Run 4. Outer Step 52. Inner Step 38.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5576145,
-    5576148,
-    5576150,
-    5576153,
-    5576156,
-    5576159,
-    5576160
+    5576162,
+    5576165,
+    5576168,
+    5576171,
+    5576173
   ],
   "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": 5574901,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd88bccc71b78d54a16a13e2ff3ba00e35be20bdf14b03bad7af935f9a43a275
+oid sha256:43a9871a0cb16d3761a1484fb5c7d746d214671854a029c4cb2ef4809b856693
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5de59fe9f51daeec1b39b903e0c94105fa8d696c3dc59d9ea85c18ff3553393f
+oid sha256:8256a0d4e90465cb14683b1d3141bd9a75472c563120f07283ab7ae024b8926e
 size 4040701744