Run 4. Outer Step 29. Inner Step 22.

config.json

@@ -268,21 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5539744,
-    5539746,
-    5539749,
-    5539751,
-    5539753,
-    5539755,
-    5539757,
-    5539759
+    5539762,
+    5539765,
+    5539766,
+    5539768,
+    5539769
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 21,
+  "inner_step": 22,
   "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 sha256:9e63d4ab106674f9043e5614b7581049a6ea2f0a8d846cf8255b36f270acf50f
+oid sha256:a5bc4a725f9c25b99b95b83f9d878c7b2a224b19578aa14ba1cdb9c6c6f6b2e1
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6985954bd6c099cc81fe8225a8a649d9c07beecedb1c187cc8f659575b9b610b
+oid sha256:1ff0177794dcfac9d06ec3bbb85e9a73bdb24eaebb01c3f8efe2af0c5848c1a9
 size 4040701744