gemma7b-summarize-claude3sonnet-1k

This model is a fine-tuned version of google/gemma-7b on the llama-duo/synth_summarize_dataset_dedup dataset. It achieves the following results on the evaluation set:

• Loss: 8.5689

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: 0.0002
• train_batch_size: 4
• eval_batch_size: 2
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• gradient_accumulation_steps: 2
• total_train_batch_size: 64
• total_eval_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: 10

Training results

Training Loss	Epoch	Step	Validation Loss
33.9156	0.8	2	16.5602
27.435	2.0	5	13.6870
27.435	2.8	7	12.0752
17.6281	4.0	10	10.1279
17.6281	4.8	12	9.2971
15.107	6.0	15	8.7323
15.107	6.8	17	8.6064
14.5856	8.0	20	8.5689

Framework versions

• PEFT 0.10.0
• Transformers 4.40.0
• Pytorch 2.1.2+cu121
• Datasets 2.18.0
• Tokenizers 0.19.1