Run 4. Outer Step 33. Inner Step 26.

config.json

@@ -268,24 +268,25 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5544736,
-    5544738,
-    5544741,
-    5544743,
-    5544745,
-    5544747,
-    5544748,
-    5544750,
-    5544752,
-    5544755,
-    5544758
+    5544760,
+    5544762,
+    5544765,
+    5544767,
+    5544770,
+    5544772,
+    5544773,
+    5544775,
+    5544776,
+    5544778,
+    5544781,
+    5544783
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 25,
+  "inner_step": 26,
   "inner_steps": 0,
   "last_allreduce_block": 5543976,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c571937a5f0bfcdf0fa5db866eec936abf9bc0c47d21bde4322fea427bbd741
+oid sha256:b9de662215ed622994f478ff01f75ee82b965590507ac30d02acbaf82e815853
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fa9696d62994bbe52b95b4195b65c7b46727a5b16194feb46f11f678981dea8
+oid sha256:6bbafdc30029f45b86ab77152c98902e7e16b026e150e3b5bf3d6996780a3648
 size 4040701744