results

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

• Loss: 1.3126
• Accuracy: 0.5763

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: 10
• eval_batch_size: 16
• 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: 100
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
2.0037	0.1562	100	1.7526	0.3956
1.5105	0.3125	200	1.3946	0.5106
1.4205	0.4688	300	1.3603	0.5125
1.2743	0.625	400	1.2951	0.5275
1.2303	0.7812	500	1.2911	0.5394
1.2417	0.9375	600	1.3487	0.5162
1.1077	1.0938	700	1.2595	0.5519
0.9817	1.25	800	1.3000	0.5369
0.9348	1.4062	900	1.2245	0.5744
0.9900	1.5625	1000	1.2446	0.5569
0.9424	1.7188	1100	1.2562	0.545
0.8584	1.875	1200	1.2506	0.5631
0.8807	2.0312	1300	1.2251	0.5687
0.6016	2.1875	1400	1.2914	0.5687
0.6114	2.3438	1500	1.3173	0.5644
0.5374	2.5	1600	1.3376	0.5725
0.6132	2.6562	1700	1.3115	0.5763
0.5819	2.8125	1800	1.3140	0.5763
0.5765	2.9688	1900	1.3126	0.5763

Framework versions

• Transformers 5.2.0
• Pytorch 2.7.1+cu118
• Tokenizers 0.22.2