Run 4. Outer Step 50. Inner Step 9.

config.json

@@ -268,33 +268,27 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5571807,
-    5571809,
-    5571810,
-    5571811,
-    5571813,
-    5571814,
-    5571815,
-    5571817,
-    5571817,
-    5571817,
-    5571821,
-    5571822,
-    5571823,
-    5571824,
-    5571826,
-    5571827,
-    5571829,
-    5571829,
-    5571830,
-    5571832
+    5571834,
+    5571836,
+    5571838,
+    5571839,
+    5571840,
+    5571842,
+    5571844,
+    5571845,
+    5571847,
+    5571849,
+    5571850,
+    5571852,
+    5571853,
+    5571855
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 7,
+  "inner_step": 9,
   "inner_steps": 0,
   "last_allreduce_block": 5571611,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18bf6edbec248b5a8b78c27610dd20a08bfe343829bd02b77809c00fe0e1ba0c
+oid sha256:2ec961ed9b222d9bd16fe15d3225de1f8539d3fc42960ef95ba2a49581013a29
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:445ec243ffbc5ef499351f538067435de6b5321a17d12c627890bcf75cfc2b20
+oid sha256:0fc22bf79c2a9ab008ce076ff43ea99d124bf65029efc5d420e4f93d63fc1aa6
 size 4040701744