Run 3. Outer Step 9. Inner Step 149.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5401575,
-    5401578,
-    5401581,
-    5401585,
-    5401588
+    5402296,
+    5402300,
+    5402303,
+    5402306,
+    5402310
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 115,
+  "inner_step": 149,
   "inner_steps": 0,
   "last_allreduce_block": 5398844,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d01e81f87010b034bef59f2fb7cc2da50e608b642d3003f8b704f3bc517aa79
+oid sha256:a706cb89cf3187604bb62b0931a9fa6dab5b06c0689cf6ec8266b4056f59d94a
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88052a9bfed997d377cfb9e0ed0e86cbc63aed71e49e89d1237676e191c84680
+oid sha256:63ee90cf8e4b609699c808243d08b5c2d9ba28b3f3eecde52d1755ed4bdd59f9
 size 4040701744