Run 4. Outer Step 50. Inner Step 170.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5626065,
-    5626130,
-    5626134,
-    5626139,
-    5626143
+    5626149,
+    5626153,
+    5626157,
+    5626160,
+    5626165
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 169,
+  "inner_step": 170,
   "inner_steps": 0,
   "last_allreduce_block": 5570305,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b1ed0e2552387e84bb830c1b6f2678466835943546e82269d4c473c11d1450d
+oid sha256:ebe6496d395cd47f8b11bd40b2cb4bbcc3b49f975023e80344b0cd25c325944f
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95d0af56f0291231b3d7f9e3161df96a90f890d6e477e01964309e5f5b6c8a03
+oid sha256:685036103abc2c6a2068292b4a3e14c32c233c17a626c387dd23019e8121ec23
 size 4040701744