Run 4. Outer Step 18. Inner Step 41.

config.json

@@ -268,19 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5522219,
-    5522223,
-    5522227,
-    5522230,
-    5522234,
-    5522237
+    5522241,
+    5522245,
+    5522249,
+    5522252,
+    5522256,
+    5522260
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 40,
+  "inner_step": 41,
   "inner_steps": 0,
   "last_allreduce_block": 5509976,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cf2a09f77dbaaef2123c6858c18f7cbb94eb8132b31838ae62a11383656a2b6
+oid sha256:38dd4fbecd4d49bbe811e735f2f31856fbeb9611bb6ea203ad97cb8b1ae435b3
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e59895bf1c6c6870daa4da98da5ae677feeac0d1fad8c7fcb5c70aff6673c97
+oid sha256:6d0af7a7e1da52b01257bee3a814bf84e946be64d1430dcb36ce512afc10e194
 size 4040701744