hBERTv2_new_pretrain_w_init__mnli
This model is a fine-tuned version of gokuls/bert_12_layer_model_v2_complete_training_new_wt_init on the GLUE MNLI dataset. It achieves the following results on the evaluation set:
- Loss: 1.0956
- Accuracy: 0.3295
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: 4e-05
- train_batch_size: 128
- eval_batch_size: 128
- 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
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.1017 | 1.0 | 3068 | 1.0985 | 0.3274 |
| 1.0989 | 2.0 | 6136 | 1.0957 | 0.3274 |
| 1.0987 | 3.0 | 9204 | 1.0990 | 0.3274 |
| 1.0986 | 4.0 | 12272 | 1.0989 | 0.3274 |
| 1.0988 | 5.0 | 15340 | 1.1108 | 0.3274 |
| 1.099 | 6.0 | 18408 | 1.0968 | 0.3545 |
| 1.0988 | 7.0 | 21476 | 1.0976 | 0.3274 |
Framework versions
- Transformers 4.29.2
- Pytorch 1.14.0a0+410ce96
- Datasets 2.12.0
- Tokenizers 0.13.3
- Downloads last month
- 3
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.