Run 4. Outer Step 29. Inner Step 20.

config.json

@@ -268,18 +268,24 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5539130,
-    5539133,
-    5539135,
-    5539138,
-    5539139
+    5539143,
+    5539145,
+    5539147,
+    5539149,
+    5539152,
+    5539154,
+    5539157,
+    5539160,
+    5539161,
+    5539162,
+    5539165
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 19,
+  "inner_step": 20,
   "inner_steps": 0,
   "last_allreduce_block": 5538408,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ea4bc481517ceaa9107cda4d9307bc2c1ec225d6346ce03b1f79b2c41fc87fa
+oid sha256:e82352edd539d4964e5a189d1f3c0ce644d1f2bfb9871a2d341dfdd68e3d0997
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5c25aec702317fbd52dd54a8e193e73af4571bd8e0b36b2e71418756e1bfd13
+oid sha256:fc691dfa7b0c594208211d231b015820ce0ae4adb53ec265c6898d4c0f07107d
 size 4040701744