Robbert-v2-dutch-base-finetuned-emotion-dominance Open-source Model - Effortlessly Analyze Dutch Emotional Dominance

Home

Robbert V2 Dutch Base Finetuned Emotion Dominance

Developed by antalvdb

Emotion dominance analysis model fine-tuned based on RobBERT-v2 Dutch foundation model

Text Classification

Transformers

Open Source License:MIT #Dutch Sentiment Analysis #High-precision Emotion Recognition #Text Regression Model

Downloads 35

Release Time : 7/29/2024

Model Overview

This model is a fine-tuned version of the RobBERT-v2 Dutch foundation model for sentiment analysis tasks, specifically designed to analyze emotional dominance in text.

Model Features

Dutch Sentiment Analysis

Specialized for analyzing emotional dominance in Dutch text

Efficient Fine-tuning

Performed 50 epochs of efficient fine-tuning on the foundation model

Low Error Rate

Achieved a root mean square error of 0.1984 on the evaluation set

Model Capabilities

Dutch text analysis

Emotion intensity prediction

Text emotional dominance evaluation

Use Cases

Sentiment Analysis

Social Media Emotion Monitoring

Analyze emotional intensity in Dutch social media content

Quantifies the intensity of user emotional expression

Customer Feedback Analysis

Assess the degree of emotional dominance in Dutch customer reviews

Helps identify customer feedback with strong emotional expression

🚀 robbert-v2-dutch-base-finetuned-emotion-dominance

This model is a fine - tuned version of pdelobelle/robbert-v2-dutch-base, which can achieve good performance on relevant evaluation metrics.

🚀 Quick Start

This model is a fine-tuned version of pdelobelle/robbert-v2-dutch-base on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.0394
Rmse: 0.1984

📚 Documentation

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

🔧 Technical Details

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Rmse
0.1031	1.0	25	0.0433	0.2080
0.0444	2.0	50	0.0433	0.2082
0.0371	3.0	75	0.0443	0.2106
0.0318	4.0	100	0.0470	0.2167
0.0289	5.0	125	0.0611	0.2472
0.0267	6.0	150	0.0394	0.1984
0.0217	7.0	175	0.0419	0.2047
0.0199	8.0	200	0.0412	0.2029
0.0173	9.0	225	0.0477	0.2184
0.0164	10.0	250	0.0490	0.2213
0.0145	11.0	275	0.0417	0.2043
0.0126	12.0	300	0.0454	0.2130
0.0149	13.0	325	0.0421	0.2052
0.0113	14.0	350	0.0424	0.2059
0.0117	15.0	375	0.0426	0.2063
0.0107	16.0	400	0.0437	0.2091
0.0097	17.0	425	0.0406	0.2015
0.0102	18.0	450	0.0488	0.2209
0.01	19.0	475	0.0421	0.2053
0.0101	20.0	500	0.0383	0.1957
0.01	21.0	525	0.0404	0.2009
0.0092	22.0	550	0.0522	0.2285
0.0086	23.0	575	0.0390	0.1975
0.0085	24.0	600	0.0455	0.2133
0.0075	25.0	625	0.0427	0.2066
0.0071	26.0	650	0.0398	0.1995
0.0073	27.0	675	0.0424	0.2060
0.0079	28.0	700	0.0422	0.2055
0.0068	29.0	725	0.0388	0.1970
0.0071	30.0	750	0.0382	0.1953
0.0065	31.0	775	0.0394	0.1986
0.0066	32.0	800	0.0390	0.1975
0.006	33.0	825	0.0395	0.1987
0.0059	34.0	850	0.0404	0.2010
0.0062	35.0	875	0.0378	0.1944
0.0063	36.0	900	0.0374	0.1935
0.0056	37.0	925	0.0398	0.1995
0.0058	38.0	950	0.0383	0.1957
0.0056	39.0	975	0.0378	0.1945
0.0057	40.0	1000	0.0407	0.2017
0.006	41.0	1025	0.0392	0.1980
0.0057	42.0	1050	0.0398	0.1994
0.0053	43.0	1075	0.0377	0.1941
0.0056	44.0	1100	0.0392	0.1980
0.0053	45.0	1125	0.0410	0.2024
0.0057	46.0	1150	0.0396	0.1990
0.0048	47.0	1175	0.0398	0.1995
0.0054	48.0	1200	0.0397	0.1992
0.005	49.0	1225	0.0389	0.1972
0.0051	50.0	1250	0.0394	0.1984

Framework versions

Transformers 4.42.4
Pytorch 2.3.1+cu121
Datasets 2.20.0
Tokenizers 0.19.1

📄 License

This model is under the MIT license.

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご