Run 4. Outer Step 30. Inner Step 38.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5541012,
-    5541016,
-    5541020,
-    5541024,
-    5541028
+    5541033,
+    5541037,
+    5541041,
+    5541045,
+    5541049
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 37,
+  "inner_step": 38,
   "inner_steps": 0,
   "last_allreduce_block": 5539810,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49aee2a76ee3d70ef29afa4d6f9bf6159bad14e177f196415c62247e0209a83b
+oid sha256:32fcc2530e144f78e353f98f36e3eab20c23dd404b740cea1e31a7ee722badde
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9154872dda979b7fe94e072ba73440e105622cb98fc1752d37f983c2ad3239e7
+oid sha256:c5d7f64ae6ee75e656e5de151bdfdf0826f4ac474be4b048022dc4464d292246
 size 4040701744