README.md

metadata

license: apache-2.0
base_model: distilbert-base-uncased
tags:
  - generated_from_keras_callback
model-index:
  - name: sevvalkapcak/newModel2
    results: []

sevvalkapcak/newModel2

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: 0.0158
• Validation Loss: 0.4239
• Train Accuracy: 0.933
• Epoch: 35

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': 5e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
• training_precision: float32

Training results

Train Loss	Validation Loss	Train Accuracy	Epoch
0.2465	0.2029	0.9085	0
0.1354	0.1302	0.939	1
0.1121	0.1588	0.934	2
0.0945	0.1551	0.937	3
0.0815	0.1696	0.939	4
0.0778	0.1647	0.932	5
0.0522	0.2356	0.931	6
0.0444	0.2861	0.9335	7
0.0329	0.2144	0.9355	8
0.0290	0.2548	0.935	9
0.0222	0.2866	0.93	10
0.0256	0.2787	0.9385	11
0.0267	0.2764	0.941	12
0.0201	0.2888	0.9315	13
0.0221	0.2737	0.934	14
0.0174	0.4403	0.93	15
0.0170	0.2836	0.932	16
0.0214	0.3033	0.9375	17
0.0125	0.3894	0.934	18
0.0271	0.3687	0.9305	19
0.0154	0.3817	0.9305	20
0.0149	0.4736	0.93	21
0.0196	0.4435	0.9325	22
0.0124	0.4873	0.929	23
0.0157	0.4008	0.932	24
0.0153	0.4074	0.931	25
0.0176	0.3996	0.9295	26
0.0160	0.3652	0.9355	27
0.0081	0.4446	0.934	28
0.0098	0.5249	0.934	29
0.0151	0.4112	0.937	30
0.0124	0.4888	0.929	31
0.0146	0.5022	0.9325	32
0.0130	0.5585	0.9305	33
0.0102	0.4304	0.935	34
0.0158	0.4239	0.933	35

Framework versions

• Transformers 4.35.2
• TensorFlow 2.15.0
• Datasets 2.16.1
• Tokenizers 0.15.1