Update model card and embedded training curves

README.md

@@ -7,7 +7,7 @@ tags:
 - global
 - 3b
 - without-metadata
-- continued-pretraining
+- pretraining
 - intermediate-checkpoint
 ---
 
@@ -15,7 +15,7 @@ tags:
 
 ## Summary
 
-This repo contains the global combined model exported from the 8k checkpoint for the metadata localization project. It comes from continued pretraining of a Llama 3.2 base model on the project corpus.
+This repo contains the global combined model exported from the 8k 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
 
@@ -53,6 +53,22 @@ This repo contains the global combined model exported from the 8k checkpoint for
 - `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
+
+![Train Loss](assets/train_loss.png)
+
+### Validation Perplexity
+
+![Validation Perplexity](assets/val_perplexity.png)
+
+### Throughput
+
+![Throughput](assets/tokens_per_sec.png)
+
 ## 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](https://huggingface.co/collections/iamshnoo/metadata-conditioned-llms).
@@ -60,4 +76,4 @@ This model is part of the metadata localization release. Related checkpoints and
 - Project repository: [https://github.com/iamshnoo/metadata_localization](https://github.com/iamshnoo/metadata_localization)
 - Paper: [https://arxiv.org/abs/2601.15236](https://arxiv.org/abs/2601.15236)
 
-Last synced: `2026-04-02 13:49:22 UTC`
+Last synced: `2026-04-02 14:40:40 UTC`