README.md

metadata

license: apache-2.0
base_model: distilbert-base-uncased
tags:
  - generated_from_keras_callback
model-index:
  - name: edyfjm07/distilbert-base-uncased-QA2-finetuned-squad-es
    results: []

edyfjm07/distilbert-base-uncased-QA2-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: 0.1855
• Train End Logits Accuracy: 0.9286
• Train Start Logits Accuracy: 0.9475
• Validation Loss: 1.2809
• Validation End Logits Accuracy: 0.7994
• Validation Start Logits Accuracy: 0.7774
• Epoch: 9

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': 0.0001, '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
2.3428	0.4160	0.4317	1.3438	0.5611	0.6458	0
1.1526	0.6261	0.6397	1.0597	0.6677	0.7429	1
0.7612	0.7269	0.7647	1.0245	0.7210	0.7806	2
0.5528	0.7836	0.8319	1.2436	0.7116	0.7712	3
0.4667	0.8340	0.8435	1.0705	0.7524	0.7555	4
0.3834	0.8813	0.8687	1.1209	0.7586	0.7712	5
0.3678	0.8634	0.8876	1.2341	0.7618	0.7649	6
0.2555	0.9044	0.9181	1.1561	0.7649	0.8056	7
0.2151	0.9160	0.9328	1.0908	0.7931	0.7994	8
0.1855	0.9286	0.9475	1.2809	0.7994	0.7774	9

Framework versions

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