cefr-roberta – AI Model by MBZD1 | AlphaNeural AI

You can deploy this model and start earning money today!

MBZD1/
cefr-roberta

like

0

text-classification

generated_from_trainer

FacebookAI/roberta-base

text-embeddings-inference

endpoints_compatible

Views

No views yet

cefr-roberta

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

Loss: 1.0260
Accuracy: 0.6353
F1 Macro: 0.5873
F1 Weighted: 0.6363

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: 16
eval_batch_size: 16
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
lr_scheduler_warmup_ratio: 0.1
num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1 Macro	F1 Weighted
0.9285	1.0	438	0.8797	0.6092	0.5477	0.6093
0.9351	2.0	876	0.8099	0.6206	0.5759	0.6211
0.7249	3.0	1314	0.8247	0.6266	0.5886	0.6272
0.4899	4.0	1752	0.9293	0.6259	0.5762	0.6272
0.4114	5.0	2190	1.0260	0.6353	0.5873	0.6363

Framework versions

Transformers 4.50.2
Pytorch 2.6.0
Datasets 3.0.1
Tokenizers 0.21.1