outputs

This model is a fine-tuned version of unsloth/phi-3.5-mini-instruct-bnb-4bit on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.0415

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: 0.0002
• train_batch_size: 2
• eval_batch_size: 8
• seed: 3407
• gradient_accumulation_steps: 4
• total_train_batch_size: 8
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 5
• training_steps: 250

Training results

Training Loss	Epoch	Step	Validation Loss
1.1413	0.0183	10	1.1571
1.1366	0.0366	20	1.1230
1.2494	0.0549	30	1.1059
1.1031	0.0732	40	1.0939
1.1264	0.0915	50	1.0847
1.0365	0.1098	60	1.0806
1.0157	0.1281	70	1.0805
1.153	0.1465	80	1.0748
1.0312	0.1648	90	1.0700
0.9456	0.1831	100	1.0665
1.1037	0.2014	110	1.0634
0.9732	0.2197	120	1.0603
1.0042	0.2380	130	1.0613
1.0203	0.2563	140	1.0583
0.941	0.2746	150	1.0549
1.1907	0.2929	160	1.0517
1.1479	0.3112	170	1.0490
1.077	0.3295	180	1.0478
1.0067	0.3478	190	1.0467
1.1518	0.3661	200	1.0462
0.944	0.3844	210	1.0442
1.047	0.4027	220	1.0434
0.9985	0.4211	230	1.0423
1.1321	0.4394	240	1.0419
1.0506	0.4577	250	1.0415

Framework versions

• PEFT 0.13.2
• Transformers 4.44.2
• Pytorch 2.4.1+cu121
• Datasets 3.0.1
• Tokenizers 0.19.1