Run 4. Outer Step 54. Inner Step 83.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5580198,
-    5580199,
-    5580201,
-    5580204,
-    5580206
+    5580209,
+    5580212,
+    5580214,
+    5580215,
+    5580215
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 82,
+  "inner_step": 83,
   "inner_steps": 0,
   "last_allreduce_block": 5577515,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb5965a4f66723d2b4efeb00dae61ecf112d5a9e103f05830e394afeb2631b0f
+oid sha256:7677d45d7772052595b050ff443ac2333027be614525cc773295778f3a022ab0
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02214d39e21d7e296027f8287855660142e0c63a66f786630cf619fc4ae51c61
+oid sha256:fb4baa068e7f80c93e2039ecbac3bf1ecc44fdf7b03d17b9afbe44c3ae047607
 size 4040701744