Run 4. Outer Step 65. Inner Step 100.

config.json

@@ -268,15 +268,15 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5650734,
-    5650762
+    5650789,
+    5650816
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 98,
+  "inner_step": 100,
   "inner_steps": 0,
   "last_allreduce_block": 5648011,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79ca3a4cfdeffe7bea7aff83ab170ff441c4698acf4b9f7eaa745376f9ebdac8
+oid sha256:9dc742a4f745b176710d8ac895be63ccd878d81552e5b77f8e0f6ee211c430f5
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4dffe981b43f6f92e94a41bd9dce22450ec84d15b87e0a453ed217f6615a561c
+oid sha256:0cee284d16f0416168cb7e0bea1f323364ef5d7bef3cd8f78bb9bd9a912c704e
 size 4040701744