gemma7b-summarize-gemini1.5flash-80k

This model is a fine-tuned version of google/gemma-7b on the llama-duo/synth_summarize_dataset dataset. It achieves the following results on the evaluation set:

• Loss: 3.0229

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: 2
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• total_eval_batch_size: 4
• 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
0.8742	0.9982	280	2.1938
0.7213	2.0	561	2.1462
0.675	2.9982	841	2.1484
0.6439	4.0	1122	2.2149
0.569	4.9982	1402	2.3224
0.5317	6.0	1683	2.4839
0.472	6.9982	1963	2.6540
0.4306	8.0	2244	2.8791
0.4106	8.9982	2524	3.0011
0.4021	9.9822	2800	3.0229

Framework versions

• PEFT 0.11.1
• Transformers 4.41.0
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1