Run 4. Outer Step 62. Inner Step 10.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5610834,
-    5610838,
-    5610842,
-    5610847,
-    5610851
+    5610856,
+    5610861,
+    5610865,
+    5610870,
+    5610875
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 9,
+  "inner_step": 10,
   "inner_steps": 0,
   "last_allreduce_block": 5605539,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4d344b363f9a90841aa71cf74f5f90e3f61e7be36a173a66e3c6f63a2be133c
+oid sha256:f54387658a9f03473ce13f36285afba201be85d6a26dc2738f5b3bec222e1787
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:456361dc19599aa5ac6e2bc4d5b36fb7b4f559e574c8908a4892815965df8247
+oid sha256:f6f4dd759e3bcd8fe9d2ec4692d0720b6f9685f62ca728b8dcb50dc946c7bd3f
 size 4040701744