Run 4. Outer Step 64. Inner Step 236.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5617689,
-    5617693,
-    5617698,
-    5617703,
-    5617707
+    5617713,
+    5617718,
+    5617722,
+    5617727,
+    5617731
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 235,
+  "inner_step": 236,
   "inner_steps": 0,
   "last_allreduce_block": 5611658,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:440e0e9e754842c6c58ae12aeec4710aeb01e1046e6e209f8f4a54b2b14b4184
+oid sha256:70f75c62544ca50c6b02f6a8792ac84cb8ebad4ca95aa1fc361c12e0deca20ee
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56f0904cbeeab915d5454a0518e894a64cd99b73425fca379d91e70444569cd6
+oid sha256:250f329de35303c302f4e3aabc0f9747f9c929033342e12207a6b0a5b7550317
 size 4040701744