Run 4. Outer Step 58. Inner Step 5.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5603821,
-    5603827,
-    5603834,
-    5603839,
-    5603844
+    5603849,
+    5603854,
+    5603858,
+    5603862,
+    5603866
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 4,
+  "inner_step": 5,
   "inner_steps": 0,
   "last_allreduce_block": 5602341,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90ac93680856eff88be7930b9aae8dce41cbfb5118daba7306b5355da241c74b
+oid sha256:e5b985d139660213a3edc86138ab928be3fe0f2a7699f30873da22efcfe3fc7b
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbd31936402030e8e9a8067fc51316970061c353de3013a60348e0e1a5c47024
+oid sha256:fcbf8c45acb6fb32fdd2b9dcb9e59581e1bb8dd3a46f136c6b9f296de3f6bf6b
 size 4040701744