Run 4. Outer Step 59. Inner Step 21.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5606096,
-    5606101,
-    5606106,
-    5606110,
-    5606114
+    5606119,
+    5606123,
+    5606127,
+    5606131,
+    5606136
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 20,
+  "inner_step": 21,
   "inner_steps": 0,
   "last_allreduce_block": 5598085,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:683e9b0658e180d5aecdffcc1e5322ceb653cb3b893bc71152659ddcf9516100
+oid sha256:f266d2d971d9a37025b566e2565c8d4d5bebcd1444e28a180a50c1865a116ce1
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c617b3f6f0cc2c38bacaaa903ac513129ebd30c0cac6dbd3f066870cf4fd3e9b
+oid sha256:f506ea1ea07fad8e5105628a423a160e097a1b2e448731da751f43f44ef9d3ab
 size 4040701744