Run 4. Outer Step 43. Inner Step 80.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5563300,
-    5563304,
-    5563309,
-    5563313,
-    5563317
+    5563322,
+    5563326,
+    5563330,
+    5563335,
+    5563340
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 79,
+  "inner_step": 80,
   "inner_steps": 0,
   "last_allreduce_block": 5560919,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e48dbcaa1f02457b3c524ce0965e36bf7e376310e4983891c063e581bde5da5
+oid sha256:10b06a42c863f6e9ba9b6ef5affccacee43841a11b2ac5a64a68c8ad45e7322d
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9271417522204e95c3d5bd2066e5ab5a87060d171d6eb65db39efc2be14a766d
+oid sha256:862720d4824a85c5ad523f6b869fb43f85d7c0a7f0f604b2c302ae369bf2233b
 size 4040701744