Run 4. Outer Step 21. Inner Step 27.

config.json

@@ -268,27 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5525987,
-    5525990,
-    5525992,
-    5525994,
-    5525996,
-    5525997,
-    5525998,
-    5525998,
-    5525999,
-    5526001,
-    5526002,
-    5526003,
-    5526004,
-    5526006
+    5526008,
+    5526010,
+    5526012,
+    5526015,
+    5526017
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 26,
+  "inner_step": 27,
   "inner_steps": 0,
   "last_allreduce_block": 5525369,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6928e361bdf3282d5dd7374c3090c7663998bf1599f8433ad68bcbcea448a069
+oid sha256:812a695451997283bd4c76599442c444a250b8e9cdc33dec1ed772554620105a
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96de3b71b13d8e7fcb9be634f4c6db800b0c7838ab79d49a2cf805c466f0095c
+oid sha256:5e85a1cd37e5fff72d9026aa3c3277b37f63b17bd1810298e41342a19a601f97
 size 4040701744