Run 3. Outer Step 6. Inner Step 53.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5386737,
-    5386743,
-    5386748,
-    5386754,
-    5386759
+    5386806,
+    5386812,
+    5386817,
+    5386822,
+    5386827
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 1,
+  "inner_step": 53,
   "inner_steps": 0,
   "last_allreduce_block": 5373127,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:594320553679816d6d2755b4085ea6199269e570e53bff7074b398d46acda040
+oid sha256:337c3484e8155d7f1213f9eac421ea9007985207b6d749b7ccdca7a10353cdd9
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:962c5db4d09bef92c47ab52e7f14ce854835477ffba480e5669414a054841cda
+oid sha256:00a4811ad1837d3fc294ad18ed52ec2ff3a83ff8d7ec78c7d1ffcb5f292f528a
 size 4040701744