Run 4. Outer Step 58. Inner Step 73.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5604563,
-    5604567,
-    5604572,
-    5604577,
-    5604581
+    5604586,
+    5604591,
+    5604595,
+    5604600,
+    5604605
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 72,
+  "inner_step": 73,
   "inner_steps": 0,
   "last_allreduce_block": 5602341,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ed143bd47592190073fa0f3fd1476c53a5c482f784c2578483948c7efcbadc2
+oid sha256:a07a0575d18792048a71f28441dfc31d80be6696f51c91ea41d3dedfb1463647
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dccdd19c2ac9c17d58fca5ea310eaa97834bd16095ad473c7284a72a9521d536
+oid sha256:487b56bd5133afaf331f05e6654a4358d6ec450e0fd654a2257b61ac4398b0a0
 size 4040701744