Outer Step 2. Inner Step 155. Batch Size 124

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5074500,
-    5074504,
-    5074508,
-    5074512,
-    5074516
+    5074534,
+    5074538,
+    5074542,
+    5074547,
+    5074552
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 150,
+  "inner_step": 155,
   "inner_steps": 0,
   "last_allreduce_block": 5072405,
   "layer_norm_epsilon": 1e-05,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:364d42be24f8c2d8dd08e071325de20c8a1023dbdae92378fadb2f7c26cfbb0a
+oid sha256:49c105dbe2b65b5db83fe66b477c4df4a14021dec7396783d738ff3602ae5181
 size 4040701744