Run 4. Outer Step 58. Inner Step 33.

config.json

@@ -268,20 +268,21 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5605288,
-    5605291,
-    5605295,
-    5605299,
-    5605303,
-    5605307,
-    5605311
+    5605315,
+    5605319,
+    5605323,
+    5605327,
+    5605331,
+    5605335,
+    5605339,
+    5605343
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 32,
+  "inner_step": 33,
   "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 sha256:93763604640e036f6d0ba9305b9ff1e3c1c1fe58dd61a5f9cfbd198a9581bb7a
+oid sha256:c363ce1da3041a1331afd1555087be9ae3812fc67a1dededd4781c4d65f8326d
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63dce0571904c2b06ab34041bc18048067f7d5969a46bee2b2c00d69efbc2502
+oid sha256:a7e5dac6923c749669d9d6cf70eebfe287f4e20e2a02b4ae7bffac00d648061e
 size 4040701744