Run 4. Outer Step 62. Inner Step 15.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5610999,
-    5611003,
-    5611009,
-    5611012,
-    5611017
+    5611023,
+    5611027,
+    5611032,
+    5611036,
+    5611041
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 14,
+  "inner_step": 15,
   "inner_steps": 0,
   "last_allreduce_block": 5605539,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67da33076abfabb98916017f69517430ead52b20b5d3152a2ac683057b9a715c
+oid sha256:898a41031a0e3422737163f09d4ce6a97f37747b89a75a1a9834d9e17ba2e1fc
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ea797581c0d86529aacd1c08dbfcb8fcd1378609900a40d4d3aaaa923e7b03b
+oid sha256:a98c15c62cf877114b04e54cd58df72e3269834729bad865327809f79c0d18cd
 size 4040701744