TTC4900Model

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: 0.0667
• Accuracy: 0.9859
• F1: 0.9418
• Precision: 0.9562
• Recall: 0.9309

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: 16
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 100
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
1.5192	0.3289	50	0.9342	0.7575	0.1077	0.0947	0.125
0.6007	0.6579	100	0.4256	0.8767	0.3189	0.2983	0.3445
0.2704	0.9868	150	0.2471	0.9561	0.6877	0.6916	0.6917
0.1382	1.3158	200	0.1346	0.9727	0.8789	0.9054	0.8698
0.1132	1.6447	250	0.0824	0.9876	0.9350	0.9701	0.9103
0.0981	1.9737	300	0.0431	0.9942	0.9749	0.9892	0.9635
0.0369	2.3026	350	0.0466	0.9892	0.9376	0.9576	0.9275
0.0373	2.6316	400	0.0413	0.9909	0.9602	0.9580	0.9630
0.0235	2.9605	450	0.0407	0.9909	0.9613	0.9600	0.9630

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Tokenizers 0.19.1