Run 4. Outer Step 31. Inner Step 46.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5542658,
-    5542661,
-    5542663,
-    5542665,
-    5542667,
-    5542669,
-    5542670
+    5542673,
+    5542676,
+    5542678,
+    5542682,
+    5542683
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 45,
+  "inner_step": 46,
   "inner_steps": 0,
   "last_allreduce_block": 5541234,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a94690a54153844308f8c94c792fe2958010e785a4b512f282d448335916f1a
+oid sha256:26fea316e21bce0c87e49f182caa839075f0818a2c610f5e2d934b69e31f65e3
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91d85dcec0d5ace2d4b9a856526df2c92ba706c09639ed73e76edd261f4fd8c0
+oid sha256:4f073e648cf62ee3d40ac60fa91e8742f9951b85ad3a6e2f36f8f6abaff1d5ed
 size 4040701744