Run 4. Outer Step 40. Inner Step 8.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5555560,
-    5555565,
-    5555569,
-    5555573,
-    5555577
+    5555582,
+    5555586,
+    5555590,
+    5555594,
+    5555598
   ],
   "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": 5555115,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f866a96bae2bb9dbfa71ad5a8a721ef1b57ad3f6b8786c92c071c0754fb6d663
+oid sha256:693e5662d7272ec3dedf6774c354bc5d0c8dc44357b4127cd9b247a994afd52f
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7d30cd8ae7ccd41d463dc4051ce90c6aa138d501a4fa9e041e79a4870a69c8b
+oid sha256:4f1ac705a354964b1dab98d9479bfe1a712a35e880e3bd4d5769b74af056bd17
 size 4040701744