Run 4. Outer Step 29. Inner Step 18.

config.json

@@ -268,23 +268,26 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5539054,
-    5539057,
-    5539060,
-    5539062,
-    5539064,
-    5539067,
-    5539070,
-    5539073,
-    5539075,
-    5539076
+    5539079,
+    5539082,
+    5539084,
+    5539085,
+    5539088,
+    5539090,
+    5539092,
+    5539094,
+    5539095,
+    5539096,
+    5539099,
+    5539101,
+    5539103
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 17,
+  "inner_step": 18,
   "inner_steps": 0,
   "last_allreduce_block": 5538408,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23a799adaf031765336be7969ffd792656ae57c8b3a81307c4c2aea52b3964bb
+oid sha256:84ba2aedf6c896cf796adbeeb0daed23f9b510ec844ffa816a38fd325489a026
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd70cde116546cf415eb748300f101d18558a66838708e3ced449f8864e1742c
+oid sha256:eb4ef0c37619a341f52da78e1a0a24f050b16119d0476d2bbcbbc9a7ba9579d3
 size 4040701744