<!-- 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-mnli-from-scratch-custom-tokenizer-target-glue-stsb
This model is a fine-tuned version of muhtasham/tiny-mlm-glue-mnli-from-scratch-custom-tokenizer on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.0116
- Pearson: 0.2065
- Spearmanr: 0.2191
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 |
|---|---|---|---|---|---|
| 3.4686 | 2.78 | 500 | 2.3726 | -0.0027 | 0.0046 |
| 2.007 | 5.56 | 1000 | 2.4554 | 0.1070 | 0.1026 |
| 1.6757 | 8.33 | 1500 | 2.5454 | 0.1855 | 0.2018 |
| 1.2994 | 11.11 | 2000 | 2.6006 | 0.2215 | 0.2353 |
| 1.0455 | 13.89 | 2500 | 2.6117 | 0.2278 | 0.2338 |
| 0.8597 | 16.67 | 3000 | 2.9475 | 0.2118 | 0.2236 |
| 0.7389 | 19.44 | 3500 | 2.8112 | 0.2173 | 0.2237 |
| 0.6597 | 22.22 | 4000 | 3.0116 | 0.2065 | 0.2191 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2
