rlcc-appearance-upsample_replacement-absa-max

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

• Loss: 1.5661
• Accuracy: 0.6220
• F1 Macro: 0.5882
• Precision Macro: 0.5858
• Recall Macro: 0.6126
• Total Tf: [255, 155, 1075, 155]

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
1.092	1.0	66	1.0985	0.5171	0.4268	0.3942	0.5033	[212, 198, 1032, 198]
1.013	2.0	132	1.0659	0.6073	0.5068	0.5150	0.5646	[249, 161, 1069, 161]
0.9201	3.0	198	1.0787	0.6341	0.5833	0.6272	0.6442	[260, 150, 1080, 150]
0.7413	4.0	264	1.1163	0.6561	0.6226	0.6328	0.6475	[269, 141, 1089, 141]
0.6606	5.0	330	1.2175	0.6439	0.6095	0.6147	0.6386	[264, 146, 1084, 146]
0.5027	6.0	396	1.2477	0.6268	0.5918	0.5979	0.6114	[257, 153, 1077, 153]
0.4779	7.0	462	1.2777	0.6488	0.6188	0.6159	0.6298	[266, 144, 1086, 144]
0.3738	8.0	528	1.3978	0.6415	0.6096	0.6103	0.6312	[263, 147, 1083, 147]
0.3518	9.0	594	1.5661	0.6220	0.5882	0.5858	0.6126	[255, 155, 1075, 155]

Framework versions

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