Run 4. Outer Step 60. Inner Step 4.

config.json

@@ -268,19 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5607482,
-    5607485,
-    5607487,
-    5607490,
-    5607493,
-    5607496
+    5607498,
+    5607501,
+    5607503,
+    5607505,
+    5607509
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 3,
+  "inner_step": 4,
   "inner_steps": 0,
   "last_allreduce_block": 5607244,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2561b15284c3d143ec27deaf46621eecfb8e9ebd423af4f1e7a9be8b9f81c379
+oid sha256:2fa6489f830f67a744e92df0e1609da9689bd980c65a8fb2edee5d646eca92b8
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cb92af3b1c8507674ce992765836fd6020f094c2a01dc600dd0c47a2f01d674
+oid sha256:6be3f6242bcb7cd235e4182588898d7cbc238b650a511d99ec6da83a55593e15
 size 4040701744