Run 4. Outer Step 10. Inner Step 94.

config.json

@@ -268,19 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5506287,
-    5506291,
-    5506295,
-    5506298,
-    5506302,
-    5506306
+    5506310,
+    5506314,
+    5506317,
+    5506321,
+    5506324
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 93,
+  "inner_step": 94,
   "inner_steps": 0,
   "last_allreduce_block": 5492224,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cabbef1e4e7dfed3bbcda336b17d53c34ec9d61df28415170b4489405aae5cf
+oid sha256:9b4c6932be6cc63f271f199b1ee4e1aab03f6da3c38dcd9140c18f3d99891af8
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d0fdfbffe70088b4fe707d691d06edb839c5aa3d9138effeff88830fbda4171
+oid sha256:3e73a1cf50060a96bef44af6b1135d4895ba9f00bbab120d75a9a40b04a065fb
 size 4040701744