Run 4. Outer Step 17. Inner Step 63.

config.json

@@ -268,20 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5520747,
-    5520751,
-    5520755,
-    5520758,
-    5520762,
-    5520765,
-    5520770
+    5520775,
+    5520779,
+    5520782,
+    5520786,
+    5520791,
+    5520795
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 62,
+  "inner_step": 63,
   "inner_steps": 0,
   "last_allreduce_block": 5509976,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e1e8a5e1f6de96d2db8a0ee96988fb1bd8eb52548f260d6c6419bfa9dd95251
+oid sha256:efaddf145b375830f348768f94055b3ea4ac579488c52e4f04fc4ab1bb5bb98e
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc663d17d92dcfc6018e9bccfa3da0b6de13f67b0c0a0eea65de1722e4cb041c
+oid sha256:6e4fa32a4e1f205c75c79bfd2889d6e573f1dcf3da3ab0075a4da2466e6f06ab
 size 4040701744