Run 4. Outer Step 11. Inner Step 24.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5507972,
-    5507978,
-    5507984,
-    5507989,
-    5507995
+    5508001,
+    5508007,
+    5508012,
+    5508018,
+    5508024
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 23,
+  "inner_step": 24,
   "inner_steps": 0,
   "last_allreduce_block": 5506953,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc6e068dcdfec4fe35d0f74b4d5d055129be52170973ebeccc05fd4899144953
+oid sha256:5670465c8bc2c39c2fca3d73b5f118bcd751843d6e5e6a466a852adf0fa18d9f
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d82daeea374eff4764433c8893c7fbcc968138f813527aa08060b1e4df75e55f
+oid sha256:0fd726cd4bf2537416ee69f09ffac710b517530aa301004a50ad3df4dd9167d1
 size 4040701744