Run 4. Outer Step 50. Inner Step 3.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5571743,
-    5571748,
-    5571752,
-    5571756,
-    5571760
+    5571765,
+    5571769,
+    5571774,
+    5571778,
+    5571782
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 2,
+  "inner_step": 3,
   "inner_steps": 0,
   "last_allreduce_block": 5571611,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:620ce2c5e895dcc1da07d9035a5be6b059870fa0cd0b9db5ebb73439d7f26399
+oid sha256:c4278aed20c1a3bd6bcd57366986680c9fbe19a8ea90fc840486f64eac68eed5
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7852aa9cdb27ac6a4a46e848484697842eda7a0d6830e79c6ddbe7d4d746498d
+oid sha256:27891f54368cabf92c43387f07510c50e3f1dad8a50cdb0beb93a5372e76903a
 size 4040701744