Outer Step 0. Inner Step 2. Batch Size 464

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": [
+    5129805,
+    5129820,
+    5129829,
+    5129841,
+    5129847
+  ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 0,
+  "inner_step": 2,
   "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 sha256:10024d50c5147f2917b8388f2a3aa9528b26da292a533206efbd53083678ed8f
+oid sha256:a6280e9b93c9db11f7a5d61bee57236f5d323958f3df01b3bd8066d5c1a29f5d
 size 4040701744