Run 4. Outer Step 89. Inner Step 8.

config.json

@@ -268,15 +268,15 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5680850,
-    5680864
+    5680878,
+    5680894
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 7,
+  "inner_step": 8,
   "inner_steps": 0,
   "last_allreduce_block": 5680556,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ac1c353f1bae695805921a907858f9e7dc7eff9253c07ee7a9f478245ac2b98
+oid sha256:843c9050ddb63b620ea13c11c038bc8c063d3526ae4dac9668629d6c2a00c44d
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14941fa1e842e2187676701982ee55384bd859654cb710444bfb3331e95c04c6
+oid sha256:a96b2ca60e4c286d9af494db51238dbc0b3b8e4ca5a94970df6ca832768f85af
 size 4040701744