Run 4. Outer Step 38. Inner Step 9.

config.json

@@ -268,18 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5553833,
-    5553837,
-    5553841,
-    5553846,
-    5553850
+    5553855,
+    5553860,
+    5553864,
+    5553868,
+    5553873,
+    5553877
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 8,
+  "inner_step": 9,
   "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 sha256:09a43841eecd7f34f5e341603f79db1c09213dcaea38449d0e3fa1aaf37828e6
+oid sha256:9b97259429f54492e9e06b437b847f71f186ab59bbcf5510723d8153f939f6bc
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3a615f4c8ceec31a286363dd044b6d80f2566754dfb3c9c97b8f352addb83c5
+oid sha256:072943a707e117e9b4fa8372481cc90ef2b080431957ba645d27b05aeb424cff
 size 4040701744