Run 4. Outer Step 54. Inner Step 90.

config.json

@@ -268,22 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5580256,
-    5580257,
-    5580259,
-    5580260,
-    5580263,
-    5580266,
-    5580268,
-    5580270,
-    5580272
+    5580275,
+    5580278,
+    5580278,
+    5580280,
+    5580284
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 89,
+  "inner_step": 90,
   "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 sha256:9d76942862d021fe55aa22b0e76b3f32fae3084775c7f88e56559129ceb8151e
+oid sha256:a1a478e0ab9dfa7a22539c18a4c22565147a82750bd1b8e1a98c5b51c3653084
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:076e6d3a58d255d5ffbfa0c820c826ae9963a7caaeef456a19eef514ed9faae7
+oid sha256:b776d60cd862c2df42ccef68cf9fa71a4d965fa051bd9ea54cc1afdf2e049606
 size 4040701744