Run 4. Outer Step 61. Inner Step 53.

config.json

@@ -268,18 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5610266,
-    5610270,
-    5610274,
-    5610277,
-    5610281
+    5610286,
+    5610290,
+    5610295,
+    5610299,
+    5610303,
+    5610306
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 52,
+  "inner_step": 53,
   "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 sha256:545d9ef7c176263ffb9d10403d2db900d79259a6208e2771fafd18f83840a1a5
+oid sha256:24874d59e9c600f15143558224ece22e9f733f68216ee53a53bd9d95878d7497
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eca1a51157f4c4f824bbad134cfbd40dde497386eecf658af27273ca1e66c9b6
+oid sha256:70a37b3e91e51d4e34e66510d784ec80c85142ad870b1c1b1b27411859184ba8
 size 4040701744