Run 4. Outer Step 28. Inner Step 28.

config.json

@@ -268,21 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5537913,
-    5537917,
-    5537919,
-    5537921,
-    5537923,
-    5537925,
-    5537928,
-    5537931
+    5537934,
+    5537937,
+    5537939,
+    5537941,
+    5537943
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 27,
+  "inner_step": 28,
   "inner_steps": 0,
   "last_allreduce_block": 5537093,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afcfa617ca9f6276d10724c077a9e67f03cc83f085064d0fdbf9cf53be0e21ef
+oid sha256:fa92c3377d2c79780f67c8efcda74f808818aff0f33a86d22aec8f844d6c6d3c
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:583cc159faeb42bef7c8e17caae3c72f638cd7f1b5077a2500ff0919c299e668
+oid sha256:db89501bbe739f6f66f28a60d7c506e46f5775c88707a87f1ef2b943e1f71957
 size 4040701744