Run 4. Outer Step 58. Inner Step 14.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5602975,
-    5602981,
-    5602988,
-    5602996,
-    5603002
+    5603010,
+    5603016,
+    5603023,
+    5603030,
+    5603037
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 13,
+  "inner_step": 14,
   "inner_steps": 0,
   "last_allreduce_block": 5576204,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e1333da74585253871807bca1b0bb49c5760502657f6e83bab9da466da9dc41
+oid sha256:af3e5c6ad5a5a36393c4fbab55ff58dd24f54530bd2d84af7bd0e9379c8b9894
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91f98fd599372ef5a26b9179a58861c16ec95bea40ee28fdb8759c4527edb5d6
+oid sha256:dce0ecab2e4f3d19dea880c1870430b568ead44a3fb3fc037cfd58b38df74c8d
 size 4040701744