gemma7b-summarize-gpt4o-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: 8.6199

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
45.5656	1.0	2	16.5046
45.5656	2.0	4	14.2000
35.6654	3.0	6	12.9944
35.6654	4.0	8	11.5695
22.2461	5.0	10	10.3065
22.2461	6.0	12	9.3645
22.2461	7.0	14	8.9071
19.7508	8.0	16	8.6934
19.7508	9.0	18	8.6287
19.172	10.0	20	8.6199

Framework versions

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