Run 4. Outer Step 18. Inner Step 52.

config.json

@@ -268,19 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5522488,
-    5522492,
-    5522496,
-    5522499,
-    5522503,
-    5522506
+    5522510,
+    5522514,
+    5522518,
+    5522521,
+    5522525,
+    5522529
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 51,
+  "inner_step": 52,
   "inner_steps": 0,
   "last_allreduce_block": 5509976,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5aa380ee72140581bc1d95b3cabfb6898b3e311855346d61d3dc1460b58c0baf
+oid sha256:597dfd3d787a658aae4e44d33039dd974c9002988c18a6031b69d8ca350052c9
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:feada75e1aa6b87370077679dcb965ee7b9fc0b9671a4d9f094968cc64f6d1b8
+oid sha256:812097082daba3d03e10d0718b57029c4b330d2b753d9229d28ad44d1669f76d
 size 4040701744