Run 4. Outer Step 20. Inner Step 20.

config.json

@@ -268,29 +268,30 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5525231,
-    5525233,
-    5525235,
-    5525236,
-    5525238,
-    5525240,
-    5525241,
-    5525242,
-    5525243,
-    5525244,
-    5525246,
-    5525248,
-    5525249,
-    5525251,
-    5525252,
-    5525253
+    5525255,
+    5525256,
+    5525257,
+    5525259,
+    5525260,
+    5525262,
+    5525263,
+    5525264,
+    5525265,
+    5525265,
+    5525266,
+    5525268,
+    5525269,
+    5525271,
+    5525273,
+    5525275,
+    5525277
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 19,
+  "inner_step": 20,
   "inner_steps": 0,
   "last_allreduce_block": 5523943,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77a26297cdcfb46cec4c8b87882bc32627ed10cd6c3c647abb21b70125449369
+oid sha256:fa6f20d28b5315eaacb084c94b6cf4b182216a929b7d7f879c1352a09b89204a
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4acb33a5238ce7a19ba8bc911a0aeed938ae0f6beceefb17ef89be1c9296b976
+oid sha256:c8725f87fcff2c2b111c87f97b63dd0b68e8927e19890564c98aa9594155e0a2
 size 4040701744