# Load model directly
from transformers import AutoTokenizer, AutoModelForQuestionAnswering
tokenizer = AutoTokenizer.from_pretrained("Almancy/practica_3_model")
model = AutoModelForQuestionAnswering.from_pretrained("Almancy/practica_3_model", device_map="auto")Quick Links
practica_3_model
This model is a fine-tuned version of distilbert/distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.6600
- Start Accuracy: 0.3233
- End Accuracy: 0.33
- Total Accuracy: 0.3267
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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Start Accuracy | End Accuracy | Total Accuracy |
|---|---|---|---|---|---|---|
| 3.6709 | 1.0 | 88 | 3.6060 | 0.1367 | 0.1133 | 0.125 |
| 3.171 | 2.0 | 176 | 3.1622 | 0.1967 | 0.15 | 0.1733 |
| 2.6294 | 3.0 | 264 | 2.8054 | 0.2983 | 0.275 | 0.2867 |
| 2.3842 | 4.0 | 352 | 2.6600 | 0.3233 | 0.33 | 0.3267 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.5.0+cu121
- Datasets 3.0.2
- Tokenizers 0.19.1
- Downloads last month
- 5
Model tree for Almancy/practica_3_model
Base model
distilbert/distilbert-base-uncased
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("question-answering", model="Almancy/practica_3_model")