Run 4. Outer Step 54. Inner Step 93.

config.json

@@ -268,21 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5580413,
-    5580415,
-    5580417,
-    5580419,
-    5580421,
-    5580423,
-    5580426,
-    5580427
+    5580431,
+    5580434,
+    5580435,
+    5580437,
+    5580439
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 92,
+  "inner_step": 93,
   "inner_steps": 0,
   "last_allreduce_block": 5577515,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:752d77bd557b043df21443c84f28621942a158ed2d7cb9408eb0a0ed5cf10540
+oid sha256:a25b01ea5d2e8ed2bc377ec546dcffcd050694fb13d428848c0bc3d6e21e5917
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee66c27ccb0b2ec9bbf270820e6cb765de2b0a3a7c90fbf920ac3aec5cd72c09
+oid sha256:933be91ad2127c2888041271a6714df6c27109f8bea031208fd579d26cf5eb88
 size 4040701744