Run 4. Outer Step 51. Inner Step 13.

config.json

@@ -267,13 +267,16 @@
     "AutoConfig": "distributed/optimized-gpt2-500m--configuration_gpt_optimized.GPTOptimConfig",
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
-  "block_list": [],
+  "block_list": [
+    5627502,
+    5627536
+  ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 11,
+  "inner_step": 13,
   "inner_steps": 0,
   "last_allreduce_block": 5568918,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76477b55fb6d2ec53c1c5e443887df87f7b2d583cc7d2a726ffebdaa4f341223
+oid sha256:6b9ab4334023e5453fac98ba44da5f30517593f75f08bea38992cd9cbe54d22b
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21e146ca9dfa6fc4c63bf8abbebaf923be9c8f107a3d057d1353d6123ca7d8bf
+oid sha256:d955e4365ab0f81e5887c69181d46af98abb6eec00f92e9bae18d49b02b75bfe
 size 4040701744