Outer Step 8. Inner Step 78. Batch Size 132

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5291783,
-    5291786,
-    5291790,
-    5291793,
-    5291797,
-    5291800,
-    5291804,
-    5291807,
-    5291811,
-    5291814
+    5291853,
+    5291857,
+    5291861,
+    5291864,
+    5291868,
+    5291872,
+    5291875,
+    5291879,
+    5291882,
+    5291886
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 67,
+  "inner_step": 78,
   "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 sha256:540d72b12e00169f032865e58a2955216702c02afd9738c830be8e7bc6f7286d
+oid sha256:392b8ab21d45a589a0357894a1e14824a22505de279ae5a1e8b60d9b900f3786
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23b2b3c7fbf41e072a73a87e92237148076673453a024e60166444971d501b1a
+oid sha256:af12813d0c9e25e4d5d400a257d1e7f540de01eaf796f428b11686b5590e3bd6
 size 4040701744