snappfood_review_classifier

This model is a fine-tuned version of google-bert/bert-base-multilingual-cased on PNLPhub/snappfood-sentiment-analysis dataset. It achieves the following results on the evaluation set:

• Loss: 0.4795
• Accuracy: 0.8576

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: 30
• eval_batch_size: 30
• 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: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.2301	0.2879	500	0.4019	0.8598
0.213	0.5757	1000	0.3862	0.8607
0.2391	0.8636	1500	0.3630	0.8472
0.1895	1.1514	2000	0.3852	0.8577
0.2177	1.4393	2500	0.3732	0.8557
0.1784	1.7271	3000	0.4143	0.8581
0.1546	2.0150	3500	0.4195	0.8627
0.1377	2.3028	4000	0.4511	0.8581
0.1213	2.5907	4500	0.4887	0.8546
0.1463	2.8785	5000	0.4795	0.8576

Framework versions

• Transformers 4.53.0
• Pytorch 2.6.0+cu124
• Datasets 4.0.0
• Tokenizers 0.21.2