Outer Step 8. Inner Step 195. Batch Size 468

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5292672,
-    5292676,
-    5292679,
-    5292683,
-    5292686,
-    5292689,
-    5292693,
-    5292697,
-    5292700,
-    5292703
+    5292743,
+    5292747,
+    5292750,
+    5292754,
+    5292757,
+    5292761,
+    5292764,
+    5292768,
+    5292771,
+    5292775
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 185,
+  "inner_step": 195,
   "inner_steps": 0,
   "last_allreduce_block": 5283755,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:692e4ca7a1bf7c43e1df013c8c10fa76ee115d5afe9c10787d25c66754ed427b
+oid sha256:f89b2f9ccfd6f7822f43e8b190cb11336840dc0155853b5f06ff24d6facb1fb5
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c01f6206d7065f3ea01917938afa7bfdca395ce6b047fc71b3b0723433b5e48
+oid sha256:9c9d9045937fc6bd62872b4fb02c34c010f72753d9e22a905c8faaeb3592f352
 size 4040701744