Run 4. Outer Step 58. Inner Step 23.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5586730,
-    5586734,
-    5586738,
-    5586742,
-    5586746
+    5586751,
+    5586755,
+    5586759,
+    5586763,
+    5586766
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 22,
+  "inner_step": 23,
   "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:d7369ae873cca422707847ceb261a3296d848e8ba31b3a9c9c2b59c8d5a87940
+oid sha256:ad3c4bb17cfa940e51aadeca401e6beaa3354f3fd0127c1459a75aa768699a5b
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73fa3b018c80e6e441edd21fc18a53e1b885c0f1199a3802b057cd3fd12f6644
+oid sha256:d3705924558d68a78f0b7ceae4a538255f656d794beee5e90d59b449c229a4ea
 size 4040701744