Run 4. Outer Step 53. Inner Step 30.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5577214,
-    5577217,
-    5577218,
-    5577221,
-    5577223,
-    5577226,
-    5577228
+    5577231,
+    5577234,
+    5577236,
+    5577239,
+    5577242
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 29,
+  "inner_step": 30,
   "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 sha256:918abd68e46700fbd5c92437c1b659d34e0058e8b67ffc3f4f15e41ec7c258df
+oid sha256:fa5bea2195f882015b35212840ae0900106399bcf4034377ab4ac598e908209c
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46e205beade14acfe212ecc54fb5c667c8e3c88b4babc385954daf17eaca753a
+oid sha256:3f3375df1b821a2da3811ad3f4b8ecf31cabb2e5b8c4bbd2f981389502d11454
 size 4040701744