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_boolq_42_1776331558

train_boolq_42_1776331558

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

• Loss: 0.1885
• Num Input Tokens Seen: 12333600

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: 5e-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
0.2277	0.2507	266	0.2505	618432
0.2193	0.5014	532	0.3166	1225408
0.2554	0.7521	798	0.2179	1851072
0.3676	1.0028	1064	0.1885	2475808
0.165	1.2535	1330	0.4608	3091552
0.2207	1.5042	1596	0.3545	3699104
0.1138	1.7549	1862	0.3500	4324256
0.0762	2.0057	2128	0.3345	4940992
0.0898	2.2564	2394	0.4647	5558144
0.0692	2.5071	2660	0.4098	6183872
0.227	2.7578	2926	0.4303	6806208
0.0004	3.0085	3192	0.3937	7421856
0.0	3.2592	3458	0.5191	8043744
0.0002	3.5099	3724	0.4636	8660768
0.0	3.7606	3990	0.5201	9286304
0.0001	4.0113	4256	0.5146	9894624
0.0782	4.2620	4522	0.5548	10512416
0.0	4.5127	4788	0.5418	11115040
0.0	4.7634	5054	0.5422	11736672

Framework versions

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