Run 4. Outer Step 60. Inner Step 26.

config.json

@@ -268,18 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5607979,
-    5607983,
-    5607987,
-    5607992,
-    5607995
+    5608000,
+    5608004,
+    5608008,
+    5608012,
+    5608015,
+    5608019
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 25,
+  "inner_step": 26,
   "inner_steps": 0,
   "last_allreduce_block": 5607244,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cd6ff5e31ee2d86054298687c02959243bade17263bad6739f465d39cbfc3f4
+oid sha256:52010424d7b7d7f2b266ea2633d5f04e2edac0db290167fb22d83db0d2cf06ee
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab000cee3fe4a26c2b5d8384fb5f7d275883e338807319ccde2a9687652b7718
+oid sha256:3758c3b0209606540c343557e663d86e7d040f611e2b4bf2c8d6d8188bc71fb5
 size 4040701744