Run 4. Outer Step 28. Inner Step 16.

config.json

@@ -268,23 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5537570,
-    5537573,
-    5537575,
-    5537577,
-    5537578,
-    5537580,
-    5537583,
-    5537585,
-    5537588,
-    5537590
+    5537594,
+    5537597,
+    5537599,
+    5537601,
+    5537603
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 15,
+  "inner_step": 16,
   "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 sha256:760d3ee06847e6474c9592a6b811601a715e0a88f15d2149155a82229d3fb692
+oid sha256:c80769e9684480d92253b0b1331e9e47e7fdcfc5f8f6b1679c7e82e13df90320
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d3747478a27a0e6c6cd9c7d9f8648f39383c9b6b257303ae1601730eeef3c6a
+oid sha256:ff3dd220a88d5b5e52469c166ae2d2bb2b7f3faded5a899f2aab90566c544ed6
 size 4040701744