Run 4. Outer Step 81. Inner Step 10.

config.json

@@ -268,15 +268,15 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5669931,
-    5669961
+    5669993,
+    5670024
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 8,
+  "inner_step": 10,
   "inner_steps": 0,
   "last_allreduce_block": 5665748,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b95948e92773d73df16a93f3acd51cae19b03de3621fdd00984215112ea9e0aa
+oid sha256:b4736ab32f10e9df7d3fbf9485c1e45a5024fc96ec8909bb21e963bb683acb7c
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8de875819afd21df5f143830909cf3a318b0f4d8356940913b9ffb2498e2f920
+oid sha256:6daeeb358ec532616e6948ca3b40f4faa2b65dee7fd53ada414590537eefdb25
 size 4040701744