Outer Step 0. Inner Step 173. Batch Size 176

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5156319,
-    5156323,
-    5156329,
-    5156334,
-    5156339,
-    5156345,
-    5156350,
-    5156355,
-    5156359,
-    5156364
+    5156399,
+    5156404,
+    5156409,
+    5156415,
+    5156419,
+    5156425,
+    5156430,
+    5156435,
+    5156441,
+    5156445
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 164,
+  "inner_step": 173,
   "inner_steps": 0,
   "last_allreduce_block": 4016775,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5d89f2d69f7ed00bb0efe9220134e1719ada5f2104e3f25397387203f68e17b
+oid sha256:e73d37d6f25f23f2485b9509919feaf83f54bd33a9716b64e059b372eea80492
 size 8081781770

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51154cd10b76916a58f070757fb1491668a0e727c8c2edbdfdd98844c40fcbf4
+oid sha256:ca75f1987edc7aafceb94eab895921e845d90f0b72ed7a97eff7343c92069f6d
 size 4040701744