best_model_bert_uncasedbert-base-uncased-finetuned-sst2

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

• Loss: 0.4410
• Accuracy: 0.9071

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: 1.4078269054384274e-05
• train_batch_size: 4
• eval_batch_size: 16
• seed: 34
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	1684	0.3870	0.9025
No log	2.0	3368	0.4139	0.9060
0.4762	3.0	5052	0.4410	0.9071

Framework versions

• Transformers 4.38.2
• Pytorch 2.1.0+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2