library_name, license, base_model, tags, model-index

library_name	license	base_model	tags	model-index
transformers	llama3.2	meta-llama/Llama-3.2-1B-Instruct	peft-factory full llama-factory generated_from_trainer	name results train_qnli_42_1779286681

train_qnli_42_1779286681

This model is a fine-tuned version of meta-llama/Llama-3.2-1B-Instruct on the qnli dataset. It achieves the following results on the evaluation set:

• Loss: 0.0522
• Num Input Tokens Seen: 11312256

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: 2e-06
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Input Tokens Seen
0.093	0.0501	590	0.0805	571072
0.0911	0.1001	1180	0.0656	1136384
0.1636	0.1502	1770	0.0790	1703808
0.138	0.2003	2360	0.0773	2266496
0.0654	0.2503	2950	0.0821	2827328
0.0218	0.3004	3540	0.0740	3399808
0.0142	0.3505	4130	0.0708	3963584
0.0847	0.4005	4720	0.0573	4530304
0.0674	0.4506	5310	0.0652	5095424
0.0262	0.5007	5900	0.0528	5660352
0.0577	0.5507	6490	0.0573	6232896
0.042	0.6008	7080	0.0625	6801984
0.0449	0.6509	7670	0.0570	7363968
0.0589	0.7010	8260	0.0540	7924800
0.0597	0.7510	8850	0.0540	8494720
0.1148	0.8011	9440	0.0544	9066048
0.0761	0.8512	10030	0.0528	9634624
0.0919	0.9012	10620	0.0522	10199424
0.0039	0.9513	11210	0.0523	10764096

Framework versions

• Transformers 4.51.3
• Pytorch 2.10.0+cu128
• Datasets 4.0.0
• Tokenizers 0.21.4