slac-aroma

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

• Loss: 1.0614
• Accuracy: 0.9563
• F1 Macro: 0.9095
• Precision Macro: 0.8951
• Recall Macro: 0.9256
• Total Tf: [1532, 70, 1532, 70]

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: 64
• eval_batch_size: 64
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 212
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1 Macro	Precision Macro	Recall Macro	Total Tf
0.4534	1.0	213	0.3296	0.9426	0.8903	0.8545	0.9413	[1510, 92, 1510, 92]
0.2968	2.0	426	0.2909	0.9320	0.8743	0.8335	0.9391	[1493, 109, 1493, 109]
0.2515	3.0	639	0.3899	0.9513	0.9017	0.8794	0.9286	[1524, 78, 1524, 78]
0.085	4.0	852	0.5771	0.9576	0.9121	0.8976	0.9283	[1534, 68, 1534, 68]
0.1745	5.0	1065	0.7260	0.9588	0.9117	0.9101	0.9133	[1536, 66, 1536, 66]
0.0626	6.0	1278	1.0108	0.9638	0.9205	0.9293	0.9123	[1544, 58, 1544, 58]
0.0219	7.0	1491	0.7773	0.9501	0.8992	0.8770	0.9260	[1522, 80, 1522, 80]
0.0237	8.0	1704	0.8809	0.9526	0.9028	0.8850	0.9235	[1526, 76, 1526, 76]
0.0182	9.0	1917	0.8934	0.9501	0.8988	0.8778	0.9240	[1522, 80, 1522, 80]
0.0148	10.0	2130	1.0707	0.9613	0.9174	0.9142	0.9207	[1540, 62, 1540, 62]
0.0008	11.0	2343	1.0090	0.9538	0.9050	0.8883	0.9242	[1528, 74, 1528, 74]
0.0005	12.0	2556	1.1176	0.9563	0.9074	0.9013	0.9138	[1532, 70, 1532, 70]
0.0004	13.0	2769	1.0370	0.9563	0.9092	0.8961	0.9237	[1532, 70, 1532, 70]
0.0033	14.0	2982	1.0996	0.9569	0.9100	0.8989	0.9221	[1533, 69, 1533, 69]
0.0003	15.0	3195	1.0614	0.9563	0.9095	0.8951	0.9256	[1532, 70, 1532, 70]

Framework versions

• Transformers 4.44.0
• Pytorch 2.4.0
• Datasets 2.21.0
• Tokenizers 0.19.1