Run 3. Outer Step 6. Inner Step 186.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5388075,
-    5388079,
-    5388082,
-    5388085,
-    5388089
+    5388118,
+    5388122,
+    5388125,
+    5388129,
+    5388132
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 184,
+  "inner_step": 186,
   "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:da054b76cc345401f4aa06183e247a7a299bc0581b80eea0f6fb6c51683eedf9
+oid sha256:77405ed651ab006ef84a3567fc3d9a43e4183b7fef8d6edf0d8fb8d4a5a33328
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ca41945bb9dd09274d1ae84cc8140747c0df282f902b949b61433ef6462e3cb
+oid sha256:f64b726fbec11b1643a8d242d2404d3c61c66b7534d7b3f55ec8c168fae541dd
 size 4040701744