fine_tuned_emo_classif

This model is a fine-tuned version of facebook/wav2vec2-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.9560
• Accuracy: 0.6442

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: 3e-05
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 128
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.597	0.9965	71	1.5666	0.3676
1.3149	1.9930	142	1.2817	0.5374
1.2092	2.9895	213	1.1453	0.5858
1.0891	4.0	285	1.0779	0.6073
1.0319	4.9965	356	1.0494	0.6205
0.943	5.9930	427	1.0233	0.6201
0.8919	6.9895	498	0.9688	0.6425
0.8901	8.0	570	0.9703	0.6346
0.8899	8.9965	641	0.9506	0.6486
0.8277	9.9649	710	0.9560	0.6442

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.19.2
• Tokenizers 0.19.1