Run 4. Outer Step 55. Inner Step 35.

config.json

@@ -268,18 +268,14 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5599299,
-    5599303,
-    5599307,
-    5599312,
-    5599316
+    5599377
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 33,
+  "inner_step": 35,
   "inner_steps": 0,
   "last_allreduce_block": 5576204,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b3c0d58876622f5bd374a6cdaccb0794293e87accd644c521cb189141a52d8c
+oid sha256:44e2af65f5f09c26f722ddca9204badf13b6cc87f3488ce7d8dc6b8da4ffc48d
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98ef91e18f90960d6aa14de8f4da7a7f48676ed737f15fbb44bd67ef6b4cb911
+oid sha256:aacb9e795080c196914b7c0729b49f6afa216f3071edefd218fa2cef8c987122
 size 4040701744