Run 4. Outer Step 53. Inner Step 26.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5577092,
-    5577095,
-    5577098,
-    5577100,
-    5577102,
-    5577105,
-    5577107
+    5577109,
+    5577112,
+    5577114,
+    5577116,
+    5577119
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 25,
+  "inner_step": 26,
   "inner_steps": 0,
   "last_allreduce_block": 5576204,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b1e10a44a9839f5bf10d4d768f289d5f19e108f3eae1520e45d2235fc7dc280
+oid sha256:b45b06702a1fd0d027882d0e2376ec64261281b700255cc9e1cc4857b5f1b37f
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88380e99bc7613c19694ebc80d779cf1f5f0f975534d49a3e472f8aebdade7d7
+oid sha256:d76f82deaef6ac916b281fadd51c7226e787ec642e55903f323b2bdffb548957
 size 4040701744