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": [
-    5603367,
-    5603374,
-    5603381,
-    5603387,
-    5603394
+    5603402,
+    5603409,
+    5603416,
+    5603422,
+    5603430
   ],
   "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": 5576204,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:843543ffce2c61c3f6a2645a759b04f45ae7f0def042da9dc5edf3d8ccab14f2
+oid sha256:1051e1c4c8f60224f216e424cd6a143df566256ac5723257ea2715c3440bf682
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82f6076be5ed776d3d66c6cd12db2afb9b10a33d1e0e69157da51813b1ae1c52
+oid sha256:5fbe9a6944f5a48ef70b9c69f7922af6d6f2cb29b0d39f36b73cffe0e5ff6359
 size 4040701744