Run 4. Outer Step 35. Inner Step 35.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5549292,
-    5549296,
-    5549300,
-    5549304,
-    5549308
+    5549312,
+    5549317,
+    5549321,
+    5549325,
+    5549329
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 34,
+  "inner_step": 35,
   "inner_steps": 0,
   "last_allreduce_block": 5548219,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a01d98142970070313145e44e0aacf7eef2f654d0d4a29dc03c91a62c1679624
+oid sha256:52e1ff29ac68047cd73de9e52ee696fa02fd39f3294aa0beaa36912b1c4b41c2
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21ebf10811af4d6d4128c83e5cc407e1b9c854a235cd91a8902beadd4f9d4b12
+oid sha256:a77631d17980031e3a969424b35574d1a17244c96e2c01492c2969ffd884a5ad
 size 4040701744