rlcc-palate-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: 1.8831
• Accuracy: 0.8049
• F1 Macro: 0.5751
• Precision Macro: 0.5829
• Recall Macro: 0.6074
• Total Tf: [330, 80, 1150, 80]

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
1.1239	1.0	37	1.0929	0.7854	0.4581	0.4644	0.4843	[322, 88, 1142, 88]
1.0966	2.0	74	1.0095	0.8049	0.4341	0.4847	0.4513	[330, 80, 1150, 80]
0.9736	3.0	111	1.0467	0.8098	0.5311	0.5396	0.5271	[332, 78, 1152, 78]
0.7549	4.0	148	1.0651	0.7976	0.5381	0.5417	0.5606	[327, 83, 1147, 83]
0.6054	5.0	185	1.1613	0.8122	0.5799	0.5767	0.6065	[333, 77, 1153, 77]
0.4563	6.0	222	1.3234	0.8146	0.5998	0.6069	0.6501	[334, 76, 1154, 76]
0.3093	7.0	259	1.3972	0.8146	0.5904	0.5941	0.6094	[334, 76, 1154, 76]
0.1836	8.0	296	1.7261	0.8049	0.5787	0.5880	0.6291	[330, 80, 1150, 80]
0.1617	9.0	333	1.7743	0.8049	0.5791	0.5951	0.6291	[330, 80, 1150, 80]
0.1209	10.0	370	1.9516	0.8073	0.5921	0.6081	0.6603	[331, 79, 1151, 79]
0.0736	11.0	407	1.8831	0.8049	0.5751	0.5829	0.6074	[330, 80, 1150, 80]

Framework versions

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