Outer Step 0. Inner Step 62. Batch Size 260

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5139691,
-    5139715,
-    5139732,
-    5139740,
-    5139756,
-    5139761,
-    5139768,
-    5139773,
-    5139780,
-    5139788
+    5139820,
+    5139832,
+    5139845,
+    5139852,
+    5139859,
+    5139864,
+    5139869,
+    5139873,
+    5139883,
+    5139899
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 55,
+  "inner_step": 62,
   "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 sha256:307b86b1e944828edf78111bb2c1d936bac167db2b18108a17bd44b3da0b575c
+oid sha256:35cda9b177e9bdc5ec95d22a06121b9c6456dad867ea61ce39a6313ec1fcf971
 size 8081781770

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92ea670099f4d59e134756cf130cee1a7576d74faf13b8026a4628a51f769691
+oid sha256:a94d6da110e0c1b512a7d57a03cdc7e82aed7ccef088eacf1f6db0724a3e4d3f
 size 4040701744