Run 4. Outer Step 37. Inner Step 64.

config.json

@@ -268,20 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5552345,
-    5552349,
-    5552353,
-    5552357,
-    5552361,
-    5552364,
-    5552368
+    5552373,
+    5552377,
+    5552380,
+    5552384,
+    5552388,
+    5552391
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 63,
+  "inner_step": 64,
   "inner_steps": 0,
   "last_allreduce_block": 5543976,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39771f8c676f32850b473d2ea7c950fedb9d678b5f0e7f465211bb34e1ce81ad
+oid sha256:7ef09a6865bad99b1745bf65d47903972b2486370ce0d093fc2991ffa4b1ede9
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e0a024a67bd9e494171b43a0b329a88e5989e408c3b622f68a5391a858c0e51
+oid sha256:6ed2979346208a0cd387a2114f172e1a9ade6f10b164a74c9241308b9a372f8d
 size 4040701744