# Load model directly
from transformers import AutoTokenizer, AutoModelForMaskedLM
tokenizer = AutoTokenizer.from_pretrained("muhtasham/tiny-mlm-wikitext-from-scratch")
model = AutoModelForMaskedLM.from_pretrained("muhtasham/tiny-mlm-wikitext-from-scratch")Quick Links
tiny-mlm-wikitext-from-scratch
This model is a fine-tuned version of on the None dataset. It achieves the following results on the evaluation set:
- Loss: nan
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 |
|---|---|---|---|
| 9.4738 | 0.4 | 500 | 8.8348 |
| 8.3457 | 0.8 | 1000 | 8.1343 |
| 7.8654 | 1.2 | 1500 | nan |
| 7.7136 | 1.6 | 2000 | 7.9122 |
| 7.6903 | 2.0 | 2500 | 7.8458 |
| 7.6397 | 2.4 | 3000 | 7.8610 |
| 7.6227 | 2.8 | 3500 | 7.8522 |
| 7.5991 | 3.2 | 4000 | nan |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.1+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2
- Downloads last month
- 7
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="muhtasham/tiny-mlm-wikitext-from-scratch")