llama381binstruct_summarize_short

This model is a fine-tuned version of NousResearch/Meta-Llama-3.1-8B-Instruct on the generator dataset. It achieves the following results on the evaluation set:

• Loss: 2.8489

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: linear
• lr_scheduler_warmup_steps: 30
• training_steps: 500

Training results

Training Loss	Epoch	Step	Validation Loss
1.7667	1.25	25	1.7939
0.7156	2.5	50	1.8135
0.3944	3.75	75	1.8429
0.2053	5.0	100	2.0996
0.1153	6.25	125	2.3466
0.0316	7.5	150	2.6045
0.0224	8.75	175	2.5789
0.0198	10.0	200	2.5765
0.0112	11.25	225	2.7507
0.0053	12.5	250	2.6317
0.0047	13.75	275	2.6792
0.0039	15.0	300	2.7628
0.0041	16.25	325	2.7830
0.0013	17.5	350	2.7905
0.0014	18.75	375	2.8053
0.0017	20.0	400	2.8236
0.0017	21.25	425	2.8352
0.0012	22.5	450	2.8429
0.0011	23.75	475	2.8473
0.0013	25.0	500	2.8489

Framework versions

• PEFT 0.12.0
• Transformers 4.44.2
• Pytorch 2.4.0+cu121
• Datasets 3.0.0
• Tokenizers 0.19.1