Run 4. Outer Step 33. Inner Step 27.

config.json

@@ -268,24 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5544785,
-    5544787,
-    5544789,
-    5544791,
-    5544794,
-    5544796,
-    5544798,
-    5544800,
-    5544802,
-    5544804,
-    5544806
+    5544809,
+    5544811,
+    5544813,
+    5544815,
+    5544816
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 26,
+  "inner_step": 27,
   "inner_steps": 0,
   "last_allreduce_block": 5543976,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9de662215ed622994f478ff01f75ee82b965590507ac30d02acbaf82e815853
+oid sha256:ae1023b1d1c553a9a630acd01cd77b1e8e42e6743387307031c4e2cf400f469f
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bbafdc30029f45b86ab77152c98902e7e16b026e150e3b5bf3d6996780a3648
+oid sha256:832d3c3d8abe20a895e0ea203cc7256ca730ca0effbf325deb2a30b1b6be8a40
 size 4040701744