
0.1235	15.0	1620	1.4420	0.7070

Framework versions

• Transformers 4.34.0
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.14.1