Run 4. Outer Step 54. Inner Step 135.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5597970,
-    5597974,
-    5597978,
-    5597982,
-    5597987
+    5597992,
+    5597996,
+    5598001,
+    5598005,
+    5598009
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 134,
+  "inner_step": 135,
   "inner_steps": 0,
   "last_allreduce_block": 5573605,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e6966ff47f0638ec2b9a291803397564fe7f52098a07b7e0d61b0b42be75de8
+oid sha256:dd0ae17e468f381d7434120733f17abb11f66b6d1241ac1d4790cc1be8df7e29
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0f446cd4c5397d323ff61c53a4dfd947c8f41347f9ace5b8c0ce6d5ec713f88
+oid sha256:a563d4046f37c9ee642c2966025281fc05ea24cb1f7a6df0bf908d370d5aeb08
 size 4040701744