README.md

metadata

library_name: transformers
license: mit
base_model: microsoft/deberta-v3-base
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - precision
  - recall
  - f1
model-index:
  - name: mdeberta-domain_EN_fold1
    results: []

mdeberta-domain_EN_fold1

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: 0.5362
• Accuracy: 0.8288
• Precision: 0.7887
• Recall: 0.7656
• F1: 0.7752

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: 32
• eval_batch_size: 32
• 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
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
1.0312	1.0	19	0.8773	0.5890	0.8630	0.3333	0.2471
0.7596	2.0	38	0.7653	0.5890	0.8630	0.3333	0.2471
0.7097	3.0	57	0.7352	0.5890	0.8630	0.3333	0.2471
0.6673	4.0	76	0.7382	0.7466	0.6626	0.5889	0.5519
0.6028	5.0	95	0.7362	0.7740	0.6837	0.6406	0.5884
0.4939	6.0	114	0.6345	0.7466	0.6145	0.6034	0.5967
0.3969	7.0	133	0.5446	0.8014	0.7220	0.7140	0.6938
0.3291	8.0	152	0.5437	0.8082	0.7452	0.7468	0.7410
0.2975	9.0	171	0.5534	0.7945	0.7437	0.7101	0.7235
0.2573	10.0	190	0.5362	0.8288	0.7887	0.7656	0.7752

Framework versions

• Transformers 4.46.0
• Pytorch 2.3.1
• Datasets 2.21.0
• Tokenizers 0.20.1