Run 4. Outer Step 33. Inner Step 17.

config.json

@@ -268,24 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5544503,
-    5544505,
-    5544508,
-    5544509,
-    5544511,
-    5544511,
-    5544512,
-    5544513,
-    5544514,
-    5544516,
-    5544519
+    5544522,
+    5544525,
+    5544528,
+    5544529,
+    5544533
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 16,
+  "inner_step": 17,
   "inner_steps": 0,
   "last_allreduce_block": 5543976,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10eebb89c38ffc9ce94e126bad6575bc0c461024041e3b54a15362f9b14cdd1e
+oid sha256:342bdddf2fc674fe0097188f484165172da478e329201ef08aad2317377f4a2c
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f410b3441e2a69e86c578cbf818a5bd0adbff71763423ce7953679087b9c3dd7
+oid sha256:f7a8bf081018f21de8fa754483dd0205ab092339f06f1410be0e50601cb259ac
 size 4040701744