gemma2b-summarize-claude3sonnet-256k

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: 2.6999

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: 3
• gradient_accumulation_steps: 2
• total_train_batch_size: 48
• total_eval_batch_size: 24
• 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
0.9714	0.9994	808	2.4535
0.8916	2.0	1617	2.4785
0.8752	2.9994	2425	2.5144
0.8424	4.0	3234	2.5590
0.8173	4.9994	4042	2.6021
0.7949	6.0	4851	2.6446
0.7732	6.9994	5659	2.6786
0.7605	8.0	6468	2.6913
0.7532	8.9994	7276	2.6995
0.7647	9.9938	8080	2.6999

Framework versions

• PEFT 0.11.1
• Transformers 4.41.2
• Pytorch 2.2.2+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1