# Load model directly
from transformers import AutoModelForMaskedLM
model = AutoModelForMaskedLM.from_pretrained("gokuls/bert_12_layer_model_v2_complete_training_new_wt_init", dtype="auto")Quick Links
bert_12_layer_model_v2_complete_training_new_wt_init
This model is a fine-tuned version of on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.9056
- Accuracy: 0.4895
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 |
|---|---|---|---|---|
| 6.4002 | 0.08 | 10000 | 6.3571 | 0.1312 |
| 5.5302 | 0.16 | 20000 | 5.1885 | 0.2427 |
| 4.04 | 0.25 | 30000 | 3.8071 | 0.3863 |
| 3.7185 | 0.33 | 40000 | 3.4770 | 0.4246 |
| 3.5317 | 0.41 | 50000 | 3.3049 | 0.4441 |
| 3.4184 | 0.49 | 60000 | 3.1983 | 0.4558 |
| 3.3161 | 0.57 | 70000 | 3.1219 | 0.4650 |
| 3.2417 | 0.66 | 80000 | 3.0511 | 0.4726 |
| 3.1771 | 0.74 | 90000 | 2.9934 | 0.4789 |
| 3.1276 | 0.82 | 100000 | 2.9450 | 0.4850 |
| 3.0795 | 0.9 | 110000 | 2.9056 | 0.4895 |
Framework versions
- Transformers 4.29.2
- Pytorch 1.14.0a0+410ce96
- Datasets 2.12.0
- Tokenizers 0.13.3
- Downloads last month
- 6
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="gokuls/bert_12_layer_model_v2_complete_training_new_wt_init")