token_fine_tunned_flipkart_2_gl6

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: 0.7363
• Precision: 0.7243
• Recall: 0.7752
• F1: 0.7489
• Accuracy: 0.7558

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	120	1.0057	0.6623	0.7212	0.6905	0.6995
No log	2.0	240	0.8581	0.6660	0.7290	0.6961	0.7080
No log	3.0	360	0.8085	0.6882	0.7518	0.7186	0.7302
No log	4.0	480	0.7890	0.6970	0.7575	0.7260	0.7332
0.92	5.0	600	0.7716	0.7036	0.7596	0.7305	0.7372
0.92	6.0	720	0.7573	0.7028	0.7603	0.7304	0.7397
0.92	7.0	840	0.7510	0.7135	0.7653	0.7385	0.7462
0.92	8.0	960	0.7509	0.7192	0.7688	0.7432	0.7472
0.7004	9.0	1080	0.7409	0.7181	0.7717	0.7439	0.7472
0.7004	10.0	1200	0.7428	0.7155	0.7710	0.7422	0.7492
0.7004	11.0	1320	0.7414	0.7223	0.7752	0.7479	0.7523
0.7004	12.0	1440	0.7426	0.7207	0.7710	0.7450	0.7492
0.6265	13.0	1560	0.7368	0.7255	0.7745	0.7492	0.7553
0.6265	14.0	1680	0.7388	0.7239	0.7738	0.7480	0.7538
0.6265	15.0	1800	0.7338	0.7239	0.7738	0.7480	0.7538
0.6265	16.0	1920	0.7368	0.7243	0.7752	0.7489	0.7548
0.5879	17.0	2040	0.7371	0.7270	0.7767	0.7510	0.7568
0.5879	18.0	2160	0.7371	0.7243	0.7752	0.7489	0.7558
0.5879	19.0	2280	0.7356	0.7247	0.7752	0.7491	0.7553
0.5879	20.0	2400	0.7363	0.7243	0.7752	0.7489	0.7558

Framework versions

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