small-mlm-glue-stsb-target-glue-rte

This model is a fine-tuned version of muhtasham/small-mlm-glue-stsb on the None dataset. It achieves the following results on the evaluation set:

• Loss: 3.8025
• Accuracy: 0.5993

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: 3e-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: constant
• training_steps: 5000

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.4125	6.41	500	1.3674	0.5884
0.0577	12.82	1000	2.5654	0.6065
0.0268	19.23	1500	2.8994	0.5884
0.0158	25.64	2000	3.1525	0.6101
0.0131	32.05	2500	3.5112	0.5884
0.0137	38.46	3000	3.5227	0.5740
0.0174	44.87	3500	3.0736	0.6354
0.0139	51.28	4000	3.5635	0.5921
0.0122	57.69	4500	3.3484	0.5957
0.0074	64.1	5000	3.8025	0.5993

Framework versions

• Transformers 4.26.0.dev0
• Pytorch 1.13.0+cu116
• Datasets 2.8.1.dev0
• Tokenizers 0.13.2