Run 4. Outer Step 65. Inner Step 31.

config.json

@@ -267,16 +267,13 @@
     "AutoConfig": "distributed/optimized-gpt2-500m--configuration_gpt_optimized.GPTOptimConfig",
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
-  "block_list": [
-    5648776,
-    5648809
-  ],
+  "block_list": [],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 28,
+  "inner_step": 31,
   "inner_steps": 0,
   "last_allreduce_block": 5639485,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93ddaf00031fb1a333d0b65349d1be7f603319ef91c265222df887192f711b44
+oid sha256:c61e6faed18e3cc513debdfa7a217e6e207f7ef41592a90df22c9568cedf3def
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e8468f426864c239612351059dc6408e75f687539e6171f163d0159a734836c
+oid sha256:5e3ee46217a3189ef121ff2e7fa1af92d797db4c94724c570f6c1098245c8130
 size 4040701744