Run 3. Outer Step 10. Inner Step 35.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5422709,
-    5422712,
-    5422715,
-    5422718,
-    5422721
+    5422751,
+    5422754,
+    5422758,
+    5422761,
+    5422764
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 33,
+  "inner_step": 34,
   "inner_steps": 0,
   "last_allreduce_block": 5398844,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db075bf0553d79d4981aa818f9f67e772855671350322cb0a2e87098b9c25862
+oid sha256:e2308b0f3254c5bd08fb3647fcb582db085773dbdee6d2c12f14c5b6acb6f33e
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb54b581eafed88596a7cfa93eff601da3bbc9f61953f2cefb2f34b9ccf906b4
+oid sha256:0506ee575287ba73e9b3b6d39a5b5ca1ace4be0df6f8e94f488259b12e5ef72f
 size 4040701744