Run 4. Outer Step 11. Inner Step 53.

config.json

@@ -268,19 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5508357,
-    5508361,
-    5508365,
-    5508368,
-    5508372,
-    5508376
+    5508380,
+    5508384,
+    5508387,
+    5508391,
+    5508394,
+    5508398
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 52,
+  "inner_step": 53,
   "inner_steps": 0,
   "last_allreduce_block": 5506953,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a671be8578420aad8e2205009bdd26b445c5014c67181f2b341d5a15d5ba7ac7
+oid sha256:67028d2e12a7282d022cb5d6e14bb063ee1bb3183349ef6f78bf5a5598ace8f3
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43c0d7f62f9cb0bcbe1b55a4f44bb2c43b4656d2c5134fde37f3550701fa23cb
+oid sha256:bf3ffef5d2f68db6f4746febf381b63a801e5f1bba080ff01ff081d86654c51b
 size 4040701744