Run 4. Outer Step 59. Inner Step 55.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5607072,
-    5607076,
-    5607079,
-    5607083,
-    5607087
+    5607091,
+    5607095,
+    5607099,
+    5607103,
+    5607106
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 54,
+  "inner_step": 55,
   "inner_steps": 0,
   "last_allreduce_block": 5605539,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5210ef232e2ed75b3b90e52639220734460c14fd1024a9de56045f9ff1fdb61
+oid sha256:e6d4c312d7187332506683a147e4e9ba07e6ddb8de18dd5417db94ffb67c1bb6
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41fc1ad06144eafaa8fac49989e5cb64d39f63691223ea1602381d975443f0db
+oid sha256:130a9278ee45915d5e84545ceefa28bd41073a4b902a90cdd6b250547fd46cd8
 size 4040701744