Run 4. Outer Step 41. Inner Step 7.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5556687,
-    5556691,
-    5556695,
-    5556699,
-    5556703
+    5556708,
+    5556712,
+    5556716,
+    5556720,
+    5556724
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 6,
+  "inner_step": 7,
   "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 sha256:0fa5ff21f438f63ddcf641b9a994b667eb6f7167338be392b703bbc636dc13d7
+oid sha256:821f094a509ae161a465bdc2bdca0d2c080667b2a29f667ec4361c0c8fb7579b
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6df9b1c5adf15784472c9371b07afd18ae1f7d72992ee06b6a146bc6bf1178d4
+oid sha256:155f870a8a886c2435c1848221e3d5930bcb023d8bc1a77e8d953f2f964f6b4d
 size 4040701744