Run 4. Outer Step 62. Inner Step 1.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5610771,
-    5610775,
-    5610779,
-    5610783,
-    5610787
+    5610792,
+    5610797,
+    5610801,
+    5610806,
+    5610810
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 0,
+  "inner_step": 1,
   "inner_steps": 0,
   "last_allreduce_block": 5610584,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f7503027fc56c8e882cd5fae667854e480bf0f7693931886c0e5080a6b85fb2
+oid sha256:063a6169c63d740ce91bd60a3e47276e6aaae17e4d16161b373ecd9b768b5998
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9de0ef233a9c5332951ad43311d1d2e3b092d7d5c03b963373cc460e140bacff
+oid sha256:6bb764cb546684ad445d37ceefc4bb2363614260eccac249596d3d1e39a47150
 size 4040701744