Run 4. Outer Step 58. Inner Step 21.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5586668,
-    5586672,
-    5586676,
-    5586680,
-    5586684
+    5586689,
+    5586693,
+    5586697,
+    5586701,
+    5586705
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 20,
+  "inner_step": 21,
   "inner_steps": 0,
   "last_allreduce_block": 5580790,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c0183974ff63fd32e8aa91d59ac28da445bd384b9ed5d1bd627149a9d2934aa
+oid sha256:fc7a9255596626b436a4b2d1319ea80a4d4652ba57e251442ad2b487919a4df5
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18feca3196712333e498fd25bd56031b18ba5282e92eb23a7f84e1ec71c38031
+oid sha256:c9852121bc38b0a4cc08fc939c10591498c63b1ce20ff6e8aad2c80124d0d0dc
 size 4040701744