Run 4. Outer Step 58. Inner Step 73.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5604444,
-    5604448,
-    5604453,
-    5604457,
-    5604462
+    5604466,
+    5604470,
+    5604475,
+    5604479,
+    5604483
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 72,
+  "inner_step": 73,
   "inner_steps": 0,
   "last_allreduce_block": 5576204,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b2b5f5de7cf5c4bf15b2697210942923388ace66296971f146a1b67e27eff77
+oid sha256:4c830bfc96af63ce58b2721e362442351a1f5b6940f996e3e1d069d1770d7936
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a93b8c4c393a0bb39462c9898d55d32977780f00bff36f93c359b5dd5527994
+oid sha256:5457722ed081df34d6160d2b8691add5a265b1949f0c5e860fb4f2e6e5509c80
 size 4040701744