SS_model

This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.3980
• Accuracy: 0.9587

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: 2e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.153	1.0	4301	0.1472	0.9526
0.1165	2.0	8602	0.1376	0.9562
0.0951	3.0	12903	0.1462	0.9596
0.0851	4.0	17204	0.1550	0.9602
0.0709	5.0	21505	0.1848	0.9596
0.069	6.0	25806	0.2027	0.9586
0.0591	7.0	30107	0.2266	0.9582
0.047	8.0	34408	0.2110	0.9573
0.0391	9.0	38709	0.2405	0.9577
0.0333	10.0	43010	0.2865	0.9566
0.0336	11.0	47311	0.2671	0.9588
0.0226	12.0	51612	0.2743	0.9567
0.0266	13.0	55913	0.3281	0.9577
0.0191	14.0	60214	0.3062	0.9572
0.0232	15.0	64515	0.3479	0.9585
0.0149	16.0	68816	0.3542	0.9587
0.0099	17.0	73117	0.3646	0.9587
0.0123	18.0	77418	0.3721	0.9584
0.0091	19.0	81719	0.3896	0.9590
0.0086	20.0	86020	0.3980	0.9587

Framework versions

• Transformers 4.28.0
• Pytorch 2.0.1+cu118
• Datasets 2.14.4
• Tokenizers 0.13.3