metadata

license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - marsyas/gtzan
metrics:
  - accuracy
model-index:
  - name: distilhubert-finetuned-gtzan
    results: []

distilhubert-finetuned-gtzan

This model is a fine-tuned version of ntu-spml/distilhubert on the GTZAN dataset. It achieves the following results on the evaluation set:

Loss: 0.7554
Accuracy: 0.83

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: 5e-06
train_batch_size: 8
eval_batch_size: 8
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: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
2.3168	1.0	113	2.2998	0.06
2.2869	2.0	226	2.2880	0.15
2.2711	3.0	339	2.2649	0.32
2.2407	4.0	452	2.2306	0.36
2.1993	5.0	565	2.1723	0.41
2.1239	6.0	678	2.0768	0.54
2.0001	7.0	791	1.9675	0.63
1.9217	8.0	904	1.8527	0.63
1.7955	9.0	1017	1.7538	0.62
1.8026	10.0	1130	1.6549	0.63
1.6166	11.0	1243	1.5623	0.68
1.5788	12.0	1356	1.4857	0.67
1.4279	13.0	1469	1.4114	0.64
1.3744	14.0	1582	1.3545	0.7
1.1651	15.0	1695	1.2848	0.67
1.1956	16.0	1808	1.2487	0.69
1.1852	17.0	1921	1.1826	0.73
1.1153	18.0	2034	1.1325	0.73
1.0218	19.0	2147	1.1174	0.71
1.0623	20.0	2260	1.0428	0.73
0.9385	21.0	2373	1.0111	0.75
0.9395	22.0	2486	0.9853	0.75
0.8799	23.0	2599	0.9868	0.72
0.74	24.0	2712	0.9136	0.76
0.8411	25.0	2825	0.9025	0.74
0.8784	26.0	2938	0.8757	0.76
0.726	27.0	3051	0.8720	0.75
0.7704	28.0	3164	0.8135	0.75
0.7628	29.0	3277	0.7514	0.82
0.6254	30.0	3390	0.7675	0.77
0.5432	31.0	3503	0.7689	0.77
0.5699	32.0	3616	0.7197	0.81
0.5448	33.0	3729	0.6838	0.82
0.5634	34.0	3842	0.7029	0.81
0.4702	35.0	3955	0.7170	0.77
0.3946	36.0	4068	0.6443	0.82
0.4749	37.0	4181	0.6318	0.83
0.317	38.0	4294	0.6420	0.83
0.3082	39.0	4407	0.6190	0.82
0.2932	40.0	4520	0.6196	0.83
0.2928	41.0	4633	0.6059	0.83
0.2902	42.0	4746	0.6290	0.82
0.3297	43.0	4859	0.6039	0.82
0.2645	44.0	4972	0.5924	0.83
0.2586	45.0	5085	0.6134	0.83
0.2815	46.0	5198	0.6237	0.81
0.3678	47.0	5311	0.6001	0.81
0.2904	48.0	5424	0.5742	0.84
0.1635	49.0	5537	0.6265	0.82
0.1144	50.0	5650	0.5945	0.81
0.1677	51.0	5763	0.5986	0.83
0.1879	52.0	5876	0.6099	0.83
0.1977	53.0	5989	0.5745	0.84
0.1255	54.0	6102	0.5959	0.82
0.0789	55.0	6215	0.6409	0.83
0.0634	56.0	6328	0.5985	0.82
0.1688	57.0	6441	0.5848	0.84
0.1464	58.0	6554	0.6173	0.83
0.1089	59.0	6667	0.6245	0.83
0.0963	60.0	6780	0.6343	0.82
0.0548	61.0	6893	0.6277	0.83
0.1293	62.0	7006	0.6128	0.83
0.0406	63.0	7119	0.6339	0.83
0.0532	64.0	7232	0.6480	0.83
0.214	65.0	7345	0.6661	0.81
0.1246	66.0	7458	0.6637	0.83
0.036	67.0	7571	0.6527	0.85
0.1168	68.0	7684	0.6517	0.84
0.0322	69.0	7797	0.6714	0.83
0.0362	70.0	7910	0.6912	0.81
0.1088	71.0	8023	0.6830	0.85
0.0258	72.0	8136	0.7039	0.82
0.0776	73.0	8249	0.6931	0.83
0.0684	74.0	8362	0.6688	0.82
0.0169	75.0	8475	0.6966	0.83
0.1039	76.0	8588	0.6914	0.83
0.0361	77.0	8701	0.6978	0.84
0.0143	78.0	8814	0.7023	0.84
0.0161	79.0	8927	0.7156	0.83
0.0207	80.0	9040	0.7264	0.82
0.0129	81.0	9153	0.7155	0.82
0.0161	82.0	9266	0.7418	0.81
0.0284	83.0	9379	0.7270	0.82
0.0166	84.0	9492	0.7460	0.83
0.0144	85.0	9605	0.7430	0.83
0.0121	86.0	9718	0.7459	0.83
0.0116	87.0	9831	0.7579	0.83
0.0106	88.0	9944	0.7485	0.83
0.0104	89.0	10057	0.7586	0.81
0.0121	90.0	10170	0.7579	0.84
0.01	91.0	10283	0.7474	0.83
0.0099	92.0	10396	0.7528	0.83
0.0117	93.0	10509	0.7603	0.82
0.0174	94.0	10622	0.7646	0.83
0.0103	95.0	10735	0.7557	0.83
0.0102	96.0	10848	0.7548	0.83
0.0101	97.0	10961	0.7519	0.83
0.0096	98.0	11074	0.7557	0.83
0.0098	99.0	11187	0.7556	0.83
0.0098	100.0	11300	0.7554	0.83

Framework versions

Transformers 4.30.2
Pytorch 2.0.1+cu117
Datasets 2.13.1
Tokenizers 0.13.3