Run 4. Outer Step 17. Inner Step 62.

config.json

@@ -268,19 +268,20 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5520725,
-    5520729,
-    5520732,
-    5520736,
-    5520739,
-    5520743
+    5520747,
+    5520751,
+    5520755,
+    5520758,
+    5520762,
+    5520765,
+    5520770
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 61,
+  "inner_step": 62,
   "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 sha256:9daa30c60eaac63a96cad2ecee77fc6f80d9e9e7148373e47e181cd6afa43331
+oid sha256:9e1e8a5e1f6de96d2db8a0ee96988fb1bd8eb52548f260d6c6419bfa9dd95251
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8e28546303d92c95fc4a31ecf71b462fbcae445da8ef16a1131956faeebce0b
+oid sha256:bc663d17d92dcfc6018e9bccfa3da0b6de13f67b0c0a0eea65de1722e4cb041c
 size 4040701744