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_1779207272

train_qnli_42_1779207272

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: 0.0535
• Num Input Tokens Seen: 56574368

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: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Input Tokens Seen
0.0827	0.25	2946	0.0783	2823680
0.0452	0.5	5892	0.0612	5652800
0.0473	0.75	8838	0.0545	8482944
0.0346	1.0	11784	0.0535	11312256
0.0299	1.25	14730	0.0764	14142784
0.0363	1.5	17676	0.0833	16969472
0.0084	1.75	20622	0.0826	19782400
0.0205	2.0	23568	0.0846	22629440
0.0001	2.25	26514	0.1074	25460032
0.0001	2.5	29460	0.1115	28284608
0.0001	2.75	32406	0.1112	31130432
0.023	3.0	35352	0.1149	33947392
0.0258	3.25	38298	0.1494	36783040
0.0	3.5	41244	0.1557	39604544
0.0	3.75	44190	0.1553	42421440
0.0	4.0	47136	0.1462	45265344
0.0	4.25	50082	0.1777	48098944
0.0	4.5	53028	0.1760	50906176
0.0	4.75	55974	0.1753	53746240
0.0	5.0	58920	0.1754	56574368

Framework versions

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