Run 4. Outer Step 10. Inner Step 92.

config.json

@@ -268,19 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5506215,
-    5506219,
-    5506223,
-    5506227,
-    5506231,
-    5506236
+    5506240,
+    5506244,
+    5506247,
+    5506251,
+    5506254,
+    5506258
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 91,
+  "inner_step": 92,
   "inner_steps": 0,
   "last_allreduce_block": 5492224,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cb3d9ab033904c723e1fe3f289ecfd3667f8ea95fe0babd0584fd5273b16f95
+oid sha256:0ed03050848e3c0e0ab93987e60bde3d5a49bab72fec469ecf4a5e3e1e7cfd38
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec61f1e32bbad0cdb5a5c72942bae7780e8a7fc60c50e003474d18d5442bacfa
+oid sha256:67c5801add0eee35fc5b312be9dc687dc4b385e1f9dade3e8d695b1ebd09c26c
 size 4040701744