rlcc-taste-upsample_replacement-absa-None

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

• Loss: 1.9818
• Accuracy: 0.6268
• F1 Macro: 0.6744
• Precision Macro: 0.6735
• Recall Macro: 0.6758
• Total Tf: [257, 153, 1077, 153]

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: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 90
• num_epochs: 25

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1 Macro	Precision Macro	Recall Macro	Total Tf
1.1008	1.0	91	1.1034	0.4098	0.4187	0.6948	0.5326	[168, 242, 988, 242]
0.8457	2.0	182	0.9629	0.6024	0.6511	0.6508	0.6525	[247, 163, 1067, 163]
0.5988	3.0	273	1.0210	0.6220	0.6676	0.6704	0.6671	[255, 155, 1075, 155]
0.3711	4.0	364	1.2443	0.6268	0.6738	0.6732	0.6770	[257, 153, 1077, 153]
0.2455	5.0	455	1.3622	0.6439	0.6881	0.6873	0.6911	[264, 146, 1084, 146]
0.2254	6.0	546	1.4938	0.6195	0.6667	0.6656	0.6692	[254, 156, 1074, 156]
0.1683	7.0	637	1.7064	0.6317	0.6770	0.6759	0.6864	[259, 151, 1079, 151]
0.1288	8.0	728	1.7828	0.6122	0.6593	0.6616	0.6739	[251, 159, 1071, 159]
0.1041	9.0	819	1.8101	0.6366	0.6826	0.6906	0.6793	[261, 149, 1081, 149]
0.0638	10.0	910	1.9818	0.6268	0.6744	0.6735	0.6758	[257, 153, 1077, 153]

Framework versions

• Transformers 4.47.0
• Pytorch 2.5.1+cu121
• Datasets 3.2.0
• Tokenizers 0.21.0