Run 4. Outer Step 40. Inner Step 36.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5556234,
-    5556238,
-    5556242,
-    5556247,
-    5556251
+    5556256,
+    5556261,
+    5556265,
+    5556269,
+    5556274
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 35,
+  "inner_step": 36,
   "inner_steps": 0,
   "last_allreduce_block": 5555115,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0f0b963b551f5eeed6bcf839ec18f6fb484be04973978ba074e1e5078d08883
+oid sha256:29f4d7852a88c167620c3d1a1034fe5778abc15b217c44308ab1ed71dd4fe81b
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c1186da98411999dec194c1ebe4ba54775591acd2a2f2e0f4312c8d46f697fa
+oid sha256:edffaab7b7a392bc6859bc7efeebbd7254c0681df891e079669de7d0d261c5f1
 size 4040701744