gemma7b-summarize-claude3sonnet-64k

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: 2.5547

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
1.1216	0.9967	150	2.5805
0.9828	2.0	301	2.5169
0.9157	2.9967	451	2.4836
0.8753	4.0	602	2.5011
0.8334	4.9967	752	2.4945
0.796	6.0	903	2.5317
0.7745	6.9967	1053	2.5436
0.7582	8.0	1204	2.5522
0.754	8.9967	1354	2.5504
0.7572	9.9668	1500	2.5547

Framework versions

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