Run 4. Outer Step 40. Inner Step 26.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5556061,
-    5556065,
-    5556070,
-    5556074,
-    5556078
+    5556083,
+    5556086,
+    5556090,
+    5556096,
+    5556100
   ],
   "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": 5555115,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8050552b874187aaead112c46386cb93aa912403d114d8bbafa8325414823eea
+oid sha256:c25e7240b8369d25cd4ce7f38b0b0435d92978ad0840f568ef84e9c980bc8ff4
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:605b5a4204a3af4de269375e38b46aff8f54106a988b67627f61e4d4cb6e74b5
+oid sha256:54c6bf563e42f696c189970796ec721434a823b0e8b784b998f8ab034d8e34de
 size 4040701744