Run 4. Outer Step 54. Inner Step 80.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5579959,
-    5579961,
-    5579962,
-    5579963,
-    5579966,
-    5579968,
-    5579972
+    5579975,
+    5579978,
+    5579980,
+    5579982,
+    5579984
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 79,
+  "inner_step": 80,
   "inner_steps": 0,
   "last_allreduce_block": 5577515,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37544f1a2ef9b316efe2db66200ee4db5534b6f8577fb27009e994f434f97a82
+oid sha256:f64780a7a86b708b061ae5899728388dc111fa79d6ac268b8cb77781a032d889
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20f2192b106060ca956106f405a213e6cf9204a17f3209a84747271b87043c02
+oid sha256:0d0733928c5117b977899146634269cd41ce8c8cea1ddf2048c8816be4a774de
 size 4040701744