Run 4. Outer Step 53. Inner Step 10.

config.json

@@ -268,15 +268,15 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5630611,
-    5630638
+    5630666,
+    5630692
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 8,
+  "inner_step": 10,
   "inner_steps": 0,
   "last_allreduce_block": 5630301,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32ae4cbb61425737129b4ec8804a05eb33161d7c270494723a433bd34a4a232f
+oid sha256:7351f13884d0988b2741ddcd924d52177e575c3df39afc0ce0cdf98c9ec41b80
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:492a92727b0f49ef4f54ec05b681daea11407ae8813b8ca201627ee3628d882f
+oid sha256:9831c7c0b8e6733ef7abb640811489c4b836bbeca29eb9460599e99c2413c9b0
 size 4040701744