Run 4. Outer Step 28. Inner Step 42.

config.json

@@ -268,23 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5538323,
-    5538325,
-    5538327,
-    5538329,
-    5538330,
-    5538332,
-    5538334,
-    5538337,
-    5538340,
-    5538342
+    5538345,
+    5538346,
+    5538348,
+    5538349,
+    5538350
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 41,
+  "inner_step": 42,
   "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:bdc668ec38eabb2128a37c0daaa00f3930d4ee4bcc5b994017ea49ad93a7f7a2
+oid sha256:061011421a09b85e6f8019db602b16cb86143e5732a3fba1770901c9e1b922a8
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b2f9103bbf9a2966209cbfee6865c8c5a95b2063f4db11103d82aa863c7da77
+oid sha256:e37781e988a79ccfd23e55bc56a7004cf13914b797a0662f57fdf88f7e40d827
 size 4040701744