Outer Step 0. Inner Step 290. Batch Size 164

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5263872,
-    5263876,
-    5263881,
-    5263886,
-    5263890,
-    5263895,
-    5263899,
-    5263903,
-    5263907,
-    5263911
+    5263943,
+    5263948,
+    5263952,
+    5263956,
+    5263961,
+    5263965,
+    5263969,
+    5263973,
+    5263978,
+    5263982
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 280,
+  "inner_step": 290,
   "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:c81f9482672c43efc12358807c932be6aedac5f6dcd5da069a4c6e1a1bb9f436
+oid sha256:55d7cf75f33f8dbde89cf3df09f6c6d13bd4b38c951fcbb125a54985df35bae9
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ce8a2b10c53d285478f8c8d7393c829ac518c35a61aa5db6ee96204c97efc57
+oid sha256:eed60d3a1d5e05471f1c1d62ff54c8d865ea72a7b0296055ed0d20f0ff07d10a
 size 4040701744