cudaTest

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

• Loss: 0.6334
• Compute Metrics: :
• Accuracy: 0.676
• Balanced Accuracy: 0.4893
• F1 Score: 0.8058
• Recall: 0.9655
• Precision: 0.6914

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
• gradient_accumulation_steps: 8
• total_train_batch_size: 256
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Compute Metrics	Accuracy	Balanced Accuracy	F1 Score	Recall	Precision
No log	1.0	2	0.6369	:	0.688	0.5017	0.8134	0.9770	0.6967
No log	2.0	4	0.6302	:	0.684	0.5043	0.8092	0.9626	0.6979
No log	3.0	6	0.6313	:	0.69	0.4975	0.8161	0.9885	0.6949
No log	4.0	8	0.6338	:	0.668	0.4854	0.7995	0.9511	0.6896
0.6818	5.0	10	0.6334	:	0.676	0.4893	0.8058	0.9655	0.6914

Framework versions

• Transformers 4.26.0
• Pytorch 1.13.1+cu117
• Datasets 2.9.0
• Tokenizers 0.13.2