Six_Class_Sentimental_Classifier_DistilBERT_base

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: 5.3555

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-06
• train_batch_size: 45
• eval_batch_size: 40
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 14
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.6974	1.0	77	1.4043
0.2468	2.0	154	2.1543
0.1334	3.0	231	1.8906
0.1318	4.0	308	2.1289
0.0677	5.0	385	4.5
0.046	6.0	462	4.9570
0.027	7.0	539	4.3633
0.0174	8.0	616	4.5273
0.0201	9.0	693	4.8633
0.014	10.0	770	4.6719
0.0094	11.0	847	4.5820
0.0048	12.0	924	4.7070
0.0016	13.0	1001	5.3828
0.002	14.0	1078	5.3555

Framework versions

• Transformers 4.43.3
• Pytorch 2.4.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1