gemma7b-summarize-gemini1_5flash-8k

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: 2.8396

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
31.311	0.9630	13	11.0230
19.0651	2.0	27	7.4342
11.34	2.9630	40	6.8118
3.0136	4.0	54	3.6308
1.7786	4.9630	67	3.0973
1.4865	6.0	81	2.9241
1.4036	6.9630	94	2.8645
1.3424	8.0	108	2.8510
1.3298	8.9630	121	2.8410
1.3245	9.6296	130	2.8396

Framework versions

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