README.md

metadata

license: apache-2.0
base_model: distilbert-base-uncased
tags:
  - generated_from_keras_callback
model-index:
  - name: edyfjm07/distilbert-base-uncased-QA4-finetuned-squad-es
    results: []

edyfjm07/distilbert-base-uncased-QA4-finetuned-squad-es

This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 0.3325
• Train End Logits Accuracy: 0.8550
• Train Start Logits Accuracy: 0.9097
• Validation Loss: 1.1519
• Validation End Logits Accuracy: 0.7429
• Validation Start Logits Accuracy: 0.7900
• Epoch: 13

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:

• optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 1e-05, 'decay_steps': 5474, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
• training_precision: float32

Training results

Train Loss	Train End Logits Accuracy	Train Start Logits Accuracy	Validation Loss	Validation End Logits Accuracy	Validation Start Logits Accuracy	Epoch
3.8949	0.1733	0.1891	2.4981	0.3918	0.3981	0
2.0479	0.4097	0.4811	1.6575	0.4890	0.6113	1
1.4343	0.5599	0.6166	1.3371	0.5768	0.6426	2
1.0892	0.6313	0.6891	1.1850	0.6677	0.6865	3
0.9172	0.6870	0.7405	1.1305	0.6771	0.7335	4
0.7470	0.7258	0.7910	1.0674	0.7147	0.7524	5
0.6728	0.7426	0.8088	1.0843	0.7116	0.7680	6
0.5989	0.7721	0.8403	1.0787	0.7304	0.7649	7
0.4988	0.8057	0.8582	1.1091	0.7398	0.7618	8
0.4674	0.8214	0.8540	1.1150	0.7367	0.7774	9
0.4173	0.8256	0.8782	1.1434	0.7335	0.7774	10
0.3804	0.8319	0.8897	1.1256	0.7335	0.7900	11
0.3831	0.8456	0.8834	1.1614	0.7429	0.7931	12
0.3325	0.8550	0.9097	1.1519	0.7429	0.7900	13

Framework versions

• Transformers 4.41.2
• TensorFlow 2.15.0
• Datasets 2.20.0
• Tokenizers 0.19.1