Run 4. Outer Step 29. Inner Step 19.

config.json

@@ -268,18 +268,26 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5539107,
-    5539109,
-    5539111,
-    5539113,
-    5539114
+    5539117,
+    5539120,
+    5539122,
+    5539124,
+    5539124,
+    5539125,
+    5539127,
+    5539129,
+    5539131,
+    5539133,
+    5539136,
+    5539137,
+    5539138
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 18,
+  "inner_step": 19,
   "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:e2a5885d96d2f73d3c44b4d9cf95e4a7b935e556f73a77f471a5e8c2f689df73
+oid sha256:a4166e9bbf5f958c6c24cd501bc5a836fda594e29bfb0a675153de0968affb98
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b26c011c2cac342da5073bd0695cf84859aa0964ab23749b57e68a73eac9ac3e
+oid sha256:987dc8abf164953ece235b2653ecf311ddef53336223ee1709a2914009862ce2
 size 4040701744