Outer Step 1. Inner Step 1024. Batch Size 452

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5071860,
-    5071867,
-    5071873,
-    5071881,
-    5071888
+    5071949,
+    5071955,
+    5071961,
+    5071969,
+    5071975
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 1022,
+  "inner_step": 1024,
   "inner_steps": 0,
   "last_allreduce_block": 5063053,
   "layer_norm_epsilon": 1e-05,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab12b216c31b99c8c7b5fb1b2a184d1297959c87d7a33f582ace3fd5d0ec74a6
+oid sha256:9d094d72d3fe08f6e22b793f6d307ff3545b55d3361bf0cb4a1065f9f4712a57
 size 4040701744