Run 4. Outer Step 31. Inner Step 24.

config.json

@@ -268,18 +268,22 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5541913,
-    5541915,
-    5541916,
-    5541918,
-    5541921
+    5541923,
+    5541925,
+    5541928,
+    5541931,
+    5541934,
+    5541936,
+    5541937,
+    5541939,
+    5541941
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 23,
+  "inner_step": 24,
   "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:a8ed585e26226874a5a4f91885ea0ce8d0ee8004b7de578b581e9c77618928b6
+oid sha256:c61567c377b2fe61f04cb09a4e7574a5d21d18acae5f655b8817561d8414cc0c
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a08f9e4668ea058520eff9f8908b69c915b54dea533a455feeac2a50af7469c
+oid sha256:ad4ca0f8b03d5e5615da02f5de640344f52fd2cfeae5cbde46c2ba689c6f1d9d
 size 4040701744