Outer Step 0. Inner Step 221. Batch Size 460

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5132728,
-    5132734,
-    5132739,
-    5132743,
-    5132749,
-    5132755,
-    5132759,
-    5132765,
-    5132775,
-    5132783
+    5132817,
+    5132825,
+    5132831,
+    5132838,
+    5132851,
+    5132856,
+    5132862,
+    5132868,
+    5132873,
+    5132879
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 213,
+  "inner_step": 221,
   "inner_steps": 0,
   "last_allreduce_block": 5072405,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b3cef113e7b875a075fc902291388f05b46718bd8a6cd6005898493faf7de7a
+oid sha256:d11f6d9cea38aa82a49d2856844a75b499d3ef87dad71eaac16e26f61c482b98
 size 8081781770

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9072073c7cca8470bd543033194e753e8ed80436f348005117d6454c439ae034
+oid sha256:bdf16d79609c60c7816bc04dba9ef94718992853b88f9990c21a25fea183d200
 size 4040701744