This repo contains the global combined model exported from the 2k 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: 1b
Metadata condition: without_metadata
Checkpoint export: 2k
Base model lineage: Trained from scratch; tokenizer/vocabulary from meta-llama/Llama-3.2-1B

Weights & Biases Provenance

Run name: 14/11/2025_16:54:30_combined_without_metadata_1b
Internal run URL: https://wandb.ai/iamshnoo/nanotron/runs/09p25aoo
Note: the Weights & Biases workspace is private; public readers should use the summarized metrics and configuration below.
State: finished
Runtime: 113h 35m 30s

Run Summary

KPI/train_lm_loss: 2.171
KPI/train_perplexity: 8.7673
KPI/val_loss: 2.2472
KPI/val_perplexity: 9.4612
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: 0.003
min_decay_lr: 0.0003
checkpoint_interval: 1,000

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 14:39:43 UTC

iamshnoo/combined_without_metadata_1b_step2k

combined_without_metadata_1b_step2k

Summary