edyfjm07/distilbert-base-uncased-QA3-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: 5.9545
• Train End Logits Accuracy: 0.0032
• Train Start Logits Accuracy: 0.0
• Validation Loss: 5.9506
• Validation End Logits Accuracy: 0.0
• Validation Start Logits Accuracy: 0.0063
• Epoch: 40

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': 0.001, 'decay_steps': 2419, '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
4.7467	0.1006	0.0561	5.8046	0.0157	0.0878	0
4.8045	0.0148	0.0138	5.2042	0.0094	0.0094	1
5.9402	0.0032	0.0053	5.9506	0.0031	0.0063	2
5.9626	0.0021	0.0021	5.9506	0.0031	0.0031	3
5.9599	0.0042	0.0	5.9506	0.0	0.0	4
5.9718	0.0	0.0011	5.9506	0.0	0.0031	5
5.9587	0.0021	0.0064	5.9506	0.0031	0.0031	6
5.9657	0.0064	0.0032	5.9506	0.0031	0.0188	7
5.9617	0.0021	0.0032	5.9506	0.0031	0.0063	8
5.9596	0.0021	0.0032	5.9506	0.0	0.0031	9
5.9648	0.0021	0.0021	5.9506	0.0094	0.0063	10
5.9608	0.0021	0.0032	5.9506	0.0125	0.0094	11
5.9567	0.0021	0.0053	5.9506	0.0063	0.0	12
5.9625	0.0011	0.0011	5.9506	0.0	0.0	13
5.9640	0.0	0.0011	5.9506	0.0031	0.0	14
5.9606	0.0011	0.0	5.9506	0.0063	0.0063	15
5.9622	0.0032	0.0053	5.9506	0.0094	0.0063	16
5.9600	0.0011	0.0021	5.9506	0.0	0.0063	17
5.9579	0.0011	0.0011	5.9506	0.0063	0.0094	18
5.9598	0.0032	0.0053	5.9506	0.0031	0.0	19
5.9589	0.0021	0.0032	5.9506	0.0063	0.0031	20
5.9566	0.0032	0.0021	5.9506	0.0	0.0	21
5.9536	0.0011	0.0053	5.9506	0.0	0.0	22
5.9592	0.0021	0.0021	5.9506	0.0031	0.0031	23
5.9548	0.0032	0.0042	5.9506	0.0	0.0	24
5.9569	0.0	0.0021	5.9506	0.0	0.0	25
5.9640	0.0032	0.0011	5.9506	0.0031	0.0031	26
5.9497	0.0011	0.0011	5.9506	0.0	0.0031	27
5.9558	0.0	0.0053	5.9506	0.0063	0.0031	28
5.9563	0.0021	0.0032	5.9506	0.0063	0.0063	29
5.9585	0.0032	0.0032	5.9506	0.0	0.0094	30
5.9569	0.0011	0.0021	5.9506	0.0094	0.0063	31
5.9580	0.0011	0.0021	5.9506	0.0063	0.0	32
5.9532	0.0032	0.0011	5.9506	0.0	0.0063	33
5.9523	0.0021	0.0032	5.9506	0.0	0.0	34
5.9552	0.0042	0.0011	5.9506	0.0	0.0	35
5.9538	0.0021	0.0032	5.9506	0.0	0.0	36
5.9538	0.0032	0.0032	5.9506	0.0031	0.0063	37
5.9567	0.0011	0.0021	5.9506	0.0063	0.0031	38
5.9570	0.0053	0.0032	5.9506	0.0	0.0031	39
5.9545	0.0032	0.0	5.9506	0.0	0.0063	40

Framework versions

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