step 1600 | val_ppl=14.38

README.md

@@ -25,9 +25,9 @@ Small language model (9.9M parameters) trained from scratch.
 | Total parameters | 9.853M |
 
 ## Training
-- Tokens seen: 1,257,062,400
-- Val loss: 2.7687
-- Val PPL: 15.94
+- Tokens seen: 1,676,083,200
+- Val loss: 2.6657
+- Val PPL: 14.38
 
 ## Usage
 ```python

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6d23ec7d2a1a452230c62da1c076f1aba2a74d298b845cc1e44e11f8ea044e8
+oid sha256:0692f3ebb90934ebe0d7504caf6a2340535690e6e15117d093dc990727ef2f81
 size 39421616

resume/ckpt.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abfe18901f1c58da3ef40548191c2d25d422dd60d7096ec4fcccfca2559b20bb
+oid sha256:5f00fcbcd0047588c352e8025caceb5560dc778e003de9adc2c9f1f926741664
 size 119811943

resume/latest_step.txt

@@ -1 +1 @@
-1200
+1600

training_meta.json

@@ -1,8 +1,8 @@
 {
-  "step": 1200,
-  "val_loss": 2.7687056308746336,
-  "val_ppl": 15.937991009362028,
+  "step": 1600,
+  "val_loss": 2.6657352474212646,
+  "val_ppl": 14.378517428377364,
   "params_M": 9.853,
-  "pushed_at": "2026-06-17T13:08:06.578893",
-  "tokens_seen": 1257062400
+  "pushed_at": "2026-06-17T14:52:31.290553",
+  "tokens_seen": 1676083200
 }