botGPT2_org_ds_cosine

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

• Train Loss: 0.1752
• Train Accuracy: 0.0379
• Train Perplexity: 236.0702
• Validation Loss: 0.1399
• Validation Accuracy: 0.0368
• Validation Perplexity: 372.2610
• Epoch: 3

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': 'AdamW', 'weight_decay': 0.004, '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': 5.4921643e-06, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
• training_precision: float32

Training results

Train Loss	Train Accuracy	Train Perplexity	Validation Loss	Validation Accuracy	Validation Perplexity	Epoch
1.3340	0.0379	1745.3442	0.2794	0.0350	106.1728	0
0.2532	0.0380	138.7101	0.1499	0.0374	397.5620	1
0.1780	0.0379	232.5203	0.1403	0.0375	365.7160	2
0.1752	0.0379	236.0702	0.1399	0.0368	372.2610	3

Framework versions

• Transformers 4.26.0
• TensorFlow 2.11.0
• Datasets 2.9.0
• Tokenizers 0.13.2