06c6f8f4-0bfa-401d-876b-1e947c34efde

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

• Loss: 0.2882

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	1.2843
0.2686	0.0116	50	0.5301
0.2842	0.0233	100	0.4262
0.2464	0.0349	150	0.4392
0.2626	0.0465	200	0.3985
0.2335	0.0582	250	0.3889
0.2219	0.0698	300	0.3442
0.2303	0.0814	350	0.3102
0.235	0.0931	400	0.2953
0.2014	0.1047	450	0.2891
0.2312	0.1163	500	0.2882

Framework versions

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