Run 4. Outer Step 12. Inner Step 12.

config.json

@@ -268,20 +268,20 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5508721,
-    5508724,
-    5508728,
-    5508731,
-    5508735,
-    5508738,
-    5508742
+    5508746,
+    5508750,
+    5508754,
+    5508757,
+    5508761,
+    5508765,
+    5508768
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 11,
+  "inner_step": 12,
   "inner_steps": 0,
   "last_allreduce_block": 5506953,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:991cdf53051ef452d9fbfdc9896603f7f021d8de271e2e8d5d01ed4685a9ab26
+oid sha256:4dd0e84ac70f3e056fa5acd1b84b7741f2cdc5e182283d951bd692fd245dfbec
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2806a7430a2e399efda70be1ab69ae5c5e5f780627425ec121e6e49e03f15b4d
+oid sha256:958fc125dbb52537e28f22c7419784585258a2c80debc087c725bc9f8f40b6fb
 size 4040701744