Run 4. Outer Step 66. Inner Step 4.

config.json

@@ -268,15 +268,15 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5651081,
-    5651110
+    5651139,
+    5651168
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 2,
+  "inner_step": 4,
   "inner_steps": 0,
   "last_allreduce_block": 5641040,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:223567f0253d53183307727a0a32bde069ea7c931c247237a97eb6551bc08799
+oid sha256:e94caf84437bec7ed07f3b382fa40406e250e1548867ae4f80556cd7e563c8f7
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:153b58b37d6564092a112c6ce3e7d3666f7a78ef97bd692fbe6c93f6f00adbc2
+oid sha256:424f1110b8049e1998bae531d236a27f70954f45f1d6479486f6c087cfac42bc
 size 4040701744