Run 4. Outer Step 33. Inner Step 96.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5546690,
-    5546694,
-    5546698,
-    5546702,
-    5546706
+    5546711,
+    5546715,
+    5546719,
+    5546723,
+    5546727
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 95,
+  "inner_step": 96,
   "inner_steps": 0,
   "last_allreduce_block": 5543976,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d5f46ae0f6c9ca145da1cd4f0b837ade527c9677d9e19d2f555298b04df7220
+oid sha256:b6aec12686a2636ed113f9179f1bb5a0b598186695efbfae7cfaefead7cd9a32
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8baae0ef6d887fdf676888a01fb5fccc13514b56448076b599afd85be41b04e9
+oid sha256:0cabf30b639670a21d955bffe3aaf44d7667e6a467c8a2f47b9359b2de7e11cf
 size 4040701744