1c1610b5-db7f-4de0-ad61-9964470478c8

This model is a fine-tuned version of heegyu/WizardVicuna-open-llama-3b-v2 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.3776

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: 0.00021
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 8
• optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 50
• training_steps: 500

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0006	1	1.6402
1.6432	0.0297	50	1.5698
1.5784	0.0593	100	1.6011
1.5138	0.0890	150	1.5654
1.6622	0.1186	200	1.5684
1.6122	0.1483	250	1.4589
1.5786	0.1779	300	1.4229
1.5569	0.2076	350	1.3998
1.6038	0.2372	400	1.3831
1.4889	0.2669	450	1.3847
1.4997	0.2966	500	1.3776

Framework versions

• PEFT 0.13.2
• Transformers 4.46.0
• Pytorch 2.5.0+cu124
• Datasets 3.0.1
• Tokenizers 0.20.1