Run 4. Outer Step 54. Inner Step 92.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5580307,
-    5580309,
-    5580310,
-    5580312,
-    5580315,
-    5580318,
-    5580320
+    5580324,
+    5580326,
+    5580327,
+    5580329,
+    5580333
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 91,
+  "inner_step": 92,
   "inner_steps": 0,
   "last_allreduce_block": 5577515,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39981505f3fc10fd7bdf2774386cc0419498d1dc1170621a2793f98818e5f2c2
+oid sha256:aa786e38febf3647e2c2e8f3378fdc2d21ad239d7f23cc40f9447af6e7e3d906
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:741603cff7f2275a993b6968d86cbbd841d4dc49b3fed77b7e59a4de575e3384
+oid sha256:38ce0c69bd3f428016281cf6b9a8b15ce19dd80ae21cb186324eb191ebed0e90
 size 4040701744