gemma7b-summarize-claude3sonnet-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: 2.7259

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
18.539	0.9744	19	8.6238
11.8891	2.0	39	6.5199
2.3149	2.9744	58	3.2759
1.5266	4.0	78	2.8999
1.3332	4.9744	97	2.7966
1.2502	6.0	117	2.7460
1.2007	6.9744	136	2.7332
1.1904	8.0	156	2.7283
1.1866	8.9744	175	2.7323
1.1715	9.7436	190	2.7259

Framework versions

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