Run 4. Outer Step 53. Inner Step 31.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5577233,
-    5577235,
-    5577237,
-    5577239,
-    5577242,
-    5577245,
-    5577248
+    5577252,
+    5577254,
+    5577256,
+    5577259,
+    5577262
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 30,
+  "inner_step": 31,
   "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 sha256:9510f9266b4c18484c94ca347044b5a9f12926d27941762d361db3350192e3f6
+oid sha256:f1ce07f120d73002bd466ba0ad07ed942ab2100b3bcd64cef9c83b15156a6721
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:089b5b7004373eb21c348b3a7b9b20d96ec4cffb91ea04f12d839edf802dbbc8
+oid sha256:5e13a3ae685f8d4bea658659228deed13a9d71b3de21c789cb886388c4f4b59a
 size 4040701744