zephyr-rag-agent

This model is a fine-tuned version of HuggingFaceH4/zephyr-7b-beta on the erbacher/rag-and-roll dataset. It achieves the following results on the evaluation set:

• Loss: 1.1829

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: 4e-05
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• distributed_type: multi-GPU
• num_devices: 2
• gradient_accumulation_steps: 16
• total_train_batch_size: 128
• total_eval_batch_size: 8
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss
1.1559	0.99	27	1.1650
1.0887	1.98	54	1.1555
1.0566	2.97	81	1.1623
1.0264	6.95	91	1.1689
0.9977	7.97	105	1.1779
0.9808	9.0	119	1.1820
0.9791	9.8	130	1.1829

Framework versions

• PEFT 0.7.1
• Transformers 4.36.2
• Pytorch 2.2.2+cu121
• Datasets 2.14.6
• Tokenizers 0.15.2