Run 4. Outer Step 29. Inner Step 23.

config.json

@@ -268,24 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5539771,
-    5539773,
-    5539775,
-    5539777,
-    5539778,
-    5539778,
-    5539779,
-    5539781,
-    5539783,
-    5539784,
-    5539786
+    5539788,
+    5539789,
+    5539791,
+    5539793,
+    5539795
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 22,
+  "inner_step": 23,
   "inner_steps": 0,
   "last_allreduce_block": 5538408,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5bc4a725f9c25b99b95b83f9d878c7b2a224b19578aa14ba1cdb9c6c6f6b2e1
+oid sha256:6d9eb2fdeeb90bee9216102776da30481f9e7062b6896c2480265b2a432cd9b1
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ff0177794dcfac9d06ec3bbb85e9a73bdb24eaebb01c3f8efe2af0c5848c1a9
+oid sha256:f2c9f8001f63d1016d2729b3bb1c3be7e01581f1a379038da70e4be24393aeed
 size 4040701744