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

masakhane/zephyr-7b-gemma-sft-african-ultrachat-200k

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

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

masakhane/
zephyr-7b-gemma-sft-african-ultrachat-200k