Run 4. Outer Step 55. Inner Step 40.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5599443,
-    5599445,
-    5599447,
-    5599450,
-    5599452
+    5599455,
+    5599459,
+    5599462,
+    5599464,
+    5599466
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 39,
+  "inner_step": 40,
   "inner_steps": 0,
   "last_allreduce_block": 5598085,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d77eb286c38e9992dd67a9bf3675ae208b84a23c154a53f9f1dcf66b55de158
+oid sha256:4009b2b9aee3db7881b0d4ce54099d7799cdc719aa408ac8267f0ff91da77d8b
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:787cb41bc6bc7bcb7bbbfc2f2c9c2359bdcebe9f64c7fdf16fbb922e780d2129
+oid sha256:8fd50eaab6adc14683243329df672cbb11bde2af5d9b208ee9d616c90e93163a
 size 4040701744