Run 4. Outer Step 61. Inner Step 8.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5610029,
-    5610033,
-    5610038,
-    5610042,
-    5610046
+    5610051,
+    5610055,
+    5610060,
+    5610064,
+    5610068
   ],
   "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": 5608831,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b73a76190602c3fec757b2df15b0996a6123dac747d771ed6d018a6dd07db71
+oid sha256:38a99e1c846ec556d551b63ee308c20d85b2095427363cca67e11e92d14fb30c
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7288a3c94f9b6f7b054ed265894b22146422ebeb3568c9644f1590c7e973bff
+oid sha256:5c36aa56cc028301e6bc479911cac32a23a59ef2a29ba192f6d8ce33f9a684bb
 size 4040701744