Outer Step 0. Inner Step 221. Batch Size 172

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5132734,
-    5132739,
-    5132744,
-    5132750,
-    5132755,
-    5132759,
-    5132764,
-    5132772,
-    5132784,
-    5132790
+    5132817,
+    5132823,
+    5132830,
+    5132838,
+    5132851,
+    5132857,
+    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 sha256:6c2e1a5f9b92137f0321789081d02d4e48e3f9fbcfa46d8d39bdd38112c398be
+oid sha256:e71add4c293279e7b810e1135910f459b854e1969c4a88459b360e7df3730516
 size 8081781770

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db5ce8992b76b95e025fa1dc602dc5da46b88f602f37d6d501646d777542be32
+oid sha256:9db7d2bdca0d91946fe7651e64bc15a22c5c6321e0ecdafa7f903dbd47cad8bc
 size 4040701744