Run 4. Outer Step 52. Inner Step 40.

config.json

@@ -268,22 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5576261,
-    5576263,
-    5576265,
-    5576266,
-    5576268,
-    5576269,
-    5576271,
-    5576273,
-    5576275
+    5576277,
+    5576280,
+    5576281,
+    5576287,
+    5576290
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 39,
+  "inner_step": 40,
   "inner_steps": 0,
   "last_allreduce_block": 5574901,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e433a19ffd33a556601be33cbf7785c92df1513daec7f65c7d89a11ab4cbbc3
+oid sha256:a1fa161267bba0848f90b1e77350409552a351c39e63347fcac79bfcfac91efc
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3613a965418f4c2aeb7e8709485776766dc45e1807f8df2a1f705adbfa505874
+oid sha256:698036c2a6a87d39180b57a3d51493fcfcef398a2a538d3a96f375744cfa7639
 size 4040701744