Run 4. Outer Step 24. Inner Step 25.

config.json

@@ -268,18 +268,24 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5532301,
-    5532302,
-    5532304,
-    5532306,
-    5532308
+    5532311,
+    5532313,
+    5532316,
+    5532317,
+    5532319,
+    5532321,
+    5532323,
+    5532325,
+    5532327,
+    5532330,
+    5532332
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 24,
+  "inner_step": 25,
   "inner_steps": 0,
   "last_allreduce_block": 5529444,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41cb823e20191919119b4089c504bcd163b2a4378777264d395943dedc49c7f5
+oid sha256:e748338772f00179be4b1677081599a5de1a4f232ce2acaac7b3154fd15d25d1
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a81467b03b02a4424e446a06258dea0ee24850e2196fe529cde435e987d5ac9
+oid sha256:cb2888e83f7ce24a1cf9ccab08cef1be3e3c63c1308901bc2dbb9b888368d3c4
 size 4040701744