Run 4. Outer Step 61. Inner Step 16.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5610270,
-    5610273,
-    5610279,
-    5610283,
-    5610287
+    5610293,
+    5610296,
+    5610301,
+    5610305,
+    5610310
   ],
   "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": 5608831,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6caa8e314f7f0120dccd33b9238e0e240fa9fb4c62b6c67c9130231a3118d71
+oid sha256:42685801f3e8a32282d014d58dc3360118489ee3724ac57a869c5ac795a81885
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03156e3444e023a2acc128105b0d5119ef3cb3e0a385193c76bbb78cec3d1231
+oid sha256:988436f1bfeb44c756e69be31ffcdfc3e27fd9e324c8df8662c83954b8b380d8
 size 4040701744