Run 4. Outer Step 61. Inner Step 70.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5642963,
-    5642968,
-    5642972,
-    5642977,
-    5642981
+    5642986,
+    5642990,
+    5642994,
+    5643001,
+    5643006
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 69,
+  "inner_step": 70,
   "inner_steps": 0,
   "last_allreduce_block": 5641040,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3b4c28e4dbd1507a522c1d397342d55cf03ab06c668776ba3f272a75131ac7a
+oid sha256:1f7775f9d6a803df18d5a28c686ac230c4d3b30a7ae93f466612b1cf65a3598b
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f96e3bc75f9159cc7e44b590f91304fea7cc82f02754d0db51f064d8df48a244
+oid sha256:607bac48b0847cb2e9ce079604c17195603ed5795e383bc2b48c0f0086aa0167
 size 4040701744