Outer Step 1. Inner Step 1648. Batch Size 156

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5184368,
-    5184373,
-    5184377,
-    5184381,
-    5184385,
-    5184390,
-    5184394,
-    5184399,
-    5184403,
-    5184408
+    5184439,
+    5184443,
+    5184447,
+    5184451,
+    5184455,
+    5184458,
+    5184463,
+    5184467,
+    5184471,
+    5184475
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 1638,
+  "inner_step": 1648,
   "inner_steps": 0,
   "last_allreduce_block": 5160840,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4b72745a0e28f423d3e2c4b7a728bdd16c62554ed0ff2d9be8b02e52f3174ad
+oid sha256:587b7527aa6a015c809122bd06cd16f894156fa78080ae7fc513bd6ceac145e3
 size 8081781770

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9eb410af84ed706c40b60d49f743853701121e7a1579e969230aeafc749a6103
+oid sha256:69e913340305089feac21f70382cefbcae7bbe647b3f22ceb69884f830629bc6
 size 4040701744