Run 4. Outer Step 41. Inner Step 6.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5556646,
-    5556649,
-    5556653,
-    5556657,
-    5556661
+    5556666,
+    5556670,
+    5556674,
+    5556678,
+    5556682
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 5,
+  "inner_step": 6,
   "inner_steps": 0,
   "last_allreduce_block": 5552497,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:539d378d10884a4c4a5239514c189f0401f240f0c73141ec791c560c8586fb5b
+oid sha256:0fa5ff21f438f63ddcf641b9a994b667eb6f7167338be392b703bbc636dc13d7
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:faa7099fdf2f687205eb49fc4ea43933aaf1a3bab4675ff58c8b95c038392a9f
+oid sha256:6df9b1c5adf15784472c9371b07afd18ae1f7d72992ee06b6a146bc6bf1178d4
 size 4040701744