Run 4. Outer Step 62. Inner Step 23.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5611392,
-    5611396,
-    5611400,
-    5611404,
-    5611408
+    5611413,
+    5611417,
+    5611422,
+    5611426,
+    5611430
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 22,
+  "inner_step": 23,
   "inner_steps": 0,
   "last_allreduce_block": 5610584,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cdbad20058176f1cb695637a9304a9eb86613c3440209ddb1cfd2ec1d8820d1
+oid sha256:1b32171ed5e6f2818722ec55bcbfbccdba511870658d6b9e34d8b90d57cdd0b2
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c16e9171aa28c4d6595dc64dfca7b2cd47f043bd1dc94df9c1b9852d6c2cdd4
+oid sha256:cf0e1827ed7bec414b3aec8592cf5b460f7a79de18116c6a6a984ac6d5265256
 size 4040701744