Run 4. Outer Step 20. Inner Step 18.

config.json

@@ -268,29 +268,27 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5525185,
-    5525186,
-    5525188,
-    5525190,
-    5525192,
-    5525194,
-    5525195,
-    5525195,
-    5525196,
-    5525196,
-    5525196,
-    5525197,
-    5525198,
-    5525200,
-    5525201,
-    5525206
+    5525208,
+    5525210,
+    5525212,
+    5525214,
+    5525214,
+    5525215,
+    5525216,
+    5525218,
+    5525220,
+    5525222,
+    5525224,
+    5525225,
+    5525227,
+    5525229
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 16,
+  "inner_step": 18,
   "inner_steps": 0,
   "last_allreduce_block": 5523943,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2d4fa858bbfcea4e19a7d0760df6b689c363c03270a651aab2ee2333176018d
+oid sha256:f446eb477d064850d97339ac0dcfb6c2e0be51af2c0caaa54b1e15fc140fb224
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b6be164ce9fa02f14eafc6a0a9fa8af10631bd0052033aac1ecabb5144802b2
+oid sha256:ca06b4336fadd2732a4d4fd8032a5d36bb60bcd66ac0b030773cace6eb48f27f
 size 4040701744