distilbert_add_GLUE_Experiment_logit_kd_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: 1.1348
• 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
3.4305	1.0	23	2.1402	-0.0344	-0.0359	-0.0352
2.3785	2.0	46	1.6911	nan	nan	nan
1.8497	3.0	69	1.3624	-0.0028	-0.0046	-0.0037
1.455	4.0	92	1.1653	nan	nan	nan
1.1878	5.0	115	1.1348	nan	nan	nan
1.0926	6.0	138	1.1581	nan	nan	nan
1.0833	7.0	161	1.1832	nan	nan	nan
1.0904	8.0	184	1.2266	0.0782	0.0759	0.0771
1.0833	9.0	207	1.1724	0.0826	0.0744	0.0785
1.0805	10.0	230	1.1530	0.0798	0.0761	0.0779

Framework versions

• Transformers 4.26.0
• Pytorch 1.14.0a0+410ce96
• Datasets 2.9.0
• Tokenizers 0.13.2