Run 4. Outer Step 100. Inner Step 22.

config.json

@@ -268,15 +268,15 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5695990,
-    5696005
+    5696022,
+    5696038
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 20,
+  "inner_step": 22,
   "inner_steps": 0,
   "last_allreduce_block": 5692898,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ed4227f3d7ec2e0ba48586b76a892573b06b728cd372bab52dfd52b0fbca824
+oid sha256:f985bd1773c884c7f4d9e0725302f5637e68fd55f41a18deb62c8f7ea2dcc4b1
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4926895fea040b9aa4f25b7797e3f0831dc9be88055d7bcdf54e143a5098dfa4
+oid sha256:d7722d02843c3a44d97f24cc194cbca13174f83a73e98f76906bfe6b95d729d8
 size 4040701744