xlmr-sentiment-multilingual-ar-en-de-fr – AI Model by Einstien | AlphaNeural AI

You can deploy this model and start earning money today!

Einstien/
xlmr-sentiment-multilingual-ar-en-de-fr

like

0

text-classification

generated_from_trainer

FacebookAI/xlm-roberta-base

text-embeddings-inference

endpoints_compatible

Views

No views yet

sentiment

This model is a fine-tuned version of xlm-roberta-base on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.7687
Accuracy: 0.6986
F1 Weighted: 0.6937
F1 Negative: 0.7364
F1 Neutral: 0.6139
F1 Positive: 0.7307

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: 64
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 0.1
num_epochs: 5
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1 Weighted	F1 Negative	F1 Neutral	F1 Positive
0.9128	1.0	230	0.8246	0.6497	0.6494	0.6719	0.5809	0.6953
0.8235	2.0	460	0.7274	0.6829	0.6617	0.7775	0.4848	0.7228
0.7429	3.0	690	0.7049	0.7076	0.6984	0.7797	0.5785	0.737
0.6650	4.0	920	0.7257	0.7022	0.6937	0.7754	0.5758	0.73
0.6278	5.0	1150	0.7504	0.6952	0.6823	0.7796	0.5423	0.7248

Framework versions

Transformers 5.9.0
Pytorch 2.11.0+cu128
Datasets 3.6.0
Tokenizers 0.22.2