Run 3. Outer Step 6. Inner Step 266.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5389400,
-    5389403,
-    5389407,
-    5389411,
-    5389414
+    5389442,
+    5389446,
+    5389450,
+    5389453,
+    5389457
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 263,
+  "inner_step": 266,
   "inner_steps": 0,
   "last_allreduce_block": 5378990,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f8e6a53175cce5527966de2dfe32ed14051ee9317424d49a9f23e08b298bc08
+oid sha256:8db04564a1cda245d98ac581efc6130dd416e079d513b9e467c18d6f6353f3ff
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9af8adc6795e37f250c439e805f0d4e6f2c5eb663a34a8696d799047e3bd013b
+oid sha256:42849ac345a4da76b1ad3e370d85da4d0ef3d033fc4caae6721ec8a3d826a3e9
 size 4040701744