olm-bert-tiny-december-2022-target-glue-stsb

This model is a fine-tuned version of muhtasham/olm-bert-tiny-december-2022 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 2.4058
• Pearson: 0.3207
• Spearmanr: 0.3227

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	Pearson	Spearmanr
3.7225	2.78	500	2.3571	0.0394	0.0504
1.9638	5.56	1000	2.3486	0.1721	0.1893
1.7812	8.33	1500	2.3649	0.2248	0.2401
1.5724	11.11	2000	2.3334	0.2645	0.2767
1.3776	13.89	2500	2.4034	0.2785	0.2861
1.2174	16.67	3000	2.3773	0.2963	0.3043
1.0875	19.44	3500	2.3327	0.3213	0.3205
0.9406	22.22	4000	2.3715	0.3216	0.3222
0.8757	25.0	4500	2.3264	0.3274	0.3281
0.7946	27.78	5000	2.4058	0.3207	0.3227

Framework versions

• Transformers 4.27.0.dev0
• Pytorch 1.13.1+cu116
• Datasets 2.9.1.dev0
• Tokenizers 0.13.2