gemma7b-summarize-gemini1_5flash-2k

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: 7.7045

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
49.7965	0.8571	3	15.4869
39.0892	2.0	7	12.5338
23.1465	2.8571	10	10.1182
23.1465	4.0	14	8.4587
19.7449	4.8571	17	8.0612
18.8693	6.0	21	7.8270
18.8693	6.8571	24	7.7329
18.4335	8.0	28	7.6986
18.2424	8.5714	30	7.7045

Framework versions

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