deberta-v3-base-lora-isarcasm

w11wo/deberta-v3-base-lora-isarcasm

deberta-v3-base-lora-isarcasm is a machine learning model from w11wo. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

Access

Public

Updated Dec 14, 2023

Repo size

383 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin37.8 MB · 77%

At a glance

License: mit
Access: Public
Created: Dec 14, 2023
Updated: Dec 14, 2023
SHA: 233c7001

Base models

microsoft/deberta-v3-base

Model card

From the Hugging Face model README

deberta-v3-base-lora-isarcasm

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: 0.6943
Accuracy: 0.1770
F1: 0.3008
Precision: 0.1770
Recall: 1.0

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: 0.005
train_batch_size: 64
eval_batch_size: 16
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
No log	1.0	54	0.7069	0.8286	0.0	0.0	0.0
No log	2.0	108	0.6931	0.8286	0.0	0.0	0.0
No log	3.0	162	0.6986	0.8286	0.0	0.0	0.0
No log	4.0	216	0.6946	0.1714	0.2927	0.1714	1.0
No log	5.0	270	0.6939	0.1714	0.2927	0.1714	1.0

Framework versions

Transformers 4.32.0
Pytorch 2.1.1+cu121
Datasets 2.14.5
Tokenizers 0.13.3

License: mit
Created: Dec 14, 2023
Updated: Dec 14, 2023