finetuned_bert-base-on-IEMOCAP_2

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: 1.3186
• Accuracy: 0.7410

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
1.3127	1.0	113	1.2620	0.4192
0.957	2.0	226	0.9294	0.6095
0.6409	3.0	339	0.8338	0.6969
0.5966	4.0	452	0.8386	0.6958
0.3725	5.0	565	0.8635	0.7035
0.3556	6.0	678	0.9218	0.7069
0.2466	7.0	791	0.9679	0.6914
0.1737	8.0	904	1.1180	0.6869
0.1694	9.0	1017	1.1068	0.6947
0.1843	10.0	1130	1.1409	0.6903
0.1747	11.0	1243	1.1143	0.7080
0.1387	12.0	1356	1.2127	0.6991
0.1524	13.0	1469	1.2309	0.7069
0.1113	14.0	1582	1.2382	0.7113
0.1278	15.0	1695	1.3048	0.7124
0.1214	16.0	1808	1.3267	0.7146
0.1965	17.0	1921	1.3726	0.7013
0.1227	18.0	2034	1.3371	0.7168
0.1014	19.0	2147	1.3508	0.7124
0.1028	20.0	2260	1.3585	0.7080

Framework versions

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