Run 4. Outer Step 55. Inner Step 8.

config.json

@@ -268,19 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5583302,
-    5583305,
-    5583308,
-    5583311,
-    5583314,
-    5583317
+    5583321,
+    5583324,
+    5583326,
+    5583330,
+    5583333,
+    5583336
   ],
   "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": 5580790,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b7a22dc9e532625c431c0c46f78e3c48a6a673d3836c0cfcbc746c9d5a6fa63
+oid sha256:37ef47506085df57bad5eb80763016d42e741ac1c5aab756efa1dc4e21fb1b0a
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42900c7018e8e68c9ec0d7c24457be17f683aa5dfdaccca779ba771dc4dae1b2
+oid sha256:a4d4a00fe5d4b504b0946e551560ef750b9717d31a4da621c21adb2630d9b761
 size 4040701744