step 3600 | val_ppl=11.63

README.md

@@ -25,9 +25,9 @@ Small language model (9.9M parameters) trained from scratch.
 | Total parameters | 9.853M |
 
 ## Training
-- Tokens seen: 3,352,166,400
-- Val loss: 2.4750
-- Val PPL: 11.88
+- Tokens seen: 3,771,187,200
+- Val loss: 2.4536
+- Val PPL: 11.63
 
 ## Usage
 ```python

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c2ecf240f59ef5bb582242b08f1eebf095d8c945a7d01f4ac6535ec190ad990
+oid sha256:e7c8fd1a940963dad4d80891d35dacbaea76b3bd45eeb3aca7fef7970e6170a5
 size 39421616

resume/ckpt.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2dce5b25f1680e6920a5e01a353e7c3f60aa9a3d1f50a681f21aaf0971f9d494
+oid sha256:626d3eef635b7be8b1a6348cd6df2a8f73cd81cf03415b62cd8ed08a00d166cd
 size 119812327

resume/latest_step.txt

@@ -1 +1 @@
-3200
+3600

training_meta.json

@@ -1,8 +1,8 @@
 {
-  "step": 3200,
-  "val_loss": 2.4750425384521484,
-  "val_ppl": 11.882212553279116,
+  "step": 3600,
+  "val_loss": 2.4536261505126955,
+  "val_ppl": 11.630444088190558,
   "params_M": 9.853,
-  "pushed_at": "2026-06-17T22:32:27.223238",
-  "tokens_seen": 3352166400
+  "pushed_at": "2026-06-18T00:27:20.366594",
+  "tokens_seen": 3771187200
 }