distilbert_add_GLUE_Experiment_stsb_192

This model is a fine-tuned version of distilbert-base-uncased on the GLUE STSB dataset. It achieves the following results on the evaluation set:

• Loss: 2.2659
• Pearson: nan
• Spearmanr: nan
• Combined Score: nan

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: 256
• eval_batch_size: 256
• seed: 10
• distributed_type: multi-GPU
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 50
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Pearson	Spearmanr	Combined Score
7.0456	1.0	23	4.3280	nan	nan	nan
4.7979	2.0	46	3.4200	nan	nan	nan
3.7359	3.0	69	2.7494	nan	nan	nan
2.9308	4.0	92	2.3396	nan	nan	nan
2.3776	5.0	115	2.2659	nan	nan	nan
2.1865	6.0	138	2.3171	nan	nan	nan
2.1731	7.0	161	2.3598	nan	nan	nan
2.1793	8.0	184	2.4690	0.1389	0.1432	0.1410
2.1725	9.0	207	2.3589	0.0899	0.0808	0.0854
2.1621	10.0	230	2.3156	0.0853	0.0802	0.0827

Framework versions

• Transformers 4.26.0
• Pytorch 1.14.0a0+410ce96
• Datasets 2.8.0
• Tokenizers 0.13.2