Run 3. Outer Step 5. Inner Step 259.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5384380,
-    5384384,
-    5384388,
-    5384391,
-    5384395
+    5384421,
+    5384424,
+    5384428,
+    5384432,
+    5384436
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 257,
+  "inner_step": 259,
   "inner_steps": 0,
   "last_allreduce_block": 5378990,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61eaeec594cd0ebeec2ca9c0b15a728dc668fdeef835e1784f29b5d907d69d5b
+oid sha256:381b4bd98b78d9f9577136d344b29d758ff8074057e9eb30013fdb24af1255eb
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36426ad22381390101eb5097bc04e5e955978ddfdeec1d72fbc87249b9c3e91b
+oid sha256:356de244c87481d20bbe8a16cc38fe617c76b0503b752980d30b3fde7296baa4
 size 4040701744