Update training progress and artifacts

README.md

@@ -19,13 +19,13 @@ The model files (merged weights and tokenizer) are stored at the root of this re
 - **Diverse Datasets:** The script iterates through datasets available on the Hugging Face Hub, attempting to train on each.
 - **Short Training Iterations:** Each training run per dataset configuration is currently set to a small number of steps (`max_steps=1`) to allow for rapid iteration across many datasets.
 ## Training Progress
-- **Datasets Processed (Successfully trained on at least one config):** 6
-- **Text Examples Streamed (Total):** 36
-- **Tokens Processed (Total):** 18432
-- **Last Successful Model Update:** 2025-05-07 14:25:07 UTC
+- **Datasets Processed (Successfully trained on at least one config):** 8
+- **Text Examples Streamed (Total):** 48
+- **Tokens Processed (Total):** 24576
+- **Last Successful Model Update:** 2025-05-07 14:27:09 UTC
 ### Evaluation Metrics
 
-- **Overall Perplexity (on a small fixed dataset):** 143214.66
+- **Overall Perplexity (on a small fixed dataset):** 143114.84
 
 #### Generated Examples (Qualitative Assessment)
 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:998802bb2719e88839e658c6669416e9c9b2aef47b4ea62c81fc799f97d49026
+oid sha256:39cb03b5008417eff14aa3cb8196faf959572a7ab871ce654172bd059ee0193d
 size 80000008