Outer Step 0. Inner Step 4. Batch Size 332

config.json

@@ -267,13 +267,19 @@
     "AutoConfig": "distributed/optimized-gpt2-500m--configuration_gpt_optimized.GPTOptimConfig",
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
-  "block_list": [],
+  "block_list": [
+    5048818,
+    5048822,
+    5048826,
+    5048830,
+    5048834
+  ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 0,
+  "inner_step": 4,
   "inner_steps": 0,
   "last_allreduce_block": 4016775,
   "layer_norm_epsilon": 1e-05,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcbe9e05268c20b6c5a24174c0482f755f8a38e4487e990bdcc7b98834890d4c
+oid sha256:a4e605b04ff3e3ae191563ea99bfe1a7b3ec04e0a9e48a5345fc93803cb1bb98
 size 4040701744