rlcc-appearance-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: 1.9560
• Accuracy: 0.6610
• F1 Macro: 0.6269
• Precision Macro: 0.6302
• Recall Macro: 0.6268
• Total Tf: [271, 139, 1091, 139]

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: 65
• num_epochs: 25

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1 Macro	Precision Macro	Recall Macro	Total Tf
1.1096	1.0	66	1.0995	0.5537	0.5047	0.5097	0.5082	[227, 183, 1047, 183]
0.9472	2.0	132	1.0104	0.6488	0.6033	0.6293	0.6126	[266, 144, 1086, 144]
0.7192	3.0	198	1.0839	0.6707	0.6348	0.6642	0.6608	[275, 135, 1095, 135]
0.5434	4.0	264	1.1165	0.6780	0.6492	0.6490	0.6638	[278, 132, 1098, 132]
0.4376	5.0	330	1.2321	0.6805	0.6515	0.6493	0.6596	[279, 131, 1099, 131]
0.3084	6.0	396	1.4064	0.6585	0.6260	0.6300	0.6279	[270, 140, 1090, 140]
0.2117	7.0	462	1.6170	0.6512	0.6201	0.6284	0.6217	[267, 143, 1087, 143]
0.2113	8.0	528	1.8189	0.6610	0.6291	0.6321	0.6428	[271, 139, 1091, 139]
0.1301	9.0	594	1.8293	0.6659	0.6348	0.6390	0.6544	[273, 137, 1093, 137]
0.0893	10.0	660	1.9560	0.6610	0.6269	0.6302	0.6268	[271, 139, 1091, 139]

Framework versions

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