slac-taste

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

• Loss: 1.1289
• Accuracy: 0.9076
• F1 Macro: 0.8815
• Precision Macro: 0.8776
• Recall Macro: 0.8857
• Total Tf: [1454, 148, 1454, 148]

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
0.4647	1.0	213	0.3426	0.9082	0.8894	0.8698	0.9217	[1455, 147, 1455, 147]
0.4011	2.0	426	0.3131	0.9238	0.9051	0.8917	0.9222	[1480, 122, 1480, 122]
0.2826	3.0	639	0.3667	0.9101	0.8899	0.8731	0.9144	[1458, 144, 1458, 144]
0.2055	4.0	852	0.4153	0.9164	0.8953	0.8834	0.9101	[1468, 134, 1468, 134]
0.1422	5.0	1065	0.4790	0.9151	0.8922	0.8847	0.9008	[1466, 136, 1466, 136]
0.1222	6.0	1278	0.6584	0.9164	0.8932	0.8876	0.8993	[1468, 134, 1468, 134]
0.0732	7.0	1491	0.7369	0.9020	0.8769	0.8666	0.8896	[1445, 157, 1445, 157]
0.0567	8.0	1704	0.8350	0.9107	0.8859	0.8807	0.8916	[1459, 143, 1459, 143]
0.0377	9.0	1917	0.8175	0.9120	0.8885	0.8804	0.8979	[1461, 141, 1461, 141]
0.0358	10.0	2130	0.9032	0.9107	0.8866	0.8794	0.8947	[1459, 143, 1459, 143]
0.0326	11.0	2343	0.9523	0.9039	0.8794	0.8687	0.8924	[1448, 154, 1448, 154]
0.011	12.0	2556	1.1113	0.9082	0.8817	0.8797	0.8838	[1455, 147, 1455, 147]
0.0159	13.0	2769	1.1049	0.9064	0.8810	0.8741	0.8887	[1452, 150, 1452, 150]
0.0191	14.0	2982	1.1846	0.9101	0.8831	0.8843	0.8819	[1458, 144, 1458, 144]
0.0095	15.0	3195	1.1289	0.9076	0.8815	0.8776	0.8857	[1454, 148, 1454, 148]

Framework versions

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