Run 4. Outer Step 50. Inner Step 8.

config.json

@@ -268,30 +268,32 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5571785,
-    5571786,
-    5571788,
-    5571789,
-    5571791,
-    5571792,
-    5571793,
-    5571795,
-    5571796,
-    5571798,
-    5571800,
-    5571800,
-    5571803,
-    5571804,
-    5571805,
-    5571807,
-    5571808
+    5571810,
+    5571812,
+    5571814,
+    5571815,
+    5571816,
+    5571818,
+    5571819,
+    5571821,
+    5571823,
+    5571825,
+    5571827,
+    5571829,
+    5571830,
+    5571831,
+    5571832,
+    5571833,
+    5571834,
+    5571835,
+    5571837
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 6,
+  "inner_step": 8,
   "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:cfac97a745d097ce236c4cc329cfcef5b614055c2573c49709b2460714668444
+oid sha256:94937ec469a2553fb104a019c8edd4733e3847fd72cf81e0fe248bf0e8714af5
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3676085fa6653e9431b3fd065ece5c20d64907a2f5ac207d3870280984fdb53
+oid sha256:af6df267b6480a12d5c699d1ecc6153a4f3b8122ca0d32ae7fdd8a35f8d89eec
 size 4040701744