Run 4. Outer Step 57. Inner Step 8.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5584998,
-    5585003,
-    5585007,
-    5585012,
-    5585017
+    5585022,
+    5585026,
+    5585031,
+    5585035,
+    5585040
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 7,
+  "inner_step": 8,
   "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 sha256:76a48c40f495da698675a23073981439d0b64ebc3e6273bdf1f4f4aa2ce69de8
+oid sha256:2431c0795ac281314ca576d6ea6f63d8bf20d900065dbcf192fa6d2bc77cddf3
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69bccdb6232a3267a1fd65f34ed0a4fe65c6b1b7bfecdf143509194d98253da8
+oid sha256:66fa93c5fc4dda487cc8037e30dc045edc35902a9a13a7daebed97be71b7019a
 size 4040701744