gemma7b-summarize-gpt4o-128k

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: 2.4869

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
1.1594	0.9977	219	2.6195
1.0276	2.0	439	2.4670
0.9492	2.9977	658	2.4451
0.8751	4.0	878	2.4359
0.8477	4.9977	1097	2.4390
0.809	6.0	1317	2.4546
0.7918	6.9977	1536	2.4592
0.7847	8.0	1756	2.4783
0.7808	8.9977	1975	2.4889
0.7794	9.9772	2190	2.4869

Framework versions

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