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: 8.7240

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
51.5906	1.0	2	16.5290
51.5906	2.0	4	14.1666
38.4458	3.0	6	13.0907
38.4458	4.0	8	11.6308
23.9261	5.0	10	10.3576
23.9261	6.0	12	9.4846
23.9261	7.0	14	9.0308
20.7948	8.0	16	8.8035
20.7948	9.0	18	8.7407
20.2787	10.0	20	8.7240

Framework versions

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

llama-duo/gemma7b-summarize-gemini1_5flash-1k

gemma7b-summarize-gemini1_5flash-1k

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

llama-duo/
gemma7b-summarize-gemini1_5flash-1k