Run 4. Outer Step 46. Inner Step 8.

config.json

@@ -268,21 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5567094,
-    5567097,
-    5567099,
-    5567100,
-    5567102,
-    5567103,
-    5567105,
-    5567107
+    5567110,
+    5567113,
+    5567115,
+    5567117,
+    5567120
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 7,
+  "inner_step": 8,
   "inner_steps": 0,
   "last_allreduce_block": 5566279,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8854470a14b5bbb3ff950a74e819431a6e6920091d88dd6a7a7b8bb3d45a293
+oid sha256:9b36cd577f76f922c3941d01b0220ea9b8b8e1b528091f6baa7b899f53f524cf
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97ea6169c0e6c810ca57e87215a6789f1fd1091b633d43e65358de1d6e014aff
+oid sha256:cbfc647a5ac70fa1e7d67c3fb486dc51e41f1812e6ea52cbc55af24e99ab46fc
 size 4040701744