Run 4. Outer Step 33. Inner Step 82.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5546602,
-    5546607,
-    5546611,
-    5546615,
-    5546620
+    5546626,
+    5546630,
+    5546635,
+    5546640,
+    5546644
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 81,
+  "inner_step": 82,
   "inner_steps": 0,
   "last_allreduce_block": 5543976,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58aafeb3ddd4c2fd35fa8f4d969604f20b7724c8b316bd97dd7aabb6af8a0ad3
+oid sha256:58a63fb24304618bc0179f04499f47840085446678eddec52ef426ae5b842040
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f966f49951f293aa038507eff80647586e6793f23340b4e4e5b9d2a8e213c31
+oid sha256:b285f1850c281c17523c521a4a480f0fcb27645667d92ca96e940b99c85933bf
 size 4040701744