Run 4. Outer Step 62. Inner Step 31.

config.json

@@ -268,19 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5611555,
-    5611559,
-    5611563,
-    5611566,
-    5611570,
-    5611574
+    5611578,
+    5611582,
+    5611586,
+    5611589,
+    5611593
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 30,
+  "inner_step": 31,
   "inner_steps": 0,
   "last_allreduce_block": 5610584,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10c92c971ef5872fbb13fda38445d960bea0a5b395a4759e5929cc7da0e1ce30
+oid sha256:ae1c0bef7f68c6b44ac367aba1dae30a9366d70c28cf49d8c89c330614e10187
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:098c2952dbb9126aba289f8c10fbcfe97199c1068fd74a2d9fe833f2536396c6
+oid sha256:aca8f2f4c4050ebab1946d2ac4048d8a87850807391b5e66c385d83be2ca7059
 size 4040701744