Run 4. Outer Step 60. Inner Step 5.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5607876,
-    5607880,
-    5607884,
-    5607888,
-    5607892
+    5607897,
+    5607901,
+    5607905,
+    5607911,
+    5607915
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 4,
+  "inner_step": 5,
   "inner_steps": 0,
   "last_allreduce_block": 5607244,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20790c4d1191b2e3f17af5fe10ff74cd65baffb6c3ace3fe17a9b5c13bc24958
+oid sha256:69fb332deafb0d325ca1e27fdd566e4f07708b6e785b393789ea28dcc1971c08
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa1a2a17117ac7170e62db1f08c8d1c47b80017474651c19163a894b84cbea12
+oid sha256:d43d31cd799b74110638c066d6a9a27b43febbeefba5f73a3b87da83685ed8c7
 size 4040701744