Run 4. Outer Step 29. Inner Step 2.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5540218,
-    5540223,
-    5540228,
-    5540233,
-    5540237
+    5540242,
+    5540247,
+    5540252,
+    5540256,
+    5540261
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 1,
+  "inner_step": 2,
   "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:bc977a8eb9463ea3ec2981e86efb89cbef068fe5c1624ad405e69bdceb2cf52e
+oid sha256:8d5096fd17dfd0642913f26559bd59365845f96ae60b3100253fe4b32e0bd72f
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:130bff7c6b3e2aa7641fb0c9596e4ecde06a35c863a3c2c10f634717c82ebef8
+oid sha256:8290303ac29ccfee2f98065a413cf0aae57b862b5ce83d6a6977b22599bfd270
 size 4040701744