zephyr-7b-gemma-sft

This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the HuggingFaceH4/deita-10k-v0-sft dataset. It achieves the following results on the evaluation set:

• Loss: 0.9467

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: 8
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• gradient_accumulation_steps: 2
• total_train_batch_size: 128
• total_eval_batch_size: 64
• 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
0.8286	0.2924	100	0.8580
0.798	0.5848	200	0.8706
0.7677	0.8772	300	0.8727
0.5584	1.1696	400	0.9159
0.5186	1.4620	500	0.8920
0.5067	1.7544	600	0.8780
0.2223	2.0468	700	0.9511
0.2114	2.3392	800	0.9492
0.1983	2.6316	900	0.9508
0.2014	2.9240	1000	0.9465

Framework versions

• Transformers 4.45.2
• Pytorch 2.5.1+rocm6.2
• Datasets 3.5.0
• Tokenizers 0.20.3