Run 3. Outer Step 11. Inner Step 193.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5442947,
-    5442951,
-    5442955,
-    5442959,
-    5442962
+    5442992,
+    5442995,
+    5442999,
+    5443003,
+    5443007
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 191,
+  "inner_step": 193,
   "inner_steps": 0,
   "last_allreduce_block": 5422706,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:606b37b3d0a02d983cf094126ce3d8719daec1593711ce46d5d7028f2b968450
+oid sha256:a8c355acc91041a339c0fb45484ce49aa5f29f41986591018d6a7c18bd545bff
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7515c6e6ecbda5678bba0cdc394d075e64c4e1232ac0e9cd2db80bec03f08ad6
+oid sha256:6dd22e187947b2d47b028a251c5661c1d3b191ace638d43d1ee822b7a8543418
 size 4040701744