Run 4. Outer Step 53. Inner Step 33.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5577296,
-    5577299,
-    5577303,
-    5577306,
-    5577308,
-    5577309,
-    5577312
+    5577315,
+    5577317,
+    5577319,
+    5577322,
+    5577325
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 32,
+  "inner_step": 33,
   "inner_steps": 0,
   "last_allreduce_block": 5576204,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3dc299b6486ad569666b274f423bad89427f0aa3d415cd6a1ef73ad87662159b
+oid sha256:8efbeee3bd6e5cb2f5dd8063f4b7a6078c96f6735e250ed66a2caad93706111c
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3646a82adf7f63f9212d4a345dc1edfbbb067886827d56f1b886810047f1a1a
+oid sha256:d6e4da85cc4d131161f42ffa22df0a0df48f4c6ce88d324a8c7d7c9e0056c120
 size 4040701744