You can deploy this model and start earning money today!

trungpq/
rlcc-new-palate-upsample_replacement-absa-avg

transformers

safetensors

bert_with_absa

generated_from_trainer

endpoints_compatible

Views

No views yet

rlcc-new-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: 1.7279
Accuracy: 0.5787
F1 Macro: 0.5788
Precision Macro: 0.6284
Recall Macro: 0.5738
F1 Micro: 0.5787
Precision Micro: 0.5787
Recall Micro: 0.5787
Total Tf: [103, 75, 281, 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 OptimizerNames.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: 21
num_epochs: 25

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1 Macro	Precision Macro	Recall Macro	F1 Micro	Precision Micro	Recall Micro	Total Tf
1.1738	1.0	22	1.1040	0.3652	0.2556	0.2690	0.3612	0.3652	0.3652	0.3652	[65, 113, 243, 113]
1.0286	2.0	44	1.0621	0.4157	0.3782	0.4116	0.4253	0.4157	0.4157	0.4157	[74, 104, 252, 104]
0.8483	3.0	66	1.0167	0.5	0.4903	0.4886	0.5081	0.5	0.5	0.5	[89, 89, 267, 89]
0.6698	4.0	88	1.0451	0.5225	0.5169	0.5158	0.5272	0.5225	0.5225	0.5225	[93, 85, 271, 85]
0.5447	5.0	110	1.0517	0.5225	0.5230	0.5235	0.5275	0.5225	0.5225	0.5225	[93, 85, 271, 85]
0.4625	6.0	132	1.0768	0.5506	0.5557	0.5608	0.5525	0.5506	0.5506	0.5506	[98, 80, 276, 80]
0.3589	7.0	154	1.1766	0.5337	0.5382	0.5754	0.5312	0.5337	0.5337	0.5337	[95, 83, 273, 83]
0.2511	8.0	176	1.2353	0.5787	0.5830	0.6257	0.5757	0.5787	0.5787	0.5787	[103, 75, 281, 75]
0.1881	9.0	198	1.2861	0.5674	0.5730	0.6042	0.5676	0.5674	0.5674	0.5674	[101, 77, 279, 77]
0.1355	10.0	220	1.3305	0.5562	0.5559	0.6089	0.5514	0.5562	0.5562	0.5562	[99, 79, 277, 79]
0.1076	11.0	242	1.4219	0.5562	0.5625	0.5984	0.5559	0.5562	0.5562	0.5562	[99, 79, 277, 79]
0.0925	12.0	264	1.4681	0.5618	0.5667	0.6105	0.5594	0.5618	0.5618	0.5618	[100, 78, 278, 78]
0.1085	13.0	286	1.4877	0.5843	0.5898	0.6304	0.5824	0.5843	0.5843	0.5843	[104, 74, 282, 74]
0.0602	14.0	308	1.5180	0.5618	0.5683	0.5916	0.5623	0.5618	0.5618	0.5618	[100, 78, 278, 78]
0.0681	15.0	330	1.6498	0.5618	0.5626	0.6385	0.5578	0.5618	0.5618	0.5618	[100, 78, 278, 78]
0.0447	16.0	352	1.6794	0.5562	0.5576	0.6100	0.5515	0.5562	0.5562	0.5562	[99, 79, 277, 79]
0.0444	17.0	374	1.7401	0.5562	0.5551	0.6157	0.5507	0.5562	0.5562	0.5562	[99, 79, 277, 79]
0.0468	18.0	396	1.7279	0.5787	0.5788	0.6284	0.5738	0.5787	0.5787	0.5787	[103, 75, 281, 75]

Framework versions

Transformers 4.52.4
Pytorch 2.6.0+cu124
Datasets 3.6.0
Tokenizers 0.21.2

trungpq/rlcc-new-palate-upsample_replacement-absa-avg

rlcc-new-palate-upsample_replacement-absa-avg

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

trungpq/
rlcc-new-palate-upsample_replacement-absa-avg