Run 4. Outer Step 60. Inner Step 4.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5607481,
-    5607483,
-    5607486,
-    5607488,
-    5607490,
-    5607492,
-    5607495
+    5607497,
+    5607499,
+    5607502,
+    5607505,
+    5607508
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 3,
+  "inner_step": 4,
   "inner_steps": 0,
   "last_allreduce_block": 5607244,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:408f35560a83afeaf3c2c845a4605171ce16dfc185c6c46c0779451aceebc001
+oid sha256:705c5607a116c001ce895ca2888cf2b27ddff99e0b2bbeacc2aaa08add76d8d7
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d46edcdc2b63231face1185956b81b5ffa2000fa859a59b155380aa5c0742fa
+oid sha256:e4ec95da9b36b7432c9f34ee7089b5135ce98a139d45b1f48de2d898576e7410
 size 4040701744