Outer Step 0. Inner Step 77. Batch Size 328

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5155394,
-    5155398,
-    5155403,
-    5155407,
-    5155411,
-    5155415,
-    5155418,
-    5155423,
-    5155427,
-    5155430
+    5155463,
+    5155469,
+    5155473,
+    5155478,
+    5155481,
+    5155487,
+    5155491,
+    5155495,
+    5155499,
+    5155503
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 68,
+  "inner_step": 77,
   "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:f29e08327dc48eca5642de15d6e2dcc7e731a6a5724e5c503f834059908b30dc
+oid sha256:de434915dc2cb8051a843d7f34f020e42e32c869f8acd85433084c48559612cd
 size 8081781770

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:227d9c1976dc004898d539347bf240578cb03683f8161fd42b947fd156377f29
+oid sha256:42ee875f77c91f8ec0903582951cf65de828a4ede0d70fa81fe987af66d60a6f
 size 4040701744