Run 2. Outer Step 3. Inner Step 47.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5330875,
-    5330880,
-    5330884,
-    5330888,
-    5330893
+    5330924,
+    5330928,
+    5330932,
+    5330936,
+    5330940
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 40,
+  "inner_step": 47,
   "inner_steps": 0,
   "last_allreduce_block": 5323221,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cda11a7146d96c3ab28bc8a2e08c0fa55a05e4b93575ec8bfd54609cd7c66d05
+oid sha256:d3ad92527c57c5ccff7bbd913e29ff47ab22ceb47c8746c9610e2b4e7fe2183a
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9994ae6c4edd8e89a61cf6c28fd726cf548b616e3a15c243348ecfa4719a48c
+oid sha256:9dc2b600df597dfb5b2c530feec296ca0204b17caca604c0b540260aa1bcc235
 size 4040701744