metadata

license: mit
base_model: microsoft/deberta-v3-base
tags:
  - generated_from_trainer
metrics:
  - f1
  - precision
  - recall
  - accuracy
model-index:
  - name: debert-imeocap
    results: []

debert-imeocap

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: 1.8660
F1: 0.6185
Precision: 0.6337
Recall: 0.6154
Accuracy: 0.6154

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
num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	F1	Precision	Recall	Accuracy
0.4637	1.0	74	1.3864	0.6129	0.6262	0.6115	0.6115
0.3815	2.0	148	1.3801	0.6193	0.6348	0.6173	0.6173
0.3363	3.0	222	1.6944	0.6077	0.6297	0.6077	0.6077
0.31	4.0	296	1.6945	0.5995	0.6285	0.5942	0.5942
0.2885	5.0	370	1.5945	0.6218	0.6306	0.6192	0.6192
0.2594	6.0	444	1.7662	0.6279	0.6396	0.625	0.625
0.2319	7.0	518	1.7093	0.6210	0.6321	0.6173	0.6173
0.2306	8.0	592	1.8068	0.6279	0.6341	0.6288	0.6288
0.2167	9.0	666	1.7306	0.6376	0.6444	0.6346	0.6346
0.2158	10.0	740	1.8745	0.6262	0.6318	0.6269	0.6269
0.222	11.0	814	1.8323	0.6200	0.6348	0.6173	0.6173
0.2152	12.0	888	1.8576	0.6246	0.6363	0.6212	0.6212
0.226	13.0	962	1.8880	0.6343	0.6411	0.6308	0.6308
0.2097	14.0	1036	1.8884	0.6152	0.6326	0.6115	0.6115
0.2192	15.0	1110	1.8660	0.6185	0.6337	0.6154	0.6154

Framework versions

Transformers 4.39.3
Pytorch 2.1.2
Datasets 2.18.0
Tokenizers 0.15.2