distilbert_sa_GLUE_Experiment_logit_kd_pretrain_mnli
This model is a fine-tuned version of gokuls/distilbert_sa_pre-training-complete on the GLUE MNLI dataset. It achieves the following results on the evaluation set:
- Loss: 0.3863
- Accuracy: 0.8105
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: 5e-05
- train_batch_size: 256
- eval_batch_size: 256
- 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
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.4379 | 1.0 | 1534 | 0.3984 | 0.7976 |
0.3845 | 2.0 | 3068 | 0.3953 | 0.8047 |
0.359 | 3.0 | 4602 | 0.3935 | 0.8102 |
0.3411 | 4.0 | 6136 | 0.3962 | 0.8077 |
0.3279 | 5.0 | 7670 | 0.3959 | 0.8172 |
0.3189 | 6.0 | 9204 | 0.4018 | 0.8102 |
0.3119 | 7.0 | 10738 | 0.4040 | 0.8073 |
0.3071 | 8.0 | 12272 | 0.3990 | 0.8175 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.9.0
- Tokenizers 0.13.2
- Downloads last month
- 8
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.