Run 4. Outer Step 57. Inner Step 28.

config.json

@@ -268,21 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5601991,
-    5601993,
-    5601994,
-    5601995,
-    5601997,
-    5602000,
-    5602002,
-    5602004
+    5602006,
+    5602007,
+    5602011,
+    5602013,
+    5602016
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 27,
+  "inner_step": 28,
   "inner_steps": 0,
   "last_allreduce_block": 5600871,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5de9279973cbf1b8cf675b855f2d44a27efbe270ce3b097564c4fe6f7690a711
+oid sha256:e77e5a8d75855bb2174405aa37a09c98859a40f51726703d3dc89d172af3d4db
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76873f684a88fb97378338021db44770b161ce5f15f059bb3aed875fda6dba30
+oid sha256:3c98a639791ee11da7a4d16a20424b84bab18e3345ae4f0fe4ec8e23b0385ddb
 size 4040701744