Run 4. Outer Step 29. Inner Step 19.

config.json

@@ -268,24 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5539106,
-    5539109,
-    5539111,
-    5539113,
-    5539115,
-    5539116,
-    5539119,
-    5539122,
-    5539124,
-    5539125,
-    5539127
+    5539130,
+    5539133,
+    5539135,
+    5539138,
+    5539139
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 18,
+  "inner_step": 19,
   "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 sha256:84ba2aedf6c896cf796adbeeb0daed23f9b510ec844ffa816a38fd325489a026
+oid sha256:0ea4bc481517ceaa9107cda4d9307bc2c1ec225d6346ce03b1f79b2c41fc87fa
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb4ef0c37619a341f52da78e1a0a24f050b16119d0476d2bbcbbc9a7ba9579d3
+oid sha256:e5c25aec702317fbd52dd54a8e193e73af4571bd8e0b36b2e71418756e1bfd13
 size 4040701744