e5ea6bf9-2231-4580-8ad1-6e852a2987a8

This model is a fine-tuned version of UCLA-AGI/Gemma-2-9B-It-SPPO-Iter2 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 2.1820

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: 10
• 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	3.5360
2.5255	0.0019	50	2.4942
2.6718	0.0038	100	2.5515
2.456	0.0056	150	2.4121
2.7822	0.0075	200	2.4379
2.3685	0.0094	250	2.3165
2.3819	0.0113	300	2.3015
2.1105	0.0132	350	2.2332
2.1693	0.0150	400	2.2105
2.1511	0.0169	450	2.1875
2.4808	0.0188	500	2.1820

Framework versions

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