finetuned_bert-base-on-IEMOCAP_5

This model is a fine-tuned version of bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.3146
• Accuracy: 0.6624

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
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.3037	1.0	108	1.2852	0.4349
1.0277	2.0	216	0.9733	0.5942
0.7985	3.0	324	0.8110	0.6895
0.5244	4.0	432	0.7911	0.6919
0.3289	5.0	540	0.8518	0.7012
0.3281	6.0	648	0.9236	0.6884
0.2689	7.0	756	0.9498	0.7058
0.2162	8.0	864	1.0157	0.7023
0.1811	9.0	972	1.0196	0.7151
0.2283	10.0	1080	1.0987	0.7209
0.1449	11.0	1188	1.1462	0.7186
0.1614	12.0	1296	1.1972	0.7116
0.1589	13.0	1404	1.2174	0.7163
0.1314	14.0	1512	1.2388	0.7116
0.1587	15.0	1620	1.2722	0.7186
0.0928	16.0	1728	1.3090	0.7186
0.1394	17.0	1836	1.3286	0.7174
0.0958	18.0	1944	1.3321	0.7209
0.0862	19.0	2052	1.3439	0.7128
0.1041	20.0	2160	1.3473	0.7151

Framework versions

• Transformers 4.30.1
• Pytorch 2.0.1+cu118
• Datasets 2.12.0
• Tokenizers 0.13.3