Run 4. Outer Step 62. Inner Step 3.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5610815,
-    5610819,
-    5610824,
-    5610828,
-    5610832
+    5610839,
+    5610843,
+    5610847,
+    5610851,
+    5610855
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 2,
+  "inner_step": 3,
   "inner_steps": 0,
   "last_allreduce_block": 5610584,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c43d9bc1241fe2d4c174b5d14d57c850cbc4a4b337d29fd77739226ed505e1e8
+oid sha256:ce7b41d7eff5b9c3da69235a1eb7385b7eb1baeb08c660d533ad5a288a263c65
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02a50cabe3b940475965cba335c96f726b95aa8ab0cd2b511748556cf83170ce
+oid sha256:97681ad70f8b52bbf4d507b3521a1c014cbd2dd1a487a72d7519001665ed404c
 size 4040701744