token_fine_tunned_flipkart_2

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: 0.3435
• Precision: 0.8797
• Recall: 0.9039
• F1: 0.8916
• Accuracy: 0.9061

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: 8

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	109	0.5647	0.7398	0.8123	0.7744	0.8111
No log	2.0	218	0.3863	0.8165	0.8751	0.8448	0.8716
No log	3.0	327	0.3367	0.8599	0.8847	0.8721	0.8869
No log	4.0	436	0.3266	0.8688	0.8911	0.8798	0.8977
0.527	5.0	545	0.3508	0.8595	0.8898	0.8744	0.8909
0.527	6.0	654	0.3410	0.8748	0.9045	0.8894	0.9009
0.527	7.0	763	0.3431	0.8754	0.9045	0.8897	0.9049
0.527	8.0	872	0.3435	0.8797	0.9039	0.8916	0.9061

Framework versions

• Transformers 4.19.2
• Pytorch 1.11.0+cu102
• Datasets 2.2.2
• Tokenizers 0.12.1