Run 4. Outer Step 7. Inner Step 66.

config.json

@@ -268,19 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5496058,
-    5496062,
-    5496066,
-    5496070,
-    5496074,
-    5496077
+    5496082,
+    5496086,
+    5496090,
+    5496094,
+    5496097,
+    5496101
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 65,
+  "inner_step": 66,
   "inner_steps": 0,
   "last_allreduce_block": 5492224,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4472bbe454c726efaea0a151001255e64767858d755ac75efe9d83b1229a17d1
+oid sha256:7f4a4cfae7de14febca27d70ee8097480d6fec240e45f90a3fe0c988acbefb58
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2dd99d9b57fce67285f55c858c5834c66196ba6df5a6bf8d8d4f88c4a7ca4c50
+oid sha256:4e82bb9de733665b1d16222d0ccefc2b64d9b235f16394590fc5c24b7986592a
 size 4040701744