Run 2. Outer Step 2. Inner Step 104.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5330307,
-    5330312,
-    5330316,
-    5330320,
-    5330323
+    5330359,
+    5330364,
+    5330368,
+    5330372,
+    5330376
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 97,
+  "inner_step": 104,
   "inner_steps": 0,
   "last_allreduce_block": 5323221,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c3b8db94949bd9567dcbbdd1134cf7795c2faae9ec093a142f30156dbcaebae
+oid sha256:c10f56723c063203cb3b8369d0a230604c4b666b68e8f30500ee2770926f6a0d
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43a3b83c1ed87d7708d4479f4e8b8c5276d4112f6c73fcbf8c5041eaaef062af
+oid sha256:822a0542cdcec0ef4934556549fee966c01ed6619950ff91dc2af7780e178d07
 size 4040701744