Run 4. Outer Step 50. Inner Step 36.

config.json

@@ -268,18 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5572595,
-    5572600,
-    5572604,
-    5572608,
-    5572612
+    5572617,
+    5572621,
+    5572625,
+    5572630,
+    5572634,
+    5572639
   ],
   "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": 5556551,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43915758747ae6ee48d383cfd2a6c6859c97fc7c73eade54bc58eeaf7a498b6b
+oid sha256:e0f6156ab846405718b0ccc64f67459463b77ffcd01172bf017eb83160b4277f
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e539b1a6931323d88d2e7af4bcf8280267350d71b512f765dfa26f7025e77741
+oid sha256:28898b2e2fd966cd540be014d6cd5253a4d0cb2e8356d1083c345b3e7ec1dfa0
 size 4040701744