Run 4. Outer Step 15. Inner Step 73.

config.json

@@ -268,18 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5515284,
-    5515314,
-    5515318,
-    5515321,
-    5515325
+    5515329,
+    5515333,
+    5515337,
+    5515340,
+    5515344,
+    5515348
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 72,
+  "inner_step": 73,
   "inner_steps": 0,
   "last_allreduce_block": 5513324,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aea427d6c263209a47573a332dee9836fd9dc8f3e559f9cc3089ce9a3251a521
+oid sha256:d678cb0fd9b4f891feedd60276fb1582340f69eca659819c4fcad8f93826c86e
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbef75260785502960ec235987b66c3eb208402b972b74402f121320679d451f
+oid sha256:3986407516a071cf4ea3cd59d3b15df277143ea4fbdf4955d5e1928b555f815c
 size 4040701744