Run 4. Outer Step 35. Inner Step 20.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5548723,
-    5548727,
-    5548733,
-    5548737,
-    5548741
+    5548745,
+    5548749,
+    5548754,
+    5548758,
+    5548762
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 19,
+  "inner_step": 20,
   "inner_steps": 0,
   "last_allreduce_block": 5539810,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5e70c040e91718b44956ce031ddae2e94d89340d6afd405ae322547510f9459
+oid sha256:c1e2106110a49ff7677fd856fa01aa4dffc13d145f72754c7203262d1190df04
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca692f2bb121a1139f7855a21a0b56db11bde9648a741995b9a35d7ba0dd08e9
+oid sha256:0f4889330c414b107d03afe71faa3d299f24fc51f83fe6f2e5b4750f99706f2a
 size 4040701744