Run 4. Outer Step 55. Inner Step 12.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5583394,
-    5583398,
-    5583403,
-    5583408,
-    5583412
+    5583418,
+    5583422,
+    5583427,
+    5583432,
+    5583437
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 11,
+  "inner_step": 12,
   "inner_steps": 0,
   "last_allreduce_block": 5580790,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c81bb4619019d120d4992a57309a225884febad8849fcbfe61b5b618466e6ea
+oid sha256:a4298807019fb05266e300c65d8fcc8a12de956e4f301438fe133069089cc41b
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c99e82609c95e346aafa17b91f60de2272a5cbed13328409e75edc2185b666dc
+oid sha256:59cdbe1e9b57936e4776b01188a4bb2d45424be904727a657dd51a27786671d1
 size 4040701744