math-mistral-7b-r32

This model is a fine-tuned version of meta-math/MetaMath-Mistral-7B on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.4624

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:

• learning_rate: 2.55e-05
• train_batch_size: 4
• eval_batch_size: 2
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 1
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.6354	0.21	1000	0.4892
0.5874	0.42	2000	0.4789
0.3006	0.63	3000	0.4694
0.2786	0.84	4000	0.4624

Framework versions

• Transformers 4.36.0.dev0
• Pytorch 2.0.0
• Datasets 2.11.0
• Tokenizers 0.14.1