Run 3. Outer Step 6. Inner Step 184.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5388032,
-    5388036,
-    5388039,
-    5388043,
-    5388047
+    5388075,
+    5388079,
+    5388082,
+    5388085,
+    5388089
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 181,
+  "inner_step": 184,
   "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 sha256:4081f25348a5cf2f06622efc2c25756013d7731bccb81b5908d05e10e4757fba
+oid sha256:da054b76cc345401f4aa06183e247a7a299bc0581b80eea0f6fb6c51683eedf9
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8aa781e00d98c15fd66bf03cea34f51a47376f3492a140a7b725788d7250862b
+oid sha256:3ca41945bb9dd09274d1ae84cc8140747c0df282f902b949b61433ef6462e3cb
 size 4040701744