Run 4. Outer Step 47. Inner Step 33.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5568563,
-    5568567,
-    5568571,
-    5568575,
-    5568579
+    5568584,
+    5568588,
+    5568592,
+    5568596,
+    5568600
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 32,
+  "inner_step": 33,
   "inner_steps": 0,
   "last_allreduce_block": 5567600,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d15a42bec719fcb860edb0931e4d90f21604c88741a878fd1ee1e2c026e32af
+oid sha256:31ec66aff60b7a9b9f7fe3bec89d670089f7088b92109551fafa6208a796cc54
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:151f92a6fd6ac1fc2699438535ea0b233a26b2a1ab06e13432d390a69f493037
+oid sha256:7a62bd38e8e0e2ef044f7f77c04cce8f19f79258e0fae9bc9f0cc5315701db75
 size 4040701744