Run 4. Outer Step 61. Inner Step 25.

config.json

@@ -268,15 +268,15 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5641702,
-    5641729
+    5641758,
+    5641786
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 23,
+  "inner_step": 25,
   "inner_steps": 0,
   "last_allreduce_block": 5641040,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8a5952481826010d53c7c285af3c02f3dcc21e2765ad4c6318e2c062412649f
+oid sha256:e42412ee06305becf1c3f98514182f54454ea29e83f4b38be03732f4d37dc357
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:213a21ac1da37695dac4a4714260c6c17e5e7679eb09856abb21aca09538d767
+oid sha256:f0d80d0364c7d9e201cd6e6559de0447a0a7360cea50635019d14fe8cf8d09f9
 size 4040701744