Run 4. Outer Step 62. Inner Step 28.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5611408,
-    5611413,
-    5611418,
-    5611422,
-    5611426
+    5611432,
+    5611436,
+    5611441,
+    5611446,
+    5611450
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 27,
+  "inner_step": 28,
   "inner_steps": 0,
   "last_allreduce_block": 5605539,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d41591ca4c5e20ccc0784916180d72d9b8edfa591584d6ef8f576e9d1f0fef0
+oid sha256:1ebcdef25507137b31213c82563c29fedf4e6264ecaa81a596d7692a98373666
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08206b2adba0961e40aa06f3f29237f16ba1eb31a5d4e001906b9cc1560e90d6
+oid sha256:de6496b51c442795b5f71a92ac21773817fa2b77c8eb12e3463ba8b32d8cb9c8
 size 4040701744