Run 4. Outer Step 33. Inner Step 83.

config.json

@@ -268,18 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5546626,
-    5546630,
-    5546635,
-    5546640,
-    5546644
+    5546650,
+    5546654,
+    5546659,
+    5546663,
+    5546668,
+    5546672
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 82,
+  "inner_step": 83,
   "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 sha256:58a63fb24304618bc0179f04499f47840085446678eddec52ef426ae5b842040
+oid sha256:7bdc5fdfbf1c9cab9b7ac74bad54d2507de10bea6c9e7d84ac60b5d50ddc5220
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b285f1850c281c17523c521a4a480f0fcb27645667d92ca96e940b99c85933bf
+oid sha256:52e8ab1f27c7bf5e3f55dac2406f88a7c1e12484a1156376ab3e7b8954274edf
 size 4040701744