Outer Step 2. Inner Step 145. Batch Size 480

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5074430,
-    5074434,
-    5074438,
-    5074443,
-    5074447
+    5074466,
+    5074470,
+    5074475,
+    5074479,
+    5074483
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 141,
+  "inner_step": 145,
   "inner_steps": 0,
   "last_allreduce_block": 5072405,
   "layer_norm_epsilon": 1e-05,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84c0c4c1f7ce603cc595716dcc462485934ec173c5e0c9e17c55cd7541cd36b3
+oid sha256:205d1f3dbe09982d1f5ee9c29b43d6cec4f2c09426f5df147c66a08a72a68682
 size 4040701744