Outer Step 0. Inner Step 207. Batch Size 136

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5142345,
-    5142354,
-    5142362,
-    5142369,
-    5142377,
-    5142385,
-    5142392,
-    5142397,
-    5142402,
-    5142407
+    5142433,
+    5142443,
+    5142450,
+    5142457,
+    5142464,
+    5142471,
+    5142476,
+    5142482,
+    5142488,
+    5142494
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 199,
+  "inner_step": 207,
   "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 sha256:6a9aa26e32ba10e1ab354aa0307c41fe9fcf157fbe70acb910f3619de4869c73
+oid sha256:544ddef402271093ee7869797c9092fb41a553cdddd5fed6494faf9af027894f
 size 8081781770

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3eb72989be6fe3f16e1b3be47260c951bcd3a25621b238a7beec1f6f1b9c298
+oid sha256:7efec361cfbca2df859b7278f9e933f24b1c626d58a714ab80dcce80a958c392
 size 4040701744