Run 4. Outer Step 28. Inner Step 48.

config.json

@@ -268,18 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5538472,
-    5538474,
-    5538476,
-    5538479,
-    5538481
+    5538484,
+    5538487,
+    5538490,
+    5538492,
+    5538495,
+    5538496,
+    5538499,
+    5538501,
+    5538503,
+    5538506
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 47,
+  "inner_step": 48,
   "inner_steps": 0,
   "last_allreduce_block": 5537093,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7768b3737924181914bafe564f8793de2ce322b58193ab5651ead91bcac54a16
+oid sha256:d7d95415e4cc966a807c4a4c8494cf341f2855e22a88eca9fbbffef72517fce1
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51cb9bff59977edfefd2fe317c26b9ee27c8d24a3715067ae87530ca6e2d5fb1
+oid sha256:d7e775ab75064d82532fe308468195a739d388ab043bce498989734206f83158
 size 4040701744