Run 4. Outer Step 59. Inner Step 53.

config.json

@@ -268,19 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5607307,
-    5607310,
-    5607313,
-    5607315,
-    5607318,
-    5607320
+    5607322,
+    5607325,
+    5607328,
+    5607331,
+    5607334
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 52,
+  "inner_step": 53,
   "inner_steps": 0,
   "last_allreduce_block": 5605539,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:245a9c81db625d18817cb62ecca237bd0c698d748eb8cef9a4cb5e6f5ea2d17c
+oid sha256:f2b4234e9db43e60e81608a865cb43970fa23d0cb77082f5e5993522763dd4cb
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6532427cacbef31ed9aac5bdf1b3575ddbe6f041180865b0f442c3cb576d2ff
+oid sha256:b7c0043632c0369e07bda3d00f90d11cab28af73031968ad6a1ba513097b4692
 size 4040701744