Run 4. Outer Step 40. Inner Step 7.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5555539,
-    5555544,
-    5555548,
-    5555552,
-    5555556
+    5555560,
+    5555565,
+    5555569,
+    5555573,
+    5555577
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 6,
+  "inner_step": 7,
   "inner_steps": 0,
   "last_allreduce_block": 5555115,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b831990088d3d9b33e8112524601f0b3b1e6797a2239bf2f8fd0691954bd6d8c
+oid sha256:f866a96bae2bb9dbfa71ad5a8a721ef1b57ad3f6b8786c92c071c0754fb6d663
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1422c84bfa987eb22333f9c815d76420ad627ad7c994dc313740f3773c745c7c
+oid sha256:d7d30cd8ae7ccd41d463dc4051ce90c6aa138d501a4fa9e041e79a4870a69c8b
 size 4040701744