Run 3. Outer Step 9. Inner Step 995.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5421017,
-    5421020,
-    5421023,
-    5421026,
-    5421030
+    5421059,
+    5421063,
+    5421066,
+    5421069,
+    5421072
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 993,
+  "inner_step": 995,
   "inner_steps": 0,
   "last_allreduce_block": 5398844,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db1c866e6aec90fd9bce3eeadc2f1a5877daba4a5cf95ee7e4168b2add0730a0
+oid sha256:a691fc3794f26fc9d0aaee58c8d0ebae101af6e878e323db861ef67417069435
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7c4b053ea183e7f15e816ad49ccc5d6337ebbb4d82d658ddf5c8cbffe86cb7e
+oid sha256:514a2e7b81ad3d4281f70035f9a3e01d9ca1a7045d832b7b29b9ced0177e9a9b
 size 4040701744