Run 4. Outer Step 28. Inner Step 40.

config.json

@@ -268,18 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5538242,
-    5538245,
-    5538247,
-    5538250,
-    5538252
+    5538254,
+    5538256,
+    5538258,
+    5538260,
+    5538263,
+    5538266,
+    5538268,
+    5538270,
+    5538272,
+    5538274
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 39,
+  "inner_step": 40,
   "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 sha256:2abc9e50ab93feea744e922ff153b25c2508cca93f27cd2b4cdca5474f09fb6b
+oid sha256:4ddd17c4ab39af17466435f4043a46c89dde317e9eb52dc0256aa7a4cfb517e7
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de1fd9fa51757c6d169a20732c342a26e2757966f1dda904b1cb6867efb59758
+oid sha256:eb23f0d592a4e9ac358c0b594985ce5e7f2f2f5dadf99aef2c015e53fc8f319b
 size 4040701744