llama3-8b-summarize-gpt4o-128k

This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B on the llama-duo/synth_summarize_dataset_dedup dataset. It achieves the following results on the evaluation set:

• Loss: 2.2606

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: 4
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• gradient_accumulation_steps: 2
• total_train_batch_size: 128
• total_eval_batch_size: 32
• 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
0.8176	0.9954	109	2.1150
0.7464	2.0	219	2.1313
0.7128	2.9954	328	2.1444
0.6924	4.0	438	2.1631
0.6777	4.9954	547	2.1823
0.6526	6.0	657	2.2078
0.6326	6.9954	766	2.2296
0.6311	8.0	876	2.2485
0.6233	8.9954	985	2.2587
0.6194	9.9543	1090	2.2606

Framework versions

• PEFT 0.12.0
• Transformers 4.44.0
• Pytorch 2.2.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1