Run 4. Outer Step 65. Inner Step 3.

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": [
+    5648016,
+    5648049
+  ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 0,
+  "inner_step": 3,
   "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:ed7dd5b1edf1d51f649f39281f7d5ae324e782d22557d41242baf74a48e27e13
+oid sha256:4d7ff106602b9ec42545339c847c58802488bac9fa96ef652f2280fac25bd278
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:746c45f4ed46e64b9a0f11765821fde88c46814cc8beec8f2c85a180a830f94d
+oid sha256:b34bdb2a5c7091513d3bd0b7913edd1940368b1d77596c8c890bec827a0499c4
 size 4040701744