Run 4. Outer Step 60. Inner Step 4.

config.json

@@ -268,21 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5607474,
-    5607476,
-    5607478,
-    5607480,
-    5607481,
-    5607484,
-    5607486,
-    5607488
+    5607491,
+    5607494,
+    5607496,
+    5607499,
+    5607501
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 3,
+  "inner_step": 4,
   "inner_steps": 0,
   "last_allreduce_block": 5607244,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed7e67f9ca104c0444bd09fe94533c42865bd4b8fdfef160cf000f4177665b9f
+oid sha256:cfab54496f45cb61d09f20e049605af43aff46787bfd5ce0d84d302c57e15bb6
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8dd4d752cf6cb0796ae6ab1676c1022d3601fc2f434a619b165504ed0e08b540
+oid sha256:edb24dda3e738a2caff4d712e25b86e497430a97d5f5d9d1ef4517b74d1687e3
 size 4040701744