gemma2b-summarize-gemini1_5flash-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: 2.5319

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: 4
• gradient_accumulation_steps: 2
• total_train_batch_size: 64
• total_eval_batch_size: 32
• 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
2.0246	0.9811	26	2.6613
1.3202	2.0	53	2.5405
1.1694	2.9811	79	2.5125
1.1076	4.0	106	2.5138
1.0651	4.9811	132	2.5086
1.0394	6.0	159	2.5248
1.0232	6.9811	185	2.5264
1.0042	8.0	212	2.5296
1.0109	8.9811	238	2.5319
1.0064	9.8113	260	2.5319

Framework versions

• PEFT 0.11.1
• Transformers 4.40.1
• Pytorch 2.2.0+cu121
• Datasets 2.19.2
• Tokenizers 0.19.1