zephyr-hagrid-deduplicated-rag-agent-3b

This model is a fine-tuned version of stabilityai/stablelm-zephyr-3b on the erbacher/rag-and-roll-hagrid-deduplicated dataset. It achieves the following results on the evaluation set:

• Loss: 1.4172

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: 0.0001
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss
1.5167	0.99	66	1.4631
1.4531	2.0	133	1.4279
1.4024	2.99	199	1.4186
1.4031	4.0	266	1.4172
1.3087	4.96	330	1.4172

Framework versions

• PEFT 0.12.0
• Transformers 4.38.2
• Pytorch 2.0.1
• Datasets 2.20.0
• Tokenizers 0.15.2