You can deploy this model and start earning money today!

trungpq/
rlcc-taste-class-weight-absa-None

Name: rlcc-taste-class-weight-absa-None
Availability: InStock

transformers

safetensors

bert_with_absa

generated_from_trainer

endpoints_compatible

Views

No views yet

rlcc-taste-class-weight-absa-None

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

Loss: 0.9590
Accuracy: 0.6488
F1 Macro: 0.6917
Precision Macro: 0.6993
Recall Macro: 0.6886
Total Tf: [266, 144, 1086, 144]

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 49
num_epochs: 25

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1 Macro	Precision Macro	Recall Macro	Total Tf
1.0908	1.0	50	1.0899	0.4829	0.4197	0.4721	0.5054	[198, 212, 1018, 212]
1.0913	2.0	100	1.0815	0.4927	0.4263	0.5268	0.5130	[202, 208, 1022, 208]
1.0568	3.0	150	1.0561	0.5317	0.5438	0.5884	0.5592	[218, 192, 1038, 192]
0.9952	4.0	200	1.0291	0.5707	0.6201	0.6325	0.6166	[234, 176, 1054, 176]
0.9222	5.0	250	1.0160	0.5659	0.6200	0.6416	0.6200	[232, 178, 1052, 178]
0.8608	6.0	300	0.9883	0.6146	0.6634	0.6630	0.6680	[252, 158, 1072, 158]
0.8124	7.0	350	0.9813	0.6146	0.6562	0.6762	0.6508	[252, 158, 1072, 158]
0.767	8.0	400	0.9779	0.6146	0.6561	0.6752	0.6505	[252, 158, 1072, 158]
0.7398	9.0	450	0.9656	0.6341	0.6799	0.6890	0.6799	[260, 150, 1080, 150]
0.6974	10.0	500	0.9865	0.6049	0.6559	0.6638	0.6589	[248, 162, 1068, 162]
0.6908	11.0	550	0.9720	0.6341	0.6780	0.6999	0.6751	[260, 150, 1080, 150]
0.6581	12.0	600	0.9714	0.6317	0.6762	0.6809	0.6733	[259, 151, 1079, 151]
0.6572	13.0	650	0.9617	0.6366	0.6791	0.6943	0.6754	[261, 149, 1081, 149]
0.6365	14.0	700	0.9621	0.6415	0.6787	0.6990	0.6731	[263, 147, 1083, 147]
0.6426	15.0	750	0.9728	0.6220	0.6667	0.6815	0.6625	[255, 155, 1075, 155]
0.6179	16.0	800	0.9723	0.6293	0.6742	0.6825	0.6698	[258, 152, 1078, 152]
0.6114	17.0	850	0.9696	0.6317	0.6778	0.6824	0.6747	[259, 151, 1079, 151]
0.606	18.0	900	0.9695	0.6293	0.6734	0.6955	0.6712	[258, 152, 1078, 152]
0.6055	19.0	950	0.9685	0.6293	0.6737	0.6809	0.6698	[258, 152, 1078, 152]
0.6084	20.0	1000	0.9613	0.6366	0.6816	0.6904	0.6787	[261, 149, 1081, 149]
0.602	21.0	1050	0.9633	0.6390	0.6850	0.6887	0.6838	[262, 148, 1082, 148]
0.6086	22.0	1100	0.9574	0.6537	0.6965	0.7049	0.6930	[268, 142, 1088, 142]
0.5948	23.0	1150	0.9593	0.6439	0.6869	0.6964	0.6829	[264, 146, 1084, 146]
0.5957	24.0	1200	0.9583	0.6512	0.6937	0.7017	0.6905	[267, 143, 1087, 143]
0.5933	25.0	1250	0.9590	0.6488	0.6917	0.6993	0.6886	[266, 144, 1086, 144]

Framework versions

Transformers 4.44.2
Pytorch 2.4.1+cu121
Datasets 3.2.0
Tokenizers 0.19.1

trungpq/rlcc-taste-class-weight-absa-None

rlcc-taste-class-weight-absa-None

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

trungpq/
rlcc-taste-class-weight-absa-None