llama38binstruct_summarize_v4

This model is a fine-tuned version of NousResearch/Meta-Llama-3-8B-Instruct on the generator dataset. It achieves the following results on the evaluation set:

• Loss: 1.4313

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: 1
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: constant
• lr_scheduler_warmup_steps: 0.03
• training_steps: 100

Training results

Training Loss	Epoch	Step	Validation Loss
1.5211	1.25	25	1.4041
0.4473	2.5	50	1.3731
0.2109	3.75	75	1.3571
0.102	5.0	100	1.4313

Framework versions

• PEFT 0.11.1
• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1