23efe6b9-c681-45ca-8b27-2ae5bd46b2ee

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

• Loss: 1.2339

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: 0.000212
• 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	0.0014	1	3.1059
3.3796	0.0690	50	2.5303
3.7733	0.1380	100	2.7617
3.9363	0.2070	150	1.9593
3.1219	0.2761	200	2.4845
3.1824	0.3451	250	1.9057
3.0697	0.4141	300	1.5008
2.7207	0.4831	350	1.4267
2.5935	0.5521	400	1.2924
2.5588	0.6211	450	1.2419
2.6587	0.6901	500	1.2339

Framework versions

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