Run 4. Outer Step 91. Inner Step 3.

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": [
-    5683496
-  ],
+  "block_list": [],
   "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": 5676357,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dba9e4f690087d238d53bbab6d7c44f249df077ef2f2cc8d7e1e5b485911cd97
+oid sha256:35d752c6d251ac1fe86bab79353714dd3d217b630216c33c7338cfcc8e84ce2e
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcd9e9c22e14b669689053f25c901da2a621d9771e9453e94f95bf59d431c6a4
+oid sha256:6ebf4895df7cb9542484311e1a24685e9452cd62e6e3d131dbbb762b36d16eee
 size 4040701744