a5cd1f03-3683-4cfc-abba-916e00827951

This model is a fine-tuned version of NousResearch/Hermes-2-Pro-Mistral-7B on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.4414

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: 0.000206
• train_batch_size: 4
• eval_batch_size: 4
• seed: 60
• 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	1.6315
2.2891	0.0100	50	0.7142
2.1761	0.0200	100	0.9053
1.4774	0.0300	150	0.9257
1.5358	0.0400	200	0.6987
1.3795	0.0500	250	0.6032
1.3677	0.0599	300	0.5344
1.5626	0.0699	350	0.4987
1.2497	0.0799	400	0.4655
1.3301	0.0899	450	0.4447
1.0829	0.0999	500	0.4414

Framework versions

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