Run 4. Outer Step 50. Inner Step 6.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5571860,
-    5571862,
-    5571866,
-    5571868,
-    5571869,
-    5571870,
-    5571872
+    5571875,
+    5571878,
+    5571879,
+    5571882,
+    5571885
   ],
   "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": 5571611,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f1792aa71e7fd4bd70469e530d26ecb2c919d32678acb5de3d63f3ca5c78741
+oid sha256:7dc446cdbc3192640f50f4fc3031f54fd602d387fda43445861f5b7672be7e48
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9e985dcff4e9c69ffb3c167929f3242f9d4c1866ef6c3b5b09bd6a7fe2b0185
+oid sha256:cf7a11785c602d0580ebf8438a4583bc4f7168c58f602c6420c4cf9a8e2828c3
 size 4040701744