Run 4. Outer Step 54. Inner Step 96.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5580406,
-    5580410,
-    5580412,
-    5580414,
-    5580417,
-    5580420,
-    5580421
+    5580424,
+    5580428,
+    5580430,
+    5580433,
+    5580436
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 95,
+  "inner_step": 96,
   "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 sha256:41488af91e08aae805124694aa42c03d1f429d779a937f474c5296744e52c03f
+oid sha256:5432ff287de37b824586cb1afb98e9c0bdce9fe53e50b030d600da9dd761cbc3
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30614f5cfff7cea49878b7632a0069b779424652d2aac7b378336ea498841339
+oid sha256:203a0959da9cb662c618eabc7474e91ddb7352ccb7beab08a65d9603de84db6d
 size 4040701744