Run 4. Outer Step 13. Inner Step 6.

config.json

@@ -268,19 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5511530,
-    5511534,
-    5511538,
-    5511542,
-    5511546,
-    5511550
+    5511555,
+    5511559,
+    5511563,
+    5511567,
+    5511572,
+    5511576
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 5,
+  "inner_step": 6,
   "inner_steps": 0,
   "last_allreduce_block": 5509976,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8501cbf53b12a6d5111943cf5091115e92453ea1e390ac0d37e3233a0552d7e7
+oid sha256:1412972babf4bf2b60bfc5f8b29bcde95972e15d39a9c07efd0bf79361b94f3c
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9858ae18faf97cb0067ee7a6b45b13b7cf32b62372f7b390c9458c7d89d41e49
+oid sha256:fe05c9dd197a7023177a3b51d7caa0fb7e6a6719ddc619830c8ab7d35b919f3c
 size 4040701744