Run 4. Outer Step 58. Inner Step 6.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5604674,
-    5604678,
-    5604682,
-    5604687,
-    5604692
+    5604697,
+    5604701,
+    5604706,
+    5604710,
+    5604715
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 5,
+  "inner_step": 6,
   "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 sha256:2c2097525f1a053466c21d12ec32f49efdbd03949a755933f17fdc46cc4d6960
+oid sha256:a78006948ae14155b3f8ed749cd2943bec4507670cab75c9c0ab451112f5ffc3
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9967af2b347bc0c1150fe07d75f023d3c60569c98c0c609f5867556dff93812e
+oid sha256:e3d035a18af093d85963f6e768df907321fed90ae97e76113ce23b9ae488523a
 size 4040701744