a6691c3d-ad46-42e2-a20f-277e16c78e6e

This model is a fine-tuned version of unsloth/llama-2-7b on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.4386

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: 0.000203
• train_batch_size: 4
• eval_batch_size: 4
• seed: 30
• 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	0.0002	1	0.7003
0.6163	0.0085	50	0.5474
0.5308	0.0169	100	0.5331
0.502	0.0254	150	0.5084
0.4737	0.0339	200	0.4848
0.481	0.0424	250	0.4776
0.4418	0.0508	300	0.4578
0.4457	0.0593	350	0.4476
0.416	0.0678	400	0.4412
0.4582	0.0762	450	0.4387
0.4545	0.0847	500	0.4386

Framework versions

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