Run 4. Outer Step 43. Inner Step 40.

config.json

@@ -268,19 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5562076,
-    5562080,
-    5562085,
-    5562089,
-    5562093,
-    5562098
+    5562104,
+    5562108,
+    5562112,
+    5562117,
+    5562121,
+    5562125
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 39,
+  "inner_step": 40,
   "inner_steps": 0,
   "last_allreduce_block": 5556551,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:869711ffcd49b35e8dcb66a6567a305282662ff27ad15848e3c6cde1f6ac767d
+oid sha256:179477a40770aa5024c9ccd8070f85837911348c3ae8085d9df1a67426961dea
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5af2266e1cb436dd6174e6a2996b0b4763786c1c6284ae7ab44af9e41856395
+oid sha256:eac777877f92c1146f31ae521ef0a5e6b4ca8336271e37d3127b35f4ab091f6d
 size 4040701744