nhatminh/PatchTSTPretrain

output

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

• Loss: 0.1301

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-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
• num_epochs: 100

Training results

Training Loss	Epoch	Step	Validation Loss
0.2376	1.0	557	0.1378
0.1626	2.0	1114	0.1266
0.1515	3.0	1671	0.1213
0.146	4.0	2228	0.1188
0.1425	5.0	2785	0.1166
0.14	6.0	3342	0.1161
0.138	7.0	3899	0.1144
0.1365	8.0	4456	0.1141
0.1351	9.0	5013	0.1138
0.134	10.0	5570	0.1137
0.1329	11.0	6127	0.1124
0.132	12.0	6684	0.1122
0.1312	13.0	7241	0.1118
0.1305	14.0	7798	0.1119
0.1299	15.0	8355	0.1118
0.1294	16.0	8912	0.1112
0.129	17.0	9469	0.1112
0.1285	18.0	10026	0.1116
0.1282	19.0	10583	0.1105
0.1276	20.0	11140	0.1103
0.1273	21.0	11697	0.1106
0.1269	22.0	12254	0.1103
0.1267	23.0	12811	0.1103
0.1263	24.0	13368	0.1098
0.126	25.0	13925	0.1098
0.1257	26.0	14482	0.1098
0.1253	27.0	15039	0.1101
0.125	28.0	15596	0.1104
0.1247	29.0	16153	0.1102
0.1245	30.0	16710	0.1093
0.1241	31.0	17267	0.1112
0.124	32.0	17824	0.1092
0.1237	33.0	18381	0.1097
0.1235	34.0	18938	0.1094
0.1233	35.0	19495	0.1097
0.1229	36.0	20052	0.1101
0.1227	37.0	20609	0.1107
0.1226	38.0	21166	0.1094
0.1224	39.0	21723	0.1094
0.1221	40.0	22280	0.1102
0.122	41.0	22837	0.1109
0.1218	42.0	23394	0.1101

Framework versions

• Transformers 4.37.0
• Pytorch 2.1.2
• Datasets 2.1.0
• Tokenizers 0.15.1