Run 4. Outer Step 58. Inner Step 3.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5604606,
-    5604610,
-    5604615,
-    5604619,
-    5604624
+    5604629,
+    5604633,
+    5604637,
+    5604642,
+    5604646
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 2,
+  "inner_step": 3,
   "inner_steps": 0,
   "last_allreduce_block": 5602341,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e526c54fadb383740caf380be17ca2a913a8d27834dcbd7a7f6e62b6a9afdcf
+oid sha256:22768f1386768eba7c4c0fb3d8562fcbf24bcea7148546fa1f60fe96e36cb4cd
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1c7befd573f559cf9bae874fd56d270a19e022e5c4f8e8c56dae2bf605a07bf
+oid sha256:2cbc6e5eb85be82f6c8b08965712cfb16dc0da997037220e3a598ab7eb6d0021
 size 4040701744