metadata

library_name: transformers
license: mit
base_model: microsoft/deberta-v3-base
tags:
  - generated_from_trainer
metrics:
  - f1
model-index:
  - name: debertas_seeker
    results: []

debertas_seeker

This model is a fine-tuned version of microsoft/deberta-v3-base on the None dataset. It achieves the following results on the evaluation set:

Loss: 1.1085
F1: 0.2748

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: 5e-05
train_batch_size: 2
eval_batch_size: 2
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
num_epochs: 25

Training results

Training Loss	Epoch	Step	Validation Loss	F1
1.0582	1.0	183	1.1088	0.1245
1.1036	2.0	366	1.1238	0.2748
1.086	3.0	549	1.1455	0.2748
1.073	4.0	732	1.1285	0.2748
1.0916	5.0	915	1.1420	0.1245
1.0869	6.0	1098	1.1110	0.2748
1.0621	7.0	1281	1.1171	0.2748
1.0989	8.0	1464	1.0948	0.2748
1.0525	9.0	1647	1.1294	0.2748
1.1366	10.0	1830	1.1037	0.2748
1.0849	11.0	2013	1.0932	0.2748
1.0844	12.0	2196	1.1148	0.2748
1.0925	13.0	2379	1.1049	0.2748
1.09	14.0	2562	1.1110	0.2748
1.0739	15.0	2745	1.1129	0.2748
1.0938	16.0	2928	1.1148	0.2748
1.0961	17.0	3111	1.0970	0.2748
1.0834	18.0	3294	1.1065	0.2748
1.0885	19.0	3477	1.1149	0.2748
1.0789	20.0	3660	1.1135	0.2748
1.0893	21.0	3843	1.1135	0.2748
1.0686	22.0	4026	1.1142	0.2748
1.041	23.0	4209	1.1108	0.2748
1.0524	24.0	4392	1.1108	0.2748
1.0675	25.0	4575	1.1085	0.2748

Framework versions

Transformers 4.48.0
Pytorch 2.5.1+cu121
Datasets 3.2.0
Tokenizers 0.21.0