Run 4. Outer Step 33. Inner Step 90.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5546535,
-    5546539,
-    5546544,
-    5546548,
-    5546552
+    5546557,
+    5546562,
+    5546566,
+    5546570,
+    5546574
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 89,
+  "inner_step": 90,
   "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 sha256:840d4de104901df198190c6761a35f19553f8d265cb6e48c3da0c47ff8eef7c3
+oid sha256:a70f06298376bca404031d9d80e8113e0c70dd9e740e70bcea215a5a2c18cab1
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51096b0a58460072791da74a7105bd7cbd6b6a577ba849c50c40d8b14a9b4bf3
+oid sha256:216a3ca7a09af5d8ac5785cc7f793b7e9cf127c920aa3d3a148d7ba1d186cc76
 size 4040701744