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_record_42_1776331412

train_record_42_1776331412

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

• Loss: 0.4481
• Num Input Tokens Seen: 245808128

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
0.6094	0.2500	3906	0.5014	12292032
0.4689	0.5001	7812	0.5265	24620672
0.5124	0.7501	11718	0.4985	36894016
0.343	1.0002	15624	0.4854	49176512
0.265	1.2502	19530	0.5116	61465280
0.2897	1.5003	23436	0.4806	73739776
0.2995	1.7503	27342	0.4774	86015936
0.2658	2.0004	31248	0.4481	98341056
0.2663	2.2504	35154	0.5257	110649216
0.1792	2.5005	39060	0.5071	122910592
0.2395	2.7505	42966	0.5056	135222656
0.1496	3.0006	46872	0.5023	147516736
0.1005	3.2506	50778	0.5569	159826368
0.159	3.5007	54684	0.5747	172084032
0.1324	3.7507	58590	0.5466	184402752
0.1773	4.0008	62496	0.5555	196687936
0.0922	4.2508	66402	0.6279	209017024
0.1645	4.5009	70308	0.6087	221278272
0.1252	4.7509	74214	0.6058	233564288

Framework versions

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