Run 4. Outer Step 60. Inner Step 20.

config.json

@@ -268,19 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5607836,
-    5607840,
-    5607844,
-    5607848,
-    5607852,
-    5607856
+    5607860,
+    5607864,
+    5607868,
+    5607872,
+    5607876
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 19,
+  "inner_step": 20,
   "inner_steps": 0,
   "last_allreduce_block": 5607244,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:278168bd9b5b4be708b37be3ae7bf3cdf82aba26b55ee92f58b600b73d3c8673
+oid sha256:3ac9b7431fc0b15f811e53a6ecffa03d1e04808c75ba60dc4c18baba23fd44ec
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d77f8802ff900a4c98fbfca5b044f427fcbb59741bbd40b8866ff20ba81f34f
+oid sha256:730f4dae2467a21a38541d676c5671d75eb5a90939db43ca3dea9b89918c2b4a
 size 4040701744