llama38binstruct_summarize

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: 1.8731

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: 150

Training results

Training Loss	Epoch	Step	Validation Loss
1.6074	1.1905	25	1.2061
0.6597	2.3810	50	1.3782
0.2859	3.5714	75	1.5552
0.1349	4.7619	100	1.8426
0.068	5.9524	125	1.8918
0.039	7.1429	150	1.8731

Framework versions

• PEFT 0.11.1
• Transformers 4.41.2
• Pytorch 2.1.2
• Datasets 2.20.0
• Tokenizers 0.19.1