Run 4. Outer Step 54. Inner Step 136.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5597933,
-    5597937,
-    5597941,
-    5597945,
-    5597949
+    5597954,
+    5597958,
+    5597962,
+    5597966,
+    5597971
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 135,
+  "inner_step": 136,
   "inner_steps": 0,
   "last_allreduce_block": 5570305,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f49e3ae8bfde6dd6fc200b06ecd6c5a4b445985e45d321fed7bd12e244e4e6a4
+oid sha256:bf34790232e997b74ccfd5e457334a55db3f2001499e606da61d583a8c5bef9e
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c139747c28ce27d69d034da0719860b38d2309c67b4f7272c9aa8cfc193ccbe4
+oid sha256:e6584e012024926a401b500ca5ada4cd98387b5f3b229808c61ef0e347e87f45
 size 4040701744