This repo contains the global combined model at the final 10k-step checkpoint for the metadata localization project. It was trained from scratch on the project corpus, using the Llama 3.2 tokenizer and vocabulary.

Variant Metadata

Stage: pretrain
Family: global
Size: 3b
Metadata condition: with_metadata
Base model lineage: Trained from scratch; tokenizer/vocabulary from meta-llama/Llama-3.2-1B

Weights & Biases Provenance

Run name: 27/03/2026_19:26:23_combined_with_metadata_3b
Internal run URL: https://wandb.ai/iamshnoo/nanotron/runs/l1je3vgr
Note: the Weights & Biases workspace is private; public readers should use the summarized metrics and configuration below.
State: finished
Runtime: 16h 1m 39s

Run Summary

KPI/train_lm_loss: 1.9952
KPI/train_perplexity: 7.3539
KPI/val_loss: 2.0511
KPI/val_perplexity: 7.7764
KPI/consumed_tokens/train: 41,943,040,000
_step: 10,000

Training Configuration

train_steps: 10,000
sequence_length: 2,048
micro_batch_size: 8
batch_accumulation_per_replica: 64
learning_rate: 0.0003
min_decay_lr: 0
checkpoint_interval: 100

Training Curves

Static plots below were exported from the private Weights & Biases run and embedded here for public access.

Train Loss

Validation Perplexity

Throughput

Project Context

This model is part of the metadata localization release. Related checkpoints and variants are grouped in the public Hugging Face collection Metadata Conditioned LLMs.

Training data source: News on the Web (NOW) Corpus
Project repository: https://github.com/iamshnoo/metadata_localization
Paper: https://arxiv.org/abs/2601.15236

Last synced: 2026-04-02 14:40:23 UTC

iamshnoo/combined_with_metadata_3b

combined_with_metadata_3b

Summary