Run 4. Outer Step 29. Inner Step 37.

config.json

@@ -268,21 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5539673,
-    5539676,
-    5539678,
-    5539680,
-    5539683,
-    5539686,
-    5539688,
-    5539690
+    5539693,
+    5539695,
+    5539698,
+    5539701,
+    5539704
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 36,
+  "inner_step": 37,
   "inner_steps": 0,
   "last_allreduce_block": 5538408,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfcd48e0c32e95edf4997ad7b4aafd02a30f2bd5b3e38ac565d8a6d6dbcaf276
+oid sha256:f9267dc8a16effb948540a6b8dd1cc4fe6f3aa88e903614f87b013627593dce4
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ecb14054029b96d8a94ad25417171fe7b5ef9c46a725b1aac07f7b5e0a57c9bf
+oid sha256:cccea10e562d79bb60167b16ed7980ea531b98dade77bae7210b04d71c61cf26
 size 4040701744