b7f41a81-fc98-4dea-9ea9-2fba22471e63

This model is a fine-tuned version of NousResearch/Nous-Capybara-7B-V1 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.6312

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: 0.000201
• 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	0.0000	1	1.1474
0.7885	0.0021	50	0.7839
0.7251	0.0042	100	0.7551
0.7064	0.0063	150	0.7158
0.69	0.0084	200	0.6984
0.6673	0.0105	250	0.6767
0.6487	0.0126	300	0.6593
0.6134	0.0148	350	0.6437
0.6354	0.0169	400	0.6360
0.6264	0.0190	450	0.6319
0.6764	0.0211	500	0.6312

Framework versions

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