step 1264 | val_ppl=12.46

README.md

@@ -25,9 +25,9 @@ Small language model (9.9M parameters) trained from scratch.
 | Total parameters | 9.902M |
 
 ## Training
-- Tokens seen: 2,828,390,400
-- Val loss: 2.5314
-- Val PPL: 12.57
+- Tokens seen: 2,979,215,382
+- Val loss: 2.5222
+- Val PPL: 12.46
 
 ## Usage
 ```python

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6be7a9b4f02e8e9cb97597867bd85a5ca65c6f08a2785ba7aeefd04b6a35f3dd
+oid sha256:e3ca9fbcda9b5a5cda37b78cf0d7d7edecca719c4b7a1fc835359d6cf6d8716a
 size 39621248

resume/ckpt.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f48037530900baf5046a0a84c64874fd1b7cbffda6c96443e20ac7bd8708783
+oid sha256:20e00e9fc1202d17f2aaf8da8e481a3575c90d5f49d6217c5057fb79e3587059
 size 122094685

resume/latest_step.txt

@@ -1 +1 @@
-1200
+1264

training_meta.json

@@ -1,8 +1,8 @@
 {
-  "step": 1200,
-  "val_loss": 2.5314433860778807,
-  "val_ppl": 12.571638775705786,
+  "step": 1264,
+  "val_loss": 2.5222082792282103,
+  "val_ppl": 12.45607280175252,
   "params_M": 9.902,
-  "pushed_at": "2026-06-11T16:10:06.384972",
-  "tokens_seen": 2828390400
+  "pushed_at": "2026-06-11T16:46:41.317193",
+  "tokens_seen": 2979215382
 }