Run 3. Outer Step 9. Inner Step 977.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5420640,
-    5420643,
-    5420646,
-    5420649,
-    5420653
+    5420679,
+    5420682,
+    5420685,
+    5420688,
+    5420691
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 975,
+  "inner_step": 977,
   "inner_steps": 0,
   "last_allreduce_block": 5398844,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8482d6d9326f5821c2bd44ac9c4c1d329a13670c33784892b9b5778ad0dd29be
+oid sha256:7c384f7a8f6aea37f385270ecc4646c301d05d01e07fc688f9365a46cdb86eb1
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8764f1a900f7706ca4a7bc5cbae0c10500de62a9a8a9e12e2379301cb7140637
+oid sha256:9b7e6a6251f244483053d1a17a13a85c9031f493cc2f4dee296b8099e50733a4
 size 4040701744