Update README.md

README.md

@@ -16,6 +16,15 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bart-large-summary-map-reduce-1024
 
+A text2text model to "map-reduce" summaries of a chunked long document into one.
+
+An explanation of this model's role: 
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/60bccec062080d33f875cd0c/Sv7_-MM901qNkyHuBdTC_.png)
+
+<small> modified flowchart from Google's blog [here](https://cloud.google.com/blog/products/ai-machine-learning/long-document-summarization-with-workflows-and-gemini-models) </small>
+
+## Details
 This model is a fine-tuned version of [facebook/bart-large](https://huggingface.co/facebook/bart-large) on the pszemraj/summary-map-reduce dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.7894
@@ -75,23 +84,3 @@ The following hyperparameters were used during training:
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_ratio: 0.05
 - num_epochs: 3.0
-
-### Training results
-
-| Training Loss | Epoch  | Step | Validation Loss | Input Tokens Seen |
-|:-------------:|:------:|:----:|:---------------:|:-----------------:|
-| 1.0645        | 0.3834 | 100  | 0.9265          | 1844404           |
-| 1.0769        | 0.7668 | 200  | 0.8621          | 3640408           |
-| 0.849         | 1.1503 | 300  | 0.8502          | 5504644           |
-| 0.8612        | 1.5337 | 400  | 0.8289          | 7316212           |
-| 0.7934        | 1.9171 | 500  | 0.8072          | 9167936           |
-| 0.6701        | 2.3005 | 600  | 0.8051          | 10969348          |
-| 0.6579        | 2.6839 | 700  | 0.7903          | 12814620          |
-
-
-### Framework versions
-
-- Transformers 4.46.0.dev0
-- Pytorch 2.5.1+cu124
-- Datasets 3.1.0
-- Tokenizers 0.20.2