Outer Step 0. Inner Step 69. Batch Size 256

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5139820,
-    5139832,
-    5139845,
-    5139852,
-    5139859,
-    5139864,
-    5139869,
-    5139873,
-    5139883,
-    5139899
+    5139930,
+    5139938,
+    5139945,
+    5139950,
+    5139955,
+    5139960,
+    5139966,
+    5139979,
+    5139987,
+    5139999
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 62,
+  "inner_step": 69,
   "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 sha256:35cda9b177e9bdc5ec95d22a06121b9c6456dad867ea61ce39a6313ec1fcf971
+oid sha256:ae48dd564a5a83bca132928fc860dacbcfa126dec03a3eaef3b79411d150565e
 size 8081781770

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a94d6da110e0c1b512a7d57a03cdc7e82aed7ccef088eacf1f6db0724a3e4d3f
+oid sha256:23cb9dd7087108c660cde2e80e81c5410afb83b6debfc14d10af308f31877a83
 size 4040701744