Run 4. Outer Step 54. Inner Step 36.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5580664,
-    5580669,
-    5580674,
-    5580679,
-    5580684
+    5580690,
+    5580695,
+    5580701,
+    5580706,
+    5580711
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 35,
+  "inner_step": 36,
   "inner_steps": 0,
   "last_allreduce_block": 5577515,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2efba4ec6bfdde849794f2e09e4c4f5bffbd3a06ad6434145ab614998ef6a40e
+oid sha256:53b39afd9d9bdc44e7df5dc0c5dee013c25583d6ea1241b5b6f6dc24d800f11a
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:953e92fc5f9486572f2434f51d1a3e9e33dbde6a99b74f2553ba7dbcb9e775e0
+oid sha256:72ec4d18b04052dea69ba28a4c5ed80378e45f38c342ae65fbd6d90f464ebc5f
 size 4040701744