Run 4. Outer Step 58. Inner Step 60.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5604050,
-    5604054,
-    5604059,
-    5604063,
-    5604067
+    5604072,
+    5604076,
+    5604080,
+    5604084,
+    5604088
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 59,
+  "inner_step": 60,
   "inner_steps": 0,
   "last_allreduce_block": 5576204,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb29dd3c2e26791c99d27e275eb3a6755fce280bdfb28033ad40a91366065c96
+oid sha256:d1c235c6a685a5efc9fca6db5444b9cb470729af961518da6fbb5b1dd9f6d0cd
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2e64411137f9e9befe466a7be1e4141e56462f366fbc2677a123b46dea38328
+oid sha256:3e038fe8f56756ebba0697511b6c34ac7d44d3ca591f6a988dddb4ea99658ed3
 size 4040701744