Run 4. Outer Step 35. Inner Step 10.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5548485,
-    5548491,
-    5548495,
-    5548500,
-    5548505
+    5548510,
+    5548515,
+    5548519,
+    5548524,
+    5548529
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 9,
+  "inner_step": 10,
   "inner_steps": 0,
   "last_allreduce_block": 5546853,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b21c0a8df7c1d7e5e6f157a97ee5a3bb7724a9a2c3d25261cf5e0156f5de53b
+oid sha256:6d4fa8d3ace5a4d9afd08979d065a02082c6b09c9a199d106ea1dfa6e07cbb62
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff46898dcf6413bda51629a8d088dd66cd19f608045a2c6bd8c41c32c0f0830a
+oid sha256:fa0e35827f03d859e3c50c3c4d6ef810b6e48091c0ab4294ed558b4d50e5aa8f
 size 4040701744