gemma2b-summarize-gpt4o-16k

This model is a fine-tuned version of google/gemma-2b on the llama-duo/synth_summarize_dataset_dedup dataset. It achieves the following results on the evaluation set:

• Loss: 2.5758

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: 8
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 3
• gradient_accumulation_steps: 2
• total_train_batch_size: 48
• total_eval_batch_size: 24
• 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
1.8806	0.9863	36	2.6094
1.3239	2.0	73	2.5358
1.2327	2.9863	109	2.5192
1.1735	4.0	146	2.5203
1.1354	4.9863	182	2.5467
1.1015	6.0	219	2.5496
1.0858	6.9863	255	2.5680
1.0624	8.0	292	2.5723
1.0546	8.9863	328	2.5756
1.0623	9.8630	360	2.5758

Framework versions

• PEFT 0.11.1
• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.19.2
• Tokenizers 0.19.1