Run 4. Outer Step 52. Inner Step 42.

config.json

@@ -268,19 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5576275,
-    5576279,
-    5576282,
-    5576285,
-    5576288,
-    5576290
+    5576292,
+    5576294,
+    5576296,
+    5576300,
+    5576302
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 41,
+  "inner_step": 42,
   "inner_steps": 0,
   "last_allreduce_block": 5574901,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:552c20ae1390843c47300d4f56f29f36e05042fe0673be6bf07b58c8c212f91a
+oid sha256:8306371f64168db2d47d442299642d3fd9058f6113b90cba65409f59d404361f
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51835de4ada46cc41643a0911e4e9b84a9df6f1d7326a3cb8bc50cb34335b650
+oid sha256:38107d52d247f2cf30215eeb987a89e7f9e96b614e34c8cc9c3908b1dd2d6fcf
 size 4040701744