Outer Step 1. Inner Step 973. Batch Size 396

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5072212,
-    5072219,
-    5072225,
-    5072237,
-    5072242
+    5072254,
+    5072261,
+    5072267,
+    5072273,
+    5072278
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 970,
+  "inner_step": 973,
   "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 sha256:2406ae5c0d66f9017cfe5f73042354fb4f97f78d6ac6dae98715bc8059bc0514
+oid sha256:2b45c8edfb6ed23cc37c62cefd733caed393ac797df86e4264648e88bda49794
 size 4040701744