Outer Step 0. Inner Step 71. Batch Size 464

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5130954,
-    5130962,
-    5130969,
-    5130978,
-    5130985,
-    5130993,
-    5131005,
-    5131013,
-    5131021,
-    5131033
+    5131065,
+    5131072,
+    5131078,
+    5131085,
+    5131100,
+    5131109,
+    5131119,
+    5131129,
+    5131136,
+    5131144
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 64,
+  "inner_step": 71,
   "inner_steps": 0,
   "last_allreduce_block": 5072405,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d6884b6d007c5a0a6c032d51fd4e724ac263bd0dcf1b7273336bbbb94d7fc8f
+oid sha256:80ca2b1971e2b2fc5fe2662849ea5edfc3bdd321af37487bbfd908433cc30a26
 size 8081781770

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc294858653c79be172bfd104f176ce5aff17d25817b5f506d2b72f1eb479be0
+oid sha256:4d6c6c792d9568eeb15ef381208abb314dd63e30574f777d10c4b6221b69d5dc
 size 4040701744