Outer Step 0. Inner Step 194. Batch Size 392

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5132608,
-    5132612,
-    5132617,
-    5132622,
-    5132626,
-    5132630,
-    5132635,
-    5132639,
-    5132644,
-    5132648
+    5132680,
+    5132684,
+    5132689,
+    5132693,
+    5132698,
+    5132702,
+    5132706,
+    5132711,
+    5132715,
+    5132719
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 185,
+  "inner_step": 194,
   "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 sha256:240a531342364d31da6b66dab2b086bb2d82de8accc4057d2912ad6a37c64b67
+oid sha256:3027b10ba41ec10b8156c5e7ee4ff3fdf3f869139db41c801784de1b46a2f31a
 size 8081781770

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9fa131931c86c48eae1d1acc1b3a4d347b07e86d1a3a51265d32f35f0299675
+oid sha256:c102aa27107b45c92bd80dfde325f9b59392beed36978f701622414bad24a5cb
 size 4040701744