Run 4. Outer Step 31. Inner Step 48.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5542666,
-    5542669,
-    5542671,
-    5542672,
-    5542674,
-    5542678,
-    5542680
+    5542683,
+    5542687,
+    5542689,
+    5542690,
+    5542693
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 47,
+  "inner_step": 48,
   "inner_steps": 0,
   "last_allreduce_block": 5541234,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ff60c4cac855ace5ffe243aaa0377807aee255b7504ee1f6c5198fd526ed824
+oid sha256:dcf8f5c9a3767553ddf5cd5da239f8d68fc137ff1a5d1d5c881e1f44d4ab12b7
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75fe09e2c878f3f5cc1fe0b37ff0b2751da1457b6ba3d82222c0c0d1aced36dd
+oid sha256:3a2559684eda8c436ad43cd4be837ab7bbce2ec33e781f449fc55f34613209f4
 size 4040701744