bertnew-newscategoryclassification-fullmodel-3

This model is a fine-tuned version of distilbert-base-uncased on the None dataset.

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: 64
• eval_batch_size: 64
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 600
• training_steps: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Class 0 Accuracy	Class 1 Accuracy	Class 2 Accuracy	Class 3 Accuracy	Class 4 Accuracy	Class 5 Accuracy	Class 6 Accuracy	Class 7 Accuracy	Class 8 Accuracy	Class 9 Accuracy	Class 10 Accuracy	Class 11 Accuracy	Class 12 Accuracy	Class 13 Accuracy	Class 14 Accuracy	Class 15 Accuracy	Class 16 Accuracy	Class 17 Accuracy	Class 18 Accuracy	Class 19 Accuracy	Class 20 Accuracy	Class 21 Accuracy	Class 22 Accuracy	Class 23 Accuracy	Class 24 Accuracy	Class 25 Accuracy	Class 26 Accuracy	Class 27 Accuracy	Class 28 Accuracy	Class 29 Accuracy	Class 30 Accuracy	Class 31 Accuracy	Class 32 Accuracy	Class 33 Accuracy	Class 34 Accuracy	Class 35 Accuracy	Class 36 Accuracy	Class 37 Accuracy	Class 38 Accuracy	Class 39 Accuracy	Class 40 Accuracy	Class 41 Accuracy	Overall Accuracy
No log	0.0045	10	3.7525	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0190	0.0	0.0	0.0	0.0	0.0	0.0	0.9864	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0237

Framework versions

• Transformers 4.42.4
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1