Run 4. Outer Step 35. Inner Step 10.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5548430,
-    5548434,
-    5548438,
-    5548442,
-    5548446
+    5548451,
+    5548456,
+    5548460,
+    5548464,
+    5548468
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 9,
+  "inner_step": 10,
   "inner_steps": 0,
   "last_allreduce_block": 5539810,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dde591bf0e1ba0f35350e04b6e7a4efe375a6d11deaf74541ca90fcca6da6b50
+oid sha256:9d11f88f3179e28966b099e7672e86d8c6c211659ff6b6cece3d778d1527519c
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c927d115c858eab218c204b042cc16e33befa3fcfa6e33b62af7157504bf9b34
+oid sha256:eeba2a30d5e4f9cadbb54f65b8abfee8af12c9efda4c45475b1c3b7f6705afdd
 size 4040701744