Run 4. Outer Step 64. Inner Step 226.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5617389,
-    5617393,
-    5617398,
-    5617402,
-    5617406
+    5617411,
+    5617416,
+    5617420,
+    5617425,
+    5617430
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 225,
+  "inner_step": 226,
   "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 sha256:6685118c249619565e54940d60c995973fb74e0d8273570aa79eb03aa7c27c24
+oid sha256:39d825b67381380dc68ce52c9a39eade5f1e0f663a965f885085ce5d00e471ed
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abd1c9189fc6eb8449d80969d56a9a82597e3df7ee7215dc442f018ed18965b5
+oid sha256:c3066d998153ca32da0f8b2e42a5bd4715a4b3f52c595a4e02285de32c6ecff3
 size 4040701744