zephyr-7b-gemma-sft-african-ultrachat-200k-GGUF

Quantized GGUF model files for zephyr-7b-gemma-sft-african-ultrachat-200k from masakhane

Original Model Card:

zephyr-7b-gemma-sft-african-ultrachat-2000k

This model is a fine-tuned version of google/gemma-7b on the masakhane/african-ultrachat and the israel/untrachat_en datasets. It achieves the following results on the evaluation set:

• Loss: 1.1549

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: 1
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• 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: 3

Training results

Training Loss	Epoch	Step	Validation Loss
1.0785	1.0	17748	1.2602
0.6614	2.0	35496	1.1089
0.2983	3.0	53244	1.1549

Framework versions

• Transformers 4.39.0.dev0
• Pytorch 2.2.1+cu121
• Datasets 2.14.6
• Tokenizers 0.15.2