Run 4. Outer Step 55. Inner Step 3.

config.json

@@ -268,15 +268,15 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5632838,
-    5632896
+    5632925,
+    5632953
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 0,
+  "inner_step": 3,
   "inner_steps": 0,
   "last_allreduce_block": 5568918,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a68307304a0282da2e988c9c21c969a59ddec72863a86c25c9fc1faa11037ab
+oid sha256:4072539ec072f18b58f2e5be4bdaafd444a0cd0cd9c17ee2bb03b2a07c2e70b4
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5fd56c1395642dec56d421e0a48a988789c533ce2d6b9ac80ac554218bf55a1
+oid sha256:8dd3545254645a85cbbc1c2f0b8c98a644111909b9bc84b8d07a2f2971259521
 size 4040701744