Run 3. Outer Step 11. Inner Step 214.

config.json

@@ -268,18 +268,24 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5443509,
-    5443515,
-    5443519,
-    5443523,
-    5443527
+    5443552,
+    5443556,
+    5443559,
+    5443564,
+    5443567,
+    5443572,
+    5443577,
+    5443582,
+    5443586,
+    5443589,
+    5443594
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 212,
+  "inner_step": 214,
   "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 sha256:27321ec636a506a4498e8af14f0596b7f7343d81b1f3acb74bc95981bed458c1
+oid sha256:ce4bd962a40af2983a8f739e14b302a150d9d04134b1cdc4559838f5781c8ee3
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f932e4d9b59c70477f859f522a779d0f05cc5dc8b3c2c8c46d9bd4d163e1d2e
+oid sha256:6d6709f1ab18881695a8fa19b6e9ebe725b7ec0e3ca0bc9adea2c200a6ac2fce
 size 4040701744