rlcc-appearance-upsample_replacement-absa-avg

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

• Loss: 1.5832
• Accuracy: 0.6512
• F1 Macro: 0.6175
• Precision Macro: 0.6196
• Recall Macro: 0.6284
• Total Tf: [267, 143, 1087, 143]

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
1.0983	1.0	66	1.0816	0.5707	0.4937	0.5162	0.5104	[234, 176, 1054, 176]
1.0066	2.0	132	1.0376	0.6268	0.5145	0.4757	0.5695	[257, 153, 1077, 153]
0.938	3.0	198	1.0321	0.6293	0.5938	0.6134	0.6210	[258, 152, 1078, 152]
0.7799	4.0	264	1.0649	0.6537	0.6215	0.6371	0.6464	[268, 142, 1088, 142]
0.6479	5.0	330	1.1215	0.6634	0.6268	0.6332	0.6363	[272, 138, 1092, 138]
0.541	6.0	396	1.2126	0.6659	0.6328	0.6444	0.6322	[273, 137, 1093, 137]
0.4776	7.0	462	1.2496	0.6537	0.6222	0.6248	0.6379	[268, 142, 1088, 142]
0.375	8.0	528	1.3441	0.6585	0.6292	0.6279	0.6313	[270, 140, 1090, 140]
0.3663	9.0	594	1.4417	0.6317	0.5984	0.5967	0.6128	[259, 151, 1079, 151]
0.2935	10.0	660	1.5452	0.6488	0.6147	0.6149	0.6147	[266, 144, 1086, 144]
0.2331	11.0	726	1.5832	0.6512	0.6175	0.6196	0.6284	[267, 143, 1087, 143]

Framework versions

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