Run 4. Outer Step 33. Inner Step 43.

config.json

@@ -268,19 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5546203,
-    5546208,
-    5546212,
-    5546216,
-    5546220,
-    5546224
+    5546229,
+    5546233,
+    5546237,
+    5546241,
+    5546245
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 42,
+  "inner_step": 43,
   "inner_steps": 0,
   "last_allreduce_block": 5543976,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:338d21a9260a61f55613988f4e9da66e4d916f339a1e8a796a89c340104c985c
+oid sha256:59fd53e7ae5389325118c5c84f1c348a88cce1343feb7a94cc5cd42cc4102ade
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35077eae8e618e7d2aea498f1d5f2110a7a1408e64fee8fa9514eee9eecf39b9
+oid sha256:d74d85b9aa870c8891381b6fa265ab9863a1a557e40dcf20a2dfc393f013a433
 size 4040701744