Run 4. Outer Step 52. Inner Step 33.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5576005,
-    5576007,
-    5576010,
-    5576013,
-    5576016,
-    5576018,
-    5576022
+    5576025,
+    5576028,
+    5576030,
+    5576033,
+    5576035
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 32,
+  "inner_step": 33,
   "inner_steps": 0,
   "last_allreduce_block": 5574901,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fb707d90f27896d04df5b161016aec4e2c052ab6e43e00bbb8ca33dffd2ddf8
+oid sha256:ea3406b3bb59c1aba9a57e4b201fd31f37943ed5266460d8cecbc1c6f9cf005a
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e77559cac406b2fa331b924eef520ce9f394579184fef63cb49f5f0bb2f3dc0
+oid sha256:7a82d6020ddfd23f7bd1c6525eeaa07c4f5c320e3e3d14ed8bc8483e6ce8a0f1
 size 4040701744