Run 4. Outer Step 17. Inner Step 60.

config.json

@@ -268,19 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5520680,
-    5520683,
-    5520687,
-    5520691,
-    5520694,
-    5520698
+    5520702,
+    5520706,
+    5520709,
+    5520713,
+    5520717,
+    5520720
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 59,
+  "inner_step": 60,
   "inner_steps": 0,
   "last_allreduce_block": 5509976,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40197afb367aad17025f092535c34b3fd14321162e276764cf15dd80b0309d38
+oid sha256:c27af767239f150c0c518e4599632e68388bbf643ccb7c77a83ceda5bddc2ef6
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d85d88360d19c9b82098d040ca0092357248523c04161062ac8235632429dd4
+oid sha256:16d9b97f881b8f3ed4fd1ecdb81f0a3f4d4caa3ed14878cc58efa4c10c405a61
 size 4040701744