Run 4. Outer Step 28. Inner Step 41.

config.json

@@ -268,18 +268,22 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5538287,
-    5538290,
-    5538292,
-    5538294,
-    5538296
+    5538299,
+    5538301,
+    5538303,
+    5538306,
+    5538309,
+    5538312,
+    5538314,
+    5538316,
+    5538319
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 40,
+  "inner_step": 41,
   "inner_steps": 0,
   "last_allreduce_block": 5537093,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbf2623ee3126b19338ffcdf81baa7b77963e3686fd0d731eb2ee11a4e88959a
+oid sha256:bdc668ec38eabb2128a37c0daaa00f3930d4ee4bcc5b994017ea49ad93a7f7a2
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce644ae769afda2f154d6c610ac9b5659c1b1be001e29a680bad2e6baac15aea
+oid sha256:4b2f9103bbf9a2966209cbfee6865c8c5a95b2063f4db11103d82aa863c7da77
 size 4040701744