a8fdc686-7987-4304-921d-adb1686ae554

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: 1.9862

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: 0.000207
• 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: 419

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0024	1	3.0941
2.1505	0.1195	50	2.4442
1.8806	0.2389	100	2.7416
2.1693	0.3584	150	2.3181
1.984	0.4779	200	2.2799
1.9623	0.5974	250	2.1786
2.0553	0.7168	300	2.0686
1.9531	0.8363	350	1.9983
1.8796	0.9558	400	1.9862

Framework versions

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