Run 4. Outer Step 60. Inner Step 4.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5607477,
-    5607479,
-    5607482,
-    5607484,
-    5607486,
-    5607489,
-    5607491
+    5607494,
+    5607496,
+    5607498,
+    5607501,
+    5607503
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 3,
+  "inner_step": 4,
   "inner_steps": 0,
   "last_allreduce_block": 5607244,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fe939bd96b1303d86e4cdaaebeeb1e8c0fce53c3be0a8684cc1067d1dccb5d2
+oid sha256:0b50c5710622751478d642d287baaf4f4cfe1b04271466bdbada13151ff7674e
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:770e102f689fcb603e03d09b4b21dda87f78dd65a07ac52da72f7ccbec50f0c3
+oid sha256:acb315879dd41c6867d40909a863adf0a7bf844d4543058684e0f606793c00cd
 size 4040701744