crypto_sustainability_news_text_classifier-distilbert-base-uncased

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: 0.0678
• Accuracy: 1.0

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: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.0723	1.0	8	1.0659	0.2167
1.0079	2.0	16	0.9776	0.75
0.908	3.0	24	0.8537	0.9333
0.7741	4.0	32	0.7082	0.9667
0.6449	5.0	40	0.5749	0.9667
0.5218	6.0	48	0.4551	0.9667
0.4026	7.0	56	0.3505	1.0
0.3144	8.0	64	0.2714	1.0
0.2424	9.0	72	0.2163	1.0
0.1939	10.0	80	0.1709	1.0
0.1559	11.0	88	0.1384	1.0
0.1247	12.0	96	0.1169	1.0
0.1073	13.0	104	0.0992	1.0
0.094	14.0	112	0.0890	1.0
0.0823	15.0	120	0.0813	1.0
0.0759	16.0	128	0.0756	1.0
0.0708	17.0	136	0.0720	1.0
0.0684	18.0	144	0.0697	1.0
0.0668	19.0	152	0.0683	1.0
0.0634	20.0	160	0.0678	1.0

Framework versions

• Transformers 4.47.0.dev0
• Pytorch 2.4.0+cu121
• Datasets 3.0.2
• Tokenizers 0.20.0