Run 4. Outer Step 52. Inner Step 30.

config.json

@@ -268,21 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5575978,
-    5575981,
-    5575983,
-    5575985,
-    5575987,
-    5575989,
-    5575991,
-    5575992
+    5575995,
+    5575998,
+    5576001,
+    5576005,
+    5576008
   ],
   "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": 5574901,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6639440ae1f966da5b0f10e1ca540731f2a826fe2cfb13da582bf66be33b24b
+oid sha256:2dc516e91b6e61091b9793bdd59261de3cb9c7d61cfe737dae2e7da38db1e1b3
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32236e2bdf2092bcd3712809cdcbca1f51bec1dee8ee87a8ff6ba3d04fa01e42
+oid sha256:f7dd979ac205adb379940dbf7debe074719c93d8cf817f44a47a69e8c8ffb463
 size 4040701744