watson-cerebras

This model is a fine-tuned version of cerebras/Cerebras-GPT-111M on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 0.4660
• Validation Loss: 5.9842
• 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': 'AdamWeightDecay', 'learning_rate': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
• training_precision: float32

Training results

Train Loss	Validation Loss	Epoch
1.9574	4.6971	0
1.4977	4.9437	1
1.1154	5.1888	2
0.8291	5.4171	3
0.6540	5.5523	4
0.5654	5.6664	5
0.5230	5.7875	6
0.4976	5.8304	7
0.4838	5.8645	8
0.4660	5.9842	9

Framework versions

• Transformers 4.30.2
• TensorFlow 2.12.0
• Datasets 2.13.1
• Tokenizers 0.13.3