Run 4. Outer Step 10. Inner Step 106.

config.json

@@ -268,19 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5506579,
-    5506583,
-    5506587,
-    5506590,
-    5506594,
-    5506597
+    5506602,
+    5506606,
+    5506609,
+    5506613,
+    5506616,
+    5506620
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 105,
+  "inner_step": 106,
   "inner_steps": 0,
   "last_allreduce_block": 5492224,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c80a2ad23e64106245bcc5eb4ddeb9d6dabd307aa8fffb5050c0e0f28f5406b9
+oid sha256:3b3b54223cf3fe20dad3378cd7c41275cb92f1a42ad69242077b916d332385ad
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45d179d5ca64436b47dea9de2cf99ab9fd6c15be7c25558372187deecb787f27
+oid sha256:84513b1815f0ae77a6bb267908f91f6df344cf893f58de9befa67b2eceb970d3
 size 4040701744