Run 4. Outer Step 7. Inner Step 76.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5494154,
-    5494158,
-    5494161,
-    5494163,
-    5494169
+    5494173,
+    5494177,
+    5494181,
+    5494185,
+    5494189
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 75,
+  "inner_step": 76,
   "inner_steps": 0,
   "last_allreduce_block": 5490074,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f36f5083d9731146f356e75077360473b4565a924ed7a609f131596de6fb858c
+oid sha256:09acea443d1317cc6290766725ad14607a1524532a8624afcbe499471917e8e5
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb4e6b6c94186fe4d4bf72ad9163f2fb3118386a9e238697ab2fbc36355a76dd
+oid sha256:980fee5490a203b36e6c190ec8a2ce3367ed802bde467ff57299aa6356c7776a
 size 4040701744