Run 4. Outer Step 54. Inner Step 92.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5580296,
-    5580298,
-    5580301,
-    5580304,
-    5580306,
-    5580308,
-    5580310
+    5580313,
+    5580315,
+    5580317,
+    5580319,
+    5580321
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 91,
+  "inner_step": 92,
   "inner_steps": 0,
   "last_allreduce_block": 5577515,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e027eaf1851d65e48d408037bbbb1ebba9689f3a2362939d55bcc182e0c4119
+oid sha256:887ed8c4bf31fadf9d3537eb8a64e509f9663e247cc132eb2834d088cbe303a1
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a229a72d6a9fdf99e0b33780dfe89a32d5e488d41e0a2baf8dcc3a65e28e6719
+oid sha256:d60adbd7cad85e3b4e41b46e385fdc1ee64bf0ba324ddc20f46f78c683ffba29
 size 4040701744