Run 4. Outer Step 52. Inner Step 24.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5575752,
-    5575755,
-    5575756,
-    5575758,
-    5575760,
-    5575763,
-    5575766
+    5575768,
+    5575770,
+    5575770,
+    5575773,
+    5575775
   ],
   "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": 5574901,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47fe7b2e3ebb362947949f7b190c4c326201bfed7ba5fd9edb271ecd81ea7474
+oid sha256:93f093088e0a680246afdc57f1cf2fede59bb1b9c44619b0b24cc9753cd35534
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d606041f92ff0b3aac5a7f7c275e3e7a7622575961815cfbb224289fb5a49fb3
+oid sha256:82c9d33bf5046906e7d75d640454de0a58e1ba6000271bbf8ca7d407102769ec
 size 4040701744