Run 4. Outer Step 48. Inner Step 16.

config.json

@@ -268,20 +268,20 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5569286,
-    5569290,
-    5569294,
-    5569299,
-    5569303,
-    5569307,
-    5569311
+    5569316,
+    5569320,
+    5569324,
+    5569329,
+    5569333,
+    5569337,
+    5569342
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 15,
+  "inner_step": 16,
   "inner_steps": 0,
   "last_allreduce_block": 5523943,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d7ef13d3a2393f058a36e4cd19f1af59b25457bf28c6f4bd53bd277a6f92c3e
+oid sha256:aac51b43145bf200115570d9b828281f9d217e7d1b03bc9867b8892a8b3e1eb5
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ca4ddbe3c2695835584395fb944bd6581ea2005d48e8eb8d272eec72cfd7739
+oid sha256:c741c8f2b283cd4d491af3b7fd40d008630265e1cdb24860a44c95d4c989f33a
 size 4040701744