Run 4. Outer Step 17. Inner Step 43.

config.json

@@ -268,19 +268,20 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5520124,
-    5520128,
-    5520132,
-    5520135,
-    5520139,
-    5520142
+    5520146,
+    5520150,
+    5520153,
+    5520157,
+    5520160,
+    5520164,
+    5520167
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 42,
+  "inner_step": 43,
   "inner_steps": 0,
   "last_allreduce_block": 5509976,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2392087890f7b3d327a913e7954f206c083fd9be1e502f5dd242abe1699ddbf0
+oid sha256:686e34f3966192b3f4740e7550855161c8e139ab0814e750dcef4d8075bb3564
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad4a5e5efff5445b52e621a7c19fb9c18ee5d4314399d92ee69f3a8e3703b462
+oid sha256:5b4bd82ecbe3cd04fa395cb72e863515a8666661392be6812adc8f8b13bb3e84
 size 4040701744