chat-prompt

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: 4.4302
• Accuracy: 0.2118

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: 5e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Use 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

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	22	5.1325	0.0059
No log	2.0	44	5.1051	0.0118
No log	3.0	66	5.0410	0.0118
No log	4.0	88	4.9587	0.0059
No log	5.0	110	4.8704	0.0294
No log	6.0	132	4.8604	0.0294
No log	7.0	154	4.6148	0.1
No log	8.0	176	4.5487	0.1176
No log	9.0	198	4.4783	0.1529
No log	10.0	220	4.4302	0.2118

Framework versions

• Transformers 4.47.0
• Pytorch 2.5.1+cu121
• Datasets 3.2.0
• Tokenizers 0.21.0