rlcc-palate-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: 1.2779
• Accuracy: 0.8171
• F1 Macro: 0.5922
• Precision Macro: 0.5829
• Recall Macro: 0.6206
• Total Tf: [335, 75, 1155, 75]

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: 36
• num_epochs: 25

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1 Macro	Precision Macro	Recall Macro	Total Tf
1.1112	1.0	37	1.0729	0.8415	0.4637	0.448	0.4976	[345, 65, 1165, 65]
1.0758	2.0	74	1.0543	0.8244	0.5164	0.5073	0.5455	[338, 72, 1158, 72]
0.9471	3.0	111	1.0910	0.8098	0.5865	0.5919	0.6389	[332, 78, 1152, 78]
0.8048	4.0	148	1.1168	0.8171	0.5949	0.5950	0.6538	[335, 75, 1155, 75]
0.6768	5.0	185	1.1974	0.7659	0.4830	0.4232	0.6422	[314, 96, 1134, 96]
0.5944	6.0	222	1.1607	0.8293	0.5226	0.5111	0.5443	[340, 70, 1160, 70]
0.5677	7.0	259	1.1742	0.7707	0.5088	0.6112	0.6313	[316, 94, 1136, 94]
0.5315	8.0	296	1.2979	0.7829	0.5368	0.6392	0.6482	[321, 89, 1141, 89]
0.5361	9.0	333	1.2779	0.8171	0.5922	0.5829	0.6206	[335, 75, 1155, 75]

Framework versions

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