Run 4. Outer Step 4. Inner Step 23.

config.json

@@ -268,22 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5487080,
-    5487081,
-    5487082,
-    5487084,
-    5487086,
-    5487088,
-    5487090,
-    5487092,
-    5487094
+    5487097,
+    5487099,
+    5487102,
+    5487106,
+    5487108
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 22,
+  "inner_step": 23,
   "inner_steps": 0,
   "last_allreduce_block": 5485540,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da6df14494aa4b7fcb9b0ac5ef0a1a0bcffd222ff3ee11d614db2560617c08b3
+oid sha256:0e962b00d2b8ede3cdb053293b3ed537197c7988f5963c78ac533d383a4e02b6
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b069fcc322773dd3eafda493bb835d7b08660840b9984507fafb70693daae458
+oid sha256:ef9344be50a5754159bc3a9de2a9592d14016909c7b832af98f5a05169d8e7c2
 size 4040701744