zephyr-220m-sft-full

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

zephyr-220m-sft-full

This model is a fine-tuned version of BEE-spoke-data/smol_llama-220M-openhermes on the Ultrachat_200k dataset. It achieves the following results on the evaluation set:

• Loss: 1.6579

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: 2e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• distributed_type: multi-GPU
• num_devices: 2
• gradient_accumulation_steps: 4
• total_train_batch_size: 128
• total_eval_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• num_epochs: 1

Training results

Framework versions

• Transformers 4.37.0.dev0
• Pytorch 2.1.2+cu121
• Datasets 2.15.0
• Tokenizers 0.15.0

https://wandb.ai/amazingvince/huggingface/runs/5rffzk3x/workspace?workspace=user-amazingvince