Run 4. Outer Step 55. Inner Step 3.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5582796,
-    5582800,
-    5582804,
-    5582809,
-    5582813
+    5582817,
+    5582821,
+    5582825,
+    5582829,
+    5582833
   ],
   "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": 5580790,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed61ccb4c2b2ba3b27965392d54a112cae11b7c542bddddc50ddab6f287bce68
+oid sha256:e43ce803b00755c538d191c03a074219db9a6bd6c56891e3377c72fe9a2007e8
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:174f4039a07621f867aba44a2e2a33b47c9d2f47b2d04936bf844c6649459a6d
+oid sha256:80649e4719d950368cfcab0b9bc9c18654d27d6d89006e8a1876a176d42f8525
 size 4040701744