Run 4. Outer Step 50. Inner Step 137.

config.json

@@ -267,15 +267,13 @@
     "AutoConfig": "distributed/optimized-gpt2-500m--configuration_gpt_optimized.GPTOptimConfig",
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
-  "block_list": [
-    5625852
-  ],
+  "block_list": [],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 136,
+  "inner_step": 137,
   "inner_steps": 0,
   "last_allreduce_block": 5571611,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d32004563a90883dd6979eb40104c84fe9d4a7da4471ccabada26c9de6ec1570
+oid sha256:b418c268dda4af9334e7a4523dfc75d923b1bcc7c7b312bd07051c772156dc35
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33f83a3e082691140f983b74d07e80d0b75278066bf39a5f09d0a1e5f709b530
+oid sha256:633039a63c73dc6d209cf4bc1207ae3c70b77cccac7678f376f60dc5067e349d
 size 4040701744