model_IMDB_bert_base_peft

This model is a fine-tuned version of nlptown/bert-base-multilingual-uncased-sentiment on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.2116
• Accuracy: 0.9224

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.2559	1.0	1563	0.2355	0.9088
0.2406	2.0	3126	0.2285	0.9134
0.2322	3.0	4689	0.2185	0.9173
0.2291	4.0	6252	0.2174	0.9193
0.2177	5.0	7815	0.2171	0.9186
0.2218	6.0	9378	0.2154	0.9202
0.2116	7.0	10941	0.2127	0.9221
0.2133	8.0	12504	0.2101	0.9225
0.2076	9.0	14067	0.2125	0.9221
0.2029	10.0	15630	0.2116	0.9224

Framework versions

• PEFT 0.8.2
• Transformers 4.37.2
• Pytorch 2.0.1+cu117
• Datasets 2.17.0
• Tokenizers 0.15.2