hbertv1-emotion-logit_KD-small

This model is a fine-tuned version of gokuls/model_v1_complete_training_wt_init_48_small_freeze_new on the emotion dataset. It achieves the following results on the evaluation set:

• Loss: 0.2473
• Accuracy: 0.9335

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: 5e-05
• train_batch_size: 64
• eval_batch_size: 64
• seed: 33
• distributed_type: multi-GPU
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.4023	1.0	250	0.5204	0.8825
0.3903	2.0	500	0.3014	0.91
0.2438	3.0	750	0.2849	0.9185
0.1778	4.0	1000	0.2489	0.9265
0.1394	5.0	1250	0.2878	0.9205
0.1218	6.0	1500	0.2887	0.923
0.1083	7.0	1750	0.2788	0.9285
0.1019	8.0	2000	0.2373	0.928
0.0898	9.0	2250	0.2473	0.9335
0.0817	10.0	2500	0.2822	0.926
0.0827	11.0	2750	0.2474	0.926
0.0733	12.0	3000	0.2329	0.9285
0.0631	13.0	3250	0.2301	0.929
0.06	14.0	3500	0.2565	0.9295

Framework versions

• Transformers 4.35.2
• Pytorch 1.14.0a0+410ce96
• Datasets 2.15.0
• Tokenizers 0.15.0