test_model_1

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

• Loss: 0.4457
• Accuracy: 0.8989

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-06
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	125	0.3754	0.8949
No log	2.0	250	0.3674	0.8969
No log	3.0	375	0.3574	0.8999
0.1345	4.0	500	0.3786	0.9029
0.1345	5.0	625	0.3912	0.8979
0.1345	6.0	750	0.3946	0.8969
0.1345	7.0	875	0.4166	0.8959
0.0837	8.0	1000	0.4201	0.8969
0.0837	9.0	1125	0.4270	0.9029
0.0837	10.0	1250	0.4283	0.8969
0.0837	11.0	1375	0.4416	0.9039
0.0554	12.0	1500	0.4422	0.9019
0.0554	13.0	1625	0.4409	0.8989
0.0554	14.0	1750	0.4419	0.8989
0.0554	15.0	1875	0.4457	0.8989

Framework versions

• Transformers 4.36.1
• Pytorch 2.1.2
• Datasets 2.15.0
• Tokenizers 0.15.0