Run 4. Outer Step 12. Inner Step 13.

config.json

@@ -268,20 +268,20 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5508746,
-    5508750,
-    5508754,
-    5508757,
-    5508761,
-    5508765,
-    5508768
+    5508772,
+    5508776,
+    5508780,
+    5508783,
+    5508787,
+    5508790,
+    5508794
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 12,
+  "inner_step": 13,
   "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 sha256:4dd0e84ac70f3e056fa5acd1b84b7741f2cdc5e182283d951bd692fd245dfbec
+oid sha256:84609d93c4fdd95853876f2130163e0d74fda91d97e1d6d980cda435f72af2cc
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:958fc125dbb52537e28f22c7419784585258a2c80debc087c725bc9f8f40b6fb
+oid sha256:343676d39f0b8c20082f5142bed798324c1d1f15e670d96a16adac2bc5ce48de
 size 4040701744