Run 4. Outer Step 33. Inner Step 97.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5546731,
-    5546736,
-    5546740,
-    5546744,
-    5546748
+    5546752,
+    5546757,
+    5546760,
+    5546764,
+    5546769
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 96,
+  "inner_step": 97,
   "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:b6aec12686a2636ed113f9179f1bb5a0b598186695efbfae7cfaefead7cd9a32
+oid sha256:a958df674a9f9f040477c3328dcdd0b7153b91cb538e35fff0632bf4b8a10301
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cabf30b639670a21d955bffe3aaf44d7667e6a467c8a2f47b9359b2de7e11cf
+oid sha256:d74ccc4409aa7811b72c9fb87ce0741ce81fd3a95352c362fda10ac281d4b8f8
 size 4040701744