Run 4. Outer Step 61. Inner Step 52.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5610244,
-    5610248,
-    5610252,
-    5610256,
-    5610261
+    5610266,
+    5610270,
+    5610274,
+    5610277,
+    5610281
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 51,
+  "inner_step": 52,
   "inner_steps": 0,
   "last_allreduce_block": 5602341,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f57e7813c7c001084a69f0f2fa5562a7eb784d5f109977a3803a9f07141e26e
+oid sha256:545d9ef7c176263ffb9d10403d2db900d79259a6208e2771fafd18f83840a1a5
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ef27f5a3d84bf6bf5d4fd83a32637b565db4f723f3d54c7a6335a125c4c50ac
+oid sha256:eca1a51157f4c4f824bbad134cfbd40dde497386eecf658af27273ca1e66c9b6
 size 4040701744