<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
tiny-mlm-glue-stsb-target-glue-stsb
This model is a fine-tuned version of muhtasham/tiny-mlm-glue-stsb on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.9825
- Pearson: 0.8061
- Spearmanr: 0.8043
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
- num_epochs: 200
Training results
| Training Loss | Epoch | Step | Validation Loss | Pearson | Spearmanr |
|---|---|---|---|---|---|
| 3.5377 | 2.78 | 500 | 1.3011 | 0.6728 | 0.6791 |
| 1.1922 | 5.56 | 1000 | 1.1395 | 0.7537 | 0.7804 |
| 0.8417 | 8.33 | 1500 | 0.9970 | 0.7940 | 0.8066 |
| 0.6813 | 11.11 | 2000 | 0.8608 | 0.8097 | 0.8125 |
| 0.5633 | 13.89 | 2500 | 0.8698 | 0.8122 | 0.8111 |
| 0.4986 | 16.67 | 3000 | 0.9720 | 0.8120 | 0.8145 |
| 0.4365 | 19.44 | 3500 | 0.8846 | 0.8128 | 0.8114 |
| 0.3969 | 22.22 | 4000 | 0.9115 | 0.8139 | 0.8118 |
| 0.3544 | 25.0 | 4500 | 0.9530 | 0.8139 | 0.8116 |
| 0.3379 | 27.78 | 5000 | 0.9940 | 0.8096 | 0.8094 |
| 0.3146 | 30.56 | 5500 | 0.9590 | 0.8092 | 0.8090 |
| 0.2881 | 33.33 | 6000 | 0.9825 | 0.8061 | 0.8043 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2
