Run 4. Outer Step 52. Inner Step 23.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5575760,
-    5575763,
-    5575766,
-    5575767,
-    5575770,
-    5575772,
-    5575774
+    5575777,
+    5575779,
+    5575781,
+    5575784,
+    5575787
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 22,
+  "inner_step": 23,
   "inner_steps": 0,
   "last_allreduce_block": 5574901,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27945ffc57c5a5ed34675ae30b6a0ba62e9b1abafc6d695aaf347582d138b3e5
+oid sha256:615c160c6935dbd49d28cf0ff2f2a63912f0a37b43ce078d89da3a9e233953b9
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4564a8a0fed72ad9837a73fa7e458e5957474ab67b817f874abfdc8ac08b7fb9
+oid sha256:22290bf2c5441a6e4cf44ecf5a9b12a06a5138cf5f438561b5b1dc5062731d2d
 size 4040701744