Run 4. Outer Step 58. Inner Step 52.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5603987,
-    5603989,
-    5603992,
-    5603996,
-    5603998,
-    5604000,
-    5604003
+    5604006,
+    5604009,
+    5604011,
+    5604014,
+    5604016
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 51,
+  "inner_step": 52,
   "inner_steps": 0,
   "last_allreduce_block": 5602341,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e2394b44ddc9e373d2ae6f24d96ff608a49e08784acea872f4e5d6faa6a73e7
+oid sha256:f94483ab30ba55e4190c57f891218ecc9e17d42b6ca7bd1553496acefe8c3149
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d13f9b854362093e7fb98953ee926e23cfcbdf06929c5477b4de877e559a85a
+oid sha256:34bde196e59f662081fe2af113bb090497e965efe9de0c4cc61245ad0b96a86d
 size 4040701744