bef3b78b-3c4c-4f34-9e5e-6c54b73c72c2

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: 1.9537

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: 0.000213
• 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	0.0004	1	2.9044
2.1938	0.0180	50	2.3313
2.1463	0.0360	100	2.2186
2.0668	0.0540	150	2.1604
2.0443	0.0721	200	2.0997
1.9561	0.0901	250	2.0649
1.84	0.1081	300	2.0247
1.8607	0.1261	350	1.9961
1.8471	0.1441	400	1.9687
1.85	0.1621	450	1.9591
1.8888	0.1801	500	1.9537

Framework versions

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