Run 4. Outer Step 66. Inner Step 12.

config.json

@@ -268,15 +268,15 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5651347,
-    5651375
+    5651403,
+    5651430
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 10,
+  "inner_step": 12,
   "inner_steps": 0,
   "last_allreduce_block": 5651055,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68dd9656d89816883b70315c9fd68150769969c891511fcee5e42139818cf2da
+oid sha256:51e5633567b76968bbee0d3bd484cc353ff3ed52e64dba466309b23f8c6a1df4
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b71c332c5ab5d50385d11206da5c405487907ad08782ca9538405dd8b2492926
+oid sha256:7f68444bea986e3373a25b7da9fa122027a533b93c6714ed1dee8dedf201ce41
 size 4040701744