Run 4. Outer Step 33. Inner Step 95.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5546668,
-    5546672,
-    5546676,
-    5546680,
-    5546685
+    5546690,
+    5546694,
+    5546698,
+    5546702,
+    5546706
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 94,
+  "inner_step": 95,
   "inner_steps": 0,
   "last_allreduce_block": 5543976,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f53ccc584c6f5e7da9a8e12cc2fe5eb8e7925a06dc7d8e06d2a31968536e56d
+oid sha256:1d5f46ae0f6c9ca145da1cd4f0b837ade527c9677d9e19d2f555298b04df7220
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89a5a7ba870a0bb9dd56d1f711dd85a2c91468d78e2eef2ffb580124e7bd7442
+oid sha256:8baae0ef6d887fdf676888a01fb5fccc13514b56448076b599afd85be41b04e9
 size 4040701744