Run 4. Outer Step 7. Inner Step 71.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5494031,
-    5494034,
-    5494038,
-    5494042,
-    5494046
+    5494050,
+    5494054,
+    5494058,
+    5494062,
+    5494065
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 70,
+  "inner_step": 71,
   "inner_steps": 0,
   "last_allreduce_block": 5490074,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e2f3b613fd84b62ae5df3dcea82e4f4d38492a204d3f318cb3dd4004e8f2a73
+oid sha256:b461534aa74f54715eafbb61c2c2d45cedc673a704e40fe22fc067e136eb84c6
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efc751dfb4135acdd0cce11d7f19f0e3a3a98088e07e94d6fa047f1028255d79
+oid sha256:7e4224d88875993943f5204ed7a5c35dd75aa77c8d8722901b260f29490e469c
 size 4040701744