Outer Step 0. Inner Step 717. Batch Size 208

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5054536,
-    5054540,
-    5054544,
-    5054549,
-    5054553
+    5054576,
+    5054581,
+    5054586,
+    5054591,
+    5054596
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 712,
+  "inner_step": 717,
   "inner_steps": 0,
   "last_allreduce_block": 4016775,
   "layer_norm_epsilon": 1e-05,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b20b9716dc94be2d9e7c0868ab6147507826cc761aa835416da8aa25339d3391
+oid sha256:2c0b408a32621022da88401f0ee46495ea44d507748171ab0668f433c4e46472
 size 4040701744