Run 4. Outer Step 80. Inner Step 5.

config.json

@@ -268,15 +268,15 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5668525,
-    5668555
+    5668587,
+    5668616
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 3,
+  "inner_step": 5,
   "inner_steps": 0,
   "last_allreduce_block": 5665748,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e23720ee5eb2c67c6b248d572d7116b283126a83fd24bf3e7e32638348768aae
+oid sha256:41e9ddb01e9e621a814d02ce3fb390cf9a942b926e7be8aade4700a6f4ab0e8a
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb9a9f7819c4fbb662dfefb2f7ff79803d0edc6a87483482aa2a4d908db69a89
+oid sha256:2836d9df3dd951ab8ff14128f47f950a4bbfdf57b3df5fddece72ca7504691aa
 size 4040701744