Run 4. Outer Step 28. Inner Step 39.

config.json

@@ -268,23 +268,24 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5538218,
-    5538221,
-    5538223,
-    5538224,
-    5538226,
-    5538228,
-    5538230,
-    5538233,
-    5538235,
-    5538238
+    5538240,
+    5538242,
+    5538244,
+    5538246,
+    5538248,
+    5538250,
+    5538252,
+    5538254,
+    5538257,
+    5538259,
+    5538262
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 38,
+  "inner_step": 39,
   "inner_steps": 0,
   "last_allreduce_block": 5537093,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc7f06c963b88d503d910d5e51eeee7403bfa93f2f9d1363ca95c8eee30edea1
+oid sha256:9dca4259e2ead9be52f99e2285198fc27c4c8fecc394747191138480e21c9ac2
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3af7e8ffeea0b65bbdf762dc92f326b1879c803271a8f35a3e5a39769d630028
+oid sha256:1681079c2f3f0109e308184b0b42b790e1acc8ffc34eda271478a8238c629361
 size 4040701744