Run 4. Outer Step 33. Inner Step 20.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5544596,
-    5544599,
-    5544602,
-    5544605,
-    5544607,
-    5544609,
-    5544611
+    5544614,
+    5544617,
+    5544620,
+    5544623,
+    5544625
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 19,
+  "inner_step": 20,
   "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 sha256:326afc57a84d6f230060dd73d2276f01714d1d68db456f6d7fa9ccd556668fae
+oid sha256:6ebe02d61a09679d94e0c19d4d0e77bb548f14cdfbd2ed080aa3436fdb4bbaba
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d50c6d4d37c6da4aa904fbea20a20d59f0d8a469cf6c94f5f448e079befbb6ca
+oid sha256:7a63123a74faf62102725c99f8b9248d30ebb7f45b02f15ffce1185dd689abca
 size 4040701744