bert-base-uncased-tweet-disaster-classification

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

• Loss: 0.5396
• Accuracy: 0.8076

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: 1e-05
• train_batch_size: 64
• eval_batch_size: 64
• 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
• lr_scheduler_warmup_steps: 500
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	96	0.6598	0.7439
No log	2.0	192	0.4624	0.8011
No log	3.0	288	0.4350	0.8148
No log	4.0	384	0.4326	0.8188
No log	5.0	480	0.4331	0.8247
0.4631	6.0	576	0.4566	0.8227
0.4631	7.0	672	0.4711	0.8194
0.4631	8.0	768	0.5045	0.8102
0.4631	9.0	864	0.5400	0.8050
0.4631	10.0	960	0.5396	0.8076

Framework versions

• Transformers 4.47.1
• Pytorch 2.4.1+cu121
• Datasets 3.2.0
• Tokenizers 0.21.0