Run 4. Outer Step 34. Inner Step 1.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5546833,
-    5546838,
-    5546842,
-    5546846,
-    5546850
+    5546855,
+    5546859,
+    5546863,
+    5546867,
+    5546871
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 0,
+  "inner_step": 1,
   "inner_steps": 0,
   "last_allreduce_block": 5543976,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a466811a6db6bd6989545db8758f5c0cbff34f3f452ad60c79583e28b1ead4e2
+oid sha256:1fcc5f6e84b3633fb3f927dc78d261379f0347426346b35c19c20054fcdc5b46
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51392a79732686e75580b800ccea134d34596f5b41ae391a95f3e7445b3b4203
+oid sha256:0622f005305ce0ed023b43aa9211e98ae320dc6e5b789dc34a3f6e7b1eb2ab87
 size 4040701744