token_fine_tunned_flipkart_2_gl7

This model is a fine-tuned version of vinayak361/token_fine_tunned_flipkart_2_gl on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.7179
• Precision: 0.7122
• Recall: 0.7571
• F1: 0.7340
• Accuracy: 0.7485

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-06
• 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	Precision	Recall	F1	Accuracy
No log	1.0	135	1.0392	0.6634	0.7121	0.6869	0.6982
No log	2.0	270	0.8567	0.6697	0.7128	0.6906	0.7093
No log	3.0	405	0.8102	0.6707	0.7204	0.6947	0.7146
0.9223	4.0	540	0.7840	0.6860	0.7363	0.7103	0.7253
0.9223	5.0	675	0.7668	0.6886	0.7301	0.7088	0.7267
0.9223	6.0	810	0.7543	0.6886	0.7329	0.7100	0.7301
0.9223	7.0	945	0.7501	0.6997	0.7384	0.7185	0.7340
0.708	8.0	1080	0.7383	0.6949	0.7426	0.7180	0.7335
0.708	9.0	1215	0.7360	0.7030	0.7453	0.7235	0.7379
0.708	10.0	1350	0.7319	0.7048	0.7453	0.7245	0.7389
0.708	11.0	1485	0.7306	0.7052	0.7467	0.7254	0.7398
0.6327	12.0	1620	0.7220	0.7049	0.7488	0.7262	0.7413
0.6327	13.0	1755	0.7198	0.7059	0.7509	0.7277	0.7432
0.6327	14.0	1890	0.7203	0.7108	0.7585	0.7338	0.7481
0.5954	15.0	2025	0.7193	0.7118	0.7571	0.7337	0.7481
0.5954	16.0	2160	0.7175	0.7122	0.7585	0.7346	0.7476
0.5954	17.0	2295	0.7176	0.7144	0.7599	0.7364	0.7481
0.5954	18.0	2430	0.7183	0.7153	0.7599	0.7369	0.7490
0.5699	19.0	2565	0.7173	0.7122	0.7571	0.7340	0.7485
0.5699	20.0	2700	0.7179	0.7122	0.7571	0.7340	0.7485

Framework versions

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