Run 4. Outer Step 54. Inner Step 133.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5597926,
-    5597930,
-    5597934,
-    5597939,
-    5597943
+    5597947,
+    5597952,
+    5597956,
+    5597960,
+    5597965
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 132,
+  "inner_step": 133,
   "inner_steps": 0,
   "last_allreduce_block": 5573605,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e67509f43977e32fdd41cb87f02d10f4d754ecbfe125229d1bd71cef7f8d53ca
+oid sha256:991e0d80f8f98ae2b8b637493bf27eebee49146a9139865e53da5fd8eda48a8c
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1a1a8d48de75577b5b7cfd5b6049a54c1e727764da5f86c6ab5dbdae1748c6f
+oid sha256:a19de0dd2dd49cd13ebf8e233cf8937229f1bc8b0977428f734684e4d61e4f71
 size 4040701744