Na_L3_600steps_1e7rate_SFT

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

• Loss: 1.0537

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: 1e-07
• train_batch_size: 2
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 4
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 100
• training_steps: 600

Training results

Training Loss	Epoch	Step	Validation Loss
2.8904	0.2667	50	2.8306
2.5711	0.5333	100	2.4828
2.0286	0.8	150	1.9826
1.6431	1.0667	200	1.6198
1.4055	1.3333	250	1.3752
1.2427	1.6	300	1.2211
1.1406	1.8667	350	1.1275
1.0808	2.1333	400	1.0817
1.0548	2.4	450	1.0596
1.0453	2.6667	500	1.0556
1.0558	2.9333	550	1.0537
1.0493	3.2	600	1.0537

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.0+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1