bert_12_layer_model_v2_complete_training_new_wt_init_72
This model is a fine-tuned version of gokuls/bert_12_layer_model_v2_complete_training_new_wt_init_48 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.5130
- Accuracy: 0.5387
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: 1e-05
- train_batch_size: 48
- eval_batch_size: 48
- seed: 10
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 10000
- num_epochs: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
2.843 | 0.08 | 10000 | 2.6797 | 0.5170 |
2.819 | 0.16 | 20000 | 2.6623 | 0.5194 |
2.7956 | 0.25 | 30000 | 2.6402 | 0.5224 |
2.7843 | 0.33 | 40000 | 2.6235 | 0.5246 |
2.7551 | 0.41 | 50000 | 2.6014 | 0.5270 |
2.7415 | 0.49 | 60000 | 2.5862 | 0.5290 |
2.7141 | 0.57 | 70000 | 2.5725 | 0.5313 |
2.6996 | 0.66 | 80000 | 2.5559 | 0.5329 |
2.6786 | 0.74 | 90000 | 2.5378 | 0.5349 |
2.664 | 0.82 | 100000 | 2.5270 | 0.5371 |
2.6493 | 0.9 | 110000 | 2.5130 | 0.5387 |
Framework versions
- Transformers 4.29.2
- Pytorch 1.14.0a0+410ce96
- Datasets 2.12.0
- Tokenizers 0.13.3
- Downloads last month
- 4
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.