yahoo-bert-32shot

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: 2.3294
• Accuracy: 0.0968
• Precision: 0.1083
• Recall: 0.0971

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: 100
• eval_batch_size: 100
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 200
• 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: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall
1.2459	1.0	1	2.3337	0.0736	0.0477	0.0943
1.2503	2.0	2	2.3256	0.08	0.0801	0.0959
1.2187	3.0	3	2.2839	0.1986	0.1120	0.1018
1.1842	4.0	4	2.2784	0.2029	0.1056	0.1016
1.1529	5.0	5	2.3265	0.1042	0.1029	0.0985
1.1138	6.0	6	2.3265	0.1042	0.1029	0.0985
1.1187	7.0	7	2.3294	0.0968	0.1083	0.0971

Framework versions

• Transformers 4.52.4
• Pytorch 2.6.0+cu124
• Datasets 3.6.0
• Tokenizers 0.21.1