Run 4. Outer Step 50. Inner Step 65.

config.json

@@ -268,20 +268,20 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5573318,
-    5573322,
-    5573326,
-    5573330,
-    5573334,
-    5573338,
-    5573342
+    5573347,
+    5573351,
+    5573355,
+    5573359,
+    5573362,
+    5573366,
+    5573370
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 64,
+  "inner_step": 65,
   "inner_steps": 0,
   "last_allreduce_block": 5523943,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f81b44e9c06f936299c0fcfd1a5bd4c1046cee546543340ec547a7adb49a289f
+oid sha256:c8e9d6ea6882ffef5e37b7f843bf90decb0f4f4175271b3e2e166b8cf1e396bb
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4b3d2061d26203710692a214554417911081ceffed91fb9df019f7eaab446ae
+oid sha256:42d33499c8acd2461383e9e0800ffa115926146d8bee8d2634b108e39688c993
 size 4040701744