Run 3. Outer Step 9. Inner Step 95.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5410161,
-    5410165,
-    5410169,
-    5410173,
-    5410177
+    5410210,
+    5410214,
+    5410218,
+    5410222,
+    5410226
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 93,
+  "inner_step": 95,
   "inner_steps": 0,
   "last_allreduce_block": 5398844,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e1983db9867023b32cbbc7fc82364a853eae8accda4f8310d5bf13c99610ba2
+oid sha256:e10559c635235077ed89a8e51f96dc62caeb98ed7855aa2cbc7853d3ea74c27d
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89813d29d66684d81b7e7f33fff74d84af2156bb25622b6fd693a4d4a44757e7
+oid sha256:97f5f337daa352411671e93cbc994034426f1d66504fb9165e9bb4b413e3923b
 size 4040701744