emoBank_LaBSE_test2_epochs_20

This model is a fine-tuned version of old_models/LaBSE/0_Transformer on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0470
• Mse V: 0.0563
• Mse A: 0.0484
• Mse D: 0.0363

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: 32
• eval_batch_size: 32
• 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	Mse V	Mse A	Mse D
No log	1.0	252	0.0601	0.0677	0.0655	0.0472
0.194	2.0	504	0.0599	0.0895	0.0553	0.0348
0.194	3.0	756	0.0511	0.0524	0.0609	0.0399
0.0614	4.0	1008	0.0565	0.0719	0.0491	0.0485
0.0614	5.0	1260	0.0475	0.0661	0.0433	0.0331
0.0476	6.0	1512	0.0476	0.0561	0.0488	0.0380
0.0476	7.0	1764	0.0537	0.0587	0.0620	0.0405
0.0385	8.0	2016	0.0496	0.0543	0.0595	0.0350
0.0385	9.0	2268	0.0470	0.0563	0.0484	0.0363
0.033	10.0	2520	0.0503	0.0525	0.0585	0.0399
0.033	11.0	2772	0.0615	0.0700	0.0749	0.0396
0.028	12.0	3024	0.0509	0.0555	0.0593	0.0380
0.028	13.0	3276	0.0506	0.0572	0.0545	0.0400
0.0251	14.0	3528	0.0481	0.0537	0.0525	0.0382
0.0251	15.0	3780	0.0504	0.0512	0.0597	0.0404
0.0227	16.0	4032	0.0517	0.0580	0.0588	0.0383
0.0227	17.0	4284	0.0556	0.0541	0.0637	0.0490
0.0206	18.0	4536	0.0539	0.0595	0.0600	0.0422
0.0206	19.0	4788	0.0545	0.0571	0.0612	0.0453
0.0195	20.0	5040	0.0530	0.0563	0.0605	0.0423

Framework versions

• Transformers 4.33.1
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.13.3