zephyr-7b-math-case-4

This model is a fine-tuned version of alignment-handbook/zephyr-7b-sft-full on the EunsuKim/MATH and the EunsuKim/GSM8K datasets. It achieves the following results on the evaluation set:

• Loss: 0.0151

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: 1e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• total_train_batch_size: 32
• total_eval_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.03
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss
0.9831	1.0	9	0.6522
0.601	2.0	18	0.4056
0.3464	3.0	27	0.1887
0.1559	4.0	36	0.0765
0.0714	5.0	45	0.0478
0.0477	6.0	54	0.0351
0.0345	7.0	63	0.0256
0.0252	8.0	72	0.0192
0.0181	9.0	81	0.0158
0.0153	10.0	90	0.0151

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.1+cu121
• Datasets 3.0.0
• Tokenizers 0.19.1