Run 4. Outer Step 31. Inner Step 49.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5542674,
-    5542676,
-    5542679,
-    5542680,
-    5542682,
-    5542684,
-    5542687
+    5542689,
+    5542691,
+    5542692,
+    5542694,
+    5542697
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 48,
+  "inner_step": 49,
   "inner_steps": 0,
   "last_allreduce_block": 5541234,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1610552ffea5548d6a8d8a584c370aa3826b1276f6308025754230fa84a5a53
+oid sha256:815bdd937ef1d3b6f9bd12e055698d504e5a8ea584a13a2bb78da235149c9619
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4dc63744e064b012ac3825926e6f03b58fcb699fd417d0c12eb826c742b05fb
+oid sha256:943bed1147ed64bd36bf8a03759841b725a31c446c68668695a660710f3f5722
 size 4040701744