step 1600 | val_ppl=19.66

README.md

@@ -25,7 +25,7 @@ Small language model (9.9M parameters) trained from scratch.
 | Total parameters | 9.853M |
 
 ## Training
-- Tokens seen: 1,257,062,400
+- Tokens seen: 1,676,083,200
 - Val loss: 2.9784
 - Val PPL: 19.66
 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ac96901a4c7e8ef5cbd363d5754d25fbfe209f2f016c8fd0c45c9e4abcdfe83
+oid sha256:3d9f44382bb331571b40db43e9b8958945051e82d6947a9cc52b09f5fe957d6d
 size 39421616

resume/ckpt.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb13b6b86dc6ab4ffcc79b4a5fd9f0306abf05233e284edb458bbbe2bac0e8d3
+oid sha256:76c2848d980dc663254458a2710a874ef34f0f6f17e0de46e076635d9d57b63e
 size 119811943

resume/latest_step.txt

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

training_meta.json

@@ -1,8 +1,8 @@
 {
-  "step": 1200,
+  "step": 1600,
   "val_loss": 2.9784151458740236,
   "val_ppl": 19.656639039825286,
   "params_M": 9.853,
-  "pushed_at": "2026-06-20T12:13:00.914787",
-  "tokens_seen": 1257062400
+  "pushed_at": "2026-06-20T14:00:05.257093",
+  "tokens_seen": 1676083200
 }